Reference Hub

This research has been cited in:

Conference
The Behavioural and Topological Effects of Measurement Noise on Evolutionary Neurocontrollers2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)10.1109/SMC52423.2021.9659280
Chapter
A Case Study on the Scalability of Online Evolution of Robotic ControllersProgress in Artificial Intelligence10.1007/978-3-319-23485-4_20
Conference
Online Hyper-evolution of Controllers in Multirobot Systems2016 IEEE 10th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)10.1109/SASO.2016.7
Conference
Multiobjective Neuromodulated Controllers for Efficient Autonomous Vehicles with Mass and Drag in the Pursuit-Evasion Game2020 IEEE Congress on Evolutionary Computation (CEC)10.1109/CEC48606.2020.9185818
Conference
Self-Adaptation of Meta-Parameters for Lamarckian-Inherited Neuromodulated Neurocontrollers in the Pursuit-Evasion Game2020 IEEE Symposium Series on Computational Intelligence (SSCI)10.1109/SSCI47803.2020.9308450
Conference
Lamarckian Inheritance in Neuromodulated Multiobjective Evolutionary Neurocontrollers2019 27th Mediterranean Conference on Control and Automation (MED)10.1109/MED.2019.8798515
Chapter
Leveraging Online Racing and Population Cloning in Evolutionary Multirobot SystemsApplications of Evolutionary Computation10.1007/978-3-319-31153-1_12
Article
Open Issues in Evolutionary RoboticsEvolutionary Computation10.1162/EVCO_a_00172
Conference
Objective Comparison and Selection in Mono- and Multi-Objective Evolutionary Neurocontrollers2020 IEEE Symposium Series on Computational Intelligence (SSCI)10.1109/SSCI47803.2020.9308403
Conference
Exploring the Relationship Between Topology and Function in Evolved Neural Networks2020 IEEE Symposium Series on Computational Intelligence (SSCI)10.1109/SSCI47803.2020.9308196
Conference
Evolutionary Inherited Neuromodulated Neurocontrollers with Objective Weighted Ranking2021 IEEE Congress on Evolutionary Computation (CEC)10.1109/CEC45853.2021.9504892
Article
Multi-Agent Simulation Collision Avoidance of Complex SystemInternational Journal of Ambient Computing and Intelligence10.4018/IJACI.2018010103
Chapter
Multi-Agent Simulation Collision Avoidance of Complex SystemEmergency and Disaster Management10.4018/978-1-5225-6195-8.ch050

Online Evolution of Adaptive Robot Behaviour

Fernando Silva, Paulo Urbano, Anders Lyhne Christensen

Source Title: International Journal of Natural Computing Research (IJNCR)4(2)

ISSN: 1947-928X|EISSN: 1947-9298|EISBN13: 9781466655829|DOI: 10.4018/ijncr.2014040104

Cite Article Cite Article

MLA

Silva, Fernando, et al. "Online Evolution of Adaptive Robot Behaviour." IJNCR vol.4, no.2 2014: pp.59-77. http://doi.org/10.4018/ijncr.2014040104

APA

Silva, F., Urbano, P., & Christensen, A. L. (2014). Online Evolution of Adaptive Robot Behaviour. International Journal of Natural Computing Research (IJNCR), 4(2), 59-77. http://doi.org/10.4018/ijncr.2014040104

Chicago

Silva, Fernando, Paulo Urbano, and Anders Lyhne Christensen. "Online Evolution of Adaptive Robot Behaviour," International Journal of Natural Computing Research (IJNCR) 4, no.2: 59-77. http://doi.org/10.4018/ijncr.2014040104

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

The authors propose and evaluate a novel approach to the online synthesis of neural controllers for autonomous robots. The authors combine online evolution of weights and network topology with neuromodulated learning. The authors demonstrate our method through a series of simulation-based experiments in which an e-puck-like robot must perform a dynamic concurrent foraging task. In this task, scattered food items periodically change their nutritive value or become poisonous. The authors demonstrate that the online evolutionary process, both with and without neuromodulation, is capable of generating controllers well adapted to the periodic task changes. The authors show that when neuromodulated learning is combined with evolution, neural controllers are synthesised faster than by evolution alone. An analysis of the evolved solutions reveals that neuromodulation allows for a more effective expression of a given topology's potential due to the active modification of internal dynamics. Neuromodulated networks learn abstractions of the task and different modes of operation that are triggered by external stimulus.

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.

Username or email: *

Password: *

Forgot individual login password?

Create individual account

Online Evolution of Adaptive Robot Behaviour

MLA

APA

Chicago

Export Reference

Abstract

Request Access