Combining Programming by Demonstration with Path Optimisation and Local Replanning to Facilitate the Execution of Assembly Tasks

With the emergence of agile manufacturing in highly automated industrial environments, the demand for efficient robot adaptation to dynamic task requirements is increasing. For assembly tasks in particular, classic robot programming methods tend to be rather time intensive. Thus, effectively responding to rapid production changes requires faster and more intuitive robot teaching approaches. This work focuses on combining programming by demonstration with path optimization and local replanning methods to allow for fast and intuitive programming of assembly tasks that requires minimal user expertise. Two demonstration approaches have been developed and integrated in the framework, one that relies on human to robot motion mapping (teleoperation based approach) and a kinesthetic teaching method. The two approaches have been compared with the classic, pendant based teaching. The framework optimizes the demonstrated robot trajectories with respect to the detected obstacle space and the provided task specifications and goals. The framework has also been designed to employ a local replanning scheme that adjusts the optimized robot path based on online feedback from the camera-based perception system, ensuring collisionfree navigation and the execution of critical assembly motions. The efficiency of the methods has been validated through a series of experiments involving the execution of assembly tasks. Extensive comparisons of the different demonstration methods have been performed and the approaches have been evaluated in terms of teaching time, ease of use, and path length.

More details can be found at the following publication:

Gal Gorjup, George P. Kontoudis, Anany Dwivedi, Geng Gao, Saori Matsunaga, Toshisada Mariyama, Bruce MacDonald, and Minas Liarokapis, "Combining Programming by Demonstration with Path Optimization and Local Replanning to Facilitate the Execution of Assembly Tasks", IEEE Robotics & Automation Letters, 2020 (under review).