16 papers · 1 filter
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…
A Closed-Form 4-DoF Inter-Robot Pose Estimator using Bearing-only Measurements
Qixin De, Ao Zhuang, Yechen Zhang +2
Bearing-odometry-based cooperative localization has attracted increasing research interest due to its minimal infrastructure requirements, low communication bandwidth and broad app…
Asymmetric physics enables efficient learning in quadrupedal robot swarms
Yuang Zhang, Yunlong Song, Zhihao He +7
Animal collectives navigate cluttered environments through local coordination, yet robot swarms still struggle to reproduce this capability in the physical world. End-to-end learni…
Autonomous FPV Flight with Translational Optical Flow and Uncertainty Mask
Yang Deng, Yu Hu, Feng Yu +2
Autonomous FPV quadrotor flight in complex environments using a monocular RGB camera as the sole exteroceptive sensor remains a fundamental challenge. Recent research has shown tha…
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,…
Vision-Based End-to-End Learning for UAV Traversal of Irregular Gaps via Differentiable Simulation
Linzuo Zhang, Yu Hu, Feng Yu +3
-Navigation through narrow and irregular gaps is an essential skill in autonomous drones for applications such as inspection, search-and-rescue, and disaster response. However, tra…
QuadAgent: A Responsive Agent System for Vision-Language Guided Quadrotor Agile Flight
Ao Zhuang, Feng Yu, Tianbao Zhang +2
We present QuadAgent, a training-free agent system for agile quadrotor flight guided by vision-language inputs. Unlike prior end-to-end or serial agent approaches, QuadAgent decoup…
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…
AI-IO: An Aerodynamics-Inspired Real-Time Inertial Odometry for Quadrotors
Jiahao Cui, Feng Yu, Linzuo Zhang +2
Inertial Odometry (IO) has gained attention in quadrotor applications due to its sole reliance on inertial measurement units (IMUs), attributed to its lightweight design, low cost,…
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…