Issues in evolutionary robotics
Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Sequential behavior and learning in evolved dynamical neural networks
Adaptive Behavior
Integrating reactive, sequential, and learning behavior using dynamical neural networks
SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Adding temporary memory to ZCS
Adaptive Behavior
An Behavior-based Robotics
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Evolutionary Robotics: A Survey of Applications and Problems
Proceedings of the First European Workshop on Evolutionary Robotics
Zcs: A zeroth level classifier system
Evolutionary Computation
Evolution of homing navigation in a real mobile robot
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
| Hi-index | 0.00 |
The purpose of this paper is to explore the effect of adding known amounts of memory to pure reactive systems in a variety of tasks. Usinga finite state machine approach, we construct controllers for a simulated robot for five tasks--obstacle avoidance, wall following, exploration, and box pushing--with two sensor configurations using evolutionary computation techniques, and compare the performance of stateless and memory-based controllers. For obstacle avoidance and exploration no significant difference is observed; for wall-following and box pushing, stateless controllers are significantly worse than memory-based but increasing amounts of memory give no significant increase in performance. The need for memory in these cases reflects a need to discriminate sensorimotor contexts to effectively perform the task.