Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ni, Minheng, Zhang, Lei, Chen, Zihan, Bai, Kaixin, Chen, Zhaopeng, Zhang, Jianwei, Zuo, Wangmeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910977090387968
author Ni, Minheng
Zhang, Lei
Chen, Zihan
Bai, Kaixin
Chen, Zhaopeng
Zhang, Jianwei
Zhang, Lei
Zuo, Wangmeng
author_facet Ni, Minheng
Zhang, Lei
Chen, Zihan
Bai, Kaixin
Chen, Zhaopeng
Zhang, Jianwei
Zhang, Lei
Zuo, Wangmeng
contents Unthinking execution of human instructions in robotic manipulation can lead to severe safety risks, such as poisonings, fires, and even explosions. In this paper, we present responsible robotic manipulation, which requires robots to consider potential hazards in the real-world environment while completing instructions and performing complex operations safely and efficiently. However, such scenarios in real world are variable and risky for training. To address this challenge, we propose Safety-as-policy, which includes (i) a world model to automatically generate scenarios containing safety risks and conduct virtual interactions, and (ii) a mental model to infer consequences with reflections and gradually develop the cognition of safety, allowing robots to accomplish tasks while avoiding dangers. Additionally, we create the SafeBox synthetic dataset, which includes one hundred responsible robotic manipulation tasks with different safety risk scenarios and instructions, effectively reducing the risks associated with real-world experiments. Experiments demonstrate that Safety-as-policy can avoid risks and efficiently complete tasks in both synthetic dataset and real-world experiments, significantly outperforming baseline methods. Our SafeBox dataset shows consistent evaluation results with real-world scenarios, serving as a safe and effective benchmark for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18289
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy
Ni, Minheng
Zhang, Lei
Chen, Zihan
Bai, Kaixin
Chen, Zhaopeng
Zhang, Jianwei
Zhang, Lei
Zuo, Wangmeng
Robotics
Computer Vision and Pattern Recognition
Unthinking execution of human instructions in robotic manipulation can lead to severe safety risks, such as poisonings, fires, and even explosions. In this paper, we present responsible robotic manipulation, which requires robots to consider potential hazards in the real-world environment while completing instructions and performing complex operations safely and efficiently. However, such scenarios in real world are variable and risky for training. To address this challenge, we propose Safety-as-policy, which includes (i) a world model to automatically generate scenarios containing safety risks and conduct virtual interactions, and (ii) a mental model to infer consequences with reflections and gradually develop the cognition of safety, allowing robots to accomplish tasks while avoiding dangers. Additionally, we create the SafeBox synthetic dataset, which includes one hundred responsible robotic manipulation tasks with different safety risk scenarios and instructions, effectively reducing the risks associated with real-world experiments. Experiments demonstrate that Safety-as-policy can avoid risks and efficiently complete tasks in both synthetic dataset and real-world experiments, significantly outperforming baseline methods. Our SafeBox dataset shows consistent evaluation results with real-world scenarios, serving as a safe and effective benchmark for future research.
title Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.18289