Chun Kwang Tan

#NeurIPS #MyoChallenge submissions are heating up! A really nice solution and top-score from @NurmaMSU on the manipulation task!

MyoChallenge 22 paper is out 🔥 Have a look at the smart solutions 🧠 of last year's winners Lots of good ideas in it for this year's manipulation challenge😈 ➡️ proceedings.mlr.press/v220/caggiano2…

🔥Announcing new MyoSuite 2.0.0 Release🔥 Exciting progress -> MyoDex, SAR, deprl, reflex-controller #MyoSuite 2.0.0 contains everything to replicate them, open-source! New model 💪🦵 New manip.-objects Challenging terrains for locomotion Much more All of it just one update away!

Good news 📰 for the people going to #ISB23 in Fukuoka, Japan @GDurandau will present MyoSuite and the MyoChallenge 23 on Thuesday, Aug 1, at 16h40 Room 6. Go to him anytime if you have any questions about MyoSuite and the MyoChallenge 23 🔥

🔥Announcing🔥MyoChallenge 23 Towards Human-Level Dexterity and Agility @NeurIPS is open. 2 Tracks: ➡️Show human lvl dexterity with unknown objects on MyoArm ➡️Show human lvl agility with the MyoLeg 💰 (over $20K) + 🏅 More info + tuto+ how to guide ⇒ tinyurl.com/MyoCha23

I'm very excited to share that our latest work involves teaching quadrupedal robots lifelike agility by imitating real animals, enabling them to traverse diverse terrains and excel in high-intensity tasks like Chase Tag Game. #Robotics #ArtificialIntelligence

🔥MyoSuite 1.5 released🔥sites.google.com/view/myosuite Introducing 𝗠𝘆𝗼𝗟𝗲𝗴𝘀 (most requested feature) 🦵80 muscles, 20 degrees of freedom 💢Accurate muscle+contact+inertial dynamics ✅Locomotion baselines coming soon 👉1click-webdemo myohub.github.io/myosuite_demo

Exciting update from @MyoSuite! We've extended the Song & Geyer, 2015 reflex-based controller to work with #MyoLeg with 80 muscles! Find out more about it here: github.com/facebookresear… Song & Geyer, 2015: physoc.onlinelibrary.wiley.com/doi/full/10.11… Thanks to @Vikashplus @CaggianoVitt @SeungmoonS