Reward guided path planning improves robot task missions with limited travel
Reward-Guided RRT* for Budgeted Task and Motion Planning
RoboticsArtificial Intelligence
Summary
Robots often need to visit multiple locations to complete tasks, but they can only travel so far before running out of time or energy. This paper presents a new method that helps robots pick which tasks to do and plan their routes efficiently so they don't exceed their travel limit. The method works by gradually building a path guided by potential rewards, checking at each step that the robot can return within its travel budget. The authors tested their approach in simulations and on a car-like robot, showing it can handle complex obstacles and movement constraints.
What this means in practice
- •For autonomous vehicle developers: Plan efficient routes for vehicles with turning constraints to complete multiple tasks within limited travel budgets.
- •For warehouse robotics teams: Generate motion plans that select and sequence tasks for robots under energy and time limitations without precomputed task graphs.
Authors
Vinícius Araújo de Oliveira, Gabriel Ferreira Mendes Lourenço, Paulo L. J. Drews-Jr, Armando Alves Neto, Douglas G. Macharet
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.