Search papers, labs, and topics across Lattice.
University of Toronto, Vector Institute for Artificial Intelligence, King's College Circle
4
0
4
DEHP dramatically boosts the success rates of high-precision robotic tasks by dynamically adjusting execution horizons based on task complexity.
Torque Adaptation Module enables zero-shot robust manipulation across different robots without the need for extensive retraining or domain randomization.
No more performance cliffs: SMAC lets you smoothly fine-tune offline RL policies online by aligning policy gradients with Q-function gradients.
Simply propagating uncertainty from perception modules to motion planning can significantly improve the generalization capabilities of autonomous vehicles in complex, closed-loop scenarios.
