Ecological modularity as a means to reduce necessary training environments in evolutionary robotics

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 n^f individual environments. For a robot to be fit in the environment space it must perform well in each of the n^f 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 n^f-m+1 environments to be fit in all of the n^f 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.

References

1. 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.
2. 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.
3. 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.
4. Robert M French. 1999. Catastrophic forgetting in connectionist networks. Trends in cognitive sciences 3, 4 (1999), 128--135.
5. Hod Lipson, Jordan B Pollack, Nam P Suh, and P Wainwright. 2002. On the origin of modular variation. Evolution 56, 8 (2002), 1549--1556.
6. Maja Matarić and Dave Cliff. 1996. Challenges in evolving controllers for physical robots. Robotics and autonomous systems 19, 1 (1996), 67--83.

• Computer systems organization

  • Embedded and cyber-physical systems

• Computing methodologies

  • Artificial intelligence

    • Control methods

    • Planning and scheduling