Looking fwd to playing w this @GoogleDeepMind https://
developers.googleblog.com/en/building-th
e-next-generation-of-physical-agents-with-gemini-robotics-er-15/
…
@ken_goldberg
-
Ken Goldberg Excited About Google DeepMind Robotics Technology
By
–
-
Humans maintain slight lead in competition
By
–
Phew! Humans slightly ahead (but not for long!) https://t.co/nZdMXHBkQK
— Ken Goldberg (@Ken_Goldberg) 30 septembre 2025Phew! Humans slightly ahead (but not for long!)
-
Render Simulation Subset Matches Quasi-Static Manipulation
By
–
“…turns out the ‘render’ subset of simulation is well-matched to the ‘quasi-static’ subset of manipulation.”
-
Impressive Live Demonstration of Shirt Folding Robot
By
–
Just watched this fold shirts IRL for 15 mins. *very* impressive.
-
CoRL 2025 Data Curation Workshop Recording Now Available
By
–
Thx Chris! #CoRL2025 Workshop on Data Curation recording is now online https://
sites.google.com/stanford.edu/c
orldata25/home
… -
Unsupervised Learning of Hand-Eye Foveation Shows Great Results
By
–
Great results on learning hand-eye foveation without supervision! https://t.co/SZ9yHGGnq6
— Ken Goldberg (@Ken_Goldberg) 22 septembre 2025Great results on learning hand-eye foveation without supervision!
-
Closing the Robot Data Gap Discussion at NYU
By
–
Looking fwd to discussing how to close the massive “Robot Data Gap” tomorrow at 11am @nyuniversity
: https://
cs.nyu.edu/dynamic/about/
news/colloquium/1381/
… -
Ken Goldberg discusses new projects at The New School tonight
By
–
Looking fwd to talking about new projects tonight at 6pm (not 5:30 as shown) @TheNewSchool in NY https://
event.newschool.edu/unfamiliarinte
lligence
… -
Sim2Real Gap Challenges in Robotic Manipulation and Digital Cousins
By
–
Great summary! I also really like @DrJimFan
’s ideas about digital cousins. The challenge is the sim2real gap: it is surmountable for flying and locomotion but still an open problem for manipulation due in part to the nuances of dynamics, friction, and deformation. -
Generalist VLA Models and Specialist Models for Data Collection
By
–
I agree. Generalist VLA models can be much more versatile—given enough data. I believe specialist models can be useful for collecting this data.