Towards temporal cognition for robots: A neurodynamics approach

Abstract

If we want robots to engage effectively with humans in service applications or in collaborative work scenarios they have be endowed with the capacity to perceive the passage of time and control the timing of their actions. Here we report result of a robotics experiment in which we test a computational model of action timing based on processing principles of neurodynamics. A key assumption is that elapsed time is encoded in the consistent buildup of persistent population activity representing the memory of sensory or motor events. The stored information can be recalled using a ramp-to-threshold dynamics to guide actions in time. For the experiment we adopt an assembly paradigm from our previous work on natural human-robot interactions. The robot first watches a human executing a sequence of assembly steps. Subsequently, it has to execute the steps from memory in the correct order and in synchrony with an external timing signal. We show that the robot is able to efficiently adapt its motor timing and to store this information in memory using the temporal mismatch between the neural processing of the sensory feedback about executed actions and the external cue.

Towards Endowing Collaborative Robots with Fast Learning for Minimizing Tutors’ Demonstrations: What and When to Do?

“…The model presented in this paper is based on previous research on natural human-robot interaction [2], [16], [17] based on Dynamic Neural Fields (DNFs). DNFs provide a rigorous theoretical framework to implement neural computations that endow a robot with crucial cognitive functions such as working memory, prediction and decision making [15].…”

“…Input from external sources, such as vision, causes activation in the correspondent populations that remain active with no further external input due to recurrent excitatory and inhibitory interactions within the populations. Those interactions are able to hold an auto-sustained multi-bump pattern which can be turned into a memory mechanism for order and time interval of sequential processes ( [6], [8], [17]). Fig.…”

Rapid Learning of Complex Sequences With Time Constraints: A Dynamic Neural Field Model

“…It implements neuro-plausible processing mechanisms supporting the efficient acquisition and flexible reproduction of complex sequences with strong time constraints. The model is an extension of a previous DNF model that we have applied to endow autonomous robots with the capacity to learn the serial order of sequential tasks by observation [13], [14], [15]. The most significant advances compared to the previous work are in the processing of temporal characteristics of sequential events and a systematic test of model robustness.…”