C. Zhang's banner
C. Zhang's profile picture

C. Zhang

@ChongZzZhang • 7,663 subscribers

🤖 @ETH_AI_Center @leggedrobotics @the_sri_lab . prev @CMU_Robotics, Tsinghua ⚠️ Shitpost here. 📑 Read papers @RoboReading. ❌ Against killer robots

Shorts

following the discussion weeks ago, I asked codex to vibe a comparison for MPC vs RL for just table-top EE tracking, 1.6Mtok gone. It uses Pinocchio for MPC, and codes a cupy-based simulator, tuned RL to achieve better tracking accuracy (actually both errors are too small)

following the discussion weeks ago, I asked codex to vibe a comparison for MPC vs RL for just table-top EE tracking, 1.6Mtok gone. It uses Pinocchio for MPC, and codes a cupy-based simulator, tuned RL to achieve better tracking accuracy (actually both errors are too small)

37,475 просмотров

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

With Junzhe (JJ) He Kehan Wen Robotic Systems Lab , we push humanoid mobility to next frontier. Achieved by a generalist contact planner + a generalist tracker + a generalized neural mapping, warmstarted from few human data. Website: Promo Video 👇
1:57
ChongZzZhang's profile picture

With Junzhe (JJ) He Kehan Wen Robotic Systems Lab , we push humanoid mobility to next frontier. Achieved by a generalist contact planner + a generalist tracker + a generalized neural mapping, warmstarted from few human data. Website: Promo Video 👇

C. Zhang

46,849 просмотров • 16 дней назад

The most robotics-friendly deformable sim solver, FBA, is dropping soon. Kudos to my amazing collaborators Prana Labs In our old work we used its "baby" version to sim2real cloth folding within minutes/hours.
1:26
ChongZzZhang's profile picture

The most robotics-friendly deformable sim solver, FBA, is dropping soon. Kudos to my amazing collaborators Prana Labs In our old work we used its "baby" version to sim2real cloth folding within minutes/hours.

C. Zhang

19,370 просмотров • 12 дней назад

New paper release: Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids Paper Videos We study how to do learning and sim2real for 3d traversal, such as monkey bars and overhanging obstacles.
2:48
ChongZzZhang's profile picture

New paper release: Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids Paper Videos We study how to do learning and sim2real for 3d traversal, such as monkey bars and overhanging obstacles.

C. Zhang

83,433 просмотров • 2 месяцев назад

releasing AME2: Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding In this work, we discuss how to achieve a combination of generalization and agility in legged locomotion, and propose a general solution.
2:33
ChongZzZhang's profile picture

releasing AME2: Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding In this work, we discuss how to achieve a combination of generalization and agility in legged locomotion, and propose a general solution.

C. Zhang

103,925 просмотров • 9 месяцев назад

dropping something tomorrow?
0:29
ChongZzZhang's profile picture

dropping something tomorrow?

C. Zhang

59,677 просмотров • 9 месяцев назад

GPT6 as policy, directly outputting ee-frame actions from two rgbd and instructions. Amazing perf. Should be ~100% succ rate given inf token and time for retrials. 1) "find a wooden box (can be obscured) and put it on the yellow sign." 2) "stack the wooden boxes on each other"
0:26
ChongZzZhang's profile picture

GPT6 as policy, directly outputting ee-frame actions from two rgbd and instructions. Amazing perf. Should be ~100% succ rate given inf token and time for retrials. 1) "find a wooden box (can be obscured) and put it on the yellow sign." 2) "stack the wooden boxes on each other"

C. Zhang

12,021 просмотров • 1 месяц назад

Nice one! We also worked on cloth folding sim2real last year with a custom solver for massive parallelization. The results might look less decent but it is teleop-free. Release soon!
1:07
ChongZzZhang's profile picture

Nice one! We also worked on cloth folding sim2real last year with a custom solver for massive parallelization. The results might look less decent but it is teleop-free. Release soon!

C. Zhang

18,070 просмотров • 7 месяцев назад

Learning Time-Optimal and Speed-Adjustable Tactile In-Hand Manipulation by DLR on humanoids 2024
0:20
ChongZzZhang's profile picture

Learning Time-Optimal and Speed-Adjustable Tactile In-Hand Manipulation by DLR on humanoids 2024

C. Zhang

21,319 просмотров • 1 год назад

Больше нет контента для загрузки