Author name cluster

Claire Chen

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.

8 papers

2 author rows

ICML Conference 2025 Conference Paper

Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel

Carlota Parés-Morlans
Michelle Yi
Claire Chen
Sarah A. Wu
Rika Antonova
Tobias Gerstenberg
Jeannette Bohg

Tasks that involve complex interactions between objects with unknown dynamics make planning before execution difficult. These tasks require agents to iteratively improve their actions after actively exploring causes and effects in the environment. For these type of tasks, we propose Causal-PIK, a method that leverages Bayesian optimization to reason about causal interactions via a Physics-Informed Kernel to help guide efficient search for the best next action. Experimental results on Virtual Tools and PHYRE physical reasoning benchmarks show that Causal-PIK outperforms state-of-the-art results, requiring fewer actions to reach the goal. We also compare Causal-PIK to human studies, including results from a new user study we conducted on the PHYRE benchmark. We find that Causal-PIK remains competitive on tasks that are very challenging, even for human problem-solvers.

Details

AAAI Conference 2025 Conference Paper

Efficient Multi-Policy Evaluation for Reinforcement Learning

Shuze Daniel Liu
Claire Chen
Shangtong Zhang

To unbiasedly evaluate multiple target policies, the dominant approach among RL practitioners is to run and evaluate each target policy separately. However, this evaluation method is far from efficient because samples are not shared across policies, and running target policies to evaluate themselves is actually not optimal. In this paper, we address these two weaknesses by designing a tailored behavior policy to reduce the variance of estimators across all target policies. Theoretically, we prove that executing this behavior policy with manyfold fewer samples outperforms on-policy evaluation on every target policy under characterized conditions. Empirically, we show our estimator has a substantially lower variance compared with previous best methods and achieves state-of-the-art performance in a broad range of environments.

PDF Details DOI

IROS Conference 2024 Conference Paper

AO-Grasp: Articulated Object Grasp Generation

Carlota Parés-Morlans
Claire Chen
Yijia Weng
Michelle Yi
Yuying Huang
Nick Heppert
Linqi Zhou
Leonidas J. Guibas

We introduce AO-Grasp, a grasp proposal method that generates 6 DoF grasps that enable robots to interact with articulated objects, such as opening and closing cabinets and appliances. AO-Grasp consists of two main contributions: the AO-Grasp Model and the AO-Grasp Dataset. Given a segmented partial point cloud of a single articulated object, the AO-Grasp Model predicts the best grasp points on the object with an Actionable Grasp Point Predictor. Then, it finds corresponding grasp orientations for each of these points, resulting in stable and actionable grasp proposals. We train the AO-Grasp Model on our new AO-Grasp Dataset, which contains 78K actionable parallel-jaw grasps on synthetic articulated objects. In simulation, AO-Grasp achieves a 45. 0% grasp success rate, whereas the highest performing baseline achieves a 35. 0% success rate. Additionally, we evaluate AO-Grasp on 120 real-world scenes of objects with varied geometries, articulation axes, and joint states, where AO-Grasp produces successful grasps on 67. 5% of scenes, while the baseline only produces successful grasps on 33. 3% of scenes. To the best of our knowledge, AO-Grasp is the first method for generating 6 DoF grasps on articulated objects directly from partial point clouds without requiring part detection or hand-designed grasp heuristics. The AO-Grasp Dataset and a pre-trained AO-Grasp model are available at our project website: https://stanford-iprl-lab.github.io/ao-grasp/.

Details

ICRA Conference 2024 Conference Paper

What Do We Learn from a Large-Scale Study of Pre-Trained Visual Representations in Sim and Real Environments?

Sneha Silwal
Karmesh Yadav
Tingfan Wu
Jay Vakil
Arjun Majumdar
Sergio Arnaud
Claire Chen
Vincent-Pierre Berges

We present a large empirical investigation on the use of pre-trained visual representations (PVRs) for training downstream policies that execute real-world tasks. Our study involves five different PVRs, each trained for five distinct manipulation or indoor navigation tasks. We performed this evaluation using three different robots and two different policy learning paradigms. From this e ort, we can arrive at three insights: 1) the performance trends of PVRs in the simulation are generally indicative of their trends in the real world, 2) the use of PVRs enables a first-of-its-kind result with indoor ImageNav (zero-shot transfer to a held-out scene in the real world), and 3) the benefits from variations in PVRs, primarily data-augmentation and fine-tuning, also transfer to the real-world performance. See project website 1 for additional details and visuals.

