🤖 AI Summary
This work addresses multi-target motion planning under kinodynamic differential constraints in unstructured obstacle environments. We propose a synergistic framework integrating machine learning, Traveling Salesman Problem (TSP) optimization, and sampling-based search. Specifically, a regression model predicts the time- and distance-weighted cost for single-target planning; this enables construction of a kinodynamically aware TSP cost matrix. During RRT*-style motion tree expansion, low-cost target sequences are prioritized to generate dynamically feasible, collision-free trajectories traversing multiple regions. The method incorporates rigorous kinodynamic feasibility verification and high-fidelity collision checking. Experiments on a car-like vehicle model demonstrate a 3.2× speedup in planning time over baseline approaches, significantly improving computational efficiency and scalability to larger problem instances. Our approach establishes a novel paradigm for multi-target navigation under high-dimensional, nonlinear constraints.
📝 Abstract
This paper considers multi-goal motion planning in unstructured, obstacle-rich environments where a robot is required to reach multiple regions while avoiding collisions. The planned motions must also satisfy the differential constraints imposed by the robot dynamics. To find solutions efficiently, this paper leverages machine learning, Traveling Salesman Problem (TSP), and sampling-based motion planning. The approach expands a motion tree by adding collision-free and dynamically-feasible trajectories as branches. A TSP solver is used to compute a tour for each node to determine the order in which to reach the remaining goals by utilizing a cost matrix. An important aspect of the approach is that it leverages machine learning to construct the cost matrix by combining runtime and distance predictions to single-goal motion-planning problems. During the motion-tree expansion, priority is given to nodes associated with low-cost tours. Experiments with a vehicle model operating in obstacle-rich environments demonstrate the computational efficiency and scalability of the approach.