10 papers
Rethinking Safety for Generalist Robots
Rohan Sinha, Anushri Dixit, Ran Tian +2
Generalist robots promise to transform our society: the same system that prepares a meal or folds laundry might also repair a car, inspect infrastructure, or care for a loved one.…
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…
StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement
Junwon Seo, Sushant Veer, Ran Tian +6
Video world models (WMs) have shown promise for policy evaluation and improvement by imagining realistic future observations conditioned on ego-robot actions. While WMs can model d…
AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement Learning
Yaomin Wang, Jianting Pan, Ran Tian +4
The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value acro…
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…
QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception
Seth Z. Zhao, Huizhi Zhang, Zhaowei Li +11
Cooperative perception through Vehicle-to-Everything (V2X) communication offers significant potential for enhancing vehicle perception by mitigating occlusions and expanding the fi…
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…
Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Models Using Implicit Feedback from Pre-training Demonstrations
Ran Tian, Kratarth Goel
Recent advancements in LLMs have revolutionized motion generation models in embodied applications. While LLM-type auto-regressive motion generation models benefit from training sca…
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…