Robotics
2d ago
MIT and NYU Develop AI Platform to Enhance Robot Understanding of Human Commands
Nov 9, 2026
AI Summary
Researchers from MIT and New York University have created FLEX, an AI-assisted learning platform that enables robots to interpret natural language commands more effectively. This system allows robots to not only follow explicit instructions but also to infer broader meanings, improving their ability to navigate complex environments.
- FLEX is a new AI-assisted learning platform developed by researchers from MIT and New York University.
- The platform allows robots to understand and generalize from natural language commands, enhancing their motion-planning capabilities.
- The system incorporates a large language model (LLM) to help robots reason about potential hazards and make decisions based on inferred meanings.
- FLEX operates in three steps: Add, Generalize, and Mask, enabling robots to adapt to changing environments and user preferences.
- In simulations, the platform demonstrated its ability to follow commands while also reasoning about safety, such as avoiding fragile objects and electronics.
- The research aims to make robots more intuitive and user-friendly by reducing the need for users to specify every detail of their commands.
- The study was led by Andreea Bobu at MIT's CLEAR Lab, focusing on developing robots that can assist in household tasks through natural language interaction.
ai-assisted learningrobot reasoninginteractive robotshousehold robotsassistive technology