JunLi R
@junli_r84995
Followers
94
Following
9
Media
1
Statuses
12
PHD Candidate in Robotics Learning at HKU MMLab
香港
Joined October 2023
Pushing the boundaries of humanoids with THOR: Towards Human-level whOle-body Reaction. BAAI THOR is coming soon. #Robotics #AI #WholeBodyControl
12
54
302
I agree. In our new open book, we call it "scientific intelligence." In the last chapter, at the very end, we have posed the question what is the difference between memorization (Bayesian) and understanding (deductive), difference between compression (distribution) and
@YiMaTweets The next wave of AI -- DARPA calls it 'The Third (and final) Wave of AI -- will be based on first principles of what makes human intelligence so special. It is Cognitive AI instead of Statistical.
7
28
218
VLAI Robotics Launches High-Dexterity Dual-Arm Robot Starting at ~$5,500 USD VLAI Robotics, utilizing the open-source design of Japan’s OpenArm team, has introduced a high-dexterity, low-cost bimanual robotic system. The product is priced from 39,900 RMB (approximately 5,500
5
31
182
Great to see more research that learns adaptation beyond simply mimicking reference trajectories. Efforts on this from two perspectives in our previous works: 1) ConsMimic: https://t.co/vdniGG2Uau (constrained) 2) Motion Prior Reimagined: https://t.co/O7E6O838L8 (hierarchical)
Excited to share SoftMimic -- a new approach for learning compliant humanoid policies that interact gently with the world.
3
13
85
💡 How can humanoids achieve autonomous, generalizable, and lifelike interactions with real-world objects? 🤖 Introducing PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System Paper: https://t.co/k7iykFXjn8 Website: https://t.co/eC3oQvsLKt
5
63
296
💡 How can humanoids learn adaptable skills from a single human motion? 🤖 Introducing AdaMimic: Towards Adaptable Humanoid Control via Adaptive Motion Tracking Paper: https://t.co/fJBxNPZKeF Website: https://t.co/nVPh3yZKrf
7
30
152
Grateful to Yuman Gao for sharing the codebase for flying ball interception using an onboard camera, adapted from his previous work
0
0
0
Thanks to my wonderful collaborators: @junfeng_long, @TaouHuang , @HuayiWang04, Zirui Wang, @Jia_Fei_Yu, Wentao Zhang, and supervision from: @Alex_wangjingbo, Prof Luo Ping, @pangjiangmiao.
1
1
0
⚽️ We create a humanoid goalkeeper ! 🥅One-stage RL training ⏰Fully autonomous & real-time 📷Alternative perception: MoCap ↔️ onboard camera 🔁 Generalizes to ball grabbing, squat & jump escapes website: https://t.co/yBFT5xmiMQ paper: https://t.co/prx9qaH3ej
8
66
263