Saved in:
Bibliographic Details
Main Authors: Li, Xibo, Patel, Shruti, Büskens, Christof
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.01216
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914854387843072
author Li, Xibo
Patel, Shruti
Büskens, Christof
author_facet Li, Xibo
Patel, Shruti
Büskens, Christof
contents Deep reinforcement learning (DRL) allows a system to interact with its environment and take actions by training an efficient policy that maximizes self-defined rewards. In autonomous driving, it can be used as a strategy for high-level decision making, whereas low-level algorithms such as the hybrid A* path planning have proven their ability to solve the local trajectory planning problem. In this work, we combine these two methods where the DRL makes high-level decisions such as lane change commands. After obtaining the lane change command, the hybrid A* planner is able to generate a collision-free trajectory to be executed by a model predictive controller (MPC). In addition, the DRL algorithm is able to keep the lane change command consistent within a chosen time-period. Traffic rules are implemented using linear temporal logic (LTL), which is then utilized as a reward function in DRL. Furthermore, we validate the proposed method on a real system to demonstrate its feasibility from simulation to implementation on real hardware.
format Preprint
id arxiv_https___arxiv_org_abs_2407_01216
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Let Hybrid A* Path Planner Obey Traffic Rules: A Deep Reinforcement Learning-Based Planning Framework
Li, Xibo
Patel, Shruti
Büskens, Christof
Robotics
Artificial Intelligence
Deep reinforcement learning (DRL) allows a system to interact with its environment and take actions by training an efficient policy that maximizes self-defined rewards. In autonomous driving, it can be used as a strategy for high-level decision making, whereas low-level algorithms such as the hybrid A* path planning have proven their ability to solve the local trajectory planning problem. In this work, we combine these two methods where the DRL makes high-level decisions such as lane change commands. After obtaining the lane change command, the hybrid A* planner is able to generate a collision-free trajectory to be executed by a model predictive controller (MPC). In addition, the DRL algorithm is able to keep the lane change command consistent within a chosen time-period. Traffic rules are implemented using linear temporal logic (LTL), which is then utilized as a reward function in DRL. Furthermore, we validate the proposed method on a real system to demonstrate its feasibility from simulation to implementation on real hardware.
title Let Hybrid A* Path Planner Obey Traffic Rules: A Deep Reinforcement Learning-Based Planning Framework
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2407.01216