Journal
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
Volume 14, Issue 4, Pages 1743-1754Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCDS.2021.3137262
Keywords
Gaussian processes; Uncertainty; Task analysis; Trajectory; Robot learning; Probabilistic logic; Measurement uncertainty; Computational efficiency; human-robot interaction; robot learning
Funding
- Key Areas Research and Development Program of Guangdong Province [2020B090925001, 2020B090928002]
- Basic and Applied Basic Research Project of Guangzhou [202002030237]
- GDAS' Project of Thousand Doctors (post-doctors) Introduction [2020GDASYL-20200103128]
- National Natural Science Foundation of China [62003102]
- Natural Science Foundation of Guangdong Province [2020A1515010631]
Ask authors/readers for more resources
Robot learning from humans allows robots to adapt to stochastic and dynamic environments through demonstrations provided by non-technical users. A goal-directed robot skill learning framework named GP(m)-MOGP is proposed to reduce the effort of non-technical users and improve the efficiency and success rate of robot learning. The framework decides when and where to add new demonstrations, determines the usefulness of demonstrations, and uses a multioutput Gaussian process for skill learning.
Robot learning from humans allows robots to automatically adjust to stochastic and dynamic environments by learning from nontechnical end user's demonstrations, which is best known as robot programming by demonstration, robot learning from demonstration, apprenticeship learning, and imitation learning. Although most of those methods are probabilistic, and their performances intensively depend on the demonstrated data, measuring and evaluating human demonstrations are rarely investigated. A poorly demonstrated data set with useless prior knowledge or redundant demonstrations increases the complexity and time cost of robot learning. To solve these problems, a goal-directed robot skill learning framework named GP(m)-MOGP is presented. It 1) decides when and where to add a new demonstration by calculating the trajectory uncertainty; 2) determines which demonstration is useless or redundant by Kullback-Leibler (KL) divergence; 3) implements robot skill learning with a minimum number of demonstrations using a multioutput Gaussian process; and 4) learns orientation uncertainty and representation by combining logarithmic and exponential maps. The proposed framework significantly reduces the demonstrated effort of nontechnical end users who lack an understanding of how and what the robot learns during the demonstrating process. To evaluate the proposed framework, a pick-and-place experiment was designed with five unseen goals to verify the effectiveness of our methods. This experiment is well illustrated with two phases: 1) demonstration efficiency and 2) skill representation and reproduction. The results indicate an improvement of 60% in human demonstration efficiency, compared to common learning from demonstrations (LfD) applications that require at least ten demonstrations, and the robot average success rate of pick-and-place task reaches 85%.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available