INFANT neural controller for adaptive sensory-motor coordination

doi:10.1016/0893-6080(91)90001-L

Neural Networks

Volume 4, Issue 2, 1991, Pages 131-145

https://doi.org/10.1016/0893-6080(91)90001-L Get rights and content

Abstract

This review presents a theory and prototype for a neural controller called INFANT that learns sensory-motor coordination from its own experience. Three adaptive abilities are discussed: locating stationary targets with movable sensors; grasping arbitrarily positioned and oriented targets in 3D space with multijoint arms, and positioning an unforeseen payload with accurate and stable movements despite unknown sensor feedback delay. INFANT adapts to unforeseen changes in the geometry of the physical motor system, the internal dynamics of the control circuits and to the location, orientation, shape, weight, and size of objects. It learns to accurately grasp an elongated object with almost no information about the geometry of the physical sensory-motor system. This neural controller relies on the self-consistency between sensory and motor signals to achieve unsupervised learning. It is designed to be generalized for coordinating any number of sensory inputs with limbs of any number of joints. The principle theme of the review is how various geometries of interacting topographic neural fields can satisfy the constraints of adaptive behavior in complete sensory-motor circuits.

References (30)

A. Hein
Prerequisite for development of visually guided reaching in the kitten
Brain Research
(1974)
H. Miyamoto et al.
Feedback-error-learning neural network for trajectory control of a robotic manipulator
Neural Networks
(1988)
R. Weber et al.
Corrective movements following refixation saccades, types, and control system analysis
Vision Research
(1972)
J. Albus
A New approach to manipulator control: The cerebellar model articulation controller (CMAC)
Journal of Dynamic Systems, Measurement and Control
(1975)
R.A. Anderson et al.
Encoding of spatial location by posterior parietal neurons
Science
(1985)
M. Critchley
The parietal lobes
(1982)
S. Grossberg et al.
Neural dynamics of adaptive sensory-motor control
(1986/1989)
P.E. Hallet et al.
Saccadic eye movements to flashed targets
Vision Research
(1976)
A. Hein
Recovering spatial motor coordination after visual cortex lesion

A. Hein

Acquiring components of visually guided behavior

A. Hein et al.

A neural model for labile sensorimotor coordinations

R. Held et al.

Movement-produced stimulation in the development of visually guided behavior

Journal of Comparative Physiological Psychology

(1963)

D.H. Hubel et al.

Receptive fields, binocular interaction and functional architecture in the cat's visual cortex

Journal of Physiology

(1962)

M.I. Jordan

Generic constraints on underspecitied target trajectories

Cited by (61)

