5 papers · 1 filter
Position: Good Embodied Reward Models Need Bad Behavior Data
Ran Tian, Yilin Wu, Andrea Bajcsy
This position paper argues that to obtain reliable embodied reward models, the community must invest in ``bad'' robot data: failed, suboptimal, error-prone, and even hazardous beha…
AnySafe: Adapting Latent Safety Filters at Runtime via Safety Constraint Parameterization in the Latent Space
Sankalp Agrawal, Junwon Seo, Kensuke Nakamura +2
Recent works have shown that foundational safe control methods, such as Hamilton-Jacobi (HJ) reachability analysis, can be applied in the latent space of world models. While this e…
Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control
Yuxin Chen, Jianglan Wei, Chenfeng Xu +4
World models enable robots to "imagine" future observations given current observations and planned actions, and have been increasingly adopted as generalized dynamics models to fac…
From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
Yilin Wu, Ran Tian, Gokul Swamy +1
While generative robot policies have demonstrated significant potential in learning complex, multimodal behaviors from demonstrations, they still exhibit diverse failures at deploy…
Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
Ran Tian, Yilin Wu, Chenfeng Xu +3
Visuomotor robot policies, increasingly pre-trained on large-scale datasets, promise significant advancements across robotics domains. However, aligning these policies with end-use…