Adaptive Behavior, 7 (2)

Many basic locomotor patterns of living bodies are rhythmic, and oscillatory components of physical systems effectively contribute to the generation of the movement. The control signals for the basic locomotor patterns are generated by the central pattern generator (CPG), which is composed of collective neural oscillators, and the activity of the CPG is tightly synchronized with the movement of the physical systems. That is, appropriate locomotor patterns are realized by mutual synchronization between the physical system and the neural system. In this article a simple learning model is proposed to acquire an appropriate parameter set, the intrinsic frequency of the CPG, and the interaction between the CPG and the physical system, in order to obtain a desired locomotor pattern. The performance of the proposed learning model is confirmed by computer simulations and an adaptive control experiment of a one-dimensional hopping robot.

Key Words

CPG; nonlinear oscillator; locomotion; associative learning; adaptive control

Pages 151-172

Evolving Swimming Controllers for a Simulated Lamprey with Inspiration from Neurobiology

By Auke Jan Ijspeert, John Hallam and David Willshaw

Abstract

This paper presents how neural swimming controllers for a simulated lamprey can be developed using evolutionary algorithms. A genetic algorithm is used for evolving the architecture of a connectionist model which determines the muscular activity of a simulated body in interaction with water. This work is inspired by the biological model developed by Ekeberg which reproduces the central pattern generator observed in the real lamprey (Ekeberg, 1993). In evolving artificial controllers, we demonstrate that a genetic algorithm can be an interesting design technique for neural controllers and that there exist alternative solutions to the biological connectivity. A variety of neural controllers are evolved which can produce the pattern of oscillations necessary for swimming. These patterns can be modulated through the external excitation applied to the network in order to vary the speed and the direction of swimming. The best evolved controllers cover larger ranges of frequencies, phase lags and speeds of swimming than Ekeberg's model. We also show that the same techniques for evolving artificial solutions can be interesting tools for developing neurobiological models. In particular, biologically plausible controllers can be developed with ranges of oscillation frequency much closer to those observed in the real lamprey than Ekeberg's hand-crafted model.

Key Words

neural control; genetic algorithm; simulation; central pattern generator; swimming; lamprey

Pages 173-216

Spatial Learning and Localization in Rodents: A Computational Model of the Hippocampus and its Implications for Mobile Robots

By Karthik Balakrishnan, Olivier Bousquet and Vasant Honovar

Abstract

The ability to acquire a representation of the spatial environment and the ability to localize within it are essential for successful navigation in a-priori unknown environments. The hippocampal formation is believed to play a key role in spatial learning and localization in animals in general and rodents in particular. This paper briefly reviews the relevant neurobiological and cognitive data, and their relation to computational models of spatial learning and localization used in contemporary mobile robots. It proposes a hippocampal model of spatial learning and localization, and characterizes it using a Kalman filter based tool for information fusion from multiple uncertain sources. The resulting model not only explains neurobiological and behavioral data from rodent experiments, but also allows a robot to learn a place-based metric representation of space and to localize itself in a stochastically optimal manner. The paper presents an algorithmic implementation of the model and results of several experiments that demonstrate its capabilities. These include the ability to disambiguate perceptually similar places, scale well witch increasing errors, and the automatic acquisition of spatial information at multiple resolutions.

Key Words

spatial learning; robot localization; hippocampal model; Kalman filter; probabilistic localization

Pages 217-229

Integrating Exploration and Localization for Mobile Robots

By Brian Yamauchi, Alan Schultz and William Adams

Abstract

Exploration and localization are two of the capabilities necessary for mobile robots to navigate robustly in unknown environments. A robot needs to explore in order to learn the structure of the world, and a robot needs to know its own location in order to make use of its acquired spatial information. However, a problem arises with the integration of exploration and localization. A robot needs to know its own location in order to add new information to its map, but a robot may also need a map to determine its own location. We have addressed this problem with ARIEL, a mobile robot system that combines frontier-based exploration with continuous localization. ARIEL is capable of exploring and mapping an unknown environment while maintaining an accurate estimate of its position at all times. In this paper, we describe frontier-based exploration and continuous localization, and we explain how ARIEL integrates these techniques. Then we show results from experiments performed in the exploration of a real-world office hallway environment. These results demonstrate that maps learned using exploration without localization suffer from substantiial dead reckoning errors, while maps learned by ARIEL avoid these errors and can be used for reliable exploration and navigation.

Key Words

mobile robotics; exploration; localization; map learning

Pages 231-236

How Learning and Evolution Interact: The case of a Learning Task which Differs from the Evolutionary Task

By Stefano Nolfi

Abstract

It has been reported recently that learning has a beneficial effect on evolution even if the learning involved the acquisition of an ability which is different from the ability for which individuals were selected (Nolfi, Elman & Parisi, 1994). This effect was explained as the result of the interaction between learning and evolution. In a successive paper, however, the effect was explained as a form of recovery from weight perturbation caused by mutations (Harvey, 1996, 1997). In this paper, I provide additional data that show how the effect, at least in the case considered in the paper, can only be explained as a result of the interaction between learning and evolution as originally hypothesized.

Key Words

evolution; learning; Baldwin Effect

back to TOC, back to top

Adaptive Behavior, 7 (2)

Adaptive Behavior

Volume 7, Number 2

Winter 1999

Table of Contents

Jun Nishii

A Learning Model of a Periodic Locomotor Pattern by the Central Pattern Generator