Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

6G Multimodal AI for Robotic Lawn Mowers

Reference number
Coordinator RISE Research Institutes of Sweden AB - RISE AB - Digitala System
Funding from Vinnova SEK 99 750
Project duration January 2025 - October 2025
Status Completed
Venture 6G - Competence supply
Call 6G - Supervision of degree work

Important results from the project

The project developed an advanced multimodal AI framework for robotic lawn mowers. By integrating sound and IMU (motion) data, we significantly enhanced the robot´s ability to detect obstacles and navigate complex terrain without cameras. Validated on Husqvarna´s experimental robot, the solution demonstrated improved safety and operational efficiency. This confirms that AI-driven decision-making based on audio and motion sensors is a viable solution for resource-constrained edge devices.

Expected long term effects

This work contributes to the advancement of 6G-ready autonomous systems. The developed algorithms enable robots to operate with higher intelligence and energy efficiency. Long-term, this supports the transition towards distributed intelligence in IoT, allowing robots to interact dynamically with their environment. Furthermore, excluding cameras offers significant benefits regarding user privacy and reduced hardware costs for future smart service robots.

Approach and implementation

The project was conducted as a Master´s thesis hosted by RISE in Stockholm, in collaboration with Husqvarna and Örebro University. The work involved developing and training AI models using exclusively sound and IMU sensor data, which were then deployed on experimental hardware. Frequent validation cycles and supervision from 6G experts ensured the technology addressed real-world constraints such as latency and processing power.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 5 December 2025

Reference number 2024-04251