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

arXiv: https://arxiv.org/abs/2605.14810 · HTML: https://mlsanity.com/paper/2605.14810/

## 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.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 19 of 19)

- [Learning High-Speed Flight in the Wild](https://mlsanity.com/paper/2110.05113/) (2021)
- [Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs](https://mlsanity.com/paper/2110.05038/) (2021)
- [Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning](https://mlsanity.com/paper/2310.10943/) (2023)
- [Flightmare: A Flexible Quadrotor Simulator](https://mlsanity.com/paper/2009.00563/) (2020)
- [EGO-Planner: An ESDF-free Gradient-based Local Planner for Quadrotors](https://mlsanity.com/paper/2008.08835/) (2020)
- [FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry](https://mlsanity.com/paper/2408.14035/) (2024)
- [Learning a State Representation and Navigation in Cluttered and Dynamic Environments](https://mlsanity.com/paper/2103.04351/) (2021)
- [Agilicious: Open-Source and Open-Hardware Agile Quadrotor for Vision-Based Flight](https://mlsanity.com/paper/2307.06100/) (2023)
- [Learning Speed Adaptation for Flight in Clutter](https://mlsanity.com/paper/2403.04586/) (2024)
- [Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance](https://mlsanity.com/paper/2405.10391/) (2024)
- [Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding](https://mlsanity.com/paper/2402.03947/) (2024)
- [MAVRL: Learn to Fly in Cluttered Environments with Varying Speed](https://mlsanity.com/paper/2402.08381/) (2024)
- [Motion Primitives-based Navigation Planning using Deep Collision Prediction](https://mlsanity.com/paper/2201.03254/) (2022)
- [Vision-based Learning for Drones: A Survey](https://mlsanity.com/paper/2312.05019/) (2023)
- [Semantically-enhanced Deep Collision Prediction for Autonomous Navigation using Aerial Robots](https://mlsanity.com/paper/2307.11522/) (2023)
- [Flying on Point Clouds with Reinforcement Learning](https://mlsanity.com/paper/2503.00496/) (2025)
- [RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation](https://mlsanity.com/paper/2502.02054/) (2025)
- [Quadrotor Navigation using Reinforcement Learning with Privileged Information](https://mlsanity.com/paper/2509.08177/) (2025)
- [Learning Agile Flight Maneuvers: Deep SE(3) Motion Planning and Control for Quadrotors](https://mlsanity.com/paper/2209.11097/) (2022)

## 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/