Philipp Wu
@philippswu
Followers
2K
Following
2K
Media
44
Statuses
358
PhD @Berkeley_AI advised by @pabbeel. Previously @MetaAI @covariantai.
Berkeley, CA
Joined November 2018
šExcited to share a fun little hardware project weāve been working on. GELLO is an intuitive and low cost teleoperation device for robot arms that costs less than $300. We've seen the importance of data quality in imitation learning. Our goal is to make this more accessible .1/n
26
106
688
RT @albert_h_li: Super excited about š„judoš„, our new open-source sampling-based MPC toolbox!. š„ļøTry in under 30s:. pip install judo-rai.judā¦.
0
9
0
RT @kevin_zakka: Weāre super thrilled to have received the Outstanding Demo Paper Award for MuJoCo Playground at RSS 2025!.Huge thanks to eā¦.
0
21
0
Wow! A must see at RSS! One simple sim2real framework to power all these robots by @kevin_zakka.
Demo starting in 10 minutes, come witness the magic of open-source sim2real!
0
0
17
Active vision for bimanual manipulation!.
Your bimanual manipulators might need a Robot Neck š¤š¦. Introducing Vision in Action: Learning Active Perception from Human Demonstrations. ViA learns task-specific, active perceptual strategiesāsuch as searching, tracking, and focusingādirectly from human demos, enabling robust
0
2
9
RT @zhang_yunzhi: (1/n) Time to unify your favorite visual generative models, VLMs, and simulators for controllable visual generationāIntroā¦.
0
64
0
For more details about GELLO and scalable low cost teleoperation, see the original work! .
šExcited to share a fun little hardware project weāve been working on. GELLO is an intuitive and low cost teleoperation device for robot arms that costs less than $300. We've seen the importance of data quality in imitation learning. Our goal is to make this more accessible .1/n
0
0
3
See the updated code here: Great work from Andreas GaĆner and the Franka Robotics team!.
github.com
Contribute to wuphilipp/gello_software development by creating an account on GitHub.
1
0
3
Very excited to to have ROS integration for GELLO, built by Franka Robotics! Robot teleoperation data is becoming more and more important for large scale Robot foundation model training. Great to see larger adaption for low cost, scalable teleoperation!.
š Franka Research 3 now integrates with GELLO ā a ROS 2-based framework for real-time teleoperation!.Gripper control (Franka Hand & Robotiq) for HRI, prototyping & more. Get started: GitHub: #FrankaFR3 #ROS2
2
10
70
RT @g_k_swamy: Say ahoy to šš°šøš»š¾šāµ: a new paradigm of *learning to search* from demonstrations, enabling test-time reasoning about how to rā¦.
0
72
0
RT @younggyoseo: Excited to present FastTD3: a simple, fast, and capable off-policy RL algorithm for humanoid control -- with an open-sourcā¦.
0
113
0
RT @letian_fu: Tired of teleoperating your robots?.We built a way to scale robot datasets without teleop, dynamic simulation, or even robotā¦.
0
78
0
RT @ChungMinKim: Excited to introduce PyRoki ("Python Robot Kinematics"): easier IK, trajectory optimization, motion retargeting. with anā¦.
0
164
0
RT @smithlaura1028: last but not least, I'm excited to let people know that I'm joining PI as a full-time RS once I graduate this May!.
0
2
0
RT @smithlaura1028: My goal throughout my PhD has been to take robots out of the lab and into the real world. It was so special to be a parā¦.
0
56
0
RT @kevin_zakka: Picking 1 project outside my comfort zone and getting cracked collaborators who can compensate for my knowledge gaps has bā¦.
0
1
0
RT @danijarh: Excited to share that DreamerV3 has been published in Nature!. Dreamer solves control tasks by imagining the future outcomesā¦.
0
150
0
RT @Boyiliee: 4K Resolution! Vision is a critical part in building powerful multimodal foundation models. Super excited about this work.
0
2
0
RT @pabbeel: My knee-jerk reaction was that sim-2-real wouldn't work watching the learned policy in sim (on left), but actually it does!.
0
14
0