The dynamic approach to autonomous robotics demonstrated on a low-level vehicle platform

Abstract

The dynamic approach proposes a set of concepts with the help of which autonomous systems can be specified and designed. While the approach builds systems from elementary behaviors driven by behavior-specific sensory information, it also represents behaviors internally in terms of the state of dynamical systems, thus positioning itself somewhere between classical and behavior-based approaches. This paper demonstrates that the dynamic approach lends itself naturally to implementation on computationally weak platforms working with very low-level sensory information. Obstacle avoidance and target acquisition are implemented on a micro-controller based vehicle equipped with only five infra-red detectors and two photoresistors. We show how theoretical design, software simulation, and hardware implementation are enchained effortlessly. The resulting behavior is particularly smooth and requires no parameter optimization. As a technical novelty we demonstrate the integration of dynamics at two different levels of temporal derivative.