← 研踪 PaperTrailarXiv:2611.10938 · v1
BRACE: Belief-guided Residual Adaptive Control for Safe Navigation under Unknown Disturbances
首次提交 2026-11-08 04:05
版本更新 2026-11-08 04:05
雷达观测 2026-11-10 11:14
摘要
Disturbances encountered during autonomous navigation generally vary across space, often discontinuously, as obstacles redirect wind and changing terrain alters traction. Tracking controllers typically assume sufficient control authority to mitigate disturbances and maintain safety; the regime where this assumption fails remains underexplored. We present Belief-guided Residual Adaptive Control (BRACE), a hierarchical reinforcement learning (RL) framework for reach-avoid navigation under unknown, bounded, spatially varying disturbances. BRACE infers a disturbance belief from model prediction errors and uses that to condition a high-level policy that adapts the reference trajectory. The policy combines a nominal and a belief-guided residual term, trained jointly with a likelihood-ratio advantage reweighting heuristic. We evaluate BRACE in three simulated quadcopter environments with abruptly switching wind fields, and validate it on Crazyflie hardware with fan-generated disturbances. Across these settings, BRACE improves reach-avoid performance over model predictive control and RL baselines.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-08 04:05 · 最新观测版本
BRACE: Belief-guided Residual Adaptive Control for Safe Navigation under Unknown Disturbances
Disturbances encountered during autonomous navigation generally vary across space, often discontinuously, as obstacles redirect wind and changing terrain alters traction. Tracking controllers typically assume sufficient control authority to mitigate disturbances and maintain safety; the regime where this assumption fails remains underexplored. We present Belief-guided Residual Adaptive Control (BRACE), a hierarchical reinforcement learning (RL) framework for reach-avoid navigation under unknown, bounded, spatially varying disturbances. BRACE infers a disturbance belief from model prediction errors and uses that to condition a high-level policy that adapts the reference trajectory. The policy combines a nominal and a belief-guided residual term, trained jointly with a likelihood-ratio advantage reweighting heuristic. We evaluate BRACE in three simulated quadcopter environments with abruptly switching wind fields, and validate it on Crazyflie hardware with fan-generated disturbances. Across these settings, BRACE improves reach-avoid performance over model predictive control and RL baselines.
查看此版本解读 →查看此版本原文 ↗