no code implementations • 22 Mar 2017 • Chris Paxton, Vasumathi Raman, Gregory D. Hager, Marin Kobilarov
This paper investigates the ability of neural networks to learn both LTL constraints and control policies in order to generate task plans in complex environments.
Robotics
no code implementations • 4 Sep 2014 • Vasumathi Raman, Hadas Kress-Gazit
With the increasing ubiquity of multi-capable, general-purpose robots arises the need for enabling non-expert users to command these robots to perform complex high-level tasks.