RESC: A Reinforcement Learning Based Search-to-Control Framework for Quadrotor Local Planning in Dense Environments

TL;DR

This paper presents RESC, a reinforcement learning-based framework that enhances quadrotor local planning in dense environments by integrating visibility path searching with RL control, improving agility and efficiency.

Contribution

The paper introduces a novel Search-to-Control framework combining heuristic path search with RL control generation, directly considering quadrotor dynamics for aggressive maneuvering.

Findings

Improved time efficiency over existing methods

Enhanced dynamic maneuverability demonstrated in simulations and real-world tests

Robustness confirmed in complex environments

Abstract

Agile flight in complex environments poses significant challenges to current motion planning methods, as they often fail to fully leverage the quadrotor dynamic potential, leading to performance failures and reduced efficiency during aggressive maneuvers.Existing approaches frequently decouple trajectory optimization from control generation and neglect the dynamics, further limiting their ability to generate aggressive and feasible motions.To address these challenges, we introduce an enhanced Search-to-Control planning framework that integrates visibility path searching with reinforcement learning (RL) control generation, directly accounting for dynamics and bridging the gap between planning and control.Our method first extracts control points from collision-free paths using a proposed heuristic search, which are then refined by an RL policy to generate low-level control commands for the quadrotor controller, utilizing reduced-dimensional obstacle observations for efficient inference with lightweight neural networks.We validate the framework through simulations and real-world experiments, demonstrating improved time efficiency and dynamic maneuverability compared to existing methods, while confirming its robustness and applicability.