Ken Goldberg
6,970 posts
Artist and Engineering Prof @UCBerkeley, Co-Founder @AmbiRobotics & @JacobiRobotics. Interests: robots, rockets, redwoods, rebels.
- I get asked a lot: why stay in academia, all the excitement in AI is happening in industry with massive compute. And I am seeing some profs leaving academia, but also seeing lots of researchers in industry looking to go back to academia, especially those who don’t work on LLMs.
- That’s a massive overstatement. Please avoid overhyping to reduce the resulting backlash.Replying to @adcock_brettJohns Hopkins researchers trained surgical robots through video-based imitation learning to match human surgeon skill levels Their system enables faster robot training and could reduce medical errors, moving closer to autonomous surgical procedures
- And EECS @UCBerkeley just voted to drop the GRE from use in grad admissions. Proud of these steps toward diversity.UC system officially drops SAT, ACT scores from use in admissions and scholarships abc7.com/education/uc-s…
- The earth has experienced 5 mass extinctions where life was sustained under the oceans. Isn’t that a better bet than the moon or Mars if we one day need to take refuge?
- This is an excellent robotics survey paper contrasting deep learning “implicit” models (data driven) with the long history of “explicit” models (Good Old Fashioned Engineering) and calling for methods that integrate both: @BekrisKostas arxiv.org/abs/2410.12172
- Very impressive! "Humanoids Will Soon Replace Most Human Workers: True or False?" I'm organizing a debate with @UnitreeRobotics CEO and 5 other experts @IROS2025 on Wed, 22 Oct in Hangzhou: iros25.org/DebatesUnitree G1 Kungfu Kid V6.0 A year and a half as a trainee — I'll keep working hard! Hope to earn more of your love🥰
00:00 - Locomotion is definitely improving, but don’t confuse that with dexterity. None of these examples suggest progress in robot manipulation. Progress will come, but let’s be careful not to raise unrealistic expectations.It’s happening. Humanoid robots are walking, running, falling and getting back up. They’re becoming smarter, faster, and autonomous. 8 wild examples: 1. Unitree G1 jogging like a human
- Best robot grasping demo of the year!SpaceX continues to do some of the coolest shit on the planet
- Deep Learning Can Significantly Accelerate Grasp-Optimized Motion Planning. Results can reduce computation time for a pick-and-place task from 29 seconds to 80 milliseconds. Science Robotics @AAAS bit.ly/AUTOLab-papers…
- Phew! Humans slightly ahead (but not for long!)Humanity's move 78 by @Ken_Goldberg
00:00 - 300+ Bay Area roboticists gathering now for the first time since the Pandemic #BARS2021 Bars-2021.GitHub.io @AmbiRobotics















