Shape-Preserving and Reactive Adaptation of Robot End-Effector Trajectories

Abstract

Variation in task requirements and operation in uncertain environments require robots that can continuously adapt their motions during execution. To do this successfully, the original motion characteristics must be preserved. This paper presents an approach for on-line adaptation of end-effector trajectories for robot manipulators. The trajectory generator aims to preserve the shape of a given model trajectory through its coordinate-invariant shape description. In addition, this trajectory generator is coupled to a task specification and control framework that enables reactive behavior of the robot. Simulation results on the UR10 robot indicate the capability of the developed approach to generalize end-effector trajectories towards new targets while preserving the original trajectory shape. The controller's reactivity is shown towards moving targets and obstacles in the environment. The combination of shape preservation and reactive control may endow robots with better on-line motion generalization capabilities.