PILOT：部分可观测条件下自主无人机端到端运动规划的特权模仿学习方法
PILOT: Privileged Imitation Learning for End-to-End Motion Planning of Autonomous UAVs under Partial Observability
浏览论文内容
中文总结 AI 辅助
本文提出PILOT框架，通过特权模仿学习结合TCN时空感知融合模块，实现部分可观测下无人机端到端运动规划，性能接近最优控制专家且计算开销降超80%，零样本部署验证其可行性与泛化性。
中文摘要 AI 辅助
在杂乱环境中的自主导航会受到部分可观测性和动态约束的阻碍。本文提出了PILOT，一种用于部分可观测条件下基于视觉的无人机端到端运动规划的约束感知特权模仿学习框架。该框架通过双目标损失函数将计算密集型的最优控制专家的规划策略提炼为学生策略，该学生策略朝着安全性和动态要求进行正则化。为了缓解部分可观测性，开发了一种使用时间卷积网络（TCN）的时空感知融合模块，以整合历史深度图像和里程计信息。该模块从历史观测中推断出与任务相关的潜在上下文，在不维护持久地图内存的情况下，增强了超出瞬时视场（FOV）的空间感知。轨迹参数化层将网络输出映射为结构化轨迹，同时在训练过程中实现明确的连续性、动态一致性和障碍物软惩罚，鼓励对未见过的观测满足约束，尽管没有正式保证。对四旋翼和固定翼飞机的仿真表明，PILOT实现了与特权专家相当的性能，同时将计算开销降低了80%以上。成功的室内和零样本室外部署证实了该规划器的实际可行性和跨域泛化能力。
英文摘要
Autonomous navigation in cluttered environments is hampered by partial observability and dynamic constraints. This paper presents PILOT, a constraint-aware privileged imitation learning framework for vision-based end-to-end UAV motion planning under partial observability. The framework distills planning strategies from a computationally intensive optimal control expert into a student policy regularized toward safety and dynamic requirements via a dual-objective loss function. To mitigate partial observability, a spatiotemporal perception fusion module using a Temporal Convolutional Network (TCN) is developed to integrate historical depth images and odometry. This module infers task-relevant latent context from historical observations, enhancing spatial awareness beyond the instantaneous FOV without maintaining persistent map memory. A trajectory parameterization layer mapping network outputs to a structured trajectory, while enabling explicit continuity, dynamic-consistency, and obstacle soft penalties during training, encouraging constraint satisfaction for unseen observations without formal guarantees. Simulations on quadrotor and fixed-wing aircraft demonstrate that PILOT achieves performance comparable to the privileged expert while reducing computational overhead by over 80\%. Successful indoor and outdoor zero-shot deployment confirms the practical feasibility and cross-domain generalization of the planner.
发表机构
- School of Aeronautics and Astronautics, Sun Yat-sen University（中山大学航空航天学院）
- Sun Yat-sen University（中山大学）
机构由 AI 辅助整理，请以论文原文为准。
