RACE: Reinforced Cooperative Autonomous Vehicle Collision AvoidancE

04/02/2020
by   Yali Yuan, et al.
0

With the rapid development of autonomous driving, collision avoidance has attracted attention from both academia and industry. Many collision avoidance strategies have emerged in recent years, but the dynamic and complex nature of driving environment poses a challenge to develop robust collision avoidance algorithms. Therefore, in this paper, we propose a decentralized framework named RACE: Reinforced Cooperative Autonomous Vehicle Collision AvoidancE. Leveraging a hierarchical architecture we develop an algorithm named Co-DDPG to efficiently train autonomous vehicles. Through a security abiding channel, the autonomous vehicles distribute their driving policies. We use the relative distances obtained by the opponent sensors to build the VANET instead of locations, which ensures the vehicle's location privacy. With a leader-follower architecture and parameter distribution, RACE accelerates the learning of optimal policies and efficiently utilizes the remaining resources. We implement the RACE framework in the widely used TORCS simulator and conduct various experiments to measure the performance of RACE. Evaluations show that RACE quickly learns optimal driving policies and effectively avoids collisions. Moreover, RACE also scales smoothly with varying number of participating vehicles. We further compared RACE with existing autonomous driving systems and show that RACE outperforms them by experiencing 65 training process and exhibits improved performance under varying vehicle density.

READ FULL TEXT

page 1

page 7

research
04/21/2023

Multi-level decision framework collision avoidance algorithm in emergency scenarios

With the rapid development of autonomous driving, the attention of acade...
research
03/12/2023

Sequential Spatial Network for Collision Avoidance in Autonomous Driving

Several autonomous driving strategies have been applied to autonomous ve...
research
06/20/2023

Collision Avoidance Detour for Multi-Agent Trajectory Forecasting

We present our approach, Collision Avoidance Detour (CAD), which won the...
research
08/06/2017

Towards Social Autonomous Vehicles: Efficient Collision Avoidance Scheme Using Richardson's Arms Race Model

Background Road collisions and casualties pose a serious threat to commu...
research
08/10/2020

Safe and efficient collision avoidance control for autonomous vehicles

We study a novel principle for safe and efficient collision avoidance th...
research
12/02/2020

Driving-Policy Adaptive Safeguard for Autonomous Vehicles Using Reinforcement Learning

Safeguard functions such as those provided by advanced emergency braking...
research
09/12/2021

Autonomous Head-to-Head Racing in the Indy Autonomous Challenge Simulation Race

This paper describes Ariel Team's autonomous racing controller for the I...

Please sign up or login with your details

Forgot password? Click here to reset