Alfredo Weitzenfeld

Behavioral Models of the Praying Mantis as a Basis for Robotic Behavior

Abstract Formal models of animal sensorimotor behavior can provide effective methods for generating robotic intelligence. In this article we describe how schema-theoretic models of the praying mantis derived from behavioral and neuroscientific data can be implemented on a hexapod robot equipped with a real time color vision system. This implementation incorporates a wide range of behaviors, including obstacle avoidance, prey acquisition, predator avoidance, mating, and chantlitaxia behaviors that can provide guidance to neuroscientists, ethologists, and roboticists alike. The goals of this study are threefold: to provide an understanding and means by which fielded robotic systems are not competing with other agents that are more effective at their designated task; to permit them to be successful competitors within the ecological system and capable of displacing less efficient agents; and that they are ecologically sensitive so that agent–environment dynamics are well-modeled and as predictable as possible whenever new robotic technology is introduced.

Biologically-inspired robot spatial cognition based on rat neurophysiological studies

Abstract This paper presents a robot architecture with spatial cognition and navigation capabilities that captures some properties of the rat brain structures involved in learning and memory. This architecture relies on the integration of kinesthetic and visual information derived from artificial landmarks, as well as on Hebbian learning, to build a holistic topological-metric spatial representation during exploration, and employs reinforcement learning by means of an Actor-Critic architecture to enable learning and unlearning of goal locations. From a robotics perspective, this work can be placed in the gap between mapping and map exploitation currently existent in the SLAM literature. The exploitation of the cognitive map allows the robot to recognize places already visited and to find a target from any given departure location, thus enabling goal-directed navigation. From a biological perspective, this study aims at initiating a contribution to experimental neuroscience by providing the system as a tool to test with robots hypotheses concerned with the underlying mechanisms of rats’ spatial cognition. Results from different experiments with a mobile AIBO robot inspired on classical spatial tasks with rats are described, and a comparative analysis is provided in reference to the reversal task devised by O’Keefe in 1983.

NSL: neural simulation language

NSL, Neural Simulation Language, is a general purpose neural network simulation language and development system. NSL includes a high level language for describing neural networks, an interactive command interpreter, and powerful visualization tools. The simulator is designed and implemented using object-oriented programming methodologies. NSL provides a simulation platform for different types of applications, including both biological and artificial neural network based models, some of which are presented here. Presently, a number of research sites are involved in the development of new NSL based models, as well as in the extension and development of new libraries. The close interaction between these sites, together with the utilization of the system for teaching purposes, has provided a key part in the evolution of the system.

A Biologically-Inspired Wolf Pack Multiple Robot Hunting Model

A great amount of work has been made in biologically-inspired robotic systems on single and multiple animal behavior models. These studies have advanced the understandings of animal behavior and have provided at the same time inspiration in the design of single and multiple robotic architectures. Additionally, applications in the real word domain have benefited from such work, like exploration, surveillance, etc. In this work we present a multi-robot architecture based on wolf packs studies showing different formations during prey hunting and predator avoidance. The model has been developed and tested using the NSL/ASL, MIRO systems, and Sony AIBO robots. Results from real robot experimentation are discussed

A concurrent object-oriented framework for the simulation of neural networks

This paper discusses the issues in simulating neural networks using an object-oriented concurrent programming framework, based on our experience in developing two generations of the NSL (Neural Simulation Language) simulation system. The second generation simulation system, NSL 2.0, was designed and implemented utilizing object-oriented programming concepts. We close with future design and implementation directions.

Comparative Experimental Studies on Spatial Memory and Learning in Rats and Robots

The study of behavioral and neurophysiological mechanisms involved in rat spatial cognition provides a basis for the development of computational models and robotic experimentation of goal-oriented learning tasks. These models and robotics architectures offer neurobiologists and neuroethologists alternative platforms to study, analyze and predict spatial cognition based behaviors. In this paper we present a comparative analysis of spatial cognition in rats and robots by contrasting similar goal-oriented tasks in a cyclical maze, where studies in rat spatial cognition are used to develop computational system-level models of hippocampus and striatum integrating kinesthetic and visual information to produce a cognitive map of the environment and drive robot experimentation. During training, Hebbian learning and reinforcement learning, in the form of Actor-Critic architecture, enable robots to learn the optimal route leading to a goal from a designated fixed location in the maze. During testing, robots exploit maximum expectations of reward stored within the previously acquired cognitive map to reach the goal from different starting positions. A detailed discussion of comparative experiments in rats and robots is presented contrasting learning latency while characterizing behavioral procedures during navigation such as errors associated with the selection of a non-optimal route, body rotations, normalized length of the traveled path, and hesitations. Additionally, we present results from evaluating neural activity in rats through detection of the immediate early gene Arc to verify the engagement of hippocampus and striatum in information processing while solving the cyclical maze task, such as robots use our corresponding models of those neural structures.

A Prey Catching and Predator Avoidance Neural-Schema Architecture for Single and Multiple Robots

The paper presents a biologically inspired multi-level neural-schema architecture for prey catching and predator avoidance in single and multiple autonomous robotic systems. The architecture is inspired on anuran (frogs and toads) neuroethological studies and wolf pack group behaviors. The single robot architecture exploits visuomotor coordination models developed to explain anuran behavior in the presence of preys and predators. The multiple robot architecture extends the individual prey catching and predator avoidance model to experiment with group behavior. The robotic modeling architecture distinguishes between higher-level schemas representing behavior and lower-level neural structures representing brain regions. We present results from single and multiple robot experiments developed using the NSL/ASL/MIRO system and Sony AIBO ERS-210 robots.

From schemas to neural networks: A multi-level modelling approach to biologically-inspired autonomous robotic systems

Biology has been an important source of inspiration in building adaptive autonomous robotic systems. Due to the inherent complexity of these models, most biologically-inspired robotic systems tend to be ethological without linkage to underlying neural circuitry. Yet, neural mechanisms are crucial in modelling adaptation and learning. The work presented in this paper describes a schema and neural network multi-level modelling approach to biologically inspired autonomous robotic systems. A prey acquisition model with detour behaviour in frogs is presented to exemplify the modelling approach. The model is tested with simulated and physical robots using the ASL/NSL and MIRO robotic system.

Rat-inspired model of robot target learning and place recognition

We present a model designed on the basis of the rats brain neurophysiology to provide a robot with spatial cognition and goal-oriented navigation capabilities. We describe target learning and place recognition processes in rats as basis for topological map building and exploitation by robots. We experiment with the model in different maze configurations by training a robot to find the goal starting from a fixed location, and by testing it to reach the same target from new different starting locations.

Bio-inspired Model of Robot Spatial Cognition: Topological Place Recognition and Target Learning

In this paper we present a model designed on the basis of the rats brain neurophysiology to provide a robot with spatial cognition and goal-oriented navigation capabilities. We describe place representation and recognition processes in rats as the basis for topological map building and exploitation by robots. We experiment with the model by training a robot to find the goal in a maze starting from a fixed location, and by testing it to reach the same target from new different starting locations.