6G-Enabled Edge Computing for Real-Time Pedestrian Intent Analysis
| 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
The project, in collaboration with ASSA ABLOY, will develop an Edge AI solution for predicting pedestrian intent at smart doors, critical for energy efficiency and security in 6G networks. The goal is to implement a fast, decentralised AI model to reduce unnecessary door openings and save energy.
Expected effects and result
The main result is a validated prototype of the Edge AI system demonstrating real-time pedestrian intent analysis. This will lead to improved safety and a more energy-conscious generation of building access systems, strengthening Swedish research capacity in Edge Computing.
Planned approach and implementation
The project is implemented by developing, training, and evaluating AI models for human behaviour prediction using a large-scale video dataset. The model is deployed on an Edge device to ensure low latency, which is essential for this safety-critical application.