A path planning approach via task-objective pose selection with application to an inchworm-inspired climbing robot

Abstract

This paper presents a stepping path planning approach for a climbing robot inspired kinematically from an inchworm caterpillar's looping locomotion. This approach generates an optimised multi-step path to traverse through space and to land a specific footpad onto a selected point on a surface with a specific footpad orientation. The candidate landing joint configuration for each step is generated by a pose selection process, using an optimisation technique with task-objective functions based on the constraints of the robot. Then another technique is used to obtain a new set of poses satisfying strict constraints of the landing motion. The set of candidate landing poses is used to compute the subsequent steps. A valid motion trajectory, which avoids all obstacles, can be generated by a point-to-point planner for each of the landing poses from the current pose. This single step planning technique is then expanded to multi-step path planning by building a search tree, where a combination of steps is evaluated and optimised by a cost function, which includes objectives related to robot movement. This approach is implemented and validated on the climbing robot in real-world steel bridge environments. The planner successfully finds multi-step paths in these field trials enabling the robot to traverse through several complex structures inside the bridge steel box girders.