Author name cluster

Jiajun Wu 0001

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

47 papers

1 author row

IROS Conference 2025 Conference Paper

Generalizable Humanoid Manipulation with 3D Diffusion Policies

Yanjie Ze
Zixuan Chen
Wenhao Wang
Tianyi Chen
Xialin He
Ying Yuan
Xue Bin Peng
Jiajun Wu 0001

Humanoid robots capable of autonomous operation in diverse environments have long been a goal for roboticists. However, autonomous manipulation by humanoid robots has largely been restricted to one specific scene, primarily due to the difficulty of acquiring generalizable skills and the expensiveness of in-the-wild humanoid robot data. In this work, we build a real-world robotic system to address this challenging problem. Our system is mainly an integration of 1) a whole-upper-body robotic teleoperation system to acquire human-like robot data, 2) a 25-DoF humanoid robot platform with a height-adjustable cart and a 3D LiDAR sensor, and 3) an improved 3D Diffusion Policy learning algorithm for humanoid robots to learn from noisy human data. We run more than 2000 episodes of policy rollouts on the real robot for rigorous policy evaluation. Empowered by this system, we show that using only data collected in one single scene and with only onboard computing, a full-sized humanoid robot can autonomously perform skills in diverse real-world scenarios. Videos are available at humanoid-manipulation.github.io.

IROS Conference 2025 Conference Paper

Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies

Zixuan Chen
Xialin He
Yen-Jen Wang
Qiayuan Liao
Yanjie Ze
Zhongyu Li 0003
S. Shankar Sastry
Jiajun Wu 0001

Reinforcement learning combined with sim-to-real transfer offers a general framework for developing locomotion controllers for legged robots. To facilitate successful deployment in the real world, smoothing techniques, such as low-pass filters and smoothness rewards, are often employed to develop policies with smooth behaviors. However, because these techniques are non-differentiable and usually require tedious tuning of a large set of hyperparameters, they tend to require extensive manual tuning for each robotic platform. To address this challenge and establish a general technique for enforcing smooth behaviors, we propose a simple and effective method that imposes a Lipschitz constraint on a learned policy, which we refer to as Lipschitz-Constrained Policies (LCP). We show that the Lipschitz constraint can be implemented in the form of a gradient penalty, which provides a differentiable objective that can be easily incorporated with automatic differentiation frameworks. We demonstrate that LCP effectively replaces the need for smoothing rewards or low-pass filters and can be easily integrated into training frameworks for many distinct humanoid robots. We extensively evaluate LCP in both simulation and real-world humanoid robots, producing smooth and robust locomotion controllers. All simulation and deployment code, along with complete checkpoints, is available on our project page: https://lipschitz-constrained-policy.github.io.

ICLR Conference 2025 Conference Paper

Predicate Hierarchies Improve Few-Shot State Classification

Emily Jin
Joy Hsu
Jiajun Wu 0001

State classification of objects and their relations is core to many long-horizon tasks, particularly in robot planning and manipulation. However, the combinatorial explosion of possible object-predicate combinations, coupled with the need to adapt to novel real-world environments, makes it a desideratum for state classification models to generalize to novel queries with few examples. To this end, we propose PHIER, which leverages predicate hierarchies to generalize effectively in few-shot scenarios. PHIER uses an object-centric scene encoder, self-supervised losses that infer semantic relations between predicates, and a hyperbolic distance metric that captures hierarchical structure; it learns a structured latent space of image-predicate pairs that guides reasoning over state classification queries. We evaluate PHIER in the CALVIN and BEHAVIOR robotic environments and show that PHIER significantly outperforms existing methods in few-shot, out-of-distribution state classification, and demonstrates strong zero- and few-shot generalization from simulated to real-world tasks. Our results demonstrate that leveraging predicate hierarchies improves performance on state classification tasks with limited data.

ICLR Conference 2025 Conference Paper

Range, not Independence, Drives Modularity in Biologically Inspired Representations

Will Dorrell
Kyle Hsu
Luke Hollingsworth
Jin Hwa Lee
Jiajun Wu 0001
Chelsea Finn
Peter E. Latham
Timothy Edward John Behrens

Why do biological and artificial neurons sometimes modularise, each encoding a single meaningful variable, and sometimes entangle their representation of many variables? In this work, we develop a theory of when biologically inspired networks---those that are nonnegative and energy efficient---modularise their representation of source variables (sources). We derive necessary and sufficient conditions on a sample of sources that determine whether the neurons in an optimal biologically-inspired linear autoencoder modularise. Our theory applies to any dataset, extending far beyond the case of statistical independence studied in previous work. Rather we show that sources modularise if their support is ``sufficiently spread''. From this theory, we extract and validate predictions in a variety of empirical studies on how data distribution affects modularisation in nonlinear feedforward and recurrent neural networks trained on supervised and unsupervised tasks. Furthermore, we apply these ideas to neuroscience data, showing that range independence can be used to understand the mixing or modularising of spatial and reward information in entorhinal recordings in seemingly conflicting experiments. Further, we use these results to suggest alternate origins of mixed-selectivity, beyond the predominant theory of flexible nonlinear classification. In sum, our theory prescribes precise conditions on when neural activities modularise, providing tools for inducing and elucidating modular representations in brains and machines.

ICRA Conference 2025 Conference Paper

UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation

Yihe Tang
Wenlong Huang
Yingke Wang
Chengshu Li 0001
Roy Yuan
Ruohan Zhang
Jiajun Wu 0001
Li Fei-Fei 0001

Understanding fine-grained object affordances is imperative for robots to manipulate objects in unstructured environments given open-ended task instructions. However, existing methods of visual affordance predictions often rely on manually annotated data or conditions only on a predefined set of tasks. We introduce Unsupervised Affordance Distillation (UAD), a method for distilling affordance knowledge from foundation models into a task-conditioned affordance model without any manual annotations. By leveraging the complementary strengths of large vision models and vision-language models, UAD automatically annotates a large-scale dataset with detailed pairs. Training only a lightweight task-conditioned decoder atop frozen features, UAD exhibits notable generalization to in-the-wild robotic scenes and to various human activities, despite only being trained on rendered objects in simulation. Using affordance provided by UAD as the observation space, we show an imitation learning policy that demonstrates promising generalization to unseen object instances, object categories, and even variations in task instructions after training on as few as 10 demonstrations. Project website with Appendix: unsup-affordance.github.io/.

