A University of Vermont computer scientist helped develop the first robot capable of detecting its own shape and using this knowledge to adapt to damage.


University of Vermont

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.

More traditional robots either require extensive programming to adapt to damage, limiting their adaptability in the face of unexpected conditions, or they must experiment far more extensively and mechanically to develop new ways of moving, limiting efficiency and increasing the risk of damage in hostile environments.

‘The most important thing here for us is this is the first robot that can build up a description of its own body. So the robot can build up a sense of self; that hasn't been done before in robotics,’ said Bongard. ‘The second interesting thing about this is that it then uses that self-model, that sense of self, to actually try out different ways of moving. We commanded this robot to learn how to move; we didn't tell the robot how to move. It tries internally using this self-model, “What would happen if I tried hopping? What would happen if I crawled?” And so on. And eventually it comes up with a behaviour that it thinks will actually work and then tries it out in reality; more often than not the robot starts moving.’

‘It also suggests something about the nature of self-awareness,’ added Bongard. ‘This robot starts by having little awareness of its own body, and through interaction through the physical world it gains experience and builds up a sense of itself, a simulation of its own body, and it can then come to understand what that body is capable of and what it isn't capable of.

‘Taking that a step forward then, perhaps we can start someday to use robots as tools to start to ask questions about the nature of human self-awareness and curiosity. Is there something going on in our brains similar to what's going on in the brain of this robot?’