{"ID":2871801,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.10247","arxiv_id":"2509.10247","title":"DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning","abstract":"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.","short_abstract":"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 ca...","url_abs":"https://arxiv.org/abs/2509.10247","url_pdf":"https://arxiv.org/pdf/2509.10247v1","authors":"[\"Xinhong Zhang\",\"Runqing Wang\",\"Yunfan Ren\",\"Jian Sun\",\"Hao Fang\",\"Jie Chen\",\"Gang Wang\"]","published":"2025-09-12T13:44:49Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false,"code_links":[{"ID":609897,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2871801,"paper_url":"https://arxiv.org/abs/2509.10247","paper_title":"DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning","repo_url":"https://github.com/flyingbitac/diffaero","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}