Event

Authors propose reward-guided RRT* planning framework under budget constraints

1 reports · 1 sources

Vin\'icius Ara\'ujo de Oliveira and other authors propose Reward-Guided RRT*, a sampling-based task and motion planning framework. Through a series of local joint task selection and motion planning stages, it directly constructs budget-satisfying task sequences in continuous state space, without the need to precompute a task transition graph. The authors state that the return feasibility procedure in the framework ensures that each selected task can be visited without violating the task budget. The authors also extend the framework to Dubins turning and evaluated it in CoppeliaSim with a scaled car-like robot platform.