计算机科学
机器人
敏捷软件开发
人工智能
人工神经网络
深度学习
渲染(计算机图形)
实时计算
可微函数
深层神经网络
移动机器人
原始数据
控制工程
动力学仿真
软件
模拟
群机器人
作业成本法
群体行为
避障
控制系统
简单(哲学)
机器人学
国家(计算机科学)
人机交互
作者
Lin, Weiyao,Zhang, Yuang,Hu, Yu,Song, Yunlong,Zou, Danping
标识
DOI:10.6084/m9.figshare.26298379
摘要
Swarm navigation in cluttered environments is a grand challenge in robotics. This work combines deep learning with first-principle physics through differentiable simulation to enable autonomous navigation of multiple aerial robots through complex environments at high speed. Our approach optimizes a neural network control policy directly by backpropagating loss gradients through the robot simulation using a simple point-mass physics model and a depth rendering engine. Despite this simplicity, our method excels in challenging tasks for both multi-agent and single-agent applications with zero-shot sim-to-real transfer. In multi-agent scenarios, our system demonstrates self-organized behavior, enabling autonomous coordination without communication or centralized planning—an achievement not seen in existing traditional or learning-based methods. In single- agent scenarios, our system achieves a 90% success rate in navigating through complex environments, significantly surpassing the 60% success rate of the previ- ous state-of-the-art approach. Our system can operate without state estimation and adapt to dynamic obstacles. In real-world forest environments, it navigates at speeds up to 20 m/s, doubling the speed of previous imitation learning- based solutions. Notably, all these capabilities are deployed on a budget-friendly $21 computer, costing less than 5% of a GPU-equipped board used in existing systems.
科研通智能强力驱动
Strongly Powered by AbleSci AI