Internal models of the environment have an important role to play in adaptive systems in general and are of particular importance for the supervised learning paradigm. In this paper we demonstrate that certain classical problems associated with the notion of the \teacher " in supervised learning can be solved by judicious use of learned internal models as components of the adaptive system. In particular, we show how supervised learning algorithms can be utilized in cases in which an unknown dynamical system intervenes between actions and desired outcomes. Our approach applies to any supervised learning algorithm that is capable of learning in multi-layer networks.

Humans demonstrate a remarkable ability to generate accurate and appropriate motor behavior under many different and often uncertain environmental conditions. In this paper, we propose a modular approach to such motor learning and control. We review the behavioral evidence and benefits of modularity, and propose a new architecture based on multiple pairs of inverse (controller) and forward (predictor) models. Within each pair, the inverse and forward models are tightly coupled both during their acquisition, through motor learning, and use, during which the forward models determine the contribution of each inverse model's output to the final motor command. This architecture can simultaneously learn the multiple inverse models necessary for control as well as how to select the inverse models appropriate for a given environment. Finally, we describe specific predictions of the model, which can be tested experimentally. # 1998 Elsevier Science Ltd. All rights reserved. Keywords: Motor con...

A direct adaptive tracking control architecture is proposed and evaluated for a class of continuous -time nonlinear dynamic systems for which an explicit linear parameterization of the uncertainty in the dynamics is either unknown or impossible. The architecture employs a network of gaussian radial basis functions to adaptively compensate for the plant nonlinearities. Under mild assumptions about the degree of smoothness exhibited by the nonlinear functions, the algorithm is proven to be globally stable, with tracking errors converging to a neighborhood of zero. A constructive procedure is detailed, which directly translates the assumed smoothness properties of the nonlinearities involved into a specification of the network required to represent the plant to a chosen degree of accuracy. A stable weight adjustment mechanism is then determined using Lyapunov theory. The network construction and performance of the resulting controller are illustrated through simulations with example syst...

Fundamental and advanced developments in neuro-fuzzy synergisms for modeling and control are reviewed. The essential part of neuro-fuzzy synergisms comes from a common framework called adaptive networks, which unifies both neural networks and fuzzy models. The fuzzy models under the framework of adaptive networks is called ANFIS (Adaptive-Network-based Fuzzy Inference System), which possess certain advantages over neural networks. We introduce the design methods for ANFIS in both modeling and control applications. Current problems and future directions for neuro-fuzzy approaches are also addressed.

The sensorimotor integration system can be viewed as an observer attempting to estimate its own state and the state of the environment by integrating multiple sources of information. We describe a computational framework capturing this notion, and some specific models of integration and adaptation that result from it. Psychophysical results from two sensorimotor systems, subserving the integration and adaptation of visuo-auditory maps, and estimation of the state of the hand during arm movements, are presented and analyzed within this framework. These results suggest that: (1) Spatial information from visual and auditory systems is integrated so as to reduce the variance in localization. (2) The effects of a remapping in the relation between visual and auditory space can be predicted from a simple learning rule. (3) The temporal propagation of errors in estimating the hand's state is captured by a linear dynamic observer, providing evidence for the existence of an intern...

ABSTRACT: A multilayered neural network processor is used to control a given plant. Several learning architectures are proposed for training the neural controller to provide the appropriate inputs to the plant so that a desired response is obtained. A modified er-ror-back propagation algorithm, based on propagation of the output error through the plant, is introduced. The properties of the proposed architectures are studied through a simulation example.

This article presents a biologically inspired model for motor skills imitation. The model is composed of modules whose functinalities are inspired by corresponding brain regions responsible for the control of movement in primates. These modules are high-level abstractions of the spinal cord, the primary and premotor cortexes (M1 and PM), the cerebellum, and the temporal cortex. Each module is modeled at a connectionist level. Neurons in PM respond both to visual observation of movements and to corresponding motor commands produced by the cerebellum. As such, they give an abstract representation of mirror neurons. Learning of new combinations of movements is done in PM and in the cerebellum. Premotor cortexes and cerebellum are modeled by the DRAMA neural architecture which allows learning of times series and of spatio-temporal invariance in multimodal inputs. The model is implemented in a mechanical simulation of two humanoid avatars, the imitator and the imitatee. Three types of sequences learning are presented: (1) learning of repetitive patterns of arm and leg movements; (2) learning of oscillatory movements of shoulders and elbows, using video data of a human demonstration; 3) learning of precise movements of the extremities for grasp and reach

The aim of the present paper is to propose that the adoption of a framework of biological development is suitable for the construction of artificial systems. We will argue that a developmental approach does provide unique insights on how to build highly complex and adaptable artificial systems. To illustrate our point, we will use as an example the acquisition of goal-directed reaching. In the initial part of the paper we will outline a) how mechanisms of biological development can be adapted to the artificial world, and b) how this artificial development differs from traditional engineering approaches to robotics. An experiment performed on an artificial system initially controlled by motor reflexes is presented, showing the acquisition of visuo-motor maps for ballistic control of reaching without explicit knowledge of the system's kinematic parameters.

1 This chapter provides a basic introduction to various of the computational issues that arise in the study of motor control and motor learning. A broad set of topics is discussed, including feedback control, feedforward control, the problem of delay, observers, learning algorithms, motor learning, and reference models. The goal of the chapter is to provide a unified discussion of these topics, emphasizing the complementary roles that they play in complex control systems. The choice of topics is motivated by their relevance to problems in motor control and motor learning; however, the chapter is not intended to be a review of specific models. Rather we emphasize basic theoretical issues with broad applicability. Many of the ideas described here are developed more fully in standard textbooks in modern systems theory, particularly textbooks on discrete-time systems (˚Aström & Wittenmark, 1984), adaptive signal processing (Widrow & Stearns, 1985), and adaptive control systems (Goodwin & Sin, 1984; ˚Aström & Wittenmark, 1989). These texts assume a substantial background in control

A novel hierarchical neural network architecture for sensory-motor learning and behavior generation is proposed. Two levels of forward model neural networks are operated on different time scales while parametric interactions are allowed between the two network levels in the bottom-up and top-down directions. The models are examined through experiments of behavior learning and generation using a real robot arm equipped with a vision system. The results of the learning experiments showed that the behavioral patterns are learned by self-organizing the behavioral primitives in the lower level and combining the primitives sequentially in the higher level. The results contrast with prior work