Israeli company Mentee Robotics has come out of stealth and unveiled MenteeBot, an humanoid robot prototype with sufficient dexterity for a wide spectrum of activities in both households and industrial warehouses. The company is led by chairman Prof. Amnon Shashua, founder of Mobileye and AI company AI21 Labs.
Shashua founded Mentee Robotics two years ago with CEO Prof. Lior Wolf, a former AI researcher at Meta, and Prof. Shai Shalev-Shwartz, a computer scientist and machine learning researcher.
MenteeBot is designed to undertake household chores like washing dishes, washing and cleaning and help businesses with warehouses in such tasks as lifting and carrying heavy objects, organizing and packing. The robot can carry up to 25 kilograms.
The company expects the first robots to come off the serial production line in the first quarter of 2025 and reports that to date it has raised just $17 million to date from the founders and Ahren Innovation Capital.
As part of the unveiling, no press conference was held or demonstration of the robot was given to journalists. However, the company has released short videos showing a humanoid robot performing tasks such as walking forward and backward, carrying a six-pack of mineral water, and placing fruit in a crate and carrying it several meters. From the clips, an image emerges of a robot that understands verbal command and can complete tasks including navigation, locomotion, scene understanding, object detection and localization, grasping and natural language understanding.
The robot learns and acquires skills through observation and feedback
The company says the MenteeBot prototype unveiled today integrates AI across all operational layers. Locomotion is based on a novel Simulator to Reality (Sim2Real) machine learning approach, wherein reinforcement learning occurs on a simulated version of the robot - thus utilizing unlimited data for training, followed by adaptation to the real world with minimal data requirements. The mapping of the environment is performed on the fly using NeRF-based algorithms (the latest neural network-based technologies for representing 3D scenes). These cognitive maps store semantic information, allowing the robot to query them to find items and places. The robot localizes itself in the 3D map and automatically plans dynamic paths that avoid obstacles.
Published by Globes, Israel business news - en.globes.co.il - on April 17, 2024.
© Copyright of Globes Publisher Itonut (1983) Ltd., 2024.