This paper presents a hybrid system approach in the design of a singularityless task level controller. To achieve a singularityless motion control in the neighborhood of singulari...
Selective dynamic compilation systems, typically driven by annotations that identify run-time constants, can achieve significant program speedups. However, manually inserting ann...
We pose the problem of 3D human tracking as one of inference in a graphical model. Unlike traditional kinematic tree representations, our model of the body is a collection of loos...
Leonid Sigal, Sidharth Bhatia, Stefan Roth, Michae...
For vehicles navigating initially unknown cluttered environments, current state-of-the-art planning algorithms are able to plan and re-plan dynamically-feasible paths efficiently a...
Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...