Author name cluster

Chen Yu

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.

10 papers

2 author rows

IROS Conference 2024 Conference Paper

State Estimation Transformers for Agile Legged Locomotion

Chen Yu
Yichu Yang
Tianlin Liu
Yangwei You
Mingliang Zhou 0003
Diyun Xiang

We propose a state estimation method that can accurately predict the robot’s privileged states to push the limits of quadruped robots in executing advanced skills such as jumping in the wild. In particular, we present the State Estimation Transformers (SET), an architecture that casts the state estimation problem as conditional sequence modeling. SET outputs the robot states that are hard to obtain directly in the real world, such as the body height and velocities, by leveraging a causally masked Transformer. By conditioning an autoregressive model on the robot’s past states, our SET model can predict these privileged observations accurately even in highly dynamic locomotions. We evaluate our methods on three tasks — running jumping, running backflipping, and running sideslipping — on a low-cost quadruped robot, Cyberdog2. Results show that SET can outperform other methods in estimation accuracy and transferability in the simulation as well as success rates of jumping and triggering a recovery controller in the real world, suggesting the superiority of such a Transformer-based explicit state estimator in highly dynamic locomotion tasks.

Details

ICRA Conference 2023 Conference Paper

Multi-embodiment Legged Robot Control as a Sequence Modeling Problem

Chen Yu
Weinan Zhang 0001
Hang Lai
Zheng Tian 0002
Laurent Kneip
Jun Wang 0012

Robots are traditionally bounded by a fixed embodiment during their operational lifetime, which limits their ability to adapt to their surroundings. Co-optimizing control and morphology of a robot, however, is often inefficient due to the complex interplay between the controller and morphology. In this paper, we propose a learning-based control method that can inherently take morphology into consideration such that once the control policy is trained in the simulator, it can be easily deployed to real robots with different embodiments. In particular, we present the Embodiment-aware Transformer (EAT), an architecture that casts this control problem as conditional sequence modeling. EAT outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregressive model on the desired robot embodiment, past states, and actions, our EAT model can generate future actions that best fit the current robot embodiment. Experimental results show that EAT can outperform all other alternatives in embodiment-varying tasks, and succeed in an example of real-world evolution tasks: stepping down a stair through updating the morphology alone. We hope that EAT will inspire a new push toward real-world evolution across many domains, where algorithms like EAT can blaze a trail by bridging the field of evolutionary robotics and big data sequence modeling.

Details

ICRA Conference 2023 Conference Paper

Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformer

Hang Lai
Weinan Zhang 0001
Xialin He
Chen Yu
Zheng Tian 0002
Yong Yu 0001
Jun Wang 0012

Deep reinforcement learning has recently emerged as an appealing alternative for legged locomotion over multiple terrains by training a policy in physical simulation and then transferring it to the real world (i. e. , sim-to-real transfer). Despite considerable progress, the capacity and scalability of traditional neural networks are still limited, which may hinder their applications in more complex environments. In contrast, the Transformer architecture has shown its superiority in a wide range of large-scale sequence modeling tasks, including natural language processing and decision-making problems. In this paper, we propose Terrain Transformer (TERT), a high-capacity Transformer model for quadrupedal locomotion control on various terrains. Furthermore, to better leverage Transformer in sim-to-real scenarios, we present a novel two-stage training framework consisting of an offline pretraining stage and an online correction stage, which can naturally integrate Transformer with privileged training. Extensive experiments in simulation demonstrate that TERT outperforms state-of-the-art baselines on different terrains in terms of return, energy consumption and control smoothness. In further real-world validation, TERT successfully traverses nine challenging terrains, including sand pit and stair down, which can not be accomplished by strong baselines.

Details

TIST Journal 2022 Journal Article

Decentralized Online Learning: Take Benefits from Others’ Data without Sharing Your Own to Track Global Trend

Wendi Wu
Zongren Li
Yawei Zhao
Chen Yu
Peilin Zhao
Ji Liu
Kunlun He

Decentralized online learning (online learning in decentralized networks) has been attracting more and more attention, since it is believed that decentralized online learning can help data providers cooperatively better solve their online problems without sharing their private data to a third party or other providers. Typically, the cooperation is achieved by letting the data providers exchange their models between neighbors, e.g., recommendation model. However, the best regret bound for a decentralized online learning algorithm is 𝒪( n √ T ), where n is the number of nodes (or users) and T is the number of iterations. This is clearly insignificant, since this bound can be achieved without any communication in the networks. This reminds us to ask a fundamental question: Can people really get benefit from the decentralized online learning by exchanging information? In this article, we studied when and why the communication can help the decentralized online learning to reduce the regret. Specifically, each loss function is characterized by two components: the adversarial component and the stochastic component. Under this characterization, we show that decentralized online gradient enjoys a regret bound \( {\mathcal {O}(\sqrt {n^2TG^2 + n T \sigma ^2})} \), where G measures the magnitude of the adversarial component in the private data (or equivalently the local loss function) and σ measures the randomness within the private data. This regret suggests that people can get benefits from the randomness in the private data by exchanging private information. Another important contribution of this article is to consider the dynamic regret—a more practical regret to track users’ interest dynamics. Empirical studies are also conducted to validate our analysis.

