The Menteebot prototype, unveiled today, is a groundbreaking innovation that incorporates artificial intelligence at every level of its operation. Its unique approach uses machine learning from simulation to reality (Sim2Real), allowing the robot to be trained in a simulated version with unlimited data before adapting to the real world with minimal requirements. Real-time environment mapping is done using NeRF algorithms, creating cognitive maps for the robot to navigate and avoid obstacles.
The prototype demonstrates end-to-end action, from verbal commands to completing tasks such as navigation, understanding the environment, identifying objects, and grasping. Large transformation-based language models interpret commands and coordinate the robot’s movements for complex tasks. The robot is expected to go into serial production in 2025, equipped with camera-based sensing, electric motors for agility, and fully integrated artificial intelligence for complex thought processes.
Prof. Amnon Shashua, the company’s founder, sees a convergence of technologies in AI, computer vision, natural language understanding, and simulation-to-real-world methodologies. The robot’s AI capabilities will enable it to perform household tasks and learn new ones through imitation while moving freely in human environments. This marks the beginning of designing walking human robots for various purposes.
