arXiv subjects

Claire Chen

Publications and source records attributed to Claire Chen.

33 records · Page 2Linked to original sources

arXiv2025

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

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.

cs.LG↗

arXiv2025

DexForce: Extracting Force-informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation

Imitation learning requires high-quality demonstrations consisting of sequences of state-action pairs. For contact-rich dexterous manipulation tasks that require dexterity, the actions in these state-action pairs must produce the right forces. Current widely-used methods for collecting dexterous manipulation demonstrations are difficult to use for demonstrating contact-rich tasks due to unintuitive human-to-robot motion retargeting and the lack of direct haptic feedback. Motivated by these concerns, we propose DexForce. DexForce leverages contact forces, measured during kinesthetic demonstrations, to compute force-informed actions for policy learning. We collect demonstrations for six tasks and show that policies trained on our force-informed actions achieve an average success rate of 76% across all tasks. In contrast, policies trained directly on actions that do not account for contact forces have near-zero success rates. We also conduct a study ablating the inclusion of force data in policy observations. We find that while using force data never hurts policy performance, it helps most for tasks that require advanced levels of precision and coordination, like opening an AirPods case and unscrewing a nut.

cs.RO↗

arXiv2025

AO-Grasp: Articulated Object Grasp Generation

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. Project website: https://stanford-iprl-lab.github.io/ao-grasp

cs.RO↗

arXiv2025

Doubly Optimal Policy Evaluation for Reinforcement Learning

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting policy or data-processing method substantially deteriorates the variance of evaluation results over long time steps. Thus, policy evaluation often suffers from large variance and requires massive data to achieve the desired accuracy. In this work, we design an optimal combination of data-collecting policy and data-processing baseline. Theoretically, we prove our doubly optimal policy evaluation method is unbiased and guaranteed to have lower variance than previously best-performing methods. Empirically, compared with previous works, we show our method reduces variance substantially and achieves superior empirical performance.

cs.LG↗

arXiv2025

Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning

In reinforcement learning, classic on-policy evaluation methods often suffer from high variance and require massive online data to attain the desired accuracy. Previous studies attempt to reduce evaluation variance by searching for or designing proper behavior policies to collect data. However, these approaches ignore the safety of such behavior policies -- the designed behavior policies have no safety guarantee and may lead to severe damage during online executions. In this paper, to address the challenge of reducing variance while ensuring safety simultaneously, we propose an optimal variance-minimizing behavior policy under safety constraints. Theoretically, while ensuring safety constraints, our evaluation method is unbiased and has lower variance than on-policy evaluation. Empirically, our method is the only existing method to achieve both substantial variance reduction and safety constraint satisfaction. Furthermore, we show our method is even superior to previous methods in both variance reduction and execution safety.

cs.LG↗

arXiv2025

A Study of Afterglow Signatures in NaI and CsI Scintillator Modules for the Background and Transient Observer Instrument on COSI

We present measurements of the afterglow signatures in NaI(Tl) and CsI(Tl) detector modules as part of the Background and Transient Observer (BTO) mission detector trade-study. BTO is a NASA Student Collaboration Project flying on the Compton Spectrometer and Imager (COSI) Small Explorer mission in 2027. The detectors utilized in this study are cylindrical in shape with a height and diameter of 5.1 cm and were read out by silicon photomultipliers (SiPMs). We conducted a radiation campaign at the HIMAC accelerator in Japan where the scintillators were irradiated with a 230 MeV/u helium beam (He beam) and 350 MeV/u carbon beam (C beam). We find that both the CsI and NaI scintillators exhibit afterglow signatures when irradiated with the C and He beams. The CsI crystal exhibits a stronger afterglow intensity with afterglow pulses occurring for an average 2.40 ms for C and 0.9 ms for He after the initial particle pulse. The duration of afterglow pulses in CsI is 8.6x and 5.6x the afterglow signal duration in NaI for C and He (0.28 ms and 0.16 ms, respectively). Although CsI has advantages such as a higher light yield and radiation hardness, the stronger afterglows in the CsI detector increase the complexity of the electronics and lead to a ~7x larger dead time per afterglow event or a ~3x higher energy threshold value. We use the measured dead times to predict the amount of observing time lost to afterglow-inducing events for an instrument like BTO in low Earth orbit. We simulate the background rates in a BTO-like orbit and find a total value of 114 counts/s for the full two-detector system. Based on the particle energies in the HIMAC experiment, we then determine that an event with sufficient energy to produce an afterglow signal occurs once every ~70 s and ~1.4 s in NaI and CsI detectors, respectively. Thus, we conclude that NaI is the better choice for the BTO mission.

astro-ph.IM↗

arXiv2024

Efficient Multi-Policy Evaluation for Reinforcement Learning

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.

cs.LG↗

arXiv2024

What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?

