Kinodynamic Motion Planning
Overview
Kinodynamic motion planning searches for motions that are not only collision-free but also physically executable under a robot’s dynamics and control limits. Common approaches include sampling-based tree planners such as RRT variants, heuristic search and motion lattices, trajectory optimization and model predictive control, and learned models or policies that guide planning. Methods are tested on systems ranging from ground robots and manipulators to drones and multi-robot teams, including cluttered scenes, moving obstacles, and uncertain dynamics. A central challenge is balancing fast, robust planning in high-dimensional settings with guarantees such as safety, completeness, and near-optimality.
Latest papers
46 papers5 papers in the last four weeks, down 37% on the four weeks before. 0.0% of all new papers.