Agent-based Learning for Driving Policy Learning in Connected and Autonomous Vehicles

09/14/2017
by   Xiongzhao Wang, et al.
0

Due to the complexity of the natural world, a programmer cannot foresee all possible situations a connected and autonomous vehicle (CAV) will face during its operation, and hence, CAVs will need to learn to make decisions autonomously. Due to the sensing of its surroundings and information exchanged with other vehicles and road infrastructure a CAV will have access to large amounts of useful data. This paper investigates a data driven driving policy learning framework through an agent based learning. A reinforcement learning framework is presented in the paper, which simulates the self-evolution of a CAV over its lifetime. The results indicated that overtime the CAVs are able to learn useful policies to avoid crashes and achieve its objectives in more efficient ways. Vehicle to vehicle communication in particular, enables additional useful information to be acquired by CAVs, which in turn enables CAVs to learn driving policies more efficiently. The simulation results indicate that while a CAV can learn to make autonomous decision V2V communication of information improves this capability. The future work will investigate complex driving policies such as roundabout negotiations, cooperative learning between CAVs and deep reinforcement learning to traverse larger state spaces.

READ FULL TEXT
research
09/14/2017

An Agent-based Model for Driving Policy Learning in Connected and Autonomous Vehicles

Due to the complexity of the natural world, a programmer cannot foresee ...
research
09/14/2017

Agent-based Modelling Framework for Driving Policy Learning in Connected and Autonomous Vehicles

Due to the complexity of the natural world, a programmer cannot foresee ...
research
09/07/2020

Driving Tasks Transfer in Deep Reinforcement Learning for Decision-making of Autonomous Vehicles

Knowledge transfer is a promising concept to achieve real-time decision-...
research
11/14/2016

An Evaluation of Information Sharing Parking Guidance Policies Using a Bayesian Approach

Real-time parking occupancy information is critical for a parking manage...
research
11/23/2021

Learning Interactive Driving Policies via Data-driven Simulation

Data-driven simulators promise high data-efficiency for driving policy l...
research
08/03/2022

Reinforcement Learning for Joint V2I Network Selection and Autonomous Driving Policies

Vehicle-to-Infrastructure (V2I) communication is becoming critical for t...
research
10/30/2019

A Distributed Model-Free Algorithm for Multi-hop Ride-sharing using Deep Reinforcement Learning

The growth of autonomous vehicles, ridesharing systems, and self driving...

Please sign up or login with your details

Forgot password? Click here to reset