mlsanityData to 14 Oct 2026

AttentionSwarm: Reinforcement Learning with Attention Control Barier Function for Crazyflie Drones in Dynamic Environments

arXiv 2503.07376 ↗First posted 10 Mar 2025eess.SY cs.RO cs.SYcited by 0

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

Abstract (arXiv)

We introduce AttentionSwarm, a novel benchmark designed to evaluate safe and efficient swarm control in a dynamic drone racing scenario. Central to our approach is the Attention Model-Based Control Barrier Function (CBF) framework, which integrates attention mechanisms with safety-critical control theory to enable real-time collision avoidance and trajectory optimization. This framework dynamically prioritizes critical obstacles and agents in the swarm's vicinity using attention weights, while CBFs formally guarantee safety by enforcing collision-free constraints. The AttentionSwarm algorithm was developed and evaluated using a swarm of Crazyflie 2.1 micro quadrotors, which were tested indoors with the Vicon motion capture system to ensure precise localization and control. Experimental results show that our system achieves a 95-100% collision-free navigation rate in a dynamic multi-agent drone racing environment, underscoring its effectiveness and robustness in real-world scenarios. This work offers a promising foundation for safe, high-speed multi-robot applications in logistics, inspection, and racing.

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 30 of its 37 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

30 of 37 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025SafeSwarm: Decentralized Safe RL for the Swarm of Drones Landing in Dense Crowds13 Jan
  2. 2024NavRL: Learning Safe Flight in Dynamic Environments24 Sep
  3. 2024Vision-driven UAV River Following: Benchmarking with Safe Reinforcement Learning13 Sep
  4. 2024Demonstrating Agile Flight from Pixels without State Estimation18 Jun

Other references · 26

  1. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 176
  2. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 163
  3. 2020Learning to be Safe: Deep RL with a Safety Criticcited by 116
  4. 2021Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Controlcited by 77
  5. 2019Deep Drone Racing: From Simulation to Reality with Domain Randomizationcited by 76
  6. 2018Safe Reinforcement Learning with Model Uncertainty Estimatescited by 72
  7. 2023DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstaclescited by 37
  8. 2022Safe Reinforcement Learning for Legged Locomotioncited by 35
  9. 2024GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Controlcited by 22
  10. 2024X-MOBILITY: End-To-End Generalizable Navigation via World Modelingcited by 16
  11. 2023Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learningcited by 14
  12. 2024Learning Speed Adaptation for Flight in Cluttercited by 14
14 more
  1. 2020SL1-Simplex: Safe Velocity Regulation of Self-Driving Vehicles in Dynamic and Unforeseen Environmentscited by 9
  2. 2023Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learningcited by 8
  3. 2025UAV-VLRR: Vision-Language Informed NMPC for Rapid Response in UAV Search and Rescuecited by 7
  4. 2020Learning a Low-dimensional Representation of a Safe Region for Safe Reinforcement Learning on Dynamical Systemscited by 6
  5. 2024N-MPC for Deep Neural Network-Based Collision Avoidance exploiting Depth Imagescited by 6
  6. 2025Safe Multi-Agent Navigation guided by Goal-Conditioned Safe Reinforcement Learningcited by 6
  7. 2023Safety Guaranteed Robust Multi-Agent Reinforcement Learning with Hierarchical Control for Connected and Automated Vehiclescited by 5
  8. 2022Onboard Safety Guarantees for Racing Drones: High-speed Geofencing with Control Barrier Functionscited by 4
  9. 2024TornadoDrone: Bio-inspired DRL-based Drone Landing on 6D Platform with Wind Force Disturbancescited by 3
  10. 2021Aperiodic Communication for MPC in Autonomous Cooperative Landingcited by 2
  11. 2021Control Barrier Function Augmentation in Sampling-based Control Algorithm for Sample Efficiencycited by 2
  12. 2025AgilePilot: DRL-Based Drone Agent for Real-Time Motion Planning in Dynamic Environments by Leveraging Object Detectioncited by 2
  13. 2019A Safety Constrained Control Framework for UAVs in GPS Denied Environmentcited by 1
  14. 2024Safe Navigation in Unmapped Environments for Robotic Systems with Input Constraintscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024MARLander: A Local Path Planning for Drone Swarms using Multiagent Deep Reinforcement Learning ↗
  2. 2026Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX
  3. 2025Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racing
  4. 2025LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation
  5. 2026Curriculum Reinforcement Learning for Quadrotor Racing with Random Obstacles
  6. 2024Time-optimal Flight in Cluttered Environments via Safe Reinforcement Learning
  7. 2026MuJoCo-Drones-Gym: A GPU-Accelerated Multi-Drone Simulator for Control and Reinforcement Learning
  8. 2026Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation