发表机构
Massachusetts Institute of Technology（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对状态估计误差下避障的安全控制问题，提出DMR-CBF与NMR-CBF两种新型CBF，经理论分析、数值实验与Unitree Go2部署验证，其在保障安全性的同时降低了保守性与计算成本。
AI 中文摘要
安全滤波器是保障安全关键系统约束的有效工具，但现有多数方法假设状态信息完美，而实际中几乎无法实现。近期研究通过开发对状态估计误差鲁棒的滤波机制缩小该差距，但这类方法在估计误差增大时仍可能出现安全违规或过于保守的行为。本文聚焦避障问题，提出两种新型控制障碍函数（CBF）形式：漂移-测量鲁棒（DMR）-CBF和神经测量鲁棒（NMR）-CBF。DMR-CBF在标准CBF条件基础上，增加对漂移动力学最坏情况不确定性的内部优化，提升对估计误差的鲁棒性；随后用该DMR-CBF监督NMR-CBF的预训练阶段，NMR-CBF将内部优化替换为学习项，再通过可微轨迹回滚进行微调，得到的滤波器在达到与DMR-CBF相当的经验安全性的同时，降低了保守性和计算成本。本文对DMR-CBF进行了理论分析，并在平面双积分器和12维四旋翼上开展数值实验，结果显示两种所提方法均可防止碰撞，而其他鲁棒方法要么失效要么过于保守；最终将NMR-CBF部署到Unitree Go2上，使其在里程计误差下成功通过障碍物区域，而标准CBF在该误差下会发生碰撞。
英文摘要
Safety filters are an effective tool for enforcing constraints in safety-critical systems, but most existing methods assume perfect state information, which is rarely available in practice. Recent work has begun to close this gap by developing filtering mechanisms that are robust to state estimation error, but these methods can still exhibit safety violations or overly conservative behavior as estimation error grows. Focusing on obstacle avoidance, we develop two new control barrier function (CBF) formulations: drift-measurement-robust (DMR)-CBFs and neural measurement-robust (NMR)-CBFs. The DMR-CBF augments the standard CBF condition with an inner optimization over the worst-case uncertainty in the drift dynamics, improving robustness to estimation error. This DMR-CBF then supervises a pretraining phase for the NMR-CBF, which replaces the inner optimization with a learned term. The NMR-CBF is subsequently finetuned through differentiable trajectory rollouts, yielding a filter that achieves empirical safety comparable to the DMR-CBF while reducing both conservativeness and computational cost. We provide theoretical analysis of the DMR-CBF along with numerical results on a planar double integrator and a 12D quadrotor, where both proposed approaches prevent collisions while other robust methods either fail or are overly conservative. Finally, we deployed the NMR-CBF on a Unitree Go2, enabling successful navigation of an obstacle field under odometry errors that caused a standard CBF to collide.
Comments8 Pages, 6 figures
