The improved 3D vision of the four-legged robot allows it to navigate difficult terrains
Researchers at the University of California San Diego developed a model to train four-legged robotics to see in 3D. This advancement allowed a robot autonomously to cross difficult terrain, including stairs, rocky grounds and gaps-filled paths.
Researchers will present their research at the 2023 Conference on Computer Vision and Pattern Recognition, which will be held from June 18-22 in Vancouver, Canada.
By providing the robot with a 3D understanding of its environment, it can be used in more complex environments.
Source:
https://techxplore.com/news/2023-06-four-legged-robot-traverses-tricky-terrains.html