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.

AIKIDO - Generative AI-based Kitting with Integrated Deliberation

Reference number
Coordinator Högskolan Väst - Högskolan Väst Inst f ingenjörsvetenskap
Funding from Vinnova SEK 8 000 000
Project duration August 2025 - August 2028
Status Ongoing
Venture Advanced digitalization - Industrial needs-driven innovation
Call Advanced digitalization - Industrial innovation 2025

Purpose and goal

AIKIDO develops vision-based methods and VLMs to identify parts and select gripping points. AI-driven kinematic planning optimizes batch orders and ensures safe HRC through intelligent safety protocols. Flexible grippers eliminate the need for tool changes and handle varying parts by size and shape. Combined with natural language, these concepts enable intuitive automation and support circular manufacturing across industries.

Expected effects and result

1: An efficient and robust advanced vision-based method to identify parts, find a part gripping location and validate it with VLM. 2: Utveckla AI-planering for robot kinematics to optimally schedule incoming batch orders, with AI-based safety protocols to ensure safe HRC. 3: Enable seamless communication and natural language interaction between operators and robots during the automation process.

Planned approach and implementation

AIKIDO brings the future of manufacturing to life by combining AI vision, safe robot planning and natural language interaction. Through industrial test environments, we demonstrate how flexible, intelligent and human-friendly automation can streamline equipment manufacturing, reduce errors and increase efficiency. By connecting research and industry, AIKIDO empowers companies to adopt breakthrough solutions that make production safer, smarter and more sustainable.

External links

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

Last updated 1 September 2025

Reference number 2025-01009