Adaptive Behavior, 2 (4)

Maes has proposed a mechanism for action selection (behavioral choice) (Maes, 1989, 1990, 1991a) which is reviewed here and is evaluated using a simulated environment. This simulated environment is a detailed and complex generalized model of the action selection problem faced by an animal in the wild and presents a rather severe test for an action selection mechanism. The results of testing Maes's mechanism in the simulated environment are discussed, some observed deficiencies in the mechanism's operation are described, and the computational reasons underlying the deficiencies are explained. It is argued that some central aspects of the design of Maes's mechanism mean that it is not able to deal well with animal-like action selection problems.

Key Words

action selection; behavioral choice; mechanisms; Maes; spreading activation; animal behavior

Pages 349-373

Scaling Up Sensorimotor Systems: Constraints from Human Infancy

By Julie C. Rutkowska

Abstract

Work in human infancy and behavior-based robotics that grounds intelligent abilities in sensorimotor exchanges between a system and its environment shares recurrent problems of when, whether, and how scaling up from basic to supposedly higher abilities is possible. An action- based model of the infant is introduced that converges with features of independently motivated animat models exploiting emergent functionality and challenges alternatives that invoke conceptual representations. Adaptive change routinely exhibited in infants' everyday activities outstrips the scaling-up potential of current robotic systems and clarifies effective principles obeyed by naturally intelligent systems. A general form is outlined to subject-environment interaction that "engineers" restructuring of early abilities in the direction of greater anticipation (considered an upper boundary for the competence of concept-free human and animat systems); and an action-based account of the phenomena is provided. This emphasizes the relationship between representation and situated inference and the role of reciprocal constraints between cognitive and physical-motor mechanisms. Finally, this article questions how far typical self-organizing connectionist networks take us toward understanding a system that is capable of mapping recurrent viable patterns of activity into more permanent adaptive changes.

Key Words

action; anticipation; connectionism; emergent functionality; human infancy; ontogenesis

Pages 375-398

Failure Recognition and Fault Tolerance of an Autonomous Robot

By Cynthia Ferrell

Abstract

The purpose of this article is twofold. The first goal is to present important issues in designing fault- tolerant systems for autonomous robots. The second is to present the fault-tolerance capabilities we implemented on our autonomous robot. Our approach is characterized by a distributed network of concurrently running processes. To tolerate hardware failures, a set of fault-tolerance processes is written for each component. These processes are responsible for detecting faults in their respective component and for minimizing the impact of the failure on the robot's performance. By exploiting concurrency and distributedness, the system monitors, detects, and compensates for component failures simultaneously. The capabilities of this system have been tested by physically disabling and enabling the robot's sensors and actuators. The system quickly recognizes and compensates for both minor and severe sensor and actuator failures. It tolerates a variety of sensor failures such as decalibration, erroneous readings, and permanent failures. It also tolerates various combinations of failures such as individual failures, concurrent failures, and accumulative failures.

Key Words

fault tolerance; failure recognition; autonomous robot; distributed control; legged locomotion; adaptive sensing

Pages 399-400

Author Index to Volume 2

Pages 401-404

Key Word Index to Volume 2

back to TOC, back to top

Adaptive Behavior, 2 (4)

Adaptive Behavior

Volume 2, Number 4

Spring 1994

Table of Contents

Toby Tyrrell

An Evaluation of Maes's Bottom-Up Mechanism for Behavior Selection