Human-Robot Interactions as a Cognitive Catalyst for the Learning of Behavioral Attractors

Abstract

Abstract-We address in this paper the problem of the autonomous online learning of a sensory-motor task, demonstrated by an operator guiding the robot. For the last decade, we have developed a vision-based architecture for mobile robot navigation. Our bio-inspired model of the navigation has already proved to achieve sensory-motor tasks in real time both in unknown indoor and outdoor environments. We propose to bootstrap the underlying PerAc architecture in order to control the sensori-motor learning. The interaction leads the robot to autonomously build a precise sensorymotor dynamic approximating the behavior of the teacher. A real dialog based on actions imposed by the teacher and those proposed by the robot emerges, which catalyzes the learning of the robot. The architecture is finally tested in real indoor and outdoor environments.

Autonomous vision-based navigation: Goal-oriented action planning by transient states prediction, cognitive map building, and sensory-motor learning

“…For instance, in [23], we presented place fields having a useful radius of about 25 m., which was almost the size of the environment. In [21], we shown that an outdoor loop of 200m requires the same computation load an indoor loop of less than 15 m. For navigation capabilities, it is first possible to associate each place-cell with a particular movement in order to create a behavioral attraction basin [19], [16], [20]. We have shown that this behavior could learned by means of an intuitive human-robot interaction in indoor as well as in outdoor environments [21].…”

“…This section describes a mature and efficient model of prehippocampal visual place-cells, tested on several platforms to perform missions in open indoor and outdoor environments [19], [16], [20], [21]. One Our model of entorhinal place-cells is inspired from "what and where" functional theory of the cortical connectivity downstream the hippocampus [40].…”

“…The images may be either re-built from a set of classical images, covering the whole 360 o of the available visual field, or captured by means of a omnidirectional camera (here a Vstone VS-C42N-TR) to speed up the experimentations. The system can also operate without any panoramic reconstruction as demonstrated in [20], [21]. For sake of robustness to daylight intensity variation, the gradient image is computed from the CCD input.…”

“…In [21], we shown that an outdoor loop of 200m requires the same computation load an indoor loop of less than 15 m. For navigation capabilities, it is first possible to associate each place-cell with a particular movement in order to create a behavioral attraction basin [19], [16], [20]. We have shown that this behavior could learned by means of an intuitive human-robot interaction in indoor as well as in outdoor environments [21]. The next section focuses on a different navigation strategy which only requires an exploration phase and the discovery of goals to provide the robots with planning capability.…”

A Formalism for Learning from Demonstration*

“…One promising approach to construct such a metric is to use the demonstrations to impose constraints in a dynamical system [24,38,44]. Giovannangeli and Gaussier [35] use human-robot interaction to improve generalization when learning sensory-motor behaviors for homing and path following. In the described work, teaching by error correction (proscriptive learning), is shown to give superior generalization compared to a regular demonstration (prescriptive learning).…”