Flying through cluttered and dynamic environments with LiDAR

2025-04-24

AI Summary

To address the challenge of real-time multi-scale moving obstacle avoidance for UAVs in cluttered, dynamic environments (e.g., forests), this paper proposes the first full-stack onboard LiDAR navigation system integrating an M-detector—designed for lightweight mobile object detection—with a dynamic-prediction-enhanced integrated planning and control framework (DynIPC). Implemented on ROS2 for embedded real-time deployment, the system encompasses LiDAR perception, moving-object detection, trajectory prediction, and closed-loop control. Its key innovation lies in the deep coupling of lightweight detection with prediction-driven planning and control, significantly reducing end-to-end latency. Simulation results demonstrate an 18% improvement in task success rate and a 23% reduction in average flight time over state-of-the-art methods. Real-world experiments validate robustness and practicality, achieving real-time avoidance of sudden obstacles—including pedestrians and vehicles—in dense forest environments.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Navigating unmanned aerial vehicles (UAVs) through cluttered and dynamic environments remains a significant challenge, particularly when dealing with fast-moving or sudden-appearing obstacles. This paper introduces a complete LiDAR-based system designed to enable UAVs to avoid various moving obstacles in complex environments. Benefiting the high computational efficiency of perception and planning, the system can operate in real time using onboard computing resources with low latency. For dynamic environment perception, we have integrated our previous work, M-detector, into the system. M-detector ensures that moving objects of different sizes, colors, and types are reliably detected. For dynamic environment planning, we incorporate dynamic object predictions into the integrated planning and control (IPC) framework, namely DynIPC. This integration allows the UAV to utilize predictions about dynamic obstacles to effectively evade them. We validate our proposed system through both simulations and real-world experiments. In simulation tests, our system outperforms state-of-the-art baselines across several metrics, including success rate, time consumption, average flight time, and maximum velocity. In real-world trials, our system successfully navigates through forests, avoiding moving obstacles along its path.

Problem

• Enable UAVs to navigate cluttered dynamic environments using LiDAR
• Detect and avoid moving obstacles in real-time with low latency
• Integrate dynamic object predictions for effective obstacle evasion

Innovation

• LiDAR-based system for UAV obstacle avoidance
• M-detector for reliable moving object detection
• DynIPC framework for dynamic obstacle prediction