Saved in:
Bibliographic Details
Main Authors: Zhang, Xinhong, Wang, Runqing, Ren, Yunfan, Sun, Jian, Fang, Hao, Chen, Jie, Wang, Gang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.10247
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908535498997760
author Zhang, Xinhong
Wang, Runqing
Ren, Yunfan
Sun, Jian
Fang, Hao
Chen, Jie
Wang, Gang
author_facet Zhang, Xinhong
Wang, Runqing
Ren, Yunfan
Sun, Jian
Fang, Hao
Chen, Jie
Wang, Gang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10247
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning
Zhang, Xinhong
Wang, Runqing
Ren, Yunfan
Sun, Jian
Fang, Hao
Chen, Jie
Wang, Gang
Robotics
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.
title DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning
topic Robotics
url https://arxiv.org/abs/2509.10247