John Hallam

Evolving robot morphology

True evolvable hardware should evolve whole hardware structures. In robotics, it is not enough only to evolve the control circuit; the performance of the control circuit is dependent on other hardware parameters-the robot body plan, which might include body size, wheel radius, motor time constant, sensors, etc. Both the control circuit and the body plan co-evolve in true evolvable hardware. By including the robot body plan in the genotype as a kind of Hox gene, we co-evolve task-fulfilling behaviors and body plans, and we study the distribution of body parameters in the morphological space. Further, we have developed a new hardware module for the Khepera robot, namely ears with programmable amplifiers, synthesizers and mixers, that allow us to study true evolvable hardware by modelling the evolution of auditory sensor morphology.

TOWARDS OPTIMIZING ENTERTAINMENT IN COMPUTER GAMES

Mainly motivated by the current lack of a qualitative and quantitative entertainment formulation of computer games and the procedures to generate it, this article covers the following issues: It presents the features—extracted primarily from the opponent behavior—that make a predator/prey game appealing; provides the qualitative and quantitative means for measuring player entertainment in real time, and introduces a successful methodology for obtaining games of high satisfaction. This methodology is based on online (during play) learning opponents who demonstrate cooperative action. By testing the game against humans, we confirm our hypothesis that the proposed entertainment measure is consistent with the judgment of human players. As far as learning in real time against human players is concerned, results suggest that longer games are required for humans to notice some sort of change in their entertainment.

A hybrid GP/GA approach for co-evolving controllers and robot bodies to achieve fitness-specified tasks

Evolutionary approaches have been advocated to automate robot design. Some research work has shown the success of evolving controllers for the robots by genetic approaches. As we can observe, however, not only the controller but also the robot body itself can affect the behavior of the robot in a robot system. We develop a hybrid GP/GA approach to evolve both controllers and robot bodies to achieve behavior-specified tasks. In order to assess the performance of the developed approach, it is used to evolve a simulated agent, with its own controller and body, to do obstacle avoidance in the simulated environment. Experimental results show the promise of this work. In addition, the importance of co-evolving controllers and robot bodies is analyzed and discussed.

Evolving Swimming Controllers for a Simulated Lamprey with Inspiration from Neurobiology

This paper presents how neural swimming controllers for a simulated lamprey can be developed using evolutionary algorithms. A genetic algorithm is used for evolving the architecture of a connectionist model which determines the muscular activity of a simulated body in interaction with water. This work is inspired by the biological model developed by Ekeberg which repro duces the central pattern generator observed in the real lamprey (Ekeberg, 1993). In evolving artificial controllers, we demonstrate that a genetic algorithm can be an interesting design tech nique for neural controllers and that there exist alternative solutions to the biological connectiv ity. A variety of neural controllers are evolved which can produce the pattern of oscillations necessary for swimming. These patterns can be modulated through the external excitation ap plied to the network in order to vary the speed and the direction of swimming. The best evolved controllers cover larger ranges of frequencies, phase lags and speeds of swimming than Ekebergs model. We also show that the same techniques for evolving artificial solutions can be interesting tools for developing neurobiological models. In particular, biologically plausible controllers can be developed with ranges of oscillation frequency much closer to those observed in the real lamprey than Ekebergs hand-crafted model.

Applying genetic programming to evolve behavior primitives and arbitrators for mobile robots

The behavior-based approach has been successfully applied to designing robot control systems. This paper presents our work, based on evolutionary algorithms, to program behavior-based robots automatically. Instead of hand-coding all the behavior controllers or evolving an entire control system for an overall task, we suggest our approach at the intermediate level: it includes evolving behavior primitives and behavior arbitrators for a mobile robot to achieve the specified tasks. To examine the developed approach, we evolve a control system for a moderately complicated box-pushing task as an example. We first evolved the controllers in a simulation and then transferred them to the Khepera miniature robot. Experimental results show the promise of our approach, and the evolved controllers are transferred to the real robot without loss of performance.

