Imitation learning of motor primitives and language bootstrapping in robots

TL;DR

This paper presents a novel imitation learning framework enabling robots to learn motor skills and their linguistic labels simultaneously, including handling unlabeled demonstrations and discerning relevant speech cues for task execution.

Contribution

It introduces modifications to existing imitation learning algorithms to support joint motor and language learning, including unlabeled demonstrations and relevance detection of linguistic input.

Findings

Robots can learn motor primitives with associated acoustic labels.

The system can identify relevant speech cues without prior labeling.

Robots can distinguish between task-relevant and irrelevant linguistic input.

Abstract

Imitation learning in robots, also called programing by demonstration, has made important advances in recent years, allowing humans to teach context dependant motor skills/tasks to robots. We propose to extend the usual contexts investigated to also include acoustic linguistic expressions that might denote a given motor skill, and thus we target joint learning of the motor skills and their potential acoustic linguistic name. In addition to this, a modification of a class of existing algorithms within the imitation learning framework is made so that they can handle the unlabeled demonstration of several tasks/motor primitives without having to inform the imitator of what task is being demonstrated or what the number of tasks are, which is a necessity for language learning, i.e; if one wants to teach naturally an open number of new motor skills together with their acoustic names. Finally, a mechanism for detecting whether or not linguistic input is relevant to the task is also proposed, and our architecture also allows the robot to find the right framing for a given identified motor primitive. With these additions it becomes possible to build an imitator that bridges the gap between imitation learning and language learning by being able to learn linguistic expressions using methods from the imitation learning community. In this sense the imitator can learn a word by guessing whether a certain speech pattern present in the context means that a specific task is to be executed. The imitator is however not assumed to know that speech is relevant and has to figure this out on its own by looking at the demonstrations: indeed, the architecture allows the robot to transparently also learn tasks which should not be triggered by an acoustic word, but for example by the color or position of an object or a gesture made by someone in the environment. To demonstrate this ability to find the ...