BOWConnect: Parallel Bayesian Optimization over Windows with Learned Local Cost Maps for Sample-Efficient Kinodynamic Motion Planning (opens in new tab)

This paper presents BOWConnect, a bidirectional parallel kinodynamic motion planner that addresses three fundamental limitations of existing sampling-based methods: sample inefficiency in high-dimensional state spaces, unreliable cost heuristics under dynamic constraints, and poor performance in narrow passage environments. Unlike classical planners that rely on random control sampling and geometric distance heuristics, BOWConnect integrates Bay...