DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 12 Sep 2025.
Builds on
25 of 36 references.
References · 25
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
- 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
- 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
- 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
- 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 407
- 2021Learning High-Speed Flight in the Wildcited by 128
- 2022Accelerated Policy Learning with Parallel Differentiable Simulationcited by 104
- 2023STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learningcited by 89
- 2020Flightmare: A Flexible Quadrotor Simulatorcited by 84
- 2021Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Controlcited by 77
13 more
- 2020Deep Drone Acrobaticscited by 75
- 2024Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physicscited by 45
- 2023OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Controlcited by 33
- 2024CGD: Constraint-Guided Diffusion Policies for UAV Trajectory Planningcited by 21
- 2024Learning Quadrotor Control From Visual Features Using Differentiable Simulationcited by 19
- 2023End-to-end Reinforcement Learning for Time-Optimal Quadcopter Flightcited by 17
- 2025Aerial Gym Simulator: A Framework for Highly Parallelized Simulation of Aerial Robotscited by 15
- 2024Seeing Through Pixel Motion: Learning Obstacle Avoidance from Optical Flow with One Cameracited by 13
- 2024What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Studycited by 11
- 2024VisFly: An Efficient and Versatile Simulator for Training Vision-based Flightcited by 7
- 2021Robust Navigation for Racing Drones based on Imitation Learning and Modularizationcited by 5
- 2023Efficient and Robust Time-Optimal Trajectory Planning and Control for Agile Quadrotor Flightcited by 3
- 2025Towards Task-Oriented Flying: Framework, Infrastructure, and Principlescited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.