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

Key points

• Existing learning-based navigation policies typically rely on obstacle perception and proprioceptive observations, requiring the policy to infer time-varying disturbance effects implicitly and thereby limiting robustness under partial observability.1
• This paper proposes WAND (Wind-Aware Navigation with Disturbance Estimation), a reinforcement learning framework for navigation under time-varying wind disturbances in dense obstacle fields.1
• Specifically, WAND estimates wind-induced disturbance acceleration from historical proprioceptive states using a Temporal Convolutional Network (TCN).1
• The dual use of the estimate couples disturbance-conditioned navigation with feedforward disturbance rejection.1

Sources (1)

• [1]WAND: Learning Robust Navigation under Complex Wind Disturbances and Dense Obstacles for Quadrotors
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 12:17 PM

  Robust navigation in cluttered environments remains a fundamental challenge for quadrotors, particularly when strong wind disturbances arise, which perturb vehicle dynamics, limit control authority, and substantially increase collision risk.

  Existing learning-based navigation policies typically rely on obstacle perception and proprioceptive observations, requiring the policy to infer time-varying disturbance effects implicitly and thereby limiting robustness under partial observability.

Extractive summary: sentences quoted from the sources.