Meng Song, Yuhan Liu, Zhengqin Li, Manmohan Chandraker
University of California, San Diego
Real-world applications require a robot operating in the physical world with awareness of potential risks besides accomplishing the task. A large part of risky behaviors arises from interacting with objects in ignorance of affordance. To prevent the agent from making unsafe decisions, we propose to train a robotic agent by reinforcement learning to execute tasks with an awareness of physical properties such as mass and friction in an indoor environment. We achieve this through a novel physics-inspired reward function that encourages the agent to learn a policy discerning different masses and friction coefficients. We introduce two novel and challenging indoor rearrangement tasks -- the variable friction pushing task and the variable mass pushing task -- that allow evaluation of the learned policies in trading off performance and physics-inspired risk. Our results demonstrate that by equipping with the proposed reward, the agent is able to learn policies choosing the pushing targets or goal-reaching trajectories with minimum physical cost, which can be further utilized as a precaution to constrain the agent's behavior in a safety-critic environment.
We thank NSF CAREER 1751365, CHASE-CI and generous gifts from Adobe, Google and Qualcomm.
@misc{https://doi.org/10.48550/arxiv.2206.12784,
doi = {10.48550/ARXIV.2206.12784},
url = {https://arxiv.org/abs/2206.12784},
author = {Song, Meng and Liu, Yuhan and Li, Zhengqin and Chandraker, Manmohan},
keywords = {Robotics (cs.RO), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Learning to Rearrange with Physics-Inspired Risk Awareness},
publisher = {arXiv},
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}