ICML Conference 2025 Conference Paper

Understanding Complexity in VideoQA via Visual Program Generation

Cristóbal Eyzaguirre
Igor Vasiljevic
Achal Dave
Jiajun Wu 0001
Rares Ambrus
Thomas Kollar
Juan Carlos Niebles
Pavel Tokmakov

We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design challenging questions, yet we experimentally show that humans struggle to predict which questions are difficult for machine learning models. Our automatic approach leverages recent advances in code generation for visual question answering, using the complexity of generated code as a proxy for question difficulty. We demonstrate that this measure correlates significantly better with model performance than human estimates. To operationalize this insight, we propose an algorithm for estimating question complexity from code. It identifies fine-grained primitives that correlate with the hardest questions for any given set of models, making it easy to scale to new approaches in the future. Finally, to further illustrate the utility of our method, we extend it to automatically generate complex questions, constructing a new benchmark that is 1. 9 times harder than the popular NExT-QA.

ICLR Conference 2025 Conference Paper

What Makes a Maze Look Like a Maze?

Joy Hsu
Jiayuan Mao
Joshua B. Tenenbaum
Noah D. Goodman
Jiajun Wu 0001

A unique aspect of human visual understanding is the ability to flexibly interpret abstract concepts: acquiring lifted rules explaining what they symbolize, grounding them across familiar and unfamiliar contexts, and making predictions or reasoning about them. While off-the-shelf vision-language models excel at making literal interpretations of images (e.g., recognizing object categories such as tree branches), they still struggle to make sense of such visual abstractions (e.g., how an arrangement of tree branches may form the walls of a maze). To address this challenge, we introduce Deep Schema Grounding (DSG), a framework that leverages explicit structured representations of visual abstractions for grounding and reasoning. At the core of DSG are schemas—dependency graph descriptions of abstract concepts that decompose them into more primitive-level symbols. DSG uses large language models to extract schemas, then hierarchically grounds concrete to abstract components of the schema onto images with vision-language models. The grounded schema is used to augment visual abstraction understanding. We systematically evaluate DSG and different methods in reasoning on our new Visual Abstractions Benchmark, which consists of diverse, real-world images of abstract concepts and corresponding question-answer pairs labeled by humans. We show that DSG significantly improves the abstract visual reasoning performance of vision-language models, and is a step toward human-aligned understanding of visual abstractions.

ICML Conference 2025 Conference Paper

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

Shiqi Chen 0002
Tongyao Zhu
Ruochen Zhou
Jinghan Zhang 0006
Siyang Gao
Juan Carlos Niebles
Mor Geva
Junxian He

Large Vision Language Models (VLMs) have long struggled with spatial reasoning tasks. Surprisingly, even simple spatial reasoning tasks, such as recognizing “under” or “behind” relationships between only two objects, pose significant challenges for current VLMs. We believe it is crucial to use the lens of mechanism interpretability, opening up the model and diving into model’s internal states to examine the interactions between image and text tokens during spatial reasoning. Our analysis of attention behaviors reveals significant differences in how VLMs allocate attention to image versus text. By tracing the areas of images that receive the highest attention scores throughout intermediate layers, we observe a notable pattern: errors often coincide with attention being misdirected towards irrelevant objects within the image. Moreover, such attention patterns exhibit substantial differences between familiar (e. g. , “on the left side of ”) and unfamiliar (e. g. ,“in front of ”) spatial relationships. Motivated by these findings, we propose ADAPTVIS based on inference-time confidence scores to sharpen the attention on highly relevant regions when the model exhibits high confidence, while smoothing and broadening the attention window to consider a wider context when confidence is lower. This training-free decoding method shows significant improvement (e. g. , up to a 50 absolute point improvement) on spatial reasoning benchmarks such as WhatsUp and VSR with negligible additional cost.

ICLR Conference 2024 Conference Paper

Language-Informed Visual Concept Learning

Sharon Lee
Yunzhi Zhang
Shangzhe Wu
Jiajun Wu 0001

Our understanding of the visual world is centered around various concept axes, characterizing different aspects of visual entities. While different concept axes can be easily specified by language, e.g., color, the exact visual nuances along each axis often exceed the limitations of linguistic articulations, e.g., a particular style of painting. In this work, our goal is to learn a language-informed visual concept representation, by simply distilling large pre-trained vision-language models. Specifically, we train a set of concept encoders to encode the information pertinent to a set of language-informed concept axes, with an objective of reproducing the input image through a pre-trained Text-to-Image (T2I) model. To encourage better disentanglement of different concept encoders, we anchor the concept embeddings to a set of text embeddings obtained from a pre-trained Visual Question Answering (VQA) model. At inference time, the model extracts concept embeddings along various axes from new test images, which can be remixed to generate images with novel compositions of visual concepts. With a lightweight test-time finetuning procedure, it can also generalize to novel concepts unseen at training. Project page at https://cs.stanford.edu/~yzzhang/projects/concept-axes.

ICLR Conference 2024 Conference Paper

Learning Planning Abstractions from Language

Weiyu Liu
Geng Chen
Joy Hsu
Jiayuan Mao
Jiajun Wu 0001

This paper presents a framework for learning state and action abstractions in sequential decision-making domains. Our framework, planning abstraction from language (PARL), utilizes language-annotated demonstrations to automatically discover a symbolic and abstract action space and induce a latent state abstraction based on it. PARL consists of three stages: 1) recovering object-level and action concepts, 2) learning state abstractions, abstract action feasibility, and transition models, and 3) applying low-level policies for abstract actions. During inference, given the task description, PARL first makes abstract action plans using the latent transition and feasibility functions, then refines the high-level plan using low-level policies. PARL generalizes across scenarios involving novel object instances and environments, unseen concept compositions, and tasks that require longer planning horizons than settings it is trained on.

ICRA Conference 2024 Conference Paper

Learning to Design 3D Printable Adaptations on Everyday Objects for Robot Manipulation

Michelle Guo
Ziang Liu 0008
Stephen Tian
Zhaoming Xie
Jiajun Wu 0001
C. Karen Liu

Advancements in robot learning for object manipulation have shown promising results, yet certain everyday objects remain challenging for robots to effectively interact with. This discrepancy arises from the fact that human-designed objects are optimized for human use rather than robot manipulation. To address this gap, we propose a framework to automatically design 3D printable adaptations that can be attached to hard-to-use objects, thus improving "robot ergonomics". Our learning-based framework formulates the adaptation design and control as a dual Markov decision process and is able to improve robot-object interactions for various robot end effectors and objects. We further validate our designs in the real world with a Franka Panda robot. Please see the supplementary video and https://object-adaptation.github.io for additional visualizations.