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 effort, 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 for additional details and visuals.

cs.RO↗

arXiv2024

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

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.

cs.CV↗

arXiv2023

The Compton Spectrometer and Imager

The Compton Spectrometer and Imager (COSI) is a NASA Small Explorer (SMEX) satellite mission in development with a planned launch in 2027. COSI is a wide-field gamma-ray telescope designed to survey the entire sky at 0.2-5 MeV. It provides imaging, spectroscopy, and polarimetry of astrophysical sources, and its germanium detectors provide excellent energy resolution for emission line measurements. Science goals for COSI include studies of 0.511 MeV emission from antimatter annihilation in the Galaxy, mapping radioactive elements from nucleosynthesis, determining emission mechanisms and source geometries with polarization measurements, and detecting and localizing multimessenger sources. The instantaneous field of view for the germanium detectors is >25% of the sky, and they are surrounded on the sides and bottom by active shields, providing background rejection as well as allowing for detection of gamma-ray bursts and other gamma-ray flares over most of the sky. In the following, we provide an overview of the COSI mission, including the science, the technical design, and the project status.

astro-ph.HE↗

arXiv2023

The cosipy library: COSI's high-level analysis software

The Compton Spectrometer and Imager (COSI) is a selected Small Explorer (SMEX) mission launching in 2027. It consists of a large field-of-view Compton telescope that will probe with increased sensitivity the under-explored MeV gamma-ray sky (0.2-5 MeV). We will present the current status of cosipy, a Python library that will perform spectral and polarization fits, image deconvolution, and all high-level analysis tasks required by COSI's broad science goals: uncovering the origin of the Galactic positrons, mapping the sites of Galactic nucleosynthesis, improving our models of the jet and emission mechanism of gamma-ray bursts (GRBs) and active galactic nuclei (AGNs), and detecting and localizing gravitational wave and neutrino sources. The cosipy library builds on the experience gained during the COSI balloon campaigns and will bring the analysis of data in the Compton regime to a modern open-source likelihood-based code, capable of performing coherent joint fits with other instruments using the Multi-Mission Maximum Likelihood framework (3ML). In this contribution, we will also discuss our plans to receive feedback from the community by having yearly software releases accompanied by publicly-available data challenges.

astro-ph.HE↗

arXiv2023

Category-Independent Articulated Object Tracking with Factor Graphs

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.

cs.RO↗

arXiv2022

Real Robot Challenge: A Robotics Competition in the Cloud

Dexterous manipulation remains an open problem in robotics. To coordinate efforts of the research community towards tackling this problem, we propose a shared benchmark. We designed and built robotic platforms that are hosted at MPI for Intelligent Systems and can be accessed remotely. Each platform consists of three robotic fingers that are capable of dexterous object manipulation. Users are able to control the platforms remotely by submitting code that is executed automatically, akin to a computational cluster. Using this setup, i) we host robotics competitions, where teams from anywhere in the world access our platforms to tackle challenging tasks ii) we publish the datasets collected during these competitions (consisting of hundreds of robot hours), and iii) we give researchers access to these platforms for their own projects.

cs.RO↗

arXiv2021

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

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.

cs.RO↗

arXiv2021

Dexterous Manipulation Primitives for the Real Robot Challenge

This report describes our approach for Phase 3 of the Real Robot Challenge. To solve cuboid manipulation tasks of varying difficulty, we decompose each task into the following primitives: moving the fingers to the cuboid to grasp it, turning it on the table to minimize orientation error, and re-positioning it to the goal position. We use model-based trajectory optimization and control to plan and execute these primitives. These grasping, turning, and re-positioning primitives are sequenced with a state-machine that determines which primitive to execute given the current object state and goal. Our method shows robust performance over multiple runs with randomized initial and goal positions. With this approach, our team placed second in the challenge, under the anonymous name "sombertortoise" on the leaderboard. Example runs of our method solving each of the four levels can be seen in this video (https://www.youtube.com/watch?v=I65Kwu9PGmg&list=PLt9QxrtaftrHGXcp4Oh8-s_OnQnBnLtei&index=1).

cs.RO↗