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

2025-03-10

AI Summary

This work addresses the challenge of safe and efficient cooperative control for Crazyflie quadcopter swarms in dynamic indoor environments. We propose a real-time obstacle avoidance and trajectory optimization framework that integrates attention mechanisms with Control Barrier Functions (CBFs). Our key innovation is the Safe Attention Network (SAN), which dynamically weights critical obstacles and neighboring agents to enable adaptive safety-priority modulation—marking the first integration of formal safety guarantees with end-to-end reinforcement learning for micro-scale quadcopter swarms. Experimental validation was conducted on a Vicon motion-capture system with Crazyflie 2.1 embedded platforms: landing accuracy reached 3.02 cm within 23 s; game-based navigation achieved 100% collision-free performance; and dynamic multi-agent racing attained a 95% success rate—all under zero collisions across all scenarios. Results demonstrate strong robustness and real-time capability in realistic indoor settings.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Behavior Learning & Control

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We introduce AttentionSwarm, a novel benchmark designed to evaluate safe and efficient swarm control across three challenging environments: a landing environment with obstacles, a competitive drone game setting, and 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 swarms vicinity using attention weights, while CBFs formally guarantee safety by enforcing collision-free constraints. The safe attention net 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 landing accuracy of 3.02 cm with a mean time of 23 s and collision-free landings in a dynamic landing environment, 100% and collision-free navigation in a drone game environment, and 95% and collision-free navigation for a dynamic multiagent drone racing environment, underscoring its effectiveness and robustness in real-world scenarios. This work offers a promising foundation for applications in dynamic environments where safety and fastness are paramount.

Problem

• Safe and efficient swarm control in dynamic environments
• Real-time collision avoidance and trajectory optimization
• Precision landing and navigation in challenging drone scenarios

Innovation

• Attention Model Based Control Barrier Function
• Real-time collision avoidance and trajectory optimization
• Safe attention net algorithm for drone swarms