A demonstration trajectory segmentation approach for wheelchair-mounted assistive robots

Segmentation of demonstration trajectories and learning the contained motion primitives can effectively enhance the assistive robot's intelligence to flexibly reproduce learnt tasks in an unstructured environment. With the aim to conveniently and accurately segment demonstration trajectories, a novel demonstration trajectory segmentation approach is proposed based on the beta process autoregressive hidden Markov model (BP-AR-HMM) algorithm and generalised time warping (GTW) algorithm aiming to enhance the segmentation accuracy utilising acquired demonstration data. This approach first adopts the GTW algorithm to align the multiple demonstration trajectories for the same task. Then, it adopts the BP-AR-HMM algorithm to segment the demonstration trajectories, acquire the contained motion primitives, and establish the related task library. This segmentation approach is validated on the 6-degree-of-freedom JACO robotic arm by assisting users to accomplish a holding water glass task and an eating task. The experimental results show that the motion primitives within the trajectories can be correctly segmented with a high segmentation accuracy.