Tool use requires high levels of cognitive function and is only observed in higher mammals and some avian species such as corvids. In this paper, we will investigate how the capability to construct and use tools can spontaneously emerge in a simulated evolution of a two degree-of-freedom articulated limb. The controller for the limb was evolved as neural networks that can gradually take on arbitrary topologies (NeuroEvolution of Augmenting Topologies, or NEAT). First, we show how very broad fitness criteria such as distance to the target, number of steps to reach the target, and tool pick-up frequency are enough to give rise to tool using behavior. Second, we analyze the evolved neural circuits to find properties that enable tool use. Finally, we show that simple composite tools can be constructed and used with the same NEAT approach. We expect our results to help us understand the origin of tool construction and use and the kind of neural networks that enable such a powerful trait.
Joint work with Qinbo Li, Jaewook Yoo, and Randall Reams
Yoonsuck Choe is a professor of Computer Science and Engineering and director of the Brain Networks Laboratory at Texas A&M University. He received his B.S. degree in Computer Science at Yonsei University, and his M.A. and Ph.D. degrees in Computer Science at the University of Texas at Austin. His research interest is broadly in computational neuroscience, with works ranging from self-organization of the visual cortex, predictive dynamics, sensorimotor learning, high-throughput brain imaging, and connectomics.