Summary of the project

This project aims to realize general-purpose robots that perform diverse non-routine tasks at human-level speed, addressing severe labor shortages. We fuse the recognition and decision-making capabilities of Vision-Language-Action (VLA) models with advanced force-control technologies based on bilateral control, so that robots adapt flexibly to on-site tasks through interactive feedback. We also develop bilateral control systems with a 15 Hz control bandwidth from the motor driver and gear levels, building a robot platform that is taught and adapts on site.

Milestone by year 2030

Using VLA models capable of interactive feedback and force control, we aim to perform more than ten types of non-routine tasks—such as manipulating objects on conveyors, transporting linens, harvesting fruit, and wiping and cleaning—in logistics, food manufacturing, nursing-care facilities, agriculture, retail, and other fields, with takt time, success rates, and safety comparable to junior-level workers.

R&D Items

• [1] Research and Development of Vision-Language-Action (VLA) Models
• [2] Research and Development of Low-Level Motion Generation Models
• [3] Research and Development of Control Systems and Hardware
• [4] Real-World Deployment of General-Purpose Humanoid Robots

Performers

PDF Download

• Summary of the project (442 KB)