ICLR Conference 2024 Conference Paper

Neural Polynomial Gabor Fields for Macro Motion Analysis

Chen Geng 0001
Hong-Xing Yu
Sida Peng
Xiaowei Zhou 0001
Jiajun Wu 0001

We study macro motion analysis, where macro motion refers to the collection of all visually observable motions in a dynamic scene. Traditional filtering-based methods on motion analysis typically focus only on local and tiny motions, yet fail to represent large motions or 3D scenes. Recent dynamic neural representations can faithfully represent motions using correspondences, but they cannot be directly used for motion analysis. In this work, we propose Phase-based neural polynomial Gabor fields (Phase-PGF), which learns to represent scene dynamics with low-dimensional time-varying phases. We theoretically show that Phase-PGF has several properties suitable for macro motion analysis. In our experiments, we collect diverse 2D and 3D dynamic scenes and show that Phase-PGF enables dynamic scene analysis and editing tasks including motion loop detection, motion factorization, motion smoothing, and motion magnification. Project page: https://chen-geng.com/phasepgf

ICRA Conference 2024 Conference Paper

Open X-Embodiment: Robotic Learning Datasets and RT-X Models: Open X-Embodiment Collaboration

Abby O'Neill
Abdul Rehman
Abhiram Maddukuri
Abhishek Gupta 0004
Abhishek Padalkar
Abraham Lee
Acorn Pooley
Agrim Gupta

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x. github.io.

ICLR Conference 2024 Conference Paper

Patched Denoising Diffusion Models For High-Resolution Image Synthesis

Zheng Ding
Mengqi Zhang
Jiajun Wu 0001
Zhuowen Tu

We propose an effective denoising diffusion model for generating high-resolution images (e.g., 1024$\times$512), trained on small-size image patches (e.g., 64$\times$64). We name our algorithm Patch-DM, in which a new feature collage strategy is designed to avoid the boundary artifact when synthesizing large-size images. Feature collage systematically crops and combines partial features of the neighboring patches to predict the features of a shifted image patch, allowing the seamless generation of the entire image due to the overlap in the patch feature space. Patch-DM produces high-quality image synthesis results on our newly collected dataset of nature images (1024$\times$512), as well as on standard benchmarks of LHQ(1024$\times$ 1024), FFHQ(1024$\times$ 1024) and on other datasets with smaller sizes (256$\times$256), including LSUN-Bedroom, LSUN-Church, and FFHQ. We compare our method with previous patch-based generation methods and achieve state-of-the-art FID scores on all six datasets. Further, Patch-DM also reduces memory complexity compared to the classic diffusion models. Project page: https://patchdm.github.io.

ICRA Conference 2024 Conference Paper

Physically Grounded Vision-Language Models for Robotic Manipulation

Jensen Gao
Bidipta Sarkar
Fei Xia 0002
Ted Xiao
Jiajun Wu 0001
Brian Ichter
Anirudha Majumdar
Dorsa Sadigh

Recent advances in vision-language models (VLMs) have led to improved performance on tasks such as visual question answering and image captioning. Consequently, these models are now well-positioned to reason about the physical world, particularly within domains such as robotic manipulation. However, current VLMs are limited in their understanding of the physical concepts (e. g. , material, fragility) of common objects, which restricts their usefulness for robotic manipulation tasks that involve interaction and physical reasoning about such objects. To address this limitation, we propose PHYSOBJECTS, an object-centric dataset of 39. 6K crowd-sourced and 417K automated physical concept annotations of common household objects. We demonstrate that fine-tuning a VLM on PhysObjects improves its understanding of physical object concepts, including generalization to held-out concepts, by capturing human priors of these concepts from visual appearance. We incorporate this physically grounded VLM in an interactive framework with a large language model-based robotic planner, and show improved planning performance on tasks that require reasoning about physical object concepts, compared to baselines that do not leverage physically grounded VLMs. We additionally illustrate the benefits of our physically grounded VLM on a real robot, where it improves task success rates. We release our dataset and provide further details and visualizations of our results at https://iliad.stanford.edu/pg-vlm/.

ICML Conference 2024 Conference Paper

Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning

Kyle Hsu
Jubayer Ibn Hamid
Kaylee Burns
Chelsea Finn
Jiajun Wu 0001

Inductive biases are crucial in disentangled representation learning for narrowing down an underspecified solution set. In this work, we consider endowing a neural network autoencoder with three select inductive biases from the literature: data compression into a grid-like latent space via quantization, collective independence amongst latents, and minimal functional influence of any latent on how other latents determine data generation. In principle, these inductive biases are deeply complementary: they most directly specify properties of the latent space, encoder, and decoder, respectively. In practice, however, naively combining existing techniques instantiating these inductive biases fails to yield significant benefits. To address this, we propose adaptations to the three techniques that simplify the learning problem, equip key regularization terms with stabilizing invariances, and quash degenerate incentives. The resulting model, Tripod, achieves state-of-the-art results on a suite of four image disentanglement benchmarks. We also verify that Tripod significantly improves upon its naive incarnation and that all three of its "legs" are necessary for best performance.

ICLR Conference 2023 Conference Paper

A Control-Centric Benchmark for Video Prediction

Stephen Tian
Chelsea Finn
Jiajun Wu 0001

Video is a promising source of knowledge for embodied agents to learn models of the world's dynamics. Large deep networks have become increasingly effective at modeling complex video data in a self-supervised manner, as evaluated by metrics based on human perceptual similarity or pixel-wise comparison. However, it remains unclear whether current metrics are accurate indicators of performance on downstream tasks. We find empirically that for planning robotic manipulation, existing metrics can be unreliable at predicting execution success. To address this, we propose a benchmark for action-conditioned video prediction in the form of a control benchmark that evaluates a given model for simulated robotic manipulation through sampling-based planning. Our benchmark, Video Prediction for Visual Planning ($\text{VP}^2$), includes simulated environments with $11$ task categories and $310$ task instance definitions, a full planning implementation, and training datasets containing scripted interaction trajectories for each task category. A central design goal of our benchmark is to expose a simple interface -- a single forward prediction call -- so it is straightforward to evaluate almost any action-conditioned video prediction model. We then leverage our benchmark to study the effects of scaling model size, quantity of training data, and model ensembling by analyzing five highly-performant video prediction models, finding that while scale can improve perceptual quality when modelling visually diverse settings, other attributes such as uncertainty awareness can also aid planning performance.

