Failure Prediction from Limited Hardware Demonstrations
This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions. Prediction of failures in real-world robotic systems either requires accurate model information or extensive testing. Partial knowledge of the system model makes simulation-based failure prediction unreliable. Moreover, obtaining such demonstrations is expensive, and could potentially be risky for the robotic system to repeatedly fail during data collection. This work presents a novel three-step methodology for discovering failures that occur in the true system by using a combination of a limited number of demonstrations from the true system and the failure information processed through sampling-based testing of a model dynamical system. Given a limited budget 𝑁 of demonstrations from true system and a model dynamics (with potentially large modeling e
Failure Prediction from Limited Hardware Demonstrations Anjali Parashar, Kunal Garg, Joseph Zhang, and Chuchu Fan The authors are with the Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, USA. Email: {anjalip,kgarg,jzha,chuchu}@mit.edu Abstract Prediction of failures in real-world robotic systems either requires accurate model information or extensive testing. Partial knowledge of the system model makes simulation-based failure prediction unreliable. Moreover, obtaining such demonstrations is expensive, and could potentially be risky for the robotic system to
Explore this link on the map →related reading
- State of Robot Learning, December 2025vedder.io
- ProbabilisticRobotics.pdfdocs.ufpr.br
- Updating Robot Safety Representations Online from Natural Language Feedback ∗ Equal Contribution. † Equal Advising. 1School of Engineering, Federal University of Minas Gerais, Brazil. Email: leohmcs@ufmg.br. Work done during Robotics Institarxiv.org
- pdfopenreview.net
- [1805.12114] Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelsar5iv.labs.arxiv.org
- Predicting LLM Safety Before Release by Simulating Deploymentcdn.openai.com
- Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RLarxiv.org
- Predicting model behavior before release by simulating deployment | OpenAIopenai.com
- Eric Jang: Robots Must Be Ephemeralizedblog.evjang.com
- Interlatent — RL Platform for Physical AIinterlatent.com
- Eric Jangblog.evjang.com
- How Can We Make Robotics More like Generative Modeling? | Eric Jangevjang.com