Incremental motor skill learning and generalization from human dynamic reactions based on dynamic movement primitives and fuzzy logic system

Lu, Zhenyu; Wang, Ning; Li, Miao; Yang, Chenguang

Abstract

Different from previous work on single skill learning from human demonstrations, an incremental motor skill learning, generalization and control method based on dynamic movement primitives (DMP) and broad learning system (BLS) is proposed for extracting both ordinary skills and instant reactive skills from demonstrations, the latter of which is usually generated to avoid a sudden danger (e.g., touching a hot cup). The method is completed in three steps. First, ordinary skills are basically learned from demonstrations in normal cases by using DMP. Then the incremental learning idea of BLS is combined with DMP to achieve multi-stylistic reactive skill learning such that the forcing function of the ordinary skills will be reasonably extended into multiple stylistic functions by adding enhancement terms and updating weights of the radial basis function (RBF) kernels. Finally, electromyography (EMG) signals are collected from human muscles and processed to achieve stiffness factors. By using fuzzy logic system (FLS), the two kinds of skills learned are integrated and generalized in new cases such that not only start, end and scaling factors but also the environmental conditions, robot reactive strategies and impedance control factors will be generalized to lead to various reactions. To verify the effectiveness of the proposed method, an obstacle avoidance experiment that enables robots to approach destinations flexibly in various situations with barriers will be undertaken.

Citation

Lu, Z., Wang, N., Li, M., & Yang, C. (2022). Incremental motor skill learning and generalization from human dynamic reactions based on dynamic movement primitives and fuzzy logic system. IEEE Transactions on Fuzzy Systems, 30(6), 1506-1515. https://doi.org/10.1109/tfuzz.2021.3136933

• Journal Article Type: Article
• Acceptance Date: Dec 10, 2021
• Online Publication Date: Dec 23, 2021
• Publication Date: 2022-06
• Deposit Date: Dec 25, 2021
• Publicly Available Date: Jan 4, 2022
• Journal: IEEE Transactions on Fuzzy Systems
• Print ISSN: 1063-6706
• Electronic ISSN: 1941-0034
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 30
• Issue: 6
• Pages: 1506-1515
• DOI: https://doi.org/10.1109/tfuzz.2021.3136933
• Keywords: Applied Mathematics; Artificial Intelligence; Computational Theory and Mathematics; Control and Systems Engineering
• Public URL: https://uwe-repository.worktribe.com/output/8442092