Michael Lutter

Robotics & AI Research Scientist @BostonDynamics 🤖🧠 .
Prev: @DeepMind, @NVIDIAAI, @ias_tudarmstadt & @TU_Muenchen

[Michael Lutter @_mlutter]

Video: https://t.co/Nz1jlKcXWF

Blog: https://t.co/QtwlxaouoW

(5/5)

[Michael Lutter @_mlutter]

How should we control multi-fingered robot hands? 🖐️🤖

With RL policies. Using policies trained in simulation, our new 13 DoF hand for Atlas can autonomously rotate a ball between its fingers, spin a drumstick, and thread a nut. 🧵 (1/5)

[Michael Lutter @_mlutter]

Our hand was designed exactly for this. The actuation and backdrivable transmission make it fast and accurate to simulate, which makes RL far more effective at training robust, dexterous policies. Being easy to simulate was a hardware requirement, not an afterthought. (4/5)

[Michael Lutter @_mlutter]

@chris_j_paxton Technically, there is a fourth 🤖 in the background

[Michael Lutter @_mlutter]

Video: https://t.co/Qre2filx2M (5/5)

[Michael Lutter @_mlutter]

Tricks that work in the lab don't work at the World Cup!
🧵(1/5)

[Michael Lutter @_mlutter]

Most people love talking about AI, but it's only part of what keeps the robot standing. The unglamorous stuff becomes critical when you don't get a second chance. The hardware, firmware, and communication have to work flawlessly when it counts at the World Cup! (4/5)

[Michael Lutter @_mlutter]

A few years ago we wondered whether the WAMs could juggle 5 balls. Turns out, they can! 🤹

The hardest part often never makes it into the paper. The system integration behind this is what's truly impressive.

Great work @KaiPloeger & @Jan_R_Peters !

[Kai Ploeger @KaiPloeger]

Learning five-ball juggling on the second attempt, with two Barrett WAMs. Most humans take years of practice.

#robotics #juggling

[Michael Lutter @_mlutter]

If you want to work with us and @_albertorod_ at @BostonDynamics, we are also hiring Research Scientists and Research Engineers

RL: https://t.co/hF54HcD5yy
BC: https://t.co/WnTzaaAf2W

[Michael Lutter @_mlutter]

In 2018, I didn’t recognize the importance of the original DeepMimic paper. At the time, humanoid robots were rare and domain randomization was still relatively new. Today, many demos and whole-body controllers are powered by DeepMimic-inspired methods. 🧵

[Michael Lutter @_mlutter]

More details are in our blog post: https://t.co/eDwdpcdVtT

[Michael Lutter @_mlutter]

If you also want to work with us and @_albertorod_ , we're also hiring Research Scientists and Research Engineers:
RL: https://t.co/hF54HcD5yy
BC: https://t.co/WnTzaaAf2W

[Michael Lutter @_mlutter]

Day one of ICRA 2026 done! 🤖

Already feels like the biggest robotics conference I've been to. The expo floor is packed with new anthropomorphic hands, half-humanoids and mini humanoids.

[Michael Lutter @_mlutter]

Everyone's talking about VLAs, the problems with teleoperation, using sim-to-real RL for dexterous manipulation, and whether tactile sensing is actually necessary.

If you're working on any of these, reach out. I'm at ICRA all week and happy to talk.