Inverse Kinematics of Dextrous Manipulators
2012, Neural Systems for Robotics
Manipulators with extra, or redundant, degrees of freedom are capable of dextrous motion. However, control of such manipulators is difficult because the inverse problem; i.e., the choice of a set of control variables which positions the manipulator at a desired target location, is underdetermined. This chapter has two main points. First, it provides a taxonomy of approaches to solving the inverse problem for dextrous manipulators which outlines the relationship between the standard robotics approaches and approaches using neural networks. Second, this chapter analyzes the topological structure of the kinematics problem, showing that the inverse kinematic structure generically decomposes into a finite number of solution branches, each corresponding roughly to the notion of “posture,” such that each solution branch can be described as the product of a one-to-one inverse map and a set of free parameters describing the redundancy. Using these geometric insights, one can then generate direct inverse functions for dextrous manipulators, with which the free parameters can be used flexibly during operation to optimize any user-specified side constraint.
A developmental algorithm for ocular-motor coordination
2010, Robotics and Autonomous Systems
Citation Excerpt :
Even when saccades have been learned they have often not been very closely aligned with existing psychological data and knowledge. For example, [39] addressed the problem of driving moveable visual sensors to locate static objects. The emphasis was on topographic mappings and artificial neural networks, but the neural controller needed 100,000 trials during training. [40]
This paper presents a model of ocular–motor development, inspired by ideas and data from developmental psychology. The learning problem concerns the growth of the transform between image space and motor space necessary for the control of visual saccades. An implementation is used to produce experimental results and these are presented and discussed. The algorithm is simple, extremely fast, self-calibrating, adaptive to change, and exhibits emergent stages of behaviour as learning progresses.
A modular neural network architecture for step-wise learning of grasping tasks
2007, Neural Networks
Citation Excerpt :
Recently, another kind of approach has emerged. This new approach is based on the utilization of neural networks to define grasping configurations or to learn the mapping from an object shape to a hand configuration or a grasp choice (Guigon, Grandguillaume, Otto, Boutkhil, & Burnod, 1994; Kuperstein, 1991; Taha, Brown, & Wright, 1997; Uno, Fukumura, Suzuki, & Kawato, 1999). The previous studies emphasize the correspondence between an object and a hand shape.
This paper proposes a neural network architecture for learning of grasping tasks. The multineural network model presented in this work, allows acquisition of different neural representations of the grasping task through a successive learning over two stages in a strategy that uses already learned representations for the acquisition of the subsequent knowledge. Systematic computer simulations have been carried out in order to test learning and generalization capabilities of the system. The neural activity at different subparts of the artificial neural network during its performance phase, is compared to the activity of populations of real neurons in areas AIP and F5 of the distributed parieto–frontal biological neural network involved in visual guidance of grasping. A more biologically plausible development of the model presented here is also discussed. The proposed model can be also used as a high level controller for a robotic dextrous hand during learning and execution of grasping tasks.
Categorizing arbitrarily shaped objects based on grasping configurations
2006, Robotics and Autonomous Systems
In this paper, we investigate categorizing arbitrarily shaped objects on the basis of how they are grasped. Using a database that consists of 28 objects, we conducted 1200 grasping experiments in a specifically developed simulation environment. The results show that, using a generic representation of grasping rules, objects can be categorized into parent–child relationships that allow grasping rules for “parent” objects to be used successfully for “child” objects. This categorization is independent of the geometric features of objects and only dependent on the grasping configuration for each object. These results could provide an important step toward developing user-adaptive robots.
A neural network model for coordination of hand gesture during reach to grasp
2006, Neural Networks
In this paper a neural network model for spatio-temporal coordination of hand gesture during prehension is proposed. The model includes a simplified control strategy for whole hand shaping during grasping tasks, that provides a realistic coordination among fingers. This strategy uses the increasing evidence that supports the view of a synergistic control of whole fingers during prehension. In this control scheme, only two parameters are needed to define the evolution of hand shape during the task performance. The proposal involves the design and development of a Library of Hand Gestures consisting of motor primitives for finger pre-shaping of an anthropomorphic dextrous hand. Through computer simulations, we show how neural dynamics of the model leads to simulated grasping movements with human-like kinematic features. The model can provide clear-cut predictions for experimental evaluation at both the behavioural and neural levels as well as a neural control system for a dextrous robotic hand.
From behaviour-based robots to motivation-based robots
2005, Robotics and Autonomous Systems
The appearance on the market of entertainment robots for children and families has ipso facto created the new category of motivation-based robots. A taxonomy of the architectures of different robot categories is proposed. The architecture of motivation-based robots is phylogenetic and ontogenetic. A tentative architecture for a specific experimental setup is described. The results of the experiment show that a new motivation arises from the interaction between the robot and the environment. Motivation-based robots equipped with ontogenetic architecture might provide the foundation for a new generation of robots capable of ontogenetic development.

View all citing articles on Scopus

View full text

INFANT neural controller for adaptive sensory-motor coordination

Abstract

Brain Research

Neural Networks

Vision Research

A New approach to manipulator control: The cerebellar model articulation controller (CMAC)

Journal of Dynamic Systems, Measurement and Control

Encoding of spatial location by posterior parietal neurons

Science

The parietal lobes

Neural dynamics of adaptive sensory-motor control

Saccadic eye movements to flashed targets