ICLR Conference 2023 Conference Paper

An Extensible Multi-modal Multi-task Object Dataset with Materials

Trevor Standley
Ruohan Gao
Dawn Chen
Jiajun Wu 0001
Silvio Savarese

We present EMMa, an Extensible, Multimodal dataset of Amazon product listings that contains rich Material annotations. It contains more than 2.8 million objects, each with image(s), listing text, mass, price, product ratings, and position in Amazon’s product-category taxonomy. We also design a comprehensive taxonomy of 182 physical materials (e.g., Plastic → Thermoplastic → Acrylic). Objects areannotated with one or more materials from this taxonomy. With the numerous attributes available for each object, we develop a Smart Labeling framework to quickly add new binary labels to all objects with very little manual labeling effort, making the dataset extensible. Each object attribute in our dataset can be included in either the model inputs or outputs, leading to combinatorial possibilities in task configurations. For example, we can train a model to predict the object category from the listing text, or the mass and price from the product listing image. EMMa offers a new benchmark for multi-task learning in computer vision and NLP, and allows practitioners to efficiently add new tasks and object attributes at scale.

ICLR Conference 2023 Conference Paper

Learning Vortex Dynamics for Fluid Inference and Prediction

Yitong Deng
Hong-Xing Yu
Jiajun Wu 0001
Bo Zhu 0002

We propose a novel differentiable vortex particle (DVP) method to infer and predict fluid dynamics from a single video. Lying at its core is a particle-based latent space to encapsulate the hidden, Lagrangian vortical evolution underpinning the observable, Eulerian flow phenomena. Our differentiable vortex particles are coupled with a learnable, vortex-to-velocity dynamics mapping to effectively capture the complex flow features in a physically-constrained, low-dimensional space. This representation facilitates the learning of a fluid simulator tailored to the input video that can deliver robust, long-term future predictions. The value of our method is twofold: first, our learned simulator enables the inference of hidden physics quantities (e.g., velocity field) purely from visual observation; secondly, it also supports future prediction, constructing the input video's sequel along with its future dynamics evolution. We compare our method with a range of existing methods on both synthetic and real-world videos, demonstrating improved reconstruction quality, visual plausibility, and physical integrity.

ICLR Conference 2023 Conference Paper

MaskViT: Masked Visual Pre-Training for Video Prediction

Agrim Gupta
Stephen Tian
Yunzhi Zhang
Jiajun Wu 0001
Roberto Martín-Martín
Li Fei-Fei 0001

The ability to predict future visual observations conditioned on past observations and motor commands can enable embodied agents to plan solutions to a variety of tasks in complex environments. This work shows that we can create good video prediction models by pre-training transformers via masked visual modeling. Our approach, named MaskViT, is based on two simple design decisions. First, for memory and training efficiency, we use two types of window attention: spatial and spatiotemporal. Second, during training, we mask a variable percentage of tokens instead of a fixed mask ratio. For inference, MaskViT generates all tokens via iterative refinement where we incrementally decrease the masking ratio following a mask scheduling function. On several datasets we demonstrate that MaskViT outperforms prior works in video prediction, is parameter efficient, and can generate high resolution videos ($256 \times $256). Further, we demonstrate the benefits of inference speedup (up to $512 \times$) due to iterative decoding by using MaskViT for planning on a real robot. Our work suggests that we can endow embodied agents with powerful predictive models by leveraging the general framework of masked visual modeling with minimal domain knowledge.

ICML Conference 2023 Conference Paper

Modeling Dynamic Environments with Scene Graph Memory

Andrey Kurenkov
Michael Lingelbach
Tanmay Agarwal
Emily Jin
Chengshu Li 0002
Ruohan Zhang
Li Fei-Fei 0001
Jiajun Wu 0001

Embodied AI agents that search for objects in large environments such as households often need to make efficient decisions by predicting object locations based on partial information. We pose this as a new type of link prediction problem: link prediction on partially observable dynamic graphs Our graph is a representation of a scene in which rooms and objects are nodes, and their relationships are encoded in the edges; only parts of the changing graph are known to the agent at each timestep. This partial observability poses a challenge to existing link prediction approaches, which we address. We propose a novel state representation – Scene Graph Memory (SGM) – with captures the agent’s accumulated set of observations, as well as a neural net architecture called a Node Edge Predictor (NEP) that extracts information from the SGM to search efficiently. We evaluate our method in the Dynamic House Simulator, a new benchmark that creates diverse dynamic graphs following the semantic patterns typically seen at homes, and show that NEP can be trained to predict the locations of objects in a variety of environments with diverse object movement dynamics, outperforming baselines both in terms of new scene adaptability and overall accuracy. The codebase and more can be found www. scenegraphmemory. com.

ICML Conference 2023 Conference Paper

Motion Question Answering via Modular Motion Programs

Mark Endo
Joy Hsu
Jiaman Li
Jiajun Wu 0001

In order to build artificial intelligence systems that can perceive and reason with human behavior in the real world, we must first design models that conduct complex spatio-temporal reasoning over motion sequences. Moving towards this goal, we propose the HumanMotionQA task to evaluate complex, multi-step reasoning abilities of models on long-form human motion sequences. We generate a dataset of question-answer pairs that require detecting motor cues in small portions of motion sequences, reasoning temporally about when events occur, and querying specific motion attributes. In addition, we propose NSPose, a neuro-symbolic method for this task that uses symbolic reasoning and a modular design to ground motion through learning motion concepts, attribute neural operators, and temporal relations. We demonstrate the suitability of NSPose for the HumanMotionQA task, outperforming all baseline methods.

IROS Conference 2023 Conference Paper

Primitive Skill-Based Robot Learning from Human Evaluative Feedback

Ayano Hiranaka
Minjune Hwang
Sharon Lee
Chen Wang 0053
Li Fei-Fei 0001
Jiajun Wu 0001
Ruohan Zhang

Reinforcement learning (RL) algorithms face significant challenges when dealing with long-horizon robot manipulation tasks in real-world environments due to sample inefficiency and safety issues. To overcome these challenges, we propose a novel framework, SEED, which leverages two approaches: reinforcement learning from human feedback (RLHF) and primitive skill-based reinforcement learning. Both approaches are particularly effective in addressing sparse reward issues and the complexities involved in long-horizon tasks. By combining them, SEED reduces the human effort required in RLHF and increases safety in training robot manipulation with RL in real-world settings. Additionally, parameterized skills provide a clear view of the agent's high-level intentions, allowing humans to evaluate skill choices before they are executed. This feature makes the training process even safer and more efficient. To evaluate the performance of SEED, we conducted extensive experiments on five manipulation tasks with varying levels of complexity. Our results show that SEED significantly outperforms state-of-the-art RL algorithms in sample efficiency and safety. In addition, SEED also exhibits a substantial reduction of human effort compared to other RLHF methods. Further details and video results can be found at https://seediros23.github.io/.

