After clicking “Watch Now” you will be prompted to login or join.
Gibson Environment
Roberto Martin-Martin, Stanford University | Silvio Savarese, Stanford University
GTC 2020
Gibson Environment is a simulation environment that supports rendering of high-fidelity images from 3D reconstructed buildings. This environment is fundamental to train visuo-motor navigation skills for robotic agents. These models learn to navigate within the simulated environment based on the visual information. We further developed our simulator to enable not only navigation, but also interactions with the simulated environment. This opens new avenues in robotics, enabling agents to be trained for new tasks in simulation while maintaining a simple sim2real transfer, thanks to the visual realism. We'll present our techniques to improve photo realism (computer vision and computer graphics) and examples of navigation and interactive agents trained in Gibson (robotics, machine learning, and reinforcement learning based on visual information).