Learning to Perform Trajectory Generation From Low-Quality Demonstrations

Human–robot skill transfer is an important means for robots to learn skills and has received more and more attention and research in recent years. Typically, to ensure effective skill transfer, a skill is demonstrated several times by a human, from which a robot learns the features contained in the demonstrations and reproduces the skill in a new environment. However, it is necessary to consider the cases such as errors in human demonstrations and sensor issues, resulting in imperfect demonstrations, unrelated data, information loss, and variations in the lengths and amplitudes of the demonstrations. Therefore, this brief proposes a new trajectory alignment and filtering method for extracting relatively useful information from multiple demonstrations. This method can be used in conjunction with most probabilistic movement learning methods (this brief uses probabilistic movement primitives (ProMPs) as an example) for learning from demonstrations (LfDs), so that the robot can eventually learn and generate trajectories for completing skills from multiple demonstrations of varying quality. The effectiveness of the proposed method is verified by simulation results.