ICLR Conference 2023 Conference Paper

Programmatically Grounded, Compositionally Generalizable Robotic Manipulation

Renhao Wang
Jiayuan Mao
Joy Hsu
Hang Zhao 0021
Jiajun Wu 0001
Yang Gao 0029

Robots operating in the real world require both rich manipulation skills as well as the ability to semantically reason about when to apply those skills. Towards this goal, recent works have integrated semantic representations from large-scale pretrained vision-language (VL) models into manipulation models, imparting them with more general reasoning capabilities. However, we show that the conventional {\it pretraining-finetuning} pipeline for integrating such representations entangles the learning of domain-specific action information and domain-general visual information, leading to less data-efficient training and poor generalization to unseen objects and tasks. To this end, we propose \ours, a {\it modular} approach to better leverage pretrained VL models by exploiting the syntactic and semantic structures of language instructions. Our framework uses a semantic parser to recover an executable program, composed of functional modules grounded on vision and action across different modalities. Each functional module is realized as a combination of deterministic computation and learnable neural networks. Program execution produces parameters to general manipulation primitives for a robotic end-effector. The entire modular network can be trained with end-to-end imitation learning objectives. Experiments show that our model successfully disentangles action and perception, translating to improved zero-shot and compositional generalization in a variety of manipulation behaviors. Project webpage at: \url{https://progport.github.io}.

ICRA Conference 2023 Conference Paper

Sonicverse: A Multisensory Simulation Platform for Embodied Household Agents that See and Hear

Ruohan Gao
Hao Li 0076
Gokul Dharan
Zhuzhu Wang
Chengshu Li 0002
Fei Xia 0002
Silvio Savarese
Li Fei-Fei 0001

Developing embodied agents in simulation has been a key research topic in recent years. Exciting new tasks, algorithms, and benchmarks have been developed in various simulators. However, most of them assume deaf agents in silent environments, while we humans perceive the world with multiple senses. We introduce Sonicverse, a multisensory simulation platform with integrated audio-visual simulation for training household agents that can both see and hear. Sonicverse models realistic continuous audio rendering in 3D environments in real-time. Together with a new audio-visual VR interface that allows humans to interact with agents with audio, Sonicverse enables a series of embodied AI tasks that need audio-visual perception. For semantic audio-visual navigation in particular, we also propose a new multi-task learning model that achieves state-of-the-art performance. In addition, we demonstrate Sonicverse's realism via sim-to-real transfer, which has not been achieved by other simulators: an agent trained in Sonicverse can successfully perform audio-visual navigation in real-world environments. Sonicverse is available at: https://github.com/StanfordVL/Sonicverse.

ICRA Conference 2023 Conference Paper

STAP: Sequencing Task-Agnostic Policies

Christopher Agia
Toki Migimatsu
Jiajun Wu 0001
Jeannette Bohg

Advances in robotic skill acquisition have made it possible to build general-purpose libraries of learned skills for downstream manipulation tasks. However, naively executing these skills one after the other is unlikely to succeed without accounting for dependencies between actions prevalent in longhorizon plans. We present Sequencing Task-Agnostic Policies (STAP), a scalable framework for training manipulation skills and coordinating their geometric dependencies at planning time to solve long-horizon tasks never seen by any skill during training. Given that Q-functions encode a measure of skill feasibility, we formulate an optimization problem to maximize the joint success of all skills sequenced in a plan, which we estimate by the product of their Q-values. Our experiments indicate that this objective function approximates ground truth plan feasibility and, when used as a planning objective, reduces myopic behavior and thereby promotes long-horizon task success. We further demonstrate how STAP can be used for task and motion planning by estimating the geometric feasibility of skill sequences provided by a task planner. We evaluate our approach in simulation and on a real robot. Qualitative results and code are made available at sites.google.com/stanford.edu/stap.

ICRA Conference 2023 Conference Paper

Task-Driven Graph Attention for Hierarchical Relational Object Navigation

Michael Lingelbach
Chengshu Li 0002
Minjune Hwang
Andrey Kurenkov
Alan Lou
Roberto Martín-Martín
Ruohan Zhang
Li Fei-Fei 0001

Embodied AI agents in large scenes often need to navigate to find objects. In this work, we study a naturally emerging variant of the object navigation task, hierarchical relational object navigation (HRON), where the goal is to find objects specified by logical predicates organized in a hierarchical structure-objects related to furniture and then to rooms-such as finding an apple on top of a table in the kitchen. Solving such a task requires an efficient representation to reason about object relations and correlate the relations in the environment and in the task goal. HRON in large scenes (e. g. homes) is particularly challenging due to its partial observability and long horizon, which invites solutions that can compactly store the past information while effectively exploring the scene. We demonstrate experimentally that scene graphs are the best-suited representation compared to conventional representations such as images or 2D maps. We propose a solution that uses scene graphs as part of its input and integrates graph neural networks as its backbone, with an integrated task-driven attention mechanism, and demonstrate its better scalability and learning efficiency than state-of-the-art baselines.

ICLR Conference 2022 Conference Paper

SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

Chenlin Meng
Yutong He
Yang Song 0011
Jiaming Song
Jiajun Wu 0001
Jun-Yan Zhu
Stefano Ermon

Guided image synthesis enables everyday users to create and edit photo-realistic images with minimum effort. The key challenge is balancing faithfulness to the user inputs (e.g., hand-drawn colored strokes) and realism of the synthesized images. Existing GAN-based methods attempt to achieve such balance using either conditional GANs or GAN inversions, which are challenging and often require additional training data or loss functions for individual applications. To address these issues, we introduce a new image synthesis and editing method, Stochastic Differential Editing (SDEdit), based on a diffusion model generative prior, which synthesizes realistic images by iteratively denoising through a stochastic differential equation (SDE). Given an input image with user guide in a form of manipulating RGB pixels, SDEdit first adds noise to the input, then subsequently denoises the resulting image through the SDE prior to increase its realism. SDEdit does not require task-specific training or inversions and can naturally achieve the balance between realism and faithfulness. SDEdit outperforms state-of-the-art GAN-based methods by up to 98.09% on realism and 91.72% on overall satisfaction scores, according to a human perception study, on multiple tasks, including stroke-based image synthesis and editing as well as image compositing.

