Environment Classification for Global Navigation Satellite Systems Using Attention-Based Recurrent Neural Networks

Liu, Haichun; Pei, Ling; Wang, Wei; Li, Lanzhen; Pan, Changchun; Li, Zeya

doi:10.1007/978-3-030-69873-7_5

Cited by 3 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The arctan function has also be tested instead of sigmoid but obtained inferior results. We also tried to fuse GPS and Galileo features as done in [12] but ended up with worse results. Because each constellation has its own characteristics it is better to keep their features independent.…”

Section: B Resultsmentioning

confidence: 99%

“…More recently [12] proposed a method based on a fusion of RNNs and Fully Convolutional Networks (FCN) to classify in real-time three road navigation contexts: urban canyon, trees and open sky. Note that tree class is a road bordered by trees.…”

Section: State Of the Artmentioning

confidence: 99%

“…3a). This problem is surprisingly not explained in the different papers that try to classify the context in real time [12] [13]. To resolve this matter we proposed to smooth the signal by using a filtering window on the last 10 samples (2s in our case) in which the mean and the variance are computed (6, 7) for each satellite (Fig.…”

Section: Features Of Interestmentioning

confidence: 99%

“…Firstly, only GPS data are used in the input vector and the standard Z-score normalization (13) is the only pre-processing (SVM-G). Then the Galileo constellation has been added into the input vector as shown in (12) (SVM-GGa). In a third time the normalization is improved by the use of the sigmoid function (14) in addition (SVM-GGaS).…”

Section: A Setting and Performance Metricsmentioning

confidence: 99%

See 3 more Smart Citations

GNSS-based environmental context detection for navigation

Feriol

Watanabe

Vivet

2022

2022 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Environmental context detection is a topic of interest for the navigation community since it enables to build a context-adaptive solution. Indeed if the type of environment is known it is then possible to choose the proper data processing algorithm or to select the sensors to be used to dynamically adapt the navigation solution design itself. This paper proposes to build a supervised machine learning model which can robustly classify multiple contexts such as urban canyons, urban, trees and open-sky areas using GNSS data only. A training and test database have been built with four datasets acquired at different times in order to prove the relevance of the solution. These datasets are made available to the community for research purpose. The choices of features and classifier are also discussed and compared to others papers. Our solution achieved an average 82.40% of classification accuracy.

show abstract

Section: B Resultsmentioning

confidence: 99%

Section: State Of the Artmentioning

confidence: 99%

Section: Features Of Interestmentioning

confidence: 99%

Section: A Setting and Performance Metricsmentioning

confidence: 99%

See 2 more Smart Citations

GNSS-based environmental context detection for navigation

Feriol

Watanabe

Vivet

2022

2022 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

show abstract

“…Existing research has shown that knowing the context of driving environment can help to adapt the vehicle control and plan strategies in a more predictive manner. Example applications include intelligent vehicle power management [3][4][5][6], adaptive vehicle control [7][8][9][10][11][12], adaptive positioning [13][14][15], adaptive parametrization of perception algorithm [16,17], and fleet management [18]. In this paper, we focus on the inference of the following five driving environments around vehicle's vicinity, i.e., a shopping zone, tourist zone, public station, motor service area, and security zone, which are mainly inspired by the use cases of the TransSec project [19].…”

Section: Introductionmentioning

confidence: 99%

Driving Environment Inference from POI of Navigation Map: Fuzzy Logic and Machine Learning Approaches

Li,

Metzner,

Schwieger

2023

Sensors

View full text Add to dashboard Cite

To adapt vehicle control and plan strategies in a predictive manner, it is usually desired to know the context of a driving environment. This paper aims at efficiently inferring the following five driving environments around vehicle’s vicinity: shopping zone, tourist zone, public station, motor service area, and security zone, whose existences are not necessarily mutually exclusive. To achieve that, we utilize the Point of Interest (POI) data from a navigation map as the semantic clue, and solve the inference task as a multilabel classification problem. Specifically, we first extract all relevant POI objects from a map, then transform these discrete POI objects into numerical POI features. Based on these POI features, we finally predict the occurrence of each driving environment via an inference engine. To calculate representative POI features, a statistical approach is introduced. To composite an inference engine, three inference systems are investigated: fuzzy inference system (FIS), support vector machine (SVM), and multilayer perceptron (MLP). In total, we implement 11 variants of inference engine following two inference strategies: independent and unified inference strategies, and conduct comprehensive evaluation on a manually collected dataset. The result shows that the proposed inference framework generalizes well on different inference systems, where the best overall F1 score 0.8699 is achieved by the MLP-based inference engine following the unified inference strategy, along with the fastest inference time of 0.0002 millisecond per sample. Hence, the generalization ability and efficiency of the proposed inference framework are proved.

show abstract