Authors: Zengjie Zhang, Zhiyong Sun, Sofie Haesaer

Published on: April 13, 2024

Impact Score: 7.8

Arxiv code: Arxiv:2404.09037

Summary

• What is new: A novel approach to control autonomous vehicles by considering the intentions of other vehicles they interact with, using discrete-valued random variables.
• Why this is important: Managing autonomous vehicles’ interactions with other vehicles whose intentions are unknown, while ensuring safety.
• What the research proposes: A correct-by-design controller that leverages stochastic expansion and shrinking-horizon model predictive control to adjust an autonomous vehicle’s behavior based on the intentions of other vehicles.
• Results: The method significantly limits risk probabilities, demonstrating its effectiveness in ensuring safety in autonomous driving scenarios.

Technical Details

Technological frameworks used: Shrinking-horizon model predictive control

Models used: Stochastic control models

Data used: Discrete-valued random variables for opponent intentions

Potential Impact

Autonomous vehicle manufacturers, automated traffic management systems, mobility services

Want to implement this idea in a business?

We have generated a startup concept here: IntelliDrive.