Joanne H. Walker

Evolving Controllers for Real Robots: A Survey of the Literature

For many years, researchers in the field of mobile robotics have been investigating the use of genetic and evolutionary computation (GEC) to aid the development of mobile robot controllers. Alongside the fundamental choices of the GEC mechanism and its operators, which apply to both simulated and physical evolutionary robotics, other issues have emerged which are specific to the application of GEC to physical mobile robotics. This article presents a survey of recent methods in GEC-developed mobile robot controllers, focusing on those methods that include a physical robot at some point in the learning loop. It simultaneously relates each of these methods to a framework of two orthogonal issues: the use of a simulated and/or a physical robot, and the use of finite, training phase evolution prior to a task and/or lifelong adaptation by evolution during a task. A list of evaluation criteria are presented and each of the surveyed methods are compared to them. Analyses of the framework and evaluation criteria suggest several possibilities; however, there appear to be particular advantages in combining simulated, training phase evolution (TPE) with lifelong adaptation by evolution (LAE) on a physical robot.

The balance between initial training and lifelong adaptation in evolving robot controllers

A central aim of robotics research is to design robots that can perform in the real world; a real world that is often highly changeable in nature. An important challenge for researchers is therefore to produce robots that can improve their performance when the environment is stable, and adapt when the environment changes. This paper reports on experiments which show how evolutionary methods can provide lifelong adaptation for robots, and how this evolutionary process was embodied on the robot itself. A unique combination of training and lifelong adaptation are used, and this paper highlights the importance of training to this approach.

Dynamic Function Optimisation: Comparing the Performance of Clonal Selection and Evolution Strategies

This paper reports on novel work using clonal selection (CS) for dynamic function optimisation. A comparison is made between evolution strategies (ES) and CS, for the optimisation of two significantly different dynamic functions at 2, 5 and 10 dimensions. Firstly a sensitivity analysis was performed for both the CS and the ES for both fitness functions. Secondly the performance of the two algorithms was compared over time. The main finding of this work is that the CS optimises better than the ES in problems with few dimensions, although the ES optimises more slowly. At higher dimensions however, the ES optimises both more quickly and to a better level.

A performance sensitive hormone-inspired system for task distribution amongst evolving robots

A hormone-inspired task scheduling method is described which assigns tasks to a group of robots, taking into account the robotspsila performances. This method draws on previous work using endocrine-based methodologies, and incorporates existing evolutionary robotics methods. In the resulting system, robot performance data, generated as part of evolution, is used to autonomously reassign tasks amongst the group, without the use of a central controller.

Task allocation for robots using inspiration from hormones

This article describes a robotic system which uses evolution to continuously adapt a group of heterogeneous robots to their current environment while assigning tasks to these robots using an endocrine-based system. The tasks are allocated dependent on the robots’ current ability to perform the task and whether the task is being done by another robot. A series of experiments is presented taking the work from an evolutionary training phase, through simulation trials, to experiments on real robots. The real robot trials show task swapping dependent on the robots’ ability to perform each task.

Grammatical evolution of a robot controller

An autonomous mobile robot requires an onboard controller that allows it to perform its tasks for long periods in isolation. One possibility is for the robot to adapt to its environment using some form of artificial intelligence. Evolutionary techniques such as genetic programming (GP) offer the possibility of automatically programming the controller based on the robots experience of the world. Grammatical evolution (GE) is a recent evolutionary algorithm that has been successfully applied to various problems, particularly those for which GP has been successful. We present a method for applying GE to autonomous robot control and evaluate it in simulation for the Khepera robot.

Modelling Immunological Memory

Accurate immunological models offer the possibility of performing high-throughput experiments in silico that can predict, or at least suggest, in vivo phenomena. In this chapter, we compare various models of immunological memory. We first validate an experimental immunological simulator, developed by the authors, by simulating several theories of immunological memory with known results. We then use the same system to evaluate the predicted effects of a theory of immunological memory. The resulting model has not been explored before in artificial immune systems research, and we compare the simulated in silico output with in vivo measurements. Although the theory appears valid, we suggest that there are a common set of reasons why immunological memory models are a useful support tool; not conclusive in themselves.

Lifelong evolution for adaptive robots

Researchers in mobile robotics have for many years been investigating the use of evolutionary techniques for the development of control methods. Most evolutionary robotics work has concentrated on the use of evolution exclusively during the training phase of the robot controller. Few investigators continue evolution throughout the lifetime of a robot. This paper investigates a system that uses a genetic algorithm to train a robot for a generalised test environment, then an evolutionary strategy to investigate the effect of continuing the evolution as the robot progresses with its task. It is concluded that lifelong evolution has an important role to play in producing truly adaptive robots.

Endocrine Control for Task Distribution among Heterogeneous Robots

This paper details an endocrine based system which automatically reassigns tasks among heterogeneous robots dependent on the ability of the robot to do the task. This ability (or sensitivity) to a task is initialised for each individual robot after an evolutionary training stage, then constantly adapts as the robots perform the various tasks. The system does not require a centralised controller, and relies on little communication between the robots.