Details

YNICL Journal 2023 Journal Article

Early amygdala and ERC atrophy linked to 3D reconstruction of rostral neurofibrillary tau tangle pathology in Alzheimer’s disease

Kaitlin M. Stouffer
Claire Chen
Sue Kulason
Eileen Xu
Menno P. Witter
Can Ceritoglu
Marilyn S. Albert
Susumu Mori

Previous research has emphasized the unique impact of Alzheimer's Disease (AD) pathology on the medial temporal lobe (MTL), a reflection that tau pathology is particularly striking in the entorhinal and transentorhinal cortex (ERC, TEC) early in the course of disease. However, other brain regions are affected by AD pathology during its early phases. Here, we use longitudinal diffeomorphometry to measure the atrophy rate from MRI of the amygdala compared with that in the ERC and TEC in cognitively unimpaired (CU) controls, CU individuals who progressed to mild cognitive impairment (MCI), and individuals with MCI who progressed to dementia of the AD type (DAT), using a dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Our results show significantly higher atrophy rates of the amygdala in both groups of 'converters' (CU→MCI, MCI→DAT) compared to controls, with rates of volume loss comparable to rates of thickness loss in the ERC and TEC. We localize atrophy within the amygdala within each of these groups using fixed effects modeling. Controlling for the familywise error rate highlights the medial regions of the amygdala as those with significantly higher atrophy in both groups of converters than in controls. Using our recently developed method, referred to as Projective LDDMM, we map measures of neurofibrillary tau tangles (NFTs) from digital pathology to MRI atlases and reconstruct dense 3D spatial distributions of NFT density within regions of the MTL. The distribution of NFTs is consistent with the spatial distribution of MR measured atrophy rates, revealing high densities (and atrophy) in the amygdala (particularly medial), ERC, and rostral third of the MTL. The similarity of the location of NFTs in AD and shape changes in a well-defined clinical population suggests that amygdalar atrophy rate, as measured through MRI may be a viable biomarker for AD.

Details DOI

NeurIPS Conference 2023 Conference Paper

Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?

Arjun Majumdar
Karmesh Yadav
Sergio Arnaud
Jason Ma
Claire Chen
Sneha Silwal
Aryan Jain
Vincent-Pierre Berges

We present the largest and most comprehensive empirical study of pre-trained visual representations (PVRs) or visual ‘foundation models’ for Embodied AI. First, we curate CortexBench, consisting of 17 different tasks spanning locomotion, navigation, dexterous, and mobile manipulation. Next, we systematically evaluate existing PVRs and find that none are universally dominant. To study the effect of pre-training data size and diversity, we combine over 4, 000 hours of egocentric videos from 7 different sources (over 4. 3M images) and ImageNet to train different-sized vision transformers using Masked Auto-Encoding (MAE) on slices of this data. Contrary to inferences from prior work, we find that scaling dataset size and diversity does not improve performance universally (but does so on average). Our largest model, named VC-1, outperforms all prior PVRs on average but does not universally dominate either. Next, we show that task- or domain-specific adaptation of VC-1 leads to substantial gains, with VC-1 (adapted) achieving competitive or superior performance than the best known results on all of the benchmarks in CortexBench. Finally, we present real-world hardware experiments, in which VC-1 and VC-1 (adapted) outperform the strongest pre-existing PVR. Overall, this paper presents no new techniques but a rigorous systematic evaluation, a broad set of findings about PVRs (that in some cases, refute those made in narrow domains in prior work), and open-sourced code and models (that required over 10, 000 GPU-hours to train) for the benefit of the research community.

PDF Details

IROS Conference 2022 Conference Paper

Category-Independent Articulated Object Tracking with Factor Graphs

Nick Heppert
Toki Migimatsu
Brent Yi
Claire Chen
Jeannette Bohg

Robots deployed in human-centric environments may need to manipulate a diverse range of articulated objects, such as doors, dishwashers, and cabinets. Articulated objects often come with unexpected articulation mechanisms that are inconsistent with categorical priors: for example, a drawer might rotate about a hinge joint instead of sliding open. We propose a category-independent framework for predicting the articulation models of unknown objects from sequences of RGB-D images. The prediction is performed by a two-step process: first, a visual perception module tracks object part poses from raw images, and second, a factor graph takes these poses and infers the articulation model including the current configuration between the parts as a 6D twist. We also propose a manipulation-oriented metric to evaluate predicted joint twists in terms of how well a compliant robot controller would be able to manipulate the articulated object given the predicted twist. We demonstrate that our visual perception and factor graph modules outperform baselines on simulated data and show the applicability of our factor graph on real world data.

Details

IROS Conference 2021 Conference Paper

TrajectoTree: Trajectory Optimization Meets Tree Search for Planning Multi-contact Dexterous Manipulation

Claire Chen
Preston Culbertson
Marion Lepert
Mac Schwager
Jeannette Bohg

Dexterous manipulation tasks often require contact switching, where fingers make and break contact with the object. We propose a method that plans trajectories for dexterous manipulation tasks involving contact switching using contact-implicit trajectory optimization (CITO) augmented with a high-level discrete contact sequence planner. We first use the high-level planner to find a sequence of finger contact switches given a desired object trajectory. With this contact sequence plan, we impose additional constraints in the CITO problem. We show that our method finds trajectories approximately 7 times faster than a general CITO baseline for a four-finger planar manipulation scenario. Furthermore, when executing the planned trajectories in a full dynamics simulator, we are able to more closely track the object pose trajectories planned by our method than those planned by the baselines.

Details