A collision-free motion planning method by integrating complexity-reduction SLAM and learning-based artificial force design

L. Liu, R. Guo, J. Wu

Research output: Contribution to journalArticleAcademicpeer-review

1 Downloads (Pure)

Abstract

In order to generally deal with the rotor-type UAV's collision-free motion planning problem in the unknown static environment, we propose a non-holonomic solution via integration of the KF-based SLAM technique and governing force design. The traditional SLAM is modified and reduced as a low-complexity form according to the fact that too early detected obstacle information can be regarded as nearly frozen after sufficient correction. The artificial force terms are designed in a intuitive and smart way, through employment of the wall-following rule and lessons from historical and current experience, which are taught by the bat's predation process. Further, they are converted to the real-time thrust vector expectation. Multiple simulation tests in both continuous and discrete scenes indicate that: (1) using slight sacrifice on the state estimate covariance can exchange pronounced reduction on structural complexity of the complete SLAM in return; (2) the LBAFD can not only mitigate limitations on the path oscillation, no passage between closely spaced obstacles and goal unreachability, but also lead to a high flying and exploration efficiency; (3) the integrated method demonstrates a relatively stable performance under different parameter settings and is even unconcerned to the surrounding characteristics.

Original languageEnglish
Pages (from-to)132-149
Number of pages18
JournalRobotics and Autonomous Systems
Volume100
Issue numberFebruari 2018
DOIs
Publication statusPublished - 1 Feb 2018

Fingerprint

Simultaneous Localization and Mapping
Motion Planning
Unmanned aerial vehicles (UAV)
Motion planning
Ion exchange
Collision
Rotors
Nonholonomic
Rotor
Low Complexity
Intuitive
Oscillation
Sufficient
Real-time
Unknown
Path
Term
Estimate
Demonstrate
Design

Keywords

  • Artificial force
  • Collision-free planning
  • Complexity reduction
  • Learning strategy
  • SLAM
  • Wall-following rule

Cite this

@article{45f3e5971166400386781ebd775f37a4,
title = "A collision-free motion planning method by integrating complexity-reduction SLAM and learning-based artificial force design",
abstract = "In order to generally deal with the rotor-type UAV's collision-free motion planning problem in the unknown static environment, we propose a non-holonomic solution via integration of the KF-based SLAM technique and governing force design. The traditional SLAM is modified and reduced as a low-complexity form according to the fact that too early detected obstacle information can be regarded as nearly frozen after sufficient correction. The artificial force terms are designed in a intuitive and smart way, through employment of the wall-following rule and lessons from historical and current experience, which are taught by the bat's predation process. Further, they are converted to the real-time thrust vector expectation. Multiple simulation tests in both continuous and discrete scenes indicate that: (1) using slight sacrifice on the state estimate covariance can exchange pronounced reduction on structural complexity of the complete SLAM in return; (2) the LBAFD can not only mitigate limitations on the path oscillation, no passage between closely spaced obstacles and goal unreachability, but also lead to a high flying and exploration efficiency; (3) the integrated method demonstrates a relatively stable performance under different parameter settings and is even unconcerned to the surrounding characteristics.",
keywords = "Artificial force, Collision-free planning, Complexity reduction, Learning strategy, SLAM, Wall-following rule",
author = "L. Liu and R. Guo and J. Wu",
year = "2018",
month = "2",
day = "1",
doi = "10.1016/j.robot.2017.10.017",
language = "English",
volume = "100",
pages = "132--149",
journal = "Robotics and Autonomous Systems",
issn = "0921-8890",
publisher = "Elsevier",
number = "Februari 2018",

}

A collision-free motion planning method by integrating complexity-reduction SLAM and learning-based artificial force design. / Liu, L.; Guo, R.; Wu, J.

In: Robotics and Autonomous Systems, Vol. 100, No. Februari 2018, 01.02.2018, p. 132-149.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A collision-free motion planning method by integrating complexity-reduction SLAM and learning-based artificial force design

AU - Liu, L.

AU - Guo, R.

AU - Wu, J.

PY - 2018/2/1

Y1 - 2018/2/1

N2 - In order to generally deal with the rotor-type UAV's collision-free motion planning problem in the unknown static environment, we propose a non-holonomic solution via integration of the KF-based SLAM technique and governing force design. The traditional SLAM is modified and reduced as a low-complexity form according to the fact that too early detected obstacle information can be regarded as nearly frozen after sufficient correction. The artificial force terms are designed in a intuitive and smart way, through employment of the wall-following rule and lessons from historical and current experience, which are taught by the bat's predation process. Further, they are converted to the real-time thrust vector expectation. Multiple simulation tests in both continuous and discrete scenes indicate that: (1) using slight sacrifice on the state estimate covariance can exchange pronounced reduction on structural complexity of the complete SLAM in return; (2) the LBAFD can not only mitigate limitations on the path oscillation, no passage between closely spaced obstacles and goal unreachability, but also lead to a high flying and exploration efficiency; (3) the integrated method demonstrates a relatively stable performance under different parameter settings and is even unconcerned to the surrounding characteristics.

AB - In order to generally deal with the rotor-type UAV's collision-free motion planning problem in the unknown static environment, we propose a non-holonomic solution via integration of the KF-based SLAM technique and governing force design. The traditional SLAM is modified and reduced as a low-complexity form according to the fact that too early detected obstacle information can be regarded as nearly frozen after sufficient correction. The artificial force terms are designed in a intuitive and smart way, through employment of the wall-following rule and lessons from historical and current experience, which are taught by the bat's predation process. Further, they are converted to the real-time thrust vector expectation. Multiple simulation tests in both continuous and discrete scenes indicate that: (1) using slight sacrifice on the state estimate covariance can exchange pronounced reduction on structural complexity of the complete SLAM in return; (2) the LBAFD can not only mitigate limitations on the path oscillation, no passage between closely spaced obstacles and goal unreachability, but also lead to a high flying and exploration efficiency; (3) the integrated method demonstrates a relatively stable performance under different parameter settings and is even unconcerned to the surrounding characteristics.

KW - Artificial force

KW - Collision-free planning

KW - Complexity reduction

KW - Learning strategy

KW - SLAM

KW - Wall-following rule

UR - http://www.scopus.com/inward/record.url?scp=85041373105&partnerID=8YFLogxK

U2 - 10.1016/j.robot.2017.10.017

DO - 10.1016/j.robot.2017.10.017

M3 - Article

AN - SCOPUS:85041373105

VL - 100

SP - 132

EP - 149

JO - Robotics and Autonomous Systems

JF - Robotics and Autonomous Systems

SN - 0921-8890

IS - Februari 2018

ER -