Onboard Sensors-Based Self-Localization for Autonomous Vehicle With Hierarchical Map

Xia, Chao; Shen, Yanqing; Yang, Yuedong; Deng, Xiaodong; Chen, Shitao; Xin, Jingmin; Zheng, Nanning

doi:10.1109/tcyb.2022.3155724

Cited by 8 publications

(3 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, before conducting the experiments on retrieving the nearest map nodes, it was essential to determine a reasonable value for K through experimentation. In this paper, Group 1 from each dataset was selected for experimentation, and an optimal value for K was chosen within the threshold range [2,8]. The experimental results are presented in Table 4.…”

Section: Nearest Map Node Search Resultsmentioning

confidence: 99%

“…Satellite-based localization, reliant on global navigation satellite system (GNSSs), encounters difficulties in satellite-denied areas like underground parking scenes [3]. The literature categorizes non-GNSS vehicle localization into wireless-based [4][5][6], LiDAR-based [7][8][9], and visionbased methods [10,11]. However, wireless-based methods suffer from unstable signal transmission and the costly deployment of access points.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Berth Mapping and Clothoid Trajectory Prediction Aided Intelligent Underground Localization

Li,

Chen,

Yuan

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

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.

show abstract

Section: Nearest Map Node Search Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhanced Berth Mapping and Clothoid Trajectory Prediction Aided Intelligent Underground Localization

Li,

Chen,

Yuan

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…A combination of frames and point-cloud for mapping is proposed on a low-power ARM and FPGA platform. This approach improves performance through global map encoding, LiDAR localization, and multisensor fusion [340]. Experiment on public datasets such as Apollo shows reduced latency and power consumption compared to other acceleration methods, making it suitable for large-scale urban scenes.…”

Section: B Hd Mapmentioning

confidence: 99%

A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services

Katare

Perino

Nurmi

et al. 2023

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

Autonomous driving services depends on active sensing from modules such as camera, LiDAR, radar, and communication units. Traditionally, these modules process the sensed data on high-performance computing units inside the vehicle, which can deploy intelligent algorithms and AI models. The sensors mentioned above can produce large volumes of data, potentially reaching up to 20 Terabytes. This data size is influenced by factors such as the duration of driving, the data rate, and the sensor specifications. Consequently, this substantial amount of data can lead to significant power consumption on the vehicle. Similarly, a substantial amount of data will be exchanged between infrastructure sensors and vehicles for collaborative vehicle applications or fully connected autonomous vehicles. This communication process generates an additional surge of energy consumption. Although the autonomous vehicle domain has seen advancements in sensory technologies, wireless communication, computing and AI/ML algorithms, the challenge still exists in how to apply and integrate these technology innovations to achieve energy efficiency. This survey reviews and compares the connected vehicular applications, vehicular communications, approximation and Edge AI techniques. The focus is on energy efficiency by covering newly proposed approximation and enabling frameworks. To the best of our knowledge, this survey is the first to review the latest approximate Edge AI frameworks and publicly available datasets in energy-efficient autonomous driving. The insights from this survey can benefit the collaborative driving service development on low-power and memory-constrained systems and the energy optimization of autonomous vehicles.

show abstract

OCR-RTPS: an OCR-based real-time positioning system for the valet parking

Wu¹,

Chen²,

Wang³

et al. 2023

Appl Intell

View full text Add to dashboard Cite

Onboard Sensors-Based Self-Localization for Autonomous Vehicle With Hierarchical Map

Cited by 8 publications

References 55 publications

Enhanced Berth Mapping and Clothoid Trajectory Prediction Aided Intelligent Underground Localization

Enhanced Berth Mapping and Clothoid Trajectory Prediction Aided Intelligent Underground Localization

A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services

OCR-RTPS: an OCR-based real-time positioning system for the valet parking

Contact Info

Product

Resources

About