ICLR Conference 2022 Conference Paper

Unsupervised Discovery of Object Radiance Fields

Hong-Xing Yu
Leonidas J. Guibas
Jiajun Wu 0001

We study the problem of inferring an object-centric scene representation from a single image, aiming to derive a representation that explains the image formation process, captures the scene's 3D nature, and is learned without supervision. Most existing methods on scene decomposition lack one or more of these characteristics, due to the fundamental challenge in integrating the complex 3D-to-2D image formation process into powerful inference schemes like deep networks. In this paper, we propose unsupervised discovery of Object Radiance Fields (uORF), integrating recent progresses in neural 3D scene representations and rendering with deep inference networks for unsupervised 3D scene decomposition. Trained on multi-view RGB images without annotations, uORF learns to decompose complex scenes with diverse, textured background from a single image. We show that uORF enables novel tasks, such as scene segmentation and editing in 3D, and it performs well on these tasks and on novel view synthesis on three datasets.

ICLR Conference 2022 Conference Paper

Vision-Based Manipulators Need to Also See from Their Hands

Kyle Hsu
Moo Jin Kim
Rafael Rafailov
Jiajun Wu 0001
Chelsea Finn

We study how the choice of visual perspective affects learning and generalization in the context of physical manipulation from raw sensor observations. Compared with the more commonly used global third-person perspective, a hand-centric (eye-in-hand) perspective affords reduced observability, but we find that it consistently improves training efficiency and out-of-distribution generalization. These benefits hold across a variety of learning algorithms, experimental settings, and distribution shifts, and for both simulated and real robot apparatuses. However, this is only the case when hand-centric observability is sufficient; otherwise, including a third-person perspective is necessary for learning, but also harms out-of-distribution generalization. To mitigate this, we propose to regularize the third-person information stream via a variational information bottleneck. On six representative manipulation tasks with varying hand-centric observability adapted from the Meta-World benchmark, this results in a state-of-the-art reinforcement learning agent operating from both perspectives improving its out-of-distribution generalization on every task. While some practitioners have long put cameras in the hands of robots, our work systematically analyzes the benefits of doing so and provides simple and broadly applicable insights for improving end-to-end learned vision-based robotic manipulation.

ICLR Conference 2021 Conference Paper

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning

Zhenfang Chen
Jiayuan Mao
Jiajun Wu 0001
Kwan-Yee K. Wong
Joshua B. Tenenbaum
Chuang Gan 0001

We study the problem of dynamic visual reasoning on raw videos. This is a challenging problem; currently, state-of-the-art models often require dense supervision on physical object properties and events from simulation, which are impractical to obtain in real life. In this paper, we present the Dynamic Concept Learner (DCL), a unified framework that grounds physical objects and events from video and language. DCL first adopts a trajectory extractor to track each object over time and to represent it as a latent, object-centric feature vector. Building upon this object-centric representation, DCL learns to approximate the dynamic interaction among objects using graph networks. DCL further incorporates a semantic parser to parse question into semantic programs and, finally, a program executor to run the program to answer the question, levering the learned dynamics model. After training, DCL can detect and associate objects across the frames, ground visual properties and physical events, understand the causal relationship between events, make future and counterfactual predictions, and leverage these extracted presentations for answering queries. DCL achieves state-of-the-art performance on CLEVRER, a challenging causal video reasoning dataset, even without using ground-truth attributes and collision labels from simulations for training. We further test DCL on a newly proposed video-retrieval and event localization dataset derived from CLEVRER, showing its strong generalization capacity.

ICLR Conference 2021 Conference Paper

Unsupervised Discovery of 3D Physical Objects from Video

Yilun Du
Kevin A. Smith 0001
Tomer D. Ullman
Joshua B. Tenenbaum
Jiajun Wu 0001

We study the problem of unsupervised physical object discovery. While existing frameworks aim to decompose scenes into 2D segments based off each object's appearance, we explore how physics, especially object interactions, facilitates disentangling of 3D geometry and position of objects from video, in an unsupervised manner. Drawing inspiration from developmental psychology, our Physical Object Discovery Network (POD-Net) uses both multi-scale pixel cues and physical motion cues to accurately segment observable and partially occluded objects of varying sizes, and infer properties of those objects. Our model reliably segments objects on both synthetic and real scenes. The discovered object properties can also be used to reason about physical events.

UAI Conference 2021 Conference Paper

When is particle filtering efficient for planning in partially observed linear dynamical systems?

Simon S. Du
Wei Hu 0014
Zhiyuan Li 0005
Ruoqi Shen
Zhao Song 0002
Jiajun Wu 0001

Particle filtering is a popular method for inferring latent states in stochastic dynamical systems, whose theoretical properties have been well studied in machine learning and statistics communities. In many control problems, e. g. , partially observed linear dynamical systems (POLDS), oftentimes the inferred latent state is further used for planning at each step. This paper initiates a rigorous study on the efficiency of particle filtering for sequential planning, and gives the first particle complexity bounds. Though errors in past actions may affect the future, we are able to bound the number of particles needed so that the long-run reward of the policy based on particle filtering is close to that based on exact inference. In particular, we show that, in stable systems, polynomially many particles suffice. Key in our proof is a coupling of the ideal sequence based on the exact planning and the sequence generated by approximate planning based on particle filtering. We believe this technique can be useful in other sequential decision-making problems.

ICRA Conference 2020 Conference Paper

Accurate Vision-based Manipulation through Contact Reasoning

Alina Kloss
Maria Bauzá 0001
Jiajun Wu 0001
Joshua B. Tenenbaum
Alberto Rodriguez 0003
Jeannette Bohg

Planning contact interactions is one of the core challenges of many robotic tasks. Optimizing contact locations while taking dynamics into account is computationally costly and, in environments that are only partially observable, executing contact-based tasks often suffers from low accuracy. We present an approach that addresses these two challenges for the problem of vision-based manipulation. First, we propose to disentangle contact from motion optimization. Thereby, we improve planning efficiency by focusing computation on promising contact locations. Second, we use a hybrid approach for perception and state estimation that combines neural networks with a physically meaningful state representation. In simulation and real-world experiments on the task of planar pushing, we show that our method is more efficient and achieves a higher manipulation accuracy than previous vision-based approaches.

ICLR Conference 2020 Conference Paper

CLEVRER: Collision Events for Video Representation and Reasoning

Kexin Yi
Chuang Gan 0001
Yunzhu Li
Pushmeet Kohli
Jiajun Wu 0001
Antonio Torralba 0001
Joshua B. Tenenbaum

The ability to reason about temporal and causal events from videos lies at the core of human intelligence. Most video reasoning benchmarks, however, focus on pattern recognition from complex visual and language input, instead of on causal structure. We study the complementary problem, exploring the temporal and causal structures behind videos of objects with simple visual appearance. To this end, we introduce the CoLlision Events for Video REpresentation and Reasoning (CLEVRER) dataset, a diagnostic video dataset for systematic evaluation of computational models on a wide range of reasoning tasks. Motivated by the theory of human casual judgment, CLEVRER includes four types of question: descriptive (e.g., ‘what color’), explanatory (‘what’s responsible for’), predictive (‘what will happen next’), and counterfactual (‘what if’). We evaluate various state-of-the-art models for visual reasoning on our benchmark. While these models thrive on the perception-based task (descriptive), they perform poorly on the causal tasks (explanatory, predictive and counterfactual), suggesting that a principled approach for causal reasoning should incorporate the capability of both perceiving complex visual and language inputs, and understanding the underlying dynamics and causal relations. We also study an oracle model that explicitly combines these components via symbolic representations.

