无需传感器，让机器人在推进器故障时自动适应
Privileged Critic Training Enables Sensor-Free Thruster Fault Adaptation in End-to-End RL
- 训练时让价值网络看懂真实故障状态，策略网络仅用普通观测
- 四路同时故障下成功率达70.2%，接近理想情况的84%
- 适合无人值守机器人在无专用传感条件下的容错导航
推进器驱动的机器人在故障容错导航中需在线适应非二值、不可完全观测的故障：推进器可能持续退化、完全失效或卡死。传统故障检测依赖部署时无法获得的专用传感器；能观测真实故障状态的最优控制器同样不现实。本文证明：特权评论家训练足以实现无传感器故障自适应——在训练中赋予PPO价值函数对真实退化状态dgt的访问权限，而策略网络仅接收标准任务观测，即可在部署时补偿故障，无需专用故障传感器。我们提出RAFT（RNN异构容错）策略，使用带循环记忆的不对称评论家进行训练。在含8个推进器和1个反作用轮的浮游平台机器人上测试，最多支持4个推进器同时故障，其成功率可达70.2%，弥补了从无故障感知基线（4.8%）到知晓完整退化状态的最优策略（82.4%）之间84%的差距。所有代码、模型检查点与数据均开源。
原文摘要 · Abstract (English)
Fault-tolerant navigation for thruster-actuated robots requires online adaptation to failures that are neither binary nor fully observable: thrusters may degrade continuously, fail dead, or jam stuck-open. Classical fault detection pipelines require dedicated sensors unavailable at deployment; oracle controllers that observe the true failure state are equally impractical. We show that privileged critic training is sufficient for sensor-free fault adaptation: giving the PPO value function access to the true degradation state dgt during training, while the actor receives only standard task observations, shapes a policy that compensates for failures at deployment without any dedicated fault sensing. We propose RAFT (Recurrent Asymmetric Fault Tolerant), a policy with recurrent memory trained with a privileged asymmetric critic. Evaluated on a floating-platform robot (8 thrusters, 1 reaction wheel) under up to four simultaneous thruster failures, RAFT achieves 70.2% success at four concurrent failures, closing 84% of the gap from a failure-naive baseline (4.8%) to an oracle policy that sees the full degradation state at deployment (82.4%). All code, checkpoints, and data are open-source.
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。