Direct sensorimotor control for low-cost mobile tracking applications

Citation
Dm. Wilson et al., Direct sensorimotor control for low-cost mobile tracking applications, IEEE IND E, 47(4), 2000, pp. 939-950
Citations number
11
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
ISSN journal
02780046 → ACNP
Volume
47
Issue
4
Year of publication
2000
Pages
939 - 950
Database
ISI
SICI code
0278-0046(200008)47:4<939:DSCFLM>2.0.ZU;2-Q
Abstract
A biologically inspired system for tracking objects in a visual scene is pr esented. The uniqueness of the system is in the absence of a microcontrolle r to convert sensory information to tracking decisions, reducing power, siz e, weight, and cost of the overall system. The system consists of a mobile vehicle outfitted with a custom analog VLSI architecture for encoding the p osition of an object of interest in the vehicles's field of view. Once dete rmined, the object of interest retains hysteresis proportional to its size and intensity to limit the potential for distraction by other objects in th e sensing environment. The encoded position of the object of interest is di rectly converted to a series of motor control signals to drive the vehicle in the direction of the object. The motor drive signals are pulse width mod ulated to control the speed and direction of travel induced by two de motor s via a conventional differential steering arrangement. Neural oscillators are used to drive the de motors to provide a compact single-chip system for tracking bright objects. The nature of the system is sufficiently modular so that it can be adapted relatively easily to tracking other features of v isual objects and even to objects representative of other sensing modalitie s. The system described here is one of the first efforts to fully integrate and apply analog VLSI (aVLSI) sensorimotor control to a mobile vehicle and to analyze the complete system from a control systems' perspective. The sy stem described here has the advantages of aVLSI integration in its small si ze (0.011-mm(2) elements), low power (0.3 mu W per element), and fast syste m response time (1.5 ms from sensory input to motor response).