Safe Deep Reinforcement Learning for Adaptive Cruise Control by Imposing State-Specific Safe Sets

2021 ◽  
Author(s):  
Mathis Brosowsky ◽  
Florian Keck ◽  
Jakob Ketterer ◽  
Simon Isele ◽  
Daniel Slieter ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Adaptive Cruise Control ◽  
Cruise Control

scholarly journals End-to-End Vision-Based Adaptive Cruise Control (ACC) Using Deep Reinforcement Learning

2020 ◽  
Author(s):  
Zhensong Wei ◽  
Yu Jiang ◽  
Xishun Liao ◽  
Xuewei Qi ◽  
Ziran Wang ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Adaptive Cruise Control ◽  
Cruise Control ◽  
End To End

scholarly journals Increasing the Safety of Adaptive Cruise Control Using Physics-Guided Reinforcement Learning

Energies ◽  
2021 ◽  
Vol 14 (22) ◽  
pp. 7572
Author(s):  
Sorin Liviu Jurj ◽  
Dominik Grundt ◽  
Tino Werner ◽  
Philipp Borchers ◽  
Karina Rothemann ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Autonomous Vehicles ◽  
Adaptive Cruise Control ◽  
Use Case ◽  
Cruise Control ◽  
Fleet Size ◽  
Physical Knowledge ◽  
Novel Approach ◽  
Longitudinal Distance ◽  
The Ideal

This paper presents a novel approach for improving the safety of vehicles equipped with Adaptive Cruise Control (ACC) by making use of Machine Learning (ML) and physical knowledge. More exactly, we train a Soft Actor-Critic (SAC) Reinforcement Learning (RL) algorithm that makes use of physical knowledge such as the jam-avoiding distance in order to automatically adjust the ideal longitudinal distance between the ego- and leading-vehicle, resulting in a safer solution. In our use case, the experimental results indicate that the physics-guided (PG) RL approach is better at avoiding collisions at any selected deceleration level and any fleet size when compared to a pure RL approach, proving that a physics-informed ML approach is more reliable when developing safe and efficient Artificial Intelligence (AI) components in autonomous vehicles (AVs).

Sign in / Sign up

Export Citation Format

Share Document