RAI Institute | Juggling
Summary
RAI Institute showcases a robot juggling, demonstrating advances in real-time object manipulation and coordination.
Similar Articles
Zero-Shot Sim-to-Real Robot Learning: A Dexterous Manipulation Study on Reactive Catching
This paper introduces Domain-Randomized Instance Set (DRIS), a method that simultaneously represents multiple randomized instances to improve sim-to-real transfer for dexterous manipulation. It demonstrates zero-shot transfer on a challenging reactive catching task with a flat plate end-effector, requiring no real-world fine-tuning.
Figure AI 03 swapping turns
Figure AI unveils the Figure 03 humanoid robot, featuring enhanced capabilities for dynamic movements such as swapping turns.
Figure AI running a human vs machine contest [live]
Figure AI is hosting a live human vs machine contest, showcasing its humanoid robots competing directly against humans.
RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
RICE-PO is a critic-free policy optimization framework that turns retrieval interactions into localized credit signals for training reasoning agents, outperforming prompt-based and group-based RL baselines on BRIGHT and BEIR benchmarks.
Solving Rubik’s Cube with a robot hand
OpenAI developed a robot hand capable of solving a Rubik's Cube using a novel technique called Automatic Domain Randomization (ADR), which progressively increases simulation difficulty to enable effective transfer of learned behaviors from simulation to the real world.