Details DOI

IROS Conference 2022 Conference Paper

OmniWheg: An Omnidirectional Wheel-Leg Transformable Robot

Ruixiang Cao
Jun Gu
Chen Yu
Andre Rosendo

This paper presents the design, analysis, and performance evaluation of an omnidirectional transformable wheel-leg robot called OmniWheg. We design a novel mechanism consisting of a separable omni-wheel and 4-bar linkages, allowing the robot to transform between omni-wheeled and legged modes smoothly. In wheeled mode, the robot can move in all directions and efficiently adjust the relative position of its wheels, while it can overcome common obstacles in legged mode, such as stairs and steps. Unlike other articles studying whegs, this implementation with omnidirectional wheels allows the correction of misalignments between right and left wheels before traversing obstacles, which effectively improves the success rate and simplifies the preparation process before the wheel-leg transformation. We describe the design concept, mechanism, and the dynamic characteristic of the wheel-leg structure. We then evaluate its performance in various scenarios, including passing obstacles, climbing steps of different heights, and turning/moving omnidirectionally. Our results confirm that this mobile platform can overcome common indoor obstacles and move flexibly on the flat ground with the new transformable wheel-leg mechanism, while keeping a high degree of stability.

Details

NeurIPS Conference 2019 Conference Paper

A Self Validation Network for Object-Level Human Attention Estimation

Zehua Zhang
Chen Yu
David Crandall

Due to the foveated nature of the human vision system, people can focus their visual attention on a small region of their visual field at a time, which usually contains only a single object. Estimating this object of attention in first-person (egocentric) videos is useful for many human-centered real-world applications such as augmented reality applications and driver assistance systems. A straightforward solution for this problem is to pick the object whose bounding box is hit by the gaze, where eye gaze point estimation is obtained from a traditional eye gaze estimator and object candidates are generated from an off-the-shelf object detector. However, such an approach can fail because it addresses the where and the what problems separately, despite that they are highly related, chicken-and-egg problems. In this paper, we propose a novel unified model that incorporates both spatial and temporal evidence in identifying as well as locating the attended object in firstperson videos. It introduces a novel Self Validation Module that enforces and leverages consistency of the where and the what concepts. We evaluate on two public datasets, demonstrating that Self Validation Module significantly benefits both training and testing and that our model outperforms the state-of-the-art.

PDF Details

NeurIPS Conference 2019 Conference Paper

Model Compression with Adversarial Robustness: A Unified Optimization Framework

Shupeng Gui
Haotao Wang
Haichuan Yang
Chen Yu
Zhangyang Wang
Ji Liu

Deep model compression has been extensively studied, and state-of-the-art methods can now achieve high compression ratios with minimal accuracy loss. This paper studies model compression through a different lens: could we compress models without hurting their robustness to adversarial attacks, in addition to maintaining accuracy? Previous literature suggested that the goals of robustness and compactness might sometimes contradict. We propose a novel Adversarially Trained Model Compression (ATMC) framework. ATMC constructs a unified constrained optimization formulation, where existing compression means (pruning, factorization, quantization) are all integrated into the constraints. An efficient algorithm is then developed. An extensive group of experiments are presented, demonstrating that ATMC obtains remarkably more favorable trade-off among model size, accuracy and robustness, over currently available alternatives in various settings. The codes are publicly available at: https: //github. com/shupenggui/ATMC.

PDF Details

NeurIPS Conference 2018 Conference Paper

Toddler-Inspired Visual Object Learning

Sven Bambach
David Crandall
Linda Smith
Chen Yu

Real-world learning systems have practical limitations on the quality and quantity of the training datasets that they can collect and consider. How should a system go about choosing a subset of the possible training examples that still allows for learning accurate, generalizable models? To help address this question, we draw inspiration from a highly efficient practical learning system: the human child. Using head-mounted cameras, eye gaze trackers, and a model of foveated vision, we collected first-person (egocentric) images that represents a highly accurate approximation of the "training data" that toddlers' visual systems collect in everyday, naturalistic learning contexts. We used state-of-the-art computer vision learning models (convolutional neural networks) to help characterize the structure of these data, and found that child data produce significantly better object models than egocentric data experienced by adults in exactly the same environment. By using the CNNs as a modeling tool to investigate the properties of the child data that may enable this rapid learning, we found that child data exhibit a unique combination of quality and diversity, with not only many similar large, high-quality object views but also a greater number and diversity of rare views. This novel methodology of analyzing the visual "training data" used by children may not only reveal insights to improve machine learning, but also may suggest new experimental tools to better understand infant learning in developmental psychology.

PDF Details

AAAI Conference 2004 Conference Paper

On the Integration of Grounding Language and Learning Objects

Chen Yu
Dana H. Ballard

This paper presents a multimodal learning system that can ground spoken names of objects in their physical referents and learn to recognize those objects simultaneously from naturally co-occurring multisensory input. There are two technical problems involved: (1) the correspondence problem in symbol grounding – how to associate words (symbols) with their perceptually grounded meanings from multiple cooccurrences between words and objects in the physical environment. (2) object learning – how to recognize and categorize visual objects. We argue that those two problems can be fundamentally simplified by considering them in a general system and incorporating the spatio-temporal and crossmodal constraints of multimodal data. The system collects egocentric data including image sequences as well as speech while users perform natural tasks. It is able to automatically infer the meanings of object names from vision, and categorize objects based on teaching signals potentially encoded in speech. The experimental results reported in this paper reveal the effectiveness of using multimodal data and integrating heterogeneous techniques in machine learning, natural language processing and computer vision.

PDF Details

IJCAI Conference 1983 Conference Paper

AI Research in China: A Review

Jiang Xinsong
Song Guoning
Chen Yu

Since 1970's AI research has been g e t t i n g more and more a c t i v e in China and c e r t a i n u s e f u l r e s u l t s have been achieved. This paper is intended to review b r i e f l y what was and is going on in AI f i e l d of China.

PDF