Kevin Zakka
@kevin_zakka
Followers
17K
Following
9K
Media
327
Statuses
3K
phding @Berkeley_AI
Berkeley, CA
Joined January 2016
It was a joy bringing Jason’s signature spin-kick to life on the @UnitreeRobotics G1. We trained it in mjlab with the BeyondMimic recipe but had issues on hardware last night (the IMU gyro was saturating). One more sim-tuning pass and we nailed it today. With @qiayuanliao and
Implementing motion imitation methods involves lots of nuisances. Not many codebases get all the details right. So, we're excited to release MimicKit! https://t.co/7enUVUkc3h A framework with high quality implementations of our methods: DeepMimic, AMP, ASE, ADD, and more to come!
25
93
653
No better time to learn about that #AI thing everyone's talking about... 📢 I'm recruiting PhD students in Computer Science or Information Science @Cornell_Bowers! If you're interested, apply to either department (yes, either program!) and list me as a potential advisor!
15
94
476
Ever wanted to simulate an entire house in MuJoCo or a very cluttered kitchen? Well now you can with the newly introduced sleeping islands: groups of stationary bodies that drop out of the physics pipeline until disturbed. Check out Yuval's amazing video and documentation 👇
MuJoCo now supports sleeping islands! https://t.co/LWqZ0dRGQn
https://t.co/EThtiDRm6C
4
2
65
just cooked up a new sprinter policy, do we attempt sim2real?
62
27
630
Didn’t go max speed for safety and space reasons but pretty happy with the result!
0
0
10
I tried this setup with Talos, I only changed a few things and it already looks really good!!
Coming to mjlab today! This is vanilla RL, no motion imitation/AMP. Natural gaits emerge from minimal rewards: velocity tracking, upright torso, speed-adaptive joint regularization, and contact quality (foot clearance, slip, soft landings). No reference trajectories or gait
3
11
105
Merged to main! For mjlab users, happy hacking :) https://t.co/u4G9iYqivy
github.com
Fix velocity task.
2
1
22
Didn’t go max speed for safety and space reasons but pretty happy with the result!
Coming to mjlab today! This is vanilla RL, no motion imitation/AMP. Natural gaits emerge from minimal rewards: velocity tracking, upright torso, speed-adaptive joint regularization, and contact quality (foot clearance, slip, soft landings). No reference trajectories or gait
4
18
186
I spend so much time in MuJoCo I made a Halloween edition 🎃👻
10
8
196
An almost identical reward setup works for the quadruped (turned off 1 reward). We get a beautiful symmetric trot gait without explicitly optimizing for it.
2
2
30
Coming to mjlab today! This is vanilla RL, no motion imitation/AMP. Natural gaits emerge from minimal rewards: velocity tracking, upright torso, speed-adaptive joint regularization, and contact quality (foot clearance, slip, soft landings). No reference trajectories or gait
20
51
453
How can we create a single navigation policy that works for different robots in diverse environments AND can reach navigation goals with high precision? Happy to share our new paper, "VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable
4
40
119
1
1
25
Super happy and honored to be a 2025 Google PhD Fellow! Thank you @Googleorg for believing in my research. I'm looking forward to making humanoid robots more capable and trustworthy partners 🤗
🎉 We're excited to announce the 2025 Google PhD Fellows! @GoogleOrg is providing over $10 million to support 255 PhD students across 35 countries, fostering the next generation of research talent to strengthen the global scientific landscape. Read more: https://t.co/0Pvuv6hsgP
35
4
196
If you're at #ICCV2025, swing by our poster today! We'll show how you can directly fine-tune an image generator with a VLM's language modeling loss. 📍 https://t.co/bu6WrGtVrF 🔗 https://t.co/67P9uxWS1y cc @jongranskog @holynski_ @trevordarrell
1
5
44
very excited about the upgrade GaussGym provides for environments for training locomotion capabilities
Simulation drives robotics progress, but how do we close the reality gap? Introducing GaussGym: an open-source framework for learning locomotion from pixels with ultra-fast parallelized photorealistic rendering across >4,000 iPhone, GrandTour, ARKit, and Veo scenes! Thread 🧵
1
12
133
Lovely new paper from @gabe_mrgl that uses mink ( https://t.co/JbDSaXOKgM) to pre-compute compliant responses to external wrenches and trains a policy to match them with DeepMimic style RL.
Excited to share SoftMimic -- a new approach for learning compliant humanoid policies that interact gently with the world.
2
4
79
Simulation drives robotics progress, but how do we close the reality gap? Introducing GaussGym: an open-source framework for learning locomotion from pixels with ultra-fast parallelized photorealistic rendering across >4,000 iPhone, GrandTour, ARKit, and Veo scenes! Thread 🧵
11
63
324
@brenthyi and I are at #IROS2025 to present PyRoki 🫶 Find us either: - tomorrow (tues 10:30am) in room 102C, or - anytime during the conference!
Excited to introduce PyRoki ("Python Robot Kinematics"): easier IK, trajectory optimization, motion retargeting... with an open-source toolkit on both CPU and GPU
1
3
67
Wow Harrison taught me Python and now he’s using mjlab 😅
exceptionally easy install and demo at least. Didn't realize viz ran via browser immediately makes it easy to visualize training progress from a personal computer while processing occurs on a server/workhorse machine true test will be trying this on custom problem and robot
5
17
299