Josh Bongard
University of Vermont, Burlington, USA
Resilient Machines and Why Morphology Matters
Summary -- Resilient Machines
If the body plays a central role in intelligence, as a roboticist, how do we choose an appropriate body for our robot? Evolutionary robotics allows us to automatically optimize the physical layout of our robots as we also optimize their controllers. In this talk I will demonstrate how selecting or evolving an appropriate robot body can (1) simplify control, (2) make seemingly difficult tasks easier, (3) increase evolvability, (4) provide new behaviors, (5) facilitate the extraction of information from the environment, (6) generate new research questions, and (7) improve scalability.
Summary -- Why Morphology Matters
Embodied artificial intelligence argues that the body and brain play equally important roles in the generation of adaptive behavior. This raises the question then of not only what brain, but also what body is appropriate for a given task. An increasingly common approach therefore is to evolve an agent's morphology along with its control in the hope that evolution will find a good coupled system. In order for embodied artificial intelligence to gain credibility within the robotics and cognitive science communities however, it is necessary to amass evidence not only for *how* to co-optimize morphology and control of adaptive machines, but *why*. This presentation will describe two new lines of evidence for why this co-optimization is useful: I will show that as task difficulty increases, there is an increasing benefit to evolving more aspects of a robot's body; and that co-optimizing a robot's body and controller leads to the discovery of legged locomotion faster than if only the robot's controller is optimized.
Resume
Josh Bongard is a professor in the University of Vermont. He received his Bachelors degree in Computer Science from McMaster University, Canada, his Masters degree from the University of Sussex, UK, and his PhD from the University of Zurich, Switzerland. He served as a postdoctoral associate under Hod Lipson in the Computational Synthesis Laboratory at Cornell University from 2003 to 2006. He is the co-author of the book entitled "How the Body Shapes the Way We Think: A New View of Intelligence". |