Reverse parking a car-like mobile robot with deep reinforcement learning and preview control

Eduardo Bejar, Antonio Moran

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

This paper presents a control technique for reverse parking car-like vehicles based on deep reinforcement learning and preview control. The deep deterministic policy gradient (DDPG) algorithm is used for training a neurocontroller using a reward function defined in terms of the desired final state of the system. A preview control approach is employed to leverage knowledge of a known a priori reference input to generate a predictive control signal coupled into the neurocontroller output. Simulation results are presented to validate the proposed method. Moreover, these results show that incorporating a preview control signal improves the parking time.

Original languageEnglish
Title of host publication2019 IEEE 9th Annual Computing and Communication Workshop and Conference, CCWC 2019
EditorsSatyajit Chakrabarti, Himadri Nath Saha
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages377-383
Number of pages7
ISBN (Electronic)9781728105543
DOIs
StatePublished - 12 Mar 2019
Event9th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2019 - Las Vegas, United States
Duration: 7 Jan 20199 Jan 2019

Publication series

Name2019 IEEE 9th Annual Computing and Communication Workshop and Conference, CCWC 2019

Conference

Conference9th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2019
Country/TerritoryUnited States
CityLas Vegas
Period7/01/199/01/19

Keywords

  • control systems
  • deep learning
  • reinforcement learning
  • robotics
  • self-driving vehicles

Fingerprint

Dive into the research topics of 'Reverse parking a car-like mobile robot with deep reinforcement learning and preview control'. Together they form a unique fingerprint.

Cite this