Abstract:  Grasping and manipulating objects is an important human skill. Because contact between hand and object is fundamental to grasping, measuring it can lead to important insights. However, observing contact through external sensors is challenging because of occlusion and the complexity of the human hand. I will discuss the use of thermal cameras to capture contact maps for household objects that encode the rich hand-object contact during grasping. Participants in our studies grasp 3D printed objects with instructions such as “grasp this like you would use it” or “grasp this like you will hand it off”. Analysis of this data shows the influence of functional intent and object size on grasping, the tendency to touch/avoid “active areas” on the object surface, and the importance of palm and lower finger contact. In more recent work, we capture hand pose in addition to thermal contact maps for deeper understanding of hand-object interaction.

In addition, I will discuss the Argoverse dataset for autonomous driving. We recently concluded the first Argoverse competition which led to exciting advances in 3D tracking and motion forecasting.

Bio:  James Hays an associate professor of computing at Georgia Institute of Technology since fall 2015. Since 2017, James is also a principal scientist at Argo AI. Previously, James was the Manning assistant professor of computer science at Brown University. James received his Ph.D. from Carnegie Mellon University and was a postdoc at Massachusetts Institute of Technology. His research interests span computer vision, computer graphics, robotics, and machine learning. His research often involves exploiting non-traditional data sources (e.g. internet imagery, crowdsourced annotations, thermal imagery, human sketches, autonomous vehicle sensor data) to explore new research problems (e.g. global geolocalization, sketch to real, hand-object contact prediction).

Homepage:  https://cc.gatech.edu/~hays/