DiffAero用GPU加速实现无人机策略快速学习，效率远超传统仿真器。
DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning
- 基于GPU全并行物理与渲染，消除数据传输瓶颈。
- 在消费级硬件上数小时内训练出鲁棒飞行策略。
- 支持多传感器与混合学习算法，适合强化学习研究者。
本文介绍DiffAero，一个轻量级、GPU加速且完全可微分的仿真框架，用于高效四旋翼控制策略学习。DiffAero支持环境级和智能体级并行，集成多种动力学模型、可定制传感器堆栈（IMU、深度相机、LiDAR）及多样飞行任务，提供统一的GPU原生训练接口。通过在GPU上完全并行化物理计算与渲染，DiffAero消除了CPU-GPU数据传输瓶颈，仿真吞吐量提升数个数量级。相比现有仿真器，DiffAero不仅提供高性能仿真，还作为可微分与混合学习算法的研究平台。大量基准测试与真实飞行实验表明，结合DiffAero与混合学习算法，可在消费级硬件上数小时内学习到鲁棒飞行策略。代码已开源：https://github.com/flyingbitac/diffaero。
原文摘要 · Abstract (English)
This letter introduces DiffAero, a lightweight, GPU-accelerated, and fully differentiable simulation framework designed for efficient quadrotor control policy learning. DiffAero supports both environment-level and agent-level parallelism and integrates multiple dynamics models, customizable sensor stacks (IMU, depth camera, and LiDAR), and diverse flight tasks within a unified, GPU-native training interface. By fully parallelizing both physics and rendering on the GPU, DiffAero eliminates CPU-GPU data transfer bottlenecks and delivers orders-of-magnitude improvements in simulation throughput. In contrast to existing simulators, DiffAero not only provides high-performance simulation but also serves as a research platform for exploring differentiable and hybrid learning algorithms. Extensive benchmarks and real-world flight experiments demonstrate that DiffAero and hybrid learning algorithms combined can learn robust flight policies in hours on consumer-grade hardware. The code is available at https://github.com/flyingbitac/diffaero.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。