Multi‐group motion planning in virtual environments

Toward enhancing automation, this paper proposes an efficient approach for multi‐group motion planning, where the set of goals is divided into k groups and the objective is to compute a collision‐free and dynamically feasible trajectory that enables a virtual vehicle to reach at least one goal from each group. The approach works with ground and aerial vehicles operating in complex environments containing numerous obstacles. In addition to modeling the vehicle dynamics by differential equations, the approach can use physics‐based game engines, which provide an increased level of realism. The approach is based on a hybrid search that uses generalized traveling salesman tours over a probabilistic roadmap to effectively guide the sampling‐based expansion of a motion tree. As the motion tree is expanded with collision‐free and dynamically feasible trajectories, tours are adjusted based on a partition of the motion tree into equivalence classes. This gives the approach the flexibility to discover new tours that avoid collisions and are compatible with the vehicle dynamics. Comparisons to related work show significant improvements both in terms of runtime and solution length. Copyright © 2016 John Wiley & Sons, Ltd.