The conscious robot

A

computer scientist helped develop the first robot capable of detecting its own shape and using this knowledge to efficiently adapt to damage. The new technology may have applications for robots used as planetary rovers or in disaster relief.

Joshua Bongard, an assistant professor in the College of Engineering and Mathematical Sciences, is lead author of a paper describing the project, ‘Resilient Machines Through Continuous Self-Modelling,’ that appeared in a recent issue the journal Science. Bongard was assisted by Victor Zykov and Hod Lipson of Cornell University.

The group's robot, which resembles a starfish, initially has no sense of its own shape. It measures the results of a limited number of small movements to develop plausible models of its shape and construction. The robot evaluates and refines these competing candidate models through more movements and observation, and arriving at an accurate internal model of its shape. The robot can then use this continuously updated self-model to detect damage and develop new ways to move even after sustaining damage like the loss of a leg.