ACM TechNews

Piecing Together the Next Generation of Cognitive Robots

ICT Results (05/05/08)

European researchers in the Cognitive Systems for Cognitive Assistants (CoSy) project are creating robots that are more aware of their environment and better able to interact with humans. The CoSy project has used a collaborative effort to develop advances in artificial cognitive systems (ACSs). "We have brought together one of the broadest and most varied teams of researchers in this field," says Geert-Jan Kruijff, the CoSy project manager at the German Research Center for Artificial Intelligence. "This has resulted in an ACS architecture that integrates multiple cognitive functions to create robots that are more self-aware, understand their environment, and can better interact with humans." Kruijff says the integration of different ACS components is one of the greatest challenges in robotics, and getting robots to understand their environment from visual inputs, getting them to interact with humans through spoken commands, and making them relate to their environment is an enormously complex task. The CoSy project has developed a robot called Explorer that has a more human-like understanding of its environment, to the point that it can talk about its surroundings with a human. Instead of using geometric data to map its surroundings, Explorer incorporates qualitative and topographical information, and is capable of learning to recognize objects, space, and their uses through interactions with humans. Another CoSy robot called PlayMate uses applied machine vision and spatial recognition to manipulate objects in response to human instructions.