6G-Enabled Cloud Reasoning and End-to-End VLAs for Autonomous Robots
| Reference number | |
| Coordinator | RISE Research Institutes of Sweden AB - RISE AB - Digitala System |
| Funding from Vinnova | SEK 99 946 |
| Project duration | February 2026 - September 2026 |
| Status | Ongoing |
| Venture | 6G - Competence supply |
| Call | 6G - Supervision of degree work |
Purpose and goal
This thesis explores the ultimate performance boundary of AI for autonomous robotic lawn mowers (Husqvarna). It focuses on a hybrid 6G architecture where the robot queries a large-scale cloud VLA (Vision-Language Agent) for complex scenarios. The goal is to validate this architecture and define future performance benchmarks.
Expected effects and result
The main contribution is a strategic innovation deliverable for Husqvarna. The result is a functional proof-of-concept of the 6G-enabled hybrid system, providing a "gold standard" performance benchmark. The effect ensures Swedish industry remains a global leader by demonstrating the transformative capabilities of cloud AI.
Planned approach and implementation
The project focuses on two architectures: a monolithic End-to-End VLA on the device and a 6G-hybrid architecture. Implementation involves designing the orchestration logic between the Edge (robot) and the Cloud VLA. The work will evaluate how 6G can enable near-infinite reasoning capacity for the robot.