Abstract
Autonomous drone racing in complex environments requires agile, high-speed flight while maintaining reliable obstacle avoidance. Differentiable-physics-based policy learning has recently demonstrated high sample efficiency and remarkable performance across various tasks, including agile drone flight and quadruped locomotion. However, applying such methods to drone racing remains difficult, as key objective like gate traversal are inherently hard to express as smooth, differentiable losses. To address these challenges, we propose DiffRacing, a novel vector field-augmented differentiable policy learning framework. DiffRacing integrates differentiable losses and vector fields into the training process to provide continuous and stable gradient signals, balancing obstacle avoidance and high-speed gate traversal. In addition, a differentiable Delta Action Model compensates for dynamics mismatch, enabling efficient sim-to-real transfer without explicit system identification. Extensive simulation and real-world experiments demonstrate that DiffRacing achieves superior sample efficiency, faster convergence, and robust flight performance, thereby demonstrating that vector fields can augment traditional gradient-based policy learning with a task-specific geometric prior.
Abstract (translated)
在复杂环境中进行自主无人机竞速需要高速飞行并保持可靠的障碍物规避。基于可微物理的策略学习方法最近展示了高样本效率和跨多个任务(包括敏捷无人机飞行和四足机器人运动)的出色性能。然而,将这些方法应用于无人机竞赛仍然具有挑战性,因为诸如穿越门等关键目标本质上难以表达为平滑、可微分的损失函数。 为了应对这一挑战,我们提出了一种新的框架——DiffRacing,这是一种基于向量场增强的可微策略学习框架。DiffRacing 将可微分损失和向量场整合到训练过程中,提供连续且稳定的梯度信号,在障碍物规避与高速门穿越之间取得平衡。 此外,一种可微的Delta动作模型补偿了动力学不匹配问题,使得无需显式系统识别即可实现高效的仿真到现实环境转换。 大量的模拟实验和真实世界的测试表明,DiffRacing 在样本效率、更快的收敛速度以及稳健的飞行性能方面表现出色。这证明了向量场能够增强传统的梯度基策略学习,并为特定任务引入几何先验知识。
URL
https://arxiv.org/abs/2603.08019