We showed how to use Vision-language models like CLIP in conjunction to language models and object detectors to perform open-lanhuage navigation in a household (so "warm up my lunch" goes to the microwave.)
We showed how to use Vision-language models like CLIP in conjunction to language models and object detectors to perform open-lanhuage navigation in a household (so "warm up my lunch" goes to the microwave.)
Curious about the claims on that patent. Robotics is already hard enough, I'm sure it will become easier with people suing each other because "you copied my wheeled robot with an arm attached to it!".
If your robot doesn't have these specific design choices, plus some others, it's not in violation. * Have a unibody base * Have an arm that is raised and lowered along a trapezoidal rail by a belt-driven linear actuator * Have a fisheye camera mounted on the center pole
[1] https://patents.google.com/patent/US11230000B2/en?oq=11%2c23...
Anyway, a base that looks like a Roomba, with a pole and an arm attached to it doesn't strike me as novel.