Preference Learning for Cognitive Modeling: A Case Study on Entertainment Preferences

Learning from preferences, which provide means for expressing a subjects desires, constitutes an important topic in machine learning research. This paper presents a comparative study of four alternative instance preference learning algorithms (both linear and nonlinear). The case study investigated is to learn to predict the expressed entertainment preferences of children when playing physical games built on their personalized playing features ( entertainment modeling). Two of the approaches are derived from the literature-the large-margin algorithm (LMA) and preference learning with Gaussian processes-while the remaining two are custom-designed approaches for the problem under investigation: meta-LMA and neuroevolution. Preference learning techniques are combined with feature set selection methods permitting the construction of effective preference models, given suitable individual playing features. The underlying preference model that best reflects children preferences is obtained through neuroevolution: 82.22% of cross-validation accuracy in predicting reported entertainment in the main set of game survey experimentation. The model is able to correctly match expressed preferences in 66.66% of cases on previously unseen data (p -value = 0.0136) of a second physical activity control experiment. Results indicate the benefit of the use of neuroevolution and sequential forward selection for the investigated complex case study of cognitive modeling in physical games.

Towards capturing and enhancing entertainment in computer games

This paper introduces quantitative measurements/metrics of qualitative entertainment features within computer game environments and proposes artificial intelligence (AI) techniques for optimizing entertainment in such interactive systems. A human-verified metric of interest (i.e. player entertainment in real-time) for predator/prey games and a neuro-evolution on-line learning (i.e. during play) approach have already been reported in the literature to serve this purpose. In this paper, an alternative quantitative approach to entertainment modeling based on psychological studies in the field of computer games is introduced and a comparative study of the two approaches is presented. Artificial neural networks (ANNs) and fuzzy ANNs are used to model player satisfaction (interest) in real-time and investigate quantitatively how the qualitative factors of challenge and curiosity contribute to human entertainment. We demonstrate that appropriate non-extreme levels of challenge and curiosity generate high values of entertainment and we discuss the extensibility of the approach to other genres of digital entertainment and edutainment.

Ranking vs. Preference: a comparative study of self-reporting

This paper introduces a comparative analysis between rating and pairwise self-reporting via questionnaires in user survey experiments. Two dissimilar game user survey experiments are employed in which the two questionnaire schemes are tested and compared for reliable affect annotation. The statistical analysis followed to test our hypotheses shows that even though the two selfreporting schemes are consistent there are significant order of reporting effects when subjects report via a rating questionnaire. The paper concludes with a discussion of the appropriateness of each self-reporting scheme under conditions drawn from the experimental results obtained.

EMOTION-TRIGGERED LEARNING IN AUTONOMOUS ROBOT CONTROL

The fact that emotions are considered to be essential to human reasoning suggests that they might play an important role in autonomous robots as well. In particular, the decision of when to interrupt ongoing behavior is often associated with emotions in natural systems. The question under examination here is whether this role of emotions can be useful for a robot which adapts to its environment. For this purpose, an emotion model was developed and integrated in a reinforcement-learning framework. Robot experiments were done to test an emotion-dependent mechanism for the automatic detection of the relevant events of a learning task against more traditional approaches. Experimental results are presented that confirm that emotions can be useful in this role, specifically by improving the efficiency of the learning algorithm.The fact that emotions are considered to be essential to human reasoning suggests that they might play an important role in autonomous robots as well. In particular, the decision of when to interrupt ongoing behavior is often associated with emotions in natural systems. The question under examination here is whether this role of emotions can be useful for a robot which adapts to its environment. For this purpose, an emotion model was developed and integrated in a reinforcement-learning framework. Robot experiments were done to test an emotion-dependent mechanism for the automatic detection of the relevant events of a learning task against more traditional approaches. Experimental results are presented that confirm that emotions can be useful in this role, specifically by improving the efficiency of the learning algorithm.

Real-time challenge balance in an RTS game using rtNEAT

This paper explores using the NEAT and rtNEAT neuro-evolution methodologies to generate intelligent opponents in real-time strategy (RTS) games. The main objective is to adapt the challenge generated by the game opponents to match the skill of a player in real-time, ultimately leading to a higher entertainment value perceived by a human player of the game. Results indicate the effectiveness of NEAT and rtNEAT but demonstrate their limitations for use in real-time strategy games.