There’s a paradox in robotics that says: what’s easy for humans is hard for robots, and vice versa. Complex calculations, for instance, are the domain of machines. Simple motor tasks like picking up an object, on the other hand, can stump a robot. That’s where our guest comes in. Jeff Mahler has spent his career working on improving the capabilities of robotic object manipulation. After completing his postdoctoral work at UC Berkeley, Mahler went on to co-found Ambi Robotics with Stephen McKinley, David Gealy, Matt Matl, and Professor Ken Goldberg, building AI-powered robots for warehouse operations. He talks to us about the state of robot assistants and how soon—if ever—we might expect a full robot revolution.
Further reading:
- TechCrunch article on the launch of Ambi Stack
- UC Berkeley News article on Berkeley’s latest breakthroughs in robot learning
- WIRED article covering Amazon’s new tactile-sensing warehouse robot, Vulcan.
- Mahler et al.’s 2019 Science Robotics paper, which introduces Dex-Net 4.0
- Watch Dex-Net 2.0 picking up objects
- Episode transcript
This episode was written and hosted by Nathalia Alcantara and produced by Coby McDonald.
Art by Michiko Toki and original music by Mogli Maureal. Additional music from Blue Dot Sessions.