掌握多样化、未知和杂乱的赛道以实现基于视觉的无人机赛车稳健性
Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racing
AI总结：
本文提出了一种两阶段学习框架，通过软碰撞训练和硬碰撞细化，提升无人机在多样化、未知和杂乱环境中的稳健性与泛化能力。
摘要：
大多数基于强化学习（RL）的方法用于无人机赛车都针对固定、无障碍物的赛道，留下将其推广到未知、杂乱环境的泛化能力未被充分解决。这一挑战源于在平衡赛车速度和碰撞避免之间所需的平衡，有限的可行空间导致策略探索被困在局部最优解中，在训练过程中，深度图中门和障碍物之间的感知模糊性也造成了问题，尤其是在门的位置仅粗略指定时。为了解决这些问题，我们提出了一种两阶段学习框架：一个初始的软碰撞训练阶段，该阶段保留了高速飞行的策略探索能力，随后是一个硬碰撞细化阶段，该阶段强制执行稳健的障碍物避障。一个自适应、噪声增强的课程，结合不对称的演员-评论家架构，逐渐使策略的依赖从特权门状态信息转向基于深度的视觉输入。我们进一步施加利普希茨约束，并整合一个赛道原语生成器，以增强运动稳定性和跨环境泛化能力。我们通过广泛的模拟和消融研究评估了我们的框架，并在计算受限的四旋翼无人机上进行了现实世界实验。系统实现了敏捷飞行，同时在门位置误差方面保持稳健，开发出一个具有在多样化、部分未知和杂乱环境中操作能力的通用无人机赛车框架。
英文摘要：
Most reinforcement learning(RL)-based methods for drone racing target fixed, obstacle-free tracks, leaving the generalization to unknown, cluttered environments largely unaddressed. This challenge stems from the need to balance racing speed and collision avoidance, limited feasible space causing policy exploration trapped in local optima during training, and perceptual ambiguity between gates and obstacles in depth maps-especially when gate positions are only coarsely specified. To overcome these issues, we propose a two-phase learning framework: an initial soft-collision training phase that preserves policy exploration for high-speed flight, followed by a hard-collision refinement phase that enforces robust obstacle avoidance. An adaptive, noise-augmented curriculum with an asymmetric actor-critic architecture gradually shifts the policy's reliance from privileged gate-state information to depth-based visual input. We further impose Lipschitz constraints and integrate a track-primitive generator to enhance motion stability and cross-environment generalization. We evaluate our framework through extensive simulation and ablation studies, and validate it in real-world experiments on a computationally constrained quadrotor. The system achieves agile flight while remaining robust to gate-position errors, developing a generalizable drone racing framework with the capability to operate in diverse, partially unknown and cluttered environments. https://yufengsjtu.github.io/MasterRacing.github.io/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
