Developing Capable Collaborative Robots
Robots capable of collaborating with people provide tremendous value, bringing with them the potential to revolutionize a wide array of industries ranging from health care to education to manufacturing. Particularly in domains where modern robots are ineffective, human-robot teaming can be leveraged to increase the efficiency, capability, and safety of people. Central to building these autonomous systems are the problems of teammate goal inference, task modeling, and multi-agent coordination, each of which can be extremely challenging without a priori task knowledge or behavioral models. In this talk I will cover my recent work towards developing robots that learn from co-workers and provide transparent, supportive behaviors -- actions a collaborator can perform that facilitate another's task completion or comprehension.
Brad Hayes is a Postdoctoral Associate and a member of the Interactive Robotics Group in the Computer Science and Artificial Intelligence Lab at MIT, working with Professor Julie Shah. He received his PhD from Yale University, advised by Professor Brian Scassellati. Brad is interested in building robotic systems that are supportive, interactive, and intuitive, capable of performing complex collaborative tasks with humans to reduce cognitive or physical load. His work involves a combination of learning from demonstration, human teaming psychology, intention recognition and projection, and human-robot interaction.