LAUSR

Abstract Task Parametrised Gaussian Mixture Modelling and Regression (TP-GMM/R) is an eminent algorithm to enable collaborative robots (cobots) to adapt to new environments intuitively by learning robotic paths demonstrated by humans. Task parameters in the TP-GMM/R algorithm, i.e., frames associated with demonstration paths, are considered to have orientations by default. This requirement, however, limits the range of applications that TP-GMM/R can support. To address the issue, in this paper, a novel ring Gaussian (rGaussian) is defined to cater for orientation-less frames, and an improved TP-GMM/R algorithm based on rGaussians is developed to improve the adaptability and robustness of the algorithm. In the improved algorithm, firstly, kernels are incorporated to enable Gaussians encoding points from all demonstrations, and criteria are devised to judge a frame to be oriented or orientation-less. Then, improved Gaussian mixture regression that caters for rGaussians and orientation-less frames is developed to generate regression paths adaptable to complex environments. Finally, a series of case studies are used to benchmark the improved TP-GMM/R algorithm with the conventional TP-GMM/R algorithm under different conditions. Quantitative analyses are conducted in terms of smoothness, efficiency and reachability. Results show that the improved algorithm outperformed the conventional algorithm on all the cases.