mlsanityData to 14 Oct 2026

CMRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environments

arXiv 2605.14810 ↗First posted 14 May 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

In obstacle avoidance navigation of unmanned aerial vehicles (UAVs), variations in obstacle scale have received less attention than obstacle number or density. Existing methods typically extract purely geometric features from single-frame depth observations. Such representations tend to neglect small obstacles and lose spatial context under occlusions caused by large obstacles, leading to noticeable degradation in environments with multi-scale obstacles. To address this issue, we propose CMRL, a Collision-aware and Memory-enhanced Reinforcement Learning framework for UAV navigation. The collision-aware latent representation encodes risk-sensitive depth cues to preserve fine-grained obstacle structures, thereby improving sensitivity to small obstacles. The temporal memory module integrates observations across frames, mitigating partial observability caused by large-obstacle occlusions. We evaluate CMRL with multi-scale obstacles, including ultra-small and extra-large obstacle settings. Results show that CMRL outperforms state-of-the-art baselines across all scales, with success rate gains of 0.47 and 0.29 in the ultra-small and extra-large settings, respectively. More importantly, CMRL achieves reliable navigation in cluttered outdoor environments. The code is available at https://honghongdev.github.io/camerl/

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 28 references that are in the map. First posted on arXiv 14 May 2026.

Builds on

19 of 28 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Quadrotor Navigation using Reinforcement Learning with Privileged Information9 Sep
  2. 2025Flying on Point Clouds with Reinforcement Learning1 Mar
  3. 2025RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation4 Feb
  4. 2024MAVRL: Learn to Fly in Cluttered Environments with Varying Speed13 Feb
  5. 2024Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding6 Feb

Other references · 14

  1. 2021Learning High-Speed Flight in the Wildcited by 128
  2. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 122
  3. 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 111
  4. 2020Flightmare: A Flexible Quadrotor Simulatorcited by 84
  5. 2020EGO-Planner: An ESDF-free Gradient-based Local Planner for Quadrotorscited by 55
  6. 2024FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometrycited by 44
  7. 2021Learning a State Representation and Navigation in Cluttered and Dynamic Environmentscited by 41
  8. 2023Agilicious: Open-Source and Open-Hardware Agile Quadrotor for Vision-Based Flightcited by 30
  9. 2024Learning Speed Adaptation for Flight in Cluttercited by 14
  10. 2024Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidancecited by 14
  11. 2022Motion Primitives-based Navigation Planning using Deep Collision Predictioncited by 11
  12. 2023Vision-based Learning for Drones: A Surveycited by 11
2 more
  1. 2023Semantically-enhanced Deep Collision Prediction for Autonomous Navigation using Aerial Robotscited by 7
  2. 2022Learning Agile Flight Maneuvers: Deep SE(3) Motion Planning and Control for Quadrotorscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Robust Policy Learning for Multi-UAV Collision Avoidance with Causal Feature Selection ↗
  2. 2026Learning-Based Dynamic Obstacle Avoidance for a UAV Using Only Three Range Sensors
  3. 2024Multi-UAV Formation Control with Static and Dynamic Obstacle Avoidance via Reinforcement Learning
  4. 2025Collision-Aware Object-Goal Visual Navigation via Two-Stage Deep Reinforcement Learning
  5. 2026Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation
  6. 2026High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learning
  7. 2025Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racing
  8. 2026Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction