PlumX Metrics
Embed PlumX Metrics

Enhanced Berth Mapping and Clothoid Trajectory Prediction Aided Intelligent Underground Localization

Applied Sciences (Switzerland), ISSN: 2076-3417, Vol: 14, Issue: 12
2024
  • 1
    Citations
  • 0
    Usage
  • 0
    Captures
  • 2
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

  • Citations
    1
  • Mentions
    2
    • Blog Mentions
      1
      • 1
    • News Mentions
      1
      • 1

Most Recent Blog

Applied Sciences, Vol. 14, Pages 5032: Enhanced Berth Mapping and Clothoid Trajectory Prediction Aided Intelligent Underground Localization

Applied Sciences, Vol. 14, Pages 5032: Enhanced Berth Mapping and Clothoid Trajectory Prediction Aided Intelligent Underground Localization Applied Sciences doi: 10.3390/app14125032 Authors: Fei Li Jialiang

Most Recent News

National University of Defense Technology Researcher Describes Findings in Applied Sciences (Enhanced Berth Mapping and Clothoid Trajectory Prediction Aided Intelligent Underground Localization)

2024 JUN 25 (NewsRx) -- By a News Reporter-Staff News Editor at NewsRx Science Daily -- Investigators discuss new findings in applied sciences. According to

Article Description

In response to the widespread absence of global navigation satellite system (GNSS) signals in underground parking scenes, we propose a multimodal localization method that integrates enhanced berth mapping with Clothoid trajectory prediction, enabling high-precision localization for intelligent vehicles in underground parking environments. This method began by constructing a lightweight map based on the key berths. The map consisted of a series of discrete nodes, each encompassing three elements: holistic and local scene features extracted from an around-view image, and the global pose of the mapping vehicle calculated using the positions of the key berth’s corner points. An adaptive localization strategy was employed during the localization phase based on the trajectory prediction result. A progressive localization strategy, relying on multi-scale feature matching, was applied to the nodes within the map coverage range. Additionally, a compensation localization strategy that combined odometry with the prior pose was utilized for the nodes outside the map coverage range. The experiments conducted in two typical underground parking scenes demonstrated that the proposed method achieved a trajectory prediction accuracy of 40 cm, a nearest map search accuracy exceeding 92%, and a metric localization accuracy meeting the 30 cm standard. These results indicate that the proposed approach satisfies the high-precision, robust, real-time localization requirements for intelligent vehicles in underground parking scenes, while effectively reducing the map memory requirements.

Bibliographic Details

Fei Li; Yuelin Yuan; Zhaozheng Hu; Jialiang Chen; Xiaohui Liu

MDPI AG

Materials Science; Physics and Astronomy; Engineering; Chemical Engineering; Computer Science

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know