paper-with-me

홈 › Papers

From Mystery to Mastery: Failure Diagnosis for Improving Manipulation Policies

2024-12-03 · Som Sagar, Jiafei Duan, Sreevishakh Vasudevan, Yifan Zhou, Heni Ben Amor, Dieter Fox, Ransalu Senanayake

Robot manipulation policies often fail for unknown reasons, posing significant challenges for real-world deployment. Researchers and engineers typically address these failures using heuristic approaches, which are not only labor-intensive and costly but also prone to overlooking critical failure modes (FMs). This paper introduces Robot Manipulation Diagnosis (RoboMD), a systematic framework designed to automatically identify FMs arising from unanticipated changes in the environment. Considering the vast space of potential FMs in a pre-trained manipulation policy, we leverage deep reinforcement learning (deep RL) to explore and uncover these FMs using a specially trained vision-language embedding that encodes a notion of failures. This approach enables users to probabilistically quantify and rank failures in previously unseen environmental conditions. Through extensive experiments across various manipulation tasks and algorithms, we demonstrate RoboMD's effectiveness in diagnosing unknown failures in unstructured environments, providing a systematic pathway to improve the robustness of manipulation policies.

📄 PDF Abstract BibTeX arXiv:2412.02818

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningRobot Manipulation

Similar Papers 제목 키워드 기반

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning

2026-03-10 · Zhanyi Sun, Shuran Song arxiv

We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a "distribution contraction" operator to refine pretrained generative robot policies. DICE-RL t…

Reinforcement LearningSkill Mastery

ATOM-Bench: A Real-World Benchmark for Atomic Skills and Compositional Generalization in Manipulation Policies

2026-06-15 · Zenan Wu, Bingqing Wei, Lu Liu, Zheqi He 외 arxiv

Generalist manipulation policies are increasingly presented as foundation models for robotic control, but their real-world generalization remains difficult to diagnose. A policy may succeed on demonstrated tasks while st…

Deployment-Time Reliability of Learned Robot Policies

2026-03-12 · Christopher Agia arxiv

Recent advances in learning-based robot manipulation have produced policies with remarkable capabilities. Yet, reliability at deployment remains a fundamental barrier to real-world use, where distribution shift, compound…

Robot Manipulation

Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents

2026-06-22 · Haoran Zhang, Yifu Lu, Boyang Wang, Xuhui Kang 외 arxiv

Long-horizon tasks are common in real-world robotic deployments, yet failure detection for such tasks remains underexplored. Detecting failures in long-horizon robotic tasks is particularly challenging because failure on…

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation

2026-06-02 · Jiahao Xu, Peiyuan Wang, Hanzhuo Zhang, Zihao Yu 외 arxiv

In robotic manipulation, the tight coupling between grasping and motion planning often obscures the true source of failure, leading to inefficient trial-and-error. To enable efficient long-horizon manipulation, we propos…

Motion Planning