AthenaZero can juggle barehanded using onboard vision feedback. By using multi-fingered hands, it can transition seamlessly between a wide range of juggling patterns.
We’ll be presenting robotic research that includes contact-rich bimanual manipulation and policy learning, an open source package for sample-based Model Predictive Control (MPC), how to...
How AnyTask and ExpertGen Bridge the Sim-to-Real Gap
Redesigning how we collect bespoke data for manipulation tasks.
Exploy, an open-source library that packages environment logic and neural network policies into a single, self-contained computational graph, was created for rapid iteration and deployment onto physical robotic...
Research teams at the RAI Institute had several papers accepted to IROS 2026, covering topics from closed- loop visuomotor policies and frameworks for self-supervised learning on outdoor LiDAR...
Presented at RSS 2026, Q2RL (Q-Estimation and Q-Gating from Behavior Cloning for Reinforcement Learning) is a method that avoids catastrophic forgetting when transitioning from offline behavior cloning to...
Get a closer look at the Koala gripper! The co-designed system pairs a handheld data collector and a corresponding robotic gripper, allowing a single, unassisted...
How does a robot learn to recognize an object it’s never encountered? In this case, a demo can be worth a thousand words.
AthenaZero can juggle barehanded using onboard vision feedback. By using multi-fingered hands, it can transition seamlessly between a wide range of juggling patterns.
