ABSTRACT
Due to the large number of evaluations required, evolutionary robotics experiments are generally conducted in simulated environments. One way to increase the generality of a robot's behavior is to evolve it in multiple environments. These environment spaces can be defined by the number of free parameters (f) and the number of variations each free parameter can take (n). Each environment space then has nf individual environments. For a robot to be fit in the environment space it must perform well in each of the nf environments. Thus the number of environments grows exponentially as n and f are increased. To mitigate the problem of having to evolve a robot in each environment in the space we introduce the concept of ecological modularity. Ecological modularity is here defined as the robot's modularity with respect to free parameters in the its environment space. We show that if a robot is modular along m of the free parameters in its environment space, it only needs to be evolved in nf-m+1 environments to be fit in all of the nf environments. This work thus presents a heretofore unknown relationship between the modularity of an agent and its ability to generalize evolved behaviors in new environments.
- Collin K Cappelle, Anton Bernatskiy, Kenneth Livingston, Nicholas Livingston, and Josh Bongard. 2016. Morphological Modularity Can Enable the Evolution of Robot Behavior to Scale Linearly with the Number of Environmental Features. Frontiers in Robotics and AI 3 (2016), 59.Google ScholarCross Ref
- Jeff Clune, Jean-Baptiste Mouret, and Hod Lipson. 2013. The evolutionary origins of modularity. Procs of the Royal Society B: Biological sciences 280, 1755 (2013), 20122863.Google Scholar
- Kai Olav Ellefsen, Jean-Baptiste Mouret, and Jeff Clune. 2015. Neural modularity helps organisms evolve to learn new skills without forgetting old skills. PLoS Comput Biol 11, 4 (2015), e1004128.Google ScholarCross Ref
- Robert M French. 1999. Catastrophic forgetting in connectionist networks. Trends in cognitive sciences 3, 4 (1999), 128--135.Google Scholar
- Hod Lipson, Jordan B Pollack, Nam P Suh, and P Wainwright. 2002. On the origin of modular variation. Evolution 56, 8 (2002), 1549--1556.Google ScholarCross Ref
- Maja Matarić and Dave Cliff. 1996. Challenges in evolving controllers for physical robots. Robotics and autonomous systems 19, 1 (1996), 67--83.Google Scholar
- Ecological modularity as a means to reduce necessary training environments in evolutionary robotics
Recommendations
Evolving Robot Morphology Facilitates the Evolution of Neural Modularity and Evolvability
GECCO '15: Proceedings of the 2015 Annual Conference on Genetic and Evolutionary ComputationAlthough recent work has demonstrated that modularity can increase evolvability in non-embodied systems, it remains to be seen how the morphologies of embodied agents influences the ability of an evolutionary algorithm to find useful and modular ...
Historical and futuristic perspectives of robotics
AbstractAccording to the progress and applications of robots, we can categorize them into three different generations: industrial robots, autonomous mobile robots, and social robots. At the first section, the significant characteristics, structures, and ...
Facilitating evolutionary innovation by developmental modularity and variability
GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computationNatural complex adaptive systems show many examples of self-organization and decentralization, such as pattern formation or swarm intelligence. Yet, only multicellular organisms possess the genuine architectural capabilities needed in many engineering ...
Comments