Rui Yan
@Hi_Im_RuiYan
Followers
55
Following
21
Media
1
Statuses
14
M.S. in ECE @UCSD | ML&DS, Robotics
San Diego, CA
Joined December 2024
🚀 Meet ACE-F — a next-gen teleop system merging human and robot precision. Foldable, portable, cross-platform — it enables 6-DoF haptic control for force-aware manipulation. 🦾 See our demo & talk at the Robot Hardware-Aware Intelligence workshop this Wed @RoboticsSciSys!
4
19
49
Ever want to enjoy all the privileged information in sim while seamlessly transferring to the real world? How can we correct policy mistakes after deployment? 👉Introducing GSWorld, a real2sim2real photo-realistic simulator with interaction physics with fully open-sourced code.
6
64
273
How can we leverage diverse human videos to improve robot manipulation? Excited to introduce EgoVLA — a Vision-Language-Action model trained on egocentric human videos by explicitly modeling wrist & hand motion. We build a shared action space between humans and robots, enabling
6
73
491
AMO live demo at #RSS2025 ! 👉 https://t.co/VKfGesu7ZA
Meet 𝐀𝐌𝐎 — our universal whole‑body controller that unleashes the 𝐟𝐮𝐥𝐥 kinematic workspace of humanoid robots to the physical world. AMO is a single policy trained with RL + Hybrid Mocap & Trajectory‑Opt. Accepted to #RSS2025. Try our open models & more 👉
0
8
70
@RoboticsSciSys Co-led by @JiajianFu & @ShiqiYang_17 with Lars Paulsen, @xuxin_cheng, @xiaolonw
#RSS2025
0
0
2
🗣️ Talk: 10:00–10:30 AM 🤖 Demo: 10:25–11:00 AM 📍 Location: EEB 248 We’ll be showing ACE-F, our foldable force-aware teleoperation system — come try it out!
1
0
2
🤖✨ Stop tuning and start learning! What if your robot's hardware could adapt like its control policy? Introducing our latest breakthrough: Co-Design of Soft Grippers with Neural Physics. Now, soft robots don’t just learn how to grasp—they learn what to become to grasp better.
For years, I’ve been tuning parameters for robot designs and controllers on specific tasks. Now we can automate this on dataset-scale. Introducing Co-Design of Soft Gripper with Neural Physics - a soft gripper trained in simulation to deform while handling load.
0
4
16
A behind-the-scenes video on how teleoperation is done. Whole-body manipulation with only a VisionPro.
Meet 𝐀𝐌𝐎 — our universal whole‑body controller that unleashes the 𝐟𝐮𝐥𝐥 kinematic workspace of humanoid robots to the physical world. AMO is a single policy trained with RL + Hybrid Mocap & Trajectory‑Opt. Accepted to #RSS2025. Try our open models & more 👉
9
40
269
Diverse training data leads to a more robust humanoid manipulation policy, but collecting robot demonstrations is slow. Introducing our latest work, Humanoid Policy ~ Human Policy. We advocate human data as a scalable data source for co-training egocentric manipulation policy.⬇️
8
54
247
Introducing Vega: 🤖 @DexmateAI's newest robot that makes complex manipulation tasks simple. ✨ A step closer to intelligence and automation. 🚀 🎥 Watch now: https://t.co/Eg5AI8vVHY
#Robotics #AI #Automation
27
56
242
Very cool!
Can robots leverage their entire body to sense and interact with their environment, rather than just relying on a centralized camera and end-effector? Introducing RoboPanoptes, a robot system that achieves whole-body dexterity through whole-body vision. https://t.co/encmRFhxM0
0
1
7