mlsanityData to 14 Oct 2026

MAVRL: Learn to Fly in Cluttered Environments with Varying Speed

arXiv 2402.08381 ↗First posted 13 Feb 2024cs.ROcited by 13

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

Abstract (arXiv)

Many existing obstacle avoidance algorithms overlook the crucial balance between safety and agility, especially in environments of varying complexity. In our study, we introduce an obstacle avoidance pipeline based on reinforcement learning. This pipeline enables drones to adapt their flying speed according to the environmental complexity. Moreover, to improve the obstacle avoidance performance in cluttered environments, we propose a novel latent space. The latent space in this representation is explicitly trained to retain memory of previous depth map observations. Our findings confirm that varying speed leads to a superior balance of success rate and agility in cluttered environments. Additionally, our memory-augmented latent representation outperforms the latent representation commonly used in reinforcement learning. Finally, after minimal fine-tuning, we successfully deployed our network on a real drone for enhanced obstacle avoidance.

Key facts. Cited by 13 papers in the map (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 18 of its 28 references that are in the map. First posted on arXiv 13 Feb 2024.

Builds on

18 of 28 references.

References · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016Tutorial on Variational Autoencoderscited by 409
  3. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 233
  4. 2021Learning High-Speed Flight in the Wildcited by 128
  5. 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 111
  6. 2020BADGR: An Autonomous Self-Supervised Learning-Based Navigation Systemcited by 102
  7. 2020Flightmare: A Flexible Quadrotor Simulatorcited by 84
  8. 2018Robot Motion Planning in Learned Latent Spacescited by 42
  9. 2017Learning to Fly by Crashingcited by 41
  10. 2021Learning a State Representation and Navigation in Cluttered and Dynamic Environmentscited by 41
  11. 2023Agilicious: Open-Source and Open-Hardware Agile Quadrotor for Vision-Based Flightcited by 30
  12. 2018Memory-based Deep Reinforcement Learning for Obstacle Avoidance in UAV with Limited Environment Knowledgecited by 26
6 more
  1. 2022Learning Perception-Aware Agile Flight in Cluttered Environmentscited by 23
  2. 2022Motion Primitives-based Navigation Planning using Deep Collision Predictioncited by 11
  3. 2023AvoidBench: A high-fidelity vision-based obstacle avoidance benchmarking suite for multi-rotorscited by 8
  4. 2023Semantically-enhanced Deep Collision Prediction for Autonomous Navigation using Aerial Robotscited by 7
  5. 2023Task-driven Compression for Collision Encoding based on Depth Imagescited by 7
  6. 2023SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representationscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 7.

13 papers.

Sort:

By area:

  1. 2024Learning Speed Adaptation for Flight in Cluttercited by 14
  2. 2025SkyDreamer: Interpretable End-to-End Vision-Based Drone Racing with Model-Based Reinforcement Learningcited by 8
  3. 2025Flying on Point Clouds with Reinforcement Learningcited by 7
  4. 2025RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigationcited by 6
  5. 2025Depth Transfer: Learning to See Like a Simulator for Real-World Drone Navigationcited by 3
  6. 2026AirDreamer: Generalist Drone Navigation with World Modelscited by 3
  7. 2025Towards Task-Oriented Flying: Framework, Infrastructure, and Principlescited by 1
  8. 2026High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learningcited by 1
  9. 2026Curriculum Reinforcement Learning for Quadrotor Racing with Random Obstaclescited by 1
  10. 2026Zero-Shot UAV Navigation in Forests via Relightable 3D Gaussian Splattingcited by 0
  11. 2026CMRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environmentscited by 0
  12. 2026Aerial Inspection Behaviors via RL-based Quadrotor Control for Under-canopy Forest Environmentscited by 0
1 more
  1. 2026Vision-Guided Outdoor Flight and Obstacle Evasion via Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Time-optimal Flight in Cluttered Environments via Safe Reinforcement Learning
  2. 2024Learning Generalizable Policy for Obstacle-Aware Autonomous Drone Racing
  3. 2025Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racing
  4. 2026Learning-Based Dynamic Obstacle Avoidance for a UAV Using Only Three Range Sensors
  5. 2024Multi-UAV Formation Control with Static and Dynamic Obstacle Avoidance via Reinforcement Learning
  6. 2024NavRL: Learning Safe Flight in Dynamic Environments
  7. 2025LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation
  8. 2024Dual Agent Learning Based Aerial Trajectory Tracking