Evolution of the layers in a subsumption architecture robot controller

An approach to robotics called layered evolution and merging features from the subsumption architecture into evolutionary robotics is presented, its advantages and its relevance for science and engineering are discussed. This approach is used to construct a layered controller for a simulated robot that learns which light source to approach in an environment with obstacles. The evolvability and performance of layered evolution on this task is compared to (standard) monolithic evolution, incremental and modularised evolution. To test the optimality of the evolved solutions the evolved controller is merged back into a single network. On the grounds of the test results, it is argued that layered evolution provides a superior approach for many tasks, and future research projects involving this approach are suggested.

[1]  Stefano Nolfi,et al.  Using Emergent Modularity to Develop Control Systems for Mobile Robots , 1997, Adapt. Behav..

[2]  Hod Lipson,et al.  Uncontrolled Engineering : A Review of Nolfi and Floreano ’ s Evolutionary Robotics , 2001 .

[3]  Inman Harvey,et al.  An Evolutionary Ecological Approach to the Study of Learning Behavior Using a Robot-Based Model , 2002, Adapt. Behav..

[4]  S. Laughlin,et al.  Computational neuroethology: a provisional manifesto , 1991 .

[5]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[6]  Peter Redgrave,et al.  Layered Control Architectures in Robots and Vertebrates , 1999, Adapt. Behav..

[7]  Stefano Nolfi,et al.  Evolving robots able to self-localize in the environment: the importance of viewing cognition as the result of processes occurring at different time-scales , 2002 .

[8]  Lionel Barnett,et al.  Evolutionary search on fitness landscapes with neutral networks , 2003 .

[9]  Rodney A. Brooks,et al.  A Robot that Walks; Emergent Behaviors from a Carefully Evolved Network , 1989, Neural Computation.

[10]  Ronald L. Rivest,et al.  Introduction to Algorithms, Second Edition , 2001 .

[11]  Dario Floreano,et al.  Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs , 2003, EvoWorkshops.

[12]  Risto Miikkulainen,et al.  Incremental Evolution of Complex General Behavior , 1997, Adapt. Behav..

[13]  Stanley J. Rosenschein,et al.  From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior , 1996 .

[14]  Robin R. Murphy,et al.  Introduction to AI Robotics , 2000 .

[15]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[16]  Tom Ziemke.  On 'Parts' and 'Wholes' of Adaptive Behavior: Functional Modularity and Diachronic Structure in Recurrent Neural Robot Controllers , 2000 .

[17]  Randall D. Beer,et al.  On the Dynamics of Small Continuous-Time Recurrent Neural Networks , 1995, Adapt. Behav..

[18]  Rodney A. Brooks,et al.  A robot that walks; emergent behaviors from a carefully evolved network , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[19]  D. Floreano,et al.  Incremental Evolution with Minimal Resources , 1999 .

[20]  Lionel Barnett,et al.  Netcrawling-optimal evolutionary search with neutral networks , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[21]  R. A. Brooks,et al.  Intelligence without Representation , 1991, Artif. Intell..

[22]  Rodney A. Brooks,et al.  Robot: The Future of Flesh and Machines , 2002 .

[23]  Francesco Mondada,et al.  Evolution of Plastic Neurocontrollers for Situated Agents , 1996 .