Reward-Guided RRT*：预算约束下的任务与运动规划新框架

Reward-Guided RRT* for Budgeted Task and Motion Planning

AI 导读

论文提出 Reward-Guided RRT*，一种基于采样的任务与运动规划框架，通过一系列局部联合的任务选择与运动规划阶段，直接在连续状态空间中构建满足预算约束的任务方案，无需预计算任务转移图。实验显示其解与 VNS-PRM* 相当，但所需采样状态大幅减少；框架还扩展至 Dubins 转向，并在 CoppeliaSim 中用缩比车型机器人平台验证了纳入车辆运动学约束的能力。

正文 · 原文

View PDF HTML (experimental)

Abstract:Robotic missions involving spatially distributed tasks often require jointly selecting rewarding locations and planning feasible motions under limited travel budgets. This paper proposes Reward-Guided RRT*, a new sampling-based framework that constructs a budget-feasible mission through a sequence of locally joint task-selection-and-motion-planning stages, evaluated directly in the continuous state space, without requiring a precomputed task-transition graph. The method incrementally builds a mission using reward-guided RRT* searches, while a return-feasibility procedure ensures that each selected task can be visited without violating the mission budget. Experiments with increasing obstacle complexity and number of tasks show solutions comparable to VNS-PRM* while requiring substantially fewer sampled states. We also extend the framework to Dubins steering and evaluate it in CoppeliaSim with a scaled car-like robotic platform, demonstrating its ability to incorporate vehicle kinematic constraints.

Subjects:	Robotics (cs.RO); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.35289 [cs.RO]
	(or arXiv:2610.35289v1 [cs.RO] for this version)
	https://doi.org/10.48550/arXiv.2610.35289 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Douglas G. Macharet [view email]
[v1] Mon, 26 Oct 2026 12:00:13 UTC (7,214 KB)

来源：arXiv cs.AI · arxiv.org