cs.RONov 7, 2026

BRACE: Belief-guided Residual Adaptive Control for Safe Navigation under Unknown Disturbances

Authors: Jaeyoun Choi, Niklas Schmid, Oswin So, Augustinos Saravanos, Chuchu Fan

Organizations: Reliable Autonomous Systems Lab, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Automatic Control Laboratory (IfA), ETH Zürich, 8092 Zürich, Switzerland

Abstract

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.

Figures & tables

Explore similar work

CardsList
  1. WAND: Learning Robust Navigation under Complex Wind Disturbances and Dense Obstacles for Quadrotors

    Oct 8, 2026Zhonghan Tang, Chenhui Li, Shuai Liang +5Disturbance RejectionRobot Navigation

  2. Safety-critical Control Under Partial Observability: Reach-Avoid POMDP meets Belief Space Control

    Mar 11, 2026Matti Vahs, Joris Verhagen, Jana TumovaControl Lyapunov FunctionsPartially Observable Markov Decision Processes

  3. DR-IPC: Disturbance-Resilient Integrated Planning and Control for LiDAR-Based Quadrotor Navigation

    Oct 2, 2026Peng Liu, Jingyan Wang, Qipeng Ye +5Disturbance RejectionUAV Navigation