Optimised Learning from Demonstrations for Collaborative Robots

• Published in: Robotics and computer-integrated manufacturing Vol. 71; p. 102169
• Main Authors: Wang, Y.Q., Hu, Y.D., Zaatari, S. El, Li, W.D., Zhou, Y.
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.10.2021; Elsevier BV
• Subjects: Algorithms; Clusters; Collaboration; Collaborative Robots; Gaussian elimination; Gaussian Mixture Model; Learning from Demonstrations; Machine learning; Optimization; Pick and place tasks; Probabilistic models; Random noise; Regression models; Robot control; Simulated annealing; Task complexity; ωi; LL; Ni(pj|μi,σi); E(xjtj); D; TP-GMM; μnoise; DTW; σi; ai1; ai2; K; αi(tj); IBE; Pi; Collaborative Robots; BIC; xj,yj,zj; Gaussian Mixture Model; DMP; GMM; EM; HMM; lnL(θ^B); λi2; LfD; CEO; GMR; μi; λi1; m; PGMM(pj); p; Learning from Demonstrations; r; xj; Bi,k(u); LCSS; t; SA-RL; xjGMR; RMS; pj; σnoise; Eudis; γji
• ISSN: 0736-5845; 1879-2537
• DOI: 10.1016/j.rcim.2021.102169

•A novel optimised approach is designed to improve Gaussian Mixture Model (GMM) and Gaussian Mixture Regression (GMR) in supporting Learning from Demonstrations (LfD) enabled cobots•A Gaussian noise strategy is devised to scatter demonstrations in order to better support GMM•A Simulated Annealing-Reinforcement Learning based optimisation algorithm is developed to refine Gaussian clusters to eliminate potential under-/over-fitting issues on GMM/GMR•A B-spline based cut-in algorithm is integrated with GMR to improve the adaptability of solutions for dynamic manufacturing tasks The approach of Learning from Demonstrations (LfD) can support human operators especially those without much programming experience to control a collaborative robot (cobot) in an intuitive and convenient means. Gaussian Mixture Model and Gaussian Mixture Regression (GMM and GMR) are useful tools for implementing such a LfD approach. However, well-performed GMM/GMR require a series of demonstrations without trembling and jerky features, which are challenging to achieve in actual environments. To address this issue, this paper presents a novel optimised approach to improve Gaussian clusters then further GMM/GMR so that LfD enabled cobots can carry out a variety of complex manufacturing tasks effectively. This research has three distinguishing innovative characteristics: 1) a Gaussian noise strategy is designed to scatter demonstrations with trembling and jerky features to better support the optimisation of GMM/GMR; 2) a Simulated Annealing-Reinforcement Learning (SA-RL) based optimisation algorithm is developed to refine the number of Gaussian clusters in eliminating potential under-/over-fitting issues on GMM/GMR; 3) a B-spline based cut-in algorithm is integrated with GMR to improve the adaptability of reproduced solutions for dynamic manufacturing tasks. To verify the approach, cases studies of pick-and-place tasks with different complexities were conducted. Experimental results and comparative analyses showed that this developed approach exhibited good performances in terms of computational efficiency, solution quality and adaptability.