Today, Dr. Veronica J. Santos visited our lab. She is an Associate Professor in the Mechanical and Aerospace Engineering Department at the University of California, Los Angeles, and Director of the UCLA Biomechatronics Lab. She gave an amazing talk with the title of “Artificial haptic intelligence for human-machine systems”. I presented my work in MPI to her, and we had wonderful discussions about research and future career paths.
Abstract: The functionality of artificial manipulators could be enhanced by artificial “haptic intelligence” that enables the identification of object features via touch for semi-autonomous decision-making and/or display to a human operator. This could be especially useful when complementary sensory modalities, such as vision, are unavailable. I will highlight past and present work to enhance the functionality of artificial hands in human-machine systems. I will describe efforts to develop multimodal tactile sensor skins and to teach robots how to haptically perceive salient geometric features such as edges and fingertip-sized bumps and pits using machine learning techniques. I will describe the use of reinforcement learning to teach robots goal-based policies for a functional contour-following task: the closure of a ziplock bag. Our Contextual Multi-Armed Bandits approach tightly couples robot actions to the tactile and proprioceptive consequences of the actions and selects future actions based on prior experiences, the current context, and a functional task goal. Finally, I will describe current efforts to develop real-time capabilities for the perception of tactile directionality and to develop models for haptically locating objects buried in granular media. Real-time haptic perception and decision-making capabilities could be used to advance semi-autonomous robot systems and reduce the cognitive burden on human teleoperators of devices ranging from wheelchair-mounted robots to explosive ordnance disposal robots.