让机器人用头戴相机感知球，实时躲避并精准避开身体各部位。
PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball
- 结合控制屏障与真实感知，用分割深度图实现全身安全避让。
- 在真实机器人上成功躲避95%投掷，仅靠头戴相机和语义分割。
- 适合对感知受限环境下机器人避障有需求的研究者。
我们提出PAC-MAN，一种感知意识的CBF-RL框架，将控制屏障安全机制与部署时真实的机载传感结合，实现人形机器人在躲避球游戏中的全身安全控制。部署策略仅通过头戴摄像头的分割深度图感知球体，训练阶段则利用基于每个身体部件的控制屏障（CBF）指导避让行为，并引入对抗性运动先验以规范逃避反应。我们在一个可控的任意链接接触基准上评估，包含单次投掷和循环部署场景（机器人投完后返回站位并恢复）。结果表明，该策略性能接近具备特权状态观测的参考系统：仅用固定机载摄像头即可实现有效躲避。我们发现可用的屏障结构依赖于感知可观测性：关节级CBF在球体状态准确时表现最佳，在固定摄像头观测下仅作训练引导时性能下降，而使用球追踪云台或特权运行时滤波器后可恢复。因此，我们将轻量化的链路级CBF策略零样本部署至真实单元树G1机器人，其在感知不完美条件下仍能成功躲避95%的投掷，并利用语义分割识别不同球体。
原文摘要 · Abstract (English)
We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball. The deployed policy sees the ball only as segmentation-masked depth from a head-mounted camera, while training-time CBF guidance represents clearance to every body link, and an adversarial motion prior regularizes the resulting evasive reflexes. We evaluate on a controlled any-link contact benchmark with seeded throws in two regimes: single throws and a deployment loop in which the robot walks back to its station and recovers between throws. On this benchmark, the policy comes within a few points of a privileged state oracle: a fixed onboard camera alone is adequate for evasion. We find that usable barrier structure depends on perceptual observability: Joint-CBF gives the best performance with accurate ball states, degrades under fixed-camera observations when used only as training guidance, and recovers with a ball-tracking gimbal or privileged runtime filter. We therefore deploy a lightweight Link-CBF policy zero-shot on the Unitree G1 in the real world, where it tolerates imperfect perception, succeeds on 95% of throws, and uses semantic segmentation to dodge different balls.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。