Abstract
Learning skills from kinesthetic demonstrations is a promising way of minimizing the gap between human manipulation abilities and those of robots. We propose an approach to learn sequential force interaction skills from such demonstrations. The demonstrations are decomposed into a set of movement primitives by inferring the underlying sequential structure of the task. The decomposition is based on a novel probability distribution which we call Directional Normal Distribution. The distribution allows infering the movement primitive’s composition, i.e., its coordinate frames, control variables and target coordinates from the demonstrations. In addition, it permits determining an appropriate number of movement primitives for a task via model selection. After finding the task’s composition, the system learns to sequence the resulting movement primitives in order to be able to reproduce the task on a real robot. We evaluate the approach on three different tasks, unscrewing a light bulb, box stacking and box flipping. All tasks are kinesthetically demonstrated and then reproduced on a Barrett WAM robot.
Highlights
As the variety of industrial tasks is increasing and robots are being more and more deployed in real-world settings, it becomes impossible to pre-program them for all the situations they may encounter
The results show that the decomposition is consistent over all demonstrations, even though the demonstrations are slightly over-segmented
There does not seem to be a need for fine-tuning the scale parameter for different tasks
Summary
As the variety of industrial tasks is increasing and robots are being more and more deployed in real-world settings, it becomes impossible to pre-program them for all the situations they may encounter. By generalizing existing task knowledge for new situations, robots even have the potential to allow the realization of tasks with higher complexity than just by programming alone. Learning manipulation tasks from human demonstrations has many potential application domains ranging from service robotics to industrial applications. The contribution of this paper is a concept for learning motor skills for tasks that have the following characteristics: First, the task can be represented by a sequence of object-relative point-to-point movements. We refer to tasks that have the aforementioned properties as sequential force interaction tasks
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.