Search

This paper is concerned with adaptation capabilities of evolved neural controllers. We propose to evolve mechanisms for parameter self-organization instead of evolving the parameters themselves. The method consists of encoding a set of local adaptation rules that synapses follow while the robot freely moves in the environment. In the experiments presented here, the performance of the robot is measured in environments that are different in significant ways from those used during evolution. The results show that evolutionary adaptive controllers solve the task much faster and better than evolutionary standard fixed-weight controllers, that the method scales up well to large architectures, and that evolutionary adaptive controllers can adapt to environmental changes that involve new sensory characteristics (including transfer from simulation to reality and across different robotic platforms) and new spatial relationships.

Evolutionary Robotics is a powerful method to generate efficient controllers with minimal human intervention, but its applicability to real-world problems remains a challenge because the method takes long time and it requires software simulations that do not necessarily transfer smoothly to physical robots. In this paper we describe a method that overcomes these limitations by evolving robots for the ability to adapt on-line in few seconds. Experiments show that this method require less generations and smaller populations to evolve, that evolved robots adapt in a few seconds to unpredictable change-including transfers from simulations to physical robots- and display non-trivial behaviors. Robots evolved with this method can be dispatched to other planets and to our homes where they will autonomously and quickly adapt to the specific properties of their environments if and when necessary.

We propose a modular architecture for autonomous robots which allows for the implementation of basic behavioral modules by both programming and training, and accommodates for an evolutionary development of the interconnections among modules. This architecture can implement highly complex controllers and allows for incremental shaping of the robot behavior. Our proposal is exemplified and evaluated experimentally through a number of mobile robotic tasks involving exploration, battery recharging and object manipulation.

This paper describes the design and development of a sensor based navigation system which makes it possible for a nonholonomous mobile robot to follow walls using information on its environment picked up by a belt of ultrasonic sensors. To control the robot no preliminary information regarding its environment is required, the robot adapts to them through the information gathered on the spot by the ultrasonic sensors and the information released from a spatial memory. The controller allows the generation of the signal to the robot motors. It has been developed in two directions: one being based on the concept of general perception, and the other on the concept of distributed perception. In carrying out both of these lines of development, the principle of fuzzy logic has been applied. The navigation system has been tested on a prototype mobile robot (VEA-II) developed at IKERLAN, which is highly manoeuvrable and capable of moving both in a holonomous and nonholonomous configurations.

This paper is concerned with artificial evolution of neurocontrollers with adaptive synapses for autonomous mobile robots. The method consists of encoding on the genotype a set of local modification rules that synapses obey while the robot freely moves in the environment [2]. The synaptic weights are not encoded on the genotype. In the experiments presented here, a "behavior-based fitness" function gives reproductive advantage to robots that can solve a sequential task. The results show that evolutionary adaptive controllers solve the task much faster and better than evolutionary standard (non-adaptive) controllers, that the method scales up well to large architectures whereas standard controllers do not, and that evolved adaptive controllers are not trivial and cannot be reduced to a fixed-weight network.

This paper is concerned with adaptation capabilities of evolved neural controllers. A method consisting of encoding a set of local adaptation rules that synapses obey while the robot freely moves in the environment [6] is compared to a standard fixed-weight network. In the experiments presented here, the performance of the robot is measured in environments that are different in significant ways from those used during evolution. The results show that evolutionary adaptive controllers can adapt to environmental changes that involve new sensory characteristics (including transfers from simulation to reality) and new spatial relationships.

We address two issues in Evolutionary Robotics, namely the genetic encoding and the performance criterion, also known as the fitness function. For the first aspect, we suggest to encode mechanisms for parameter self-organization, instead of the parameters themselves as in conventional approaches. We argue that the suggested encoding generates systems that can solve more complex tasks and are more robust to unpredictable sources of change. We support our arguments with a set of experiments on evolutionary neural controllers for physical robots and compare them to conventional encoding. In addition, we show that when also the genetic encoding is left free to evolve, artificial evolution will select to exploit mechanisms of self-organization. For the second aspect, we shall discuss the role of the performance criterion, also known as fitness function, and suggest Fitness Space as a framework to conceive fitness functions in Evolutionary Robotics. Fitness Space can be used as a guide to design fitness functions as well as to compare different experiments in Evolutionary Robotics.