Shuran Song

Task-dependent action frames can enhance robotic manipulation performance, with MoF outperforming traditional single-frame policies in both simulation and real-world applications.

A unified framework for understanding manipulation robustness could accelerate the development of robots that match human dexterity in uncertain environments.

Robots can now learn new tasks on-the-fly from just one demonstration, revolutionizing how we teach machines to manipulate their environments.

Adapting pretrained policies with just a modest multisensory dataset can enhance robot manipulation performance across diverse tasks without sacrificing prior knowledge.

This vine robot can autonomously navigate and manipulate in complex environments, overcoming traditional control limitations with a robust vision-based approach.

DF-ExpEnse boosts sample efficiency in robotic fine-tuning by intelligently balancing exploration and quality, outperforming traditional methods across diverse tasks.

Action-view augmentation can transform how robots adapt to unforeseen obstacles, boosting manipulation success rates significantly.

Simply feeding more history to visuomotor policies hurts performance; GMP solves this by learning when and what to remember, boosting success rates by 30% on memory-intensive robotic tasks.

Runners stick to their pace 60% better and enjoy the workout more when coached by a robot dog than when using an Apple Watch.

Scaling robot learning with human data isn't a simple "more is better" equation; alignment with robot learning objectives is key.

Turn your robot's clumsy pre-trained behaviors into expert-level skills with DICE-RL, a surprisingly stable and efficient RL fine-tuning method.