light_mode

From Mystery to Mastery: Failure Diagnosis for Improving Manipulation Policies

Som Sagar, Jiafei Duan, Sreevishakh Vasudevan, Yifan Zhou, Heni Ben Amor, Dieter Fox, Ransalu Senanayake
Robotics: Science and Systems (RSS) Workshop on Out-of-Distribution Generalization in Robotics, 2025

From Mystery to Mastery teaser figure

In one sentence. A deep reinforcement learning framework that systematically diagnoses failure modes of robot manipulation policies under unseen environmental variations, and uses the discovered vulnerabilities to fine-tune and improve policy robustness.

picture_as_pdf PDF code Code

Summary

Robot manipulation policies are highly vulnerable to external variations in the real world. This workshop paper presents a deep reinforcement learning framework that diagnoses the conditions under which a manipulation policy fails, without requiring exhaustive physical testing, and then uses the discovered failure modes to fine-tune the policy for improved robustness under out-of-distribution variations.

Note. This is the workshop version of RoboMD (ICLR 2026). Both share arXiv identifier 2412.02818; please cite the ICLR version.

BibTeX

@inproceedings{sagar2025mystery,
  title     = {From Mystery to Mastery: Failure Diagnosis for Improving Manipulation Policies},
  author    = {Sagar, Som and Duan, Jiafei and Vasudevan, Sreevishakh and Zhou, Yifan and Ben Amor, Heni and Fox, Dieter and Senanayake, Ransalu},
  booktitle = {Robotics: Science and Systems (RSS) Workshop on Out-of-Distribution Generalization in Robotics},
  year      = {2025}
}

Topics

failure diagnosis, robot manipulation, out-of-distribution generalization, reinforcement learning, policy robustness

About the author. Som Sagar is a computer science PhD student at Arizona State University, advised by Ransalu Senanayake in the LENS Lab. He works on reinforcement learning for post-training and agentic LLM systems, and on failure diagnosis, red teaming, and safety evaluation of foundation models, vision-language models, and robot manipulation policies.

home Homepage library_books All publications description CV school Google Scholar