# PILOT：用于部分可观测下自主 UAV 端到端运动规划的特权模仿学习

> 原文链接：https://robotics.hellobike.com/papers/2026-08-14-2608-14082
> 频道：papers | 更新日期：2026-08-14 | 标签：arxiv, cs.RO
> 核心摘要：PILOT面向部分可观测下UAV端到端运动规划，融合特权模仿学习与时空感知，并在仿真和室内外零样本部署验证。

# PILOT：用于部分可观测下自主 UAV 端到端运动规划的特权模仿学习

::: v-pre
> 原文链接：[PILOT: Privileged Imitation Learning for End-to-End Motion Planning of Autonomous UAVs under Partial Observability](https://arxiv.org/abs/2608.14082)（arXiv 2608.14082 · 发布日期：2026-08-14）

**PILOT: Privileged Imitation Learning for End-to-End Motion Planning of Autonomous UAVs under Partial Observability**

PILOT面向部分可观测下UAV端到端运动规划，融合特权模仿学习与时空感知，并在仿真和室内外零样本部署验证。

## 核心要点

- 拥挤环境中的自主导航受部分可观测性和动态约束影响。
- PILOT从计算开销大的最优控制专家蒸馏规划策略，并用双目标损失约束安全与动力学需求。
- TCN时空感知融合历史深度图和里程计，推断任务相关潜在上下文，无需持久地图记忆。
- 四旋翼和固定翼仿真性能接近特权专家，计算开销降低超过80%，并完成室内外零样本部署。

**验证范围与局限**：训练鼓励满足约束但无形式化保证；验证限于摘要所述仿真与室内外零样本部署。

## 英文摘要 (Abstract)

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.

作者：Qingrui Zhang, Feng Xue, Xiang Zhou, Chenghao Yu
:::

## 原始参考来源 (Sources)

- [arXiv 2608.14082：PILOT: Privileged Imitation Learning for End-to-End Motion Planning of Autonomous UAVs under Partial Observability](https://arxiv.org/abs/2608.14082)