新闻
PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Researchers developed PAC-MAN, a framework combining control-barrier functions with reinforcement learning to enable humanoid robots to dodge incoming objects using only onboard camera vision.
- 为何重要
- Roboticists building real-time safety systems for humanoids need practical perception-aware methods that work with limited onboard sensors rather than perfect state information.
- 注意
- The approach succeeds on 95% of throws in testing but relies on semantic segmentation and specific camera setups; performance degrades significantly without accurate ball tracking or privileged information.
收听本摘要
- eval
- benchmark
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。