Spline-Based Optimal Trajectory Generation for Autonomous Excavator

In this paper, we propose a novel trajectory generation method for autonomous excavator teach-and-plan applications. Rather than controlling the to precisely follow teaching path, proposed transforms arbitrary slow and jerky of human excavation into topologically equivalent path that is guaranteed be fast, smooth dynamically feasible. This optimizes trajectories in both time jerk aspects. A spline used connect these waypoints, which are path. Then reparametrized obtain minimum time-jerk with kinodynamic constraints. The optimal formulated using nonlinear programming conducted iteratively. framework paper was integrated complete platform validated achieve aggressive field environment.