A Bayesian tracker for synthesizing mobile robot behaviour from demonstration

Stéphane Magnenat (1) , Francis Colas (2)

1 ETH Zürich - Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich]
2 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment

Programming robots often involves expert knowledge in both the robot itself and the task to execute. An alternative to direct programming is for a human to show examples of the task execution and have the robot perform the task based on these examples, in a scheme known as learning or programming from demonstration. We propose and study a generic and simple learning-from-demonstration framework. Our approach is to combine the demonstrated commands according to the similarity between the demonstrated sensory trajectories and the current replay trajectory. This tracking is solely performed based on sensor values and time and completely dispenses with the usually expensive step of precomputing an internal model of the task. We analyse the behaviour of the proposed model in several simulated conditions and test it on two different robotic platforms. We show that it can reproduce different capabilities with a limited number of meta parameters.

Mots clés: programming by demonstration; learning from demonstration; non-parametric Bayesian model; teach and repeat; online tracking

Domaines: Robotique [cs.RO]

Stéphane Magnenat, Francis Colas. A Bayesian tracker for synthesizing mobile robot behaviour from demonstration. Autonomous Robots, 2021, ⟨10.1007/s10514-021-10019-4⟩. ⟨hal-03408925v2⟩