10 papers
DiffDreamer: Coupling World Models with Differentiable Simulation for Agile Quadrotor Control
Fanxing Li, Yuxiang Huang, Shengyang Wang +7
Tasks such as quadrotor dynamic-gate racing require agents to anticipate external motion while maintaining precise high-frequency control. World-model-based reinforcement learning…
Learning Agile Navigation in Crowded Environments for Quadruped Robots
Shuyu Wu, Zeyu Liu, Tianbao Zhang +6
Navigating dynamic and crowded environments presents significant challenges for quadruped robots due to severe sensor occlusion and unpredictable human motion. Existing approaches…
Simple but Stable, Fast and Safe: Achieve End-to-end Control by High-Fidelity Differentiable Simulation
Fanxing Li, Shengyang Wang, Yuxiang Huang +5
Obstacle avoidance is a fundamental vision-based task essential for enabling quadrotors to perform advanced applications. When planning the trajectory, existing approaches both on…
E2E-Fly: An Integrated Training-to-Deployment System for End-to-End Quadrotor Autonomy
Fangyu Sun, Fanxing Li, Linzuo Zhang +5
Training and transferring learning-based policies for quadrotors from simulation to reality remains challenging due to inefficient visual rendering, physical modeling inaccuracies,…
VisFly-Lab: Unified Differentiable Framework for First-Order Reinforcement Learning of Quadrotor Control
Fanxing Li, Fangyu Sun, Tianbao Zhang +5
First-order reinforcement learning with differentiable simulation is promising for quadrotor control, but practical progress remains fragmented across task-specific settings. To su…
Vector Field Augmented Differentiable Policy Learning for Vision-Based Drone Racing
Yang Su, Feng Yu, Yu Hu +4
Autonomous drone racing in complex environments requires agile, high-speed flight while maintaining reliable obstacle avoidance. Differentiable-physics-based policy learning has re…
Curriculum Reinforcement Learning for Quadrotor Racing with Random Obstacles
Fangyu Sun, Fanxing Li, Yu Hu +4
Autonomous drone racing has attracted increasing interest as a research topic for exploring the limits of agile flight. However, existing studies primarily focus on obstacle-free r…
StableTracker: Learning to Stably Track Target via Differentiable Simulation
Fanxing Li, Shengyang Wang, Fangyu Sun +5
Existing FPV object tracking methods heavily rely on handcrafted modular pipelines, which incur high onboard computation and cumulative errors. While learning-based approaches have…
ABPT: Amended Backpropagation through Time with Partially Differentiable Rewards
Fanxing Li, Fangyu Sun, Tianbao Zhang +1
Quadrotor control policies can be trained with high performance using the exact gradients of the rewards to directly optimize policy parameters via backpropagation-through-time (BP…
VisFly: An Efficient and Versatile Simulator for Training Vision-based Flight
Fanxing Li, Fangyu Sun, Tianbao Zhang +1
We present VisFly, a quadrotor simulator designed to efficiently train vision-based flight policies using reinforcement learning algorithms. VisFly offers a user-friendly framework…