IFIG framework helps robots follow instructions

Through deep reinforcement learning, neural networks can be trained to map joint representations of observations and instructions directly to actions.   More»

A learning algorithm for training robots' deep neural networks to grasp novel objects

Dinesh Manocha and colleagues' algorithm significantly simplifies the data preparation for learning-based grasping systems and leads to higher qualities of learned grasps.   More»

Alumnus Donald Martin honored by Network of Minorities in Mathematical Sciences

Martin, a member of the statistics faculty at North Carolina State University, is the network's February 13th honoree for Black History Month.   More»