ICLR Conference 2020 Conference Paper

Deep Audio Priors Emerge From Harmonic Convolutional Networks

Zhoutong Zhang
Yunyun Wang
Chuang Gan 0001
Jiajun Wu 0001
Joshua B. Tenenbaum
Antonio Torralba 0001
William T. Freeman

Convolutional neural networks (CNNs) excel in image recognition and generation. Among many efforts to explain their effectiveness, experiments show that CNNs carry strong inductive biases that capture natural image priors. Do deep networks also have inductive biases for audio signals? In this paper, we empirically show that current network architectures for audio processing do not show strong evidence in capturing such priors. We propose Harmonic Convolution, an operation that helps deep networks distill priors in audio signals by explicitly utilizing the harmonic structure within. This is done by engineering the kernel to be supported by sets of harmonic series, instead of local neighborhoods for convolutional kernels. We show that networks using Harmonic Convolution can reliably model audio priors and achieve high performance in unsupervised audio restoration tasks. With Harmonic Convolution, they also achieve better generalization performance for sound source separation.

ICLR Conference 2020 Conference Paper

Learning Compositional Koopman Operators for Model-Based Control

Yunzhu Li
Hao He 0011
Jiajun Wu 0001
Dina Katabi
Antonio Torralba 0001

Finding an embedding space for a linear approximation of a nonlinear dynamical system enables efficient system identification and control synthesis. The Koopman operator theory lays the foundation for identifying the nonlinear-to-linear coordinate transformations with data-driven methods. Recently, researchers have proposed to use deep neural networks as a more expressive class of basis functions for calculating the Koopman operators. These approaches, however, assume a fixed dimensional state space; they are therefore not applicable to scenarios with a variable number of objects. In this paper, we propose to learn compositional Koopman operators, using graph neural networks to encode the state into object-centric embeddings and using a block-wise linear transition matrix to regularize the shared structure across objects. The learned dynamics can quickly adapt to new environments of unknown physical parameters and produce control signals to achieve a specified goal. Our experiments on manipulating ropes and controlling soft robots show that the proposed method has better efficiency and generalization ability than existing baselines.

ICRA Conference 2020 Conference Paper

Look, Listen, and Act: Towards Audio-Visual Embodied Navigation

Chuang Gan 0001
Yiwei Zhang 0010
Jiajun Wu 0001
Boqing Gong
Joshua B. Tenenbaum

A crucial ability of mobile intelligent agents is to integrate the evidence from multiple sensory inputs in an environment and to make a sequence of actions to reach their goals. In this paper, we attempt to approach the problem of Audio-Visual Embodied Navigation, the task of planning the shortest path from a random starting location in a scene to the sound source in an indoor environment, given only raw egocentric visual and audio sensory data. To accomplish this task, the agent is required to learn from various modalities, i. e. , relating the audio signal to the visual environment. Here we describe an approach to audio-visual embodied navigation that takes advantage of both visual and audio pieces of evidence. Our solution is based on three key ideas: a visual perception mapper module that constructs its spatial memory of the environment, a sound perception module that infers the relative location of the sound source from the agent, and a dynamic path planner that plans a sequence of actions based on the audio-visual observations and the spatial memory of the environment to navigate toward the goal. Experimental results on a newly collected Visual-Audio-Room dataset using the simulated multi-modal environment demonstrate the effectiveness of our approach over several competitive baselines.

ICML Conference 2020 Conference Paper

Visual Grounding of Learned Physical Models

Yunzhu Li
Toru Lin
Kexin Yi
Daniel Bear
Daniel L. K. Yamins
Jiajun Wu 0001
Joshua B. Tenenbaum
Antonio Torralba 0001

Humans intuitively recognize objects’ physical properties and predict their motion, even when the objects are engaged in complicated interactions. The abilities to perform physical reasoning and to adapt to new environments, while intrinsic to humans, remain challenging to state-of-the-art computational models. In this work, we present a neural model that simultaneously reasons about physics and makes future predictions based on visual and dynamics priors. The visual prior predicts a particle-based representation of the system from visual observations. An inference module operates on those particles, predicting and refining estimates of particle locations, object states, and physical parameters, subject to the constraints imposed by the dynamics prior, which we refer to as visual grounding. We demonstrate the effectiveness of our method in environments involving rigid objects, deformable materials, and fluids. Experiments show that our model can infer the physical properties within a few observations, which allows the model to quickly adapt to unseen scenarios and make accurate predictions into the future.

ICRA Conference 2019 Conference Paper

ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics

Yuanming Hu
Jiancheng Liu
Andrew Spielberg
Joshua B. Tenenbaum
William T. Freeman
Jiajun Wu 0001
Daniela Rus
Wojciech Matusik

Physical simulators have been widely used in robot planning and control. Among them, differentiable simulators are particularly favored, as they can be incorporated into gradient-based optimization algorithms that are efficient in solving inverse problems such as optimal control and motion planning. Therefore, rigid body simulators and recently their differentiable variants are studied extensively. Simulating deformable objects is, however, more challenging compared to rigid body dynamics. The underlying physical laws of deformable objects are more complex, and the resulting systems have orders of magnitude more degrees of freedom and there-fore they are significantly more computationally expensive to simulate. Computing gradients with respect to physical design or controller parameters is typically even more computationally challenging. In this paper, we propose a real-time, differentiable hybrid Lagrangian-Eulerian physical simulator for deformable objects, ChainQueen, based on the Moving Least Squares Material Point Method (MLS-MPM). MLS-MPM can simulate deformable objects with collisions and can be seamlessly incorporated into soft robotic systems. We demonstrate that our simulator achieves high precision in both forward simulation and backward gradient computation. We have successfully employed it in a diverse set of inference, control and co-design tasks for soft robotics.

