Simulating pursuit with machine experiments with robots and artificial vision

Abstract

This article is concerned with the simulation of pursuit. The article describes one solution for the problem of pursuit of objects moving on a plane by using a mobile robot and an active vision system. The solution deals with the interaction of different control systems using visual feedback and it is accomplished by the implementation of a visual gaze holding process interacting cooperatively with the control of the trajectory of a mobile robot. These two systems are integrated to follow a moving object at constant distance and orientation with respect to the mobile robot. The orientation and the position of the active vision system running a gaze holding process give the feedback signals to the control used to pursuit the target in real-time. The paper addresses the problems of visual fixation, visual smooth pursuit, navigation using visual feedback and compensation for system's movements. The algorithms for visual processing and control are described in the article. The mechanisms of cooperation between the different control and visual algorithms are also described. The final solution is a system able to operate at approximately human walking rates as the experimental results show at the end of the article.

Vergence Using GPU Cepstral Filtering

“…For example, VARMA head [12], MDOF head [13], Rochester [14], the "Richard the First'' head [15] and the KTH robot head [16] were capable of mimicking human head motion. More recent robot heads include the POP head [23,24] used on the Bayesian Approach to Cognitive Systems project (IMPEP) [7], the LIRA-head [17], where acoustic and visual stimuli are exploited to drive the head gaze; the Yorick head [18], and the Medusa head [19] where high-accuracy calibration, gaze control, control of vergence or real-time speed tracking with log-polar images were successfully demonstrated.…”

“…There are many different possible models for implementing vergence using disparity in the context of a robotic binocular system [2,3,6,11,12]. For example, by means of saliency detection or using stereo-matching techniques such as: phase correlation method like cepstral filtering, area based matching and feature-based matching.…”

Line of sight robot navigation toward a moving goal

“…Various methods and strategies based on visual servoing control were suggested for the pursuit ( [20]- [28]). Different problems such as real-time implementation ([20], [21]), tracking in the presence of uncertainty [22], tracking of complex objects [23] and compensation for abrupt changes in the target motion [24] were considered.…”

“…Freyrer and Zell ( [26] and [27]) consider the problem of tracking humans using wheeled mobile robots based on artificial vision. Simulating the pursuit of a moving target using a robot based on artificial vision is considered in [28].…”

Modeling and Controlling a Robotic Convoy Using Guidance Laws Strategies

“…Positioning a robot with respect to its target based on visual servoing was considered in [7]. Simulation of the pursuit of moving objects using a mobile robot and an artificial vision algorithm is considered in [8].…”