Solving peg-in-hole tasks by human demonstration and exception strategies

Abstract

Purpose – The purpose of this paper is to propose a new algorithm based on programming by demonstration and exception strategies to solve assembly tasks such as peg-in-hole. Design/methodology/approach – Data describing the demonstrated tasks are obtained by kinesthetic guiding. The demonstrated trajectories are transferred to new robot workspaces using three-dimensional (3D) vision. Noise introduced by vision when transferring the task to a new configuration could cause the execution to fail, but such problems are resolved through exception strategies. Findings – This paper demonstrated that the proposed approach combined with exception strategies outperforms traditional approaches for robot-based assembly. Experimental evaluation was carried out on Cranfield Benchmark, which constitutes a standardized assembly task in robotics. This paper also performed statistical evaluation based on experiments carried out on two different robotic platforms. Practical implications – The developed framework can have an important impact for robot assembly processes, which are among the most important applications of industrial robots. Our future plans involve implementation of our framework in a commercially available robot controller. Originality/value – This paper proposes a new approach to the robot assembly based on the Learning by Demonstration (LbD) paradigm. The proposed framework enables to quickly program new assembly tasks without the need for detailed analysis of the geometric and dynamic characteristics of workpieces involved in the assembly task. The algorithm provides an effective disturbance rejection, improved stability and increased overall performance. The proposed exception strategies increase the success rate of the algorithm when the task is transferred to new areas of the workspace, where it is necessary to deal with vision noise and altered dynamic characteristics of the task.