Optimization-Based Framework for Excavation Trajectory Generation

In thisletter, we present a novel optimization-based framework for autonomous excavator trajectory generation under task-specific constraints. Traditional excavation generators over-simplify the geometric parameterization thereby limiting space optimization. To expand search space, formulate generic task specification by constraining instantaneous motion of bucket and adding target-oriented constraint to control amount excavated soil. The is represented with waypoint interpolating spline. Time intervals between waypoints are relaxed as variables facilitate generating time-optimal in one stage. Experiments on real robot platform demonstrate that our method adaptive different terrain shapes outperforms other optimal path planners terms minimum joint length travel time.