35 citations · 43 across the 2 of their papers we have counts for
5 papers
"Good Robot!": Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer
Andrew Hundt, Benjamin Killeen, Nicholas Greene +4
Current Reinforcement Learning (RL) algorithms struggle with long-horizon tasks where time can be wasted exploring dead ends and task progress may be easily reversed. We develop th…
sharpDARTS: Faster and More Accurate Differentiable Architecture Search
Andrew Hundt, Varun Jain, Gregory D. Hager
Neural Architecture Search (NAS) has been a source of dramatic improvements in neural network design, with recent results meeting or exceeding the performance of hand-tuned archite…
Evaluating Methods for End-User Creation of Robot Task Plans
Chris Paxton, Felix Jonathan, Andrew Hundt +2
How can we enable users to create effective, perception-driven task plans for collaborative robots? We conducted a 35-person user study with the Behavior Tree-based CoSTAR system t…
The CoSTAR Block Stacking Dataset: Learning with Workspace Constraints
Andrew Hundt, Varun Jain, Chia-Hung Lin +2
A robot can now grasp an object more effectively than ever before, but once it has the object what happens next? We show that a mild relaxation of the task and workspace constraint…
User Experience of the CoSTAR System for Instruction of Collaborative Robots
Chris Paxton, Felix Jonathan, Andrew Hundt +2
How can we enable novice users to create effective task plans for collaborative robots? Must there be a tradeoff between generalizability and ease of use? To answer these questions…