ICRA Conference 2019 Conference Paper

Combining Physical Simulators and Object-Based Networks for Control

Anurag Ajay
Maria Bauzá 0001
Jiajun Wu 0001
Nima Fazeli
Joshua B. Tenenbaum
Alberto Rodriguez 0003
Leslie Pack Kaelbling

Physics engines play an important role in robot planning and control; however, many real-world control problems involve complex contact dynamics that cannot be characterized analytically. Most physics engines therefore employ approximations that lead to a loss in precision. In this paper, we propose a hybrid dynamics model, simulator-augmented interaction networks (SAIN), combining a physics engine with an object-based neural network for dynamics modeling. Compared with existing models that are purely analytical or purely data-driven, our hybrid model captures the dynamics of interacting objects in a more accurate and data-efficient manner. Experiments both in simulation and on a real robot suggest that it also leads to better performance when used in complex control tasks. Finally, we show that our model generalizes to novel environments with varying object shapes and materials.

ICML Conference 2019 Conference Paper

Neurally-Guided Structure Inference

Sidi Lu
Jiayuan Mao
Joshua B. Tenenbaum
Jiajun Wu 0001

Most structure inference methods either rely on exhaustive search or are purely data-driven. Exhaustive search robustly infers the structure of arbitrarily complex data, but it is slow. Data-driven methods allow efficient inference, but do not generalize when test data have more complex structures than training data. In this paper, we propose a hybrid inference algorithm, the Neurally-Guided Structure Inference (NG-SI), keeping the advantages of both search-based and data-driven methods. The key idea of NG-SI is to use a neural network to guide the hierarchical, layer-wise search over the compositional space of structures. We evaluate our algorithm on two representative structure inference tasks: probabilistic matrix decomposition and symbolic program parsing. It outperforms data-driven and search-based alternatives on both tasks.

ICRA Conference 2019 Conference Paper

Propagation Networks for Model-Based Control Under Partial Observation

Yunzhu Li
Jiajun Wu 0001
Jun-Yan Zhu
Joshua B. Tenenbaum
Antonio Torralba 0001
Russ Tedrake

There has been an increasing interest in learning dynamics simulators for model-based control. Compared with off-the-shelf physics engines, a learnable simulator can quickly adapt to unseen objects, scenes, and tasks. However, existing models like interaction networks only work for fully observable systems; they also only consider pairwise interactions within a single time step, both restricting their use in practical systems. We introduce Propagation Networks (PropNet), a differentiable, learnable dynamics model that handles partially observable scenarios and enables instantaneous propagation of signals beyond pairwise interactions. With these innovations, our propagation networks not only outperform current learnable physics engines in forward simulation, but also achieves superior performance on various control tasks. Compared with existing deep reinforcement learning algorithms, model-based control with propagation networks is more accurate, efficient, and generalizable to novel, partially observable scenes and tasks.

ICLR Conference 2019 Conference Paper

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision

Jiayuan Mao
Chuang Gan 0001
Pushmeet Kohli
Joshua B. Tenenbaum
Jiajun Wu 0001

We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired questions and answers. Our model builds an object-based scene representation and translates sentences into executable, symbolic programs. To bridge the learning of two modules, we use a neuro-symbolic reasoning module that executes these programs on the latent scene representation. Analogical to human concept learning, the perception module learns visual concepts based on the language description of the object being referred to. Meanwhile, the learned visual concepts facilitate learning new words and parsing new sentences. We use curriculum learning to guide the searching over the large compositional space of images and language. Extensive experiments demonstrate the accuracy and efficiency of our model on learning visual concepts, word representations, and semantic parsing of sentences. Further, our method allows easy generalization to new object attributes, compositions, language concepts, scenes and questions, and even new program domains. It also empowers applications including visual question answering and bidirectional image-text retrieval.

IROS Conference 2018 Conference Paper

3D Shape Perception from Monocular Vision, Touch, and Shape Priors

Shaoxiong Wang
Jiajun Wu 0001
Xingyuan Sun
Wenzhen Yuan 0001
William T. Freeman
Joshua B. Tenenbaum
Edward H. Adelson

Perceiving accurate 3D object shape is important for robots to interact with the physical world. Current research along this direction has been primarily relying on visual observations. Vision, however useful, has inherent limitations due to occlusions and the 2D-3D ambiguities, especially for perception with a monocular camera. In contrast, touch gets precise local shape information, though its efficiency for reconstructing the entire shape could be low. In this paper, we propose a novel paradigm that efficiently perceives accurate 3D object shape by incorporating visual and tactile observations, as well as prior knowledge of common object shapes learned from large-scale shape repositories. We use vision first, applying neural networks with learned shape priors to predict an object's 3D shape from a single-view color image. We then use tactile sensing to refine the shape; the robot actively touches the object regions where the visual prediction has high uncertainty. Our method efficiently builds the 3D shape of common objects from a color image and a small number of tactile explorations (around 10). Our setup is easy to apply and has potentials to help robots better perform grasping or manipulation tasks on real-world objects.

IROS Conference 2018 Conference Paper

Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing

Anurag Ajay
Jiajun Wu 0001
Nima Fazeli
Maria Bauzá 0001
Leslie Pack Kaelbling
Joshua B. Tenenbaum
Alberto Rodriguez 0003

An efficient, generalizable physical simulator with universal uncertainty estimates has wide applications in robot state estimation, planning, and control. In this paper, we build such a simulator for two scenarios, planar pushing and ball bouncing, by augmenting an analytical rigid-body simulator with a neural network that learns to model uncertainty as residuals. Combining symbolic, deterministic simulators with learnable, stochastic neural nets provides us with expressiveness, efficiency, and generalizability simultaneously. Our model outperforms both purely analytical and purely learned simulators consistently on real, standard benchmarks. Compared with methods that model uncertainty using Gaussian processes, our model runs much faster, generalizes better to new object shapes, and is able to characterize the complex distribution of object trajectories.

UAI Conference 2018 Conference Paper

Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks

David Zheng
Vinson Luo
Jiajun Wu 0001
Joshua B. Tenenbaum

We propose a framework for the completely unsupervised learning of latent object properties from their interactions: the perceptionprediction network (PPN). Consisting of a perception module that extracts representations of latent object properties and a prediction module that uses those extracted properties to simulate system dynamics, the PPN can be trained in an end-to-end fashion purely from samples of object dynamics. The representations of latent object properties learned by PPNs not only are sufficient to accurately simulate the dynamics of systems comprised of previously unseen objects, but also can be translated directly into human-interpretable properties (e. g. mass, coefficient of restitution) in an entirely unsupervised manner. Crucially, PPNs also generalize to novel scenarios: their gradient-based training can be applied to many dynamical systems and their graph-based structure functions over systems comprised of different numbers of objects. Our results demonstrate the efficacy of graphbased neural architectures in object-centric inference and prediction tasks, and our model has the potential to discover relevant object properties in systems that are not yet well understood.