Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

Superloop is a network automation framework, used to manage networks at scale. It's a framework that auto remediates based on templates and maintains config standardization across device platforms. As well, it comes equipped with various toolsets that assist Network Engineers with their day to day tasks.

Code for Generalization Guarantees for (Multi-Modal) Imitation Learning

[RA-L 2024] Quasistatic robotic planar pushing with single-point contact using force feedback.

Visualization of mapping from the unit velocity sphere to rotation centers in the slider frame.