Saved in:
Bibliographic Details
Main Authors: Gurses, Yigit, Buyukdemirci, Kaan, Yildiz, Yildiray
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2302.02179
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908101865635840
author Gurses, Yigit
Buyukdemirci, Kaan
Yildiz, Yildiray
author_facet Gurses, Yigit
Buyukdemirci, Kaan
Yildiz, Yildiray
contents Driving in dense traffic with human and autonomous drivers is a challenging task that requires high-level planning and reasoning. Human drivers can achieve this task comfortably, and there has been many efforts to model human driver strategies. These strategies can be used as inspirations for developing autonomous driving algorithms or to create high-fidelity simulators. Reinforcement learning is a common tool to model driver policies, but conventional training of these models can be computationally expensive and time-consuming. To address this issue, in this paper, we propose ``skill-based" hierarchical driving strategies, where motion primitives, i.e. skills, are designed and used as high-level actions. This reduces the training time for applications that require multiple models with varying behavior. Simulation results in a merging scenario demonstrate that the proposed approach yields driver models that achieve higher performance with less training compared to baseline reinforcement learning methods.
format Preprint
id arxiv_https___arxiv_org_abs_2302_02179
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Developing Driving Strategies Efficiently: A Skill-Based Hierarchical Reinforcement Learning Approach
Gurses, Yigit
Buyukdemirci, Kaan
Yildiz, Yildiray
Machine Learning
Artificial Intelligence
Robotics
Driving in dense traffic with human and autonomous drivers is a challenging task that requires high-level planning and reasoning. Human drivers can achieve this task comfortably, and there has been many efforts to model human driver strategies. These strategies can be used as inspirations for developing autonomous driving algorithms or to create high-fidelity simulators. Reinforcement learning is a common tool to model driver policies, but conventional training of these models can be computationally expensive and time-consuming. To address this issue, in this paper, we propose ``skill-based" hierarchical driving strategies, where motion primitives, i.e. skills, are designed and used as high-level actions. This reduces the training time for applications that require multiple models with varying behavior. Simulation results in a merging scenario demonstrate that the proposed approach yields driver models that achieve higher performance with less training compared to baseline reinforcement learning methods.
title Developing Driving Strategies Efficiently: A Skill-Based Hierarchical Reinforcement Learning Approach
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2302.02179