Optimization-Based Maneuver Planning for a Tractor-Trailer Vehicle in a Curvy Tunnel: A Weak Reliance on Sampling and Search

This study is focused on the maneuver planning problem for a tractor-trailer vehicle in curvy and tiny tunnel. Due to curse of dimensionality, prevalent sampling-and- search-based planners used handle rigid-body well become less efficient when trailer number grows or tunnel narrows. fact also has impacts an optimization-based planner if it counts sampling-and-search-based initial guess warm-start. We propose that weakly relies sampling search, hoping get rid dimensionality thus find optima rapidly. The proposed comprises three stages: stage 1 identifies homotopy class via A* search 2D grid map; 2 recovers kinematic feasibility with softened intermediate problems iteratively solved; 3 finds optimum strictly satisfies nominal collision-avoidance constraints. Optimization-based are commonly known run slowly, but this work shows they have obvious advantages over solution space dimension high and/or constraints harsh.