Neural network assisted ultra-tightly coupled GPS/INS integration for seamless navigation

Jwo, Dah‐Jing; Chuang, Chih-Hsun; Yang, Juan; Lu, Yu-He

doi:10.1109/itst.2012.6425204

Cited by 4 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the Scaled Unscented Transformation (SUT) method was selected for the sigma point selection, which gave the ability to alter the spread of sigma points and control the higher order errors through some design parameters. An improved ultra-tightly GPS/INS integration approach is proposed in [19]. The method makes use of the neural network (NN) to improve the quality of the Doppler estimates from the Kalman filter.…”

Section: Figure 2 a Block Diagram Of Vector Tracking Systemsmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Ultra-Tight GPS/RISS Integrated System for Challenging Navigation Environments

2020

View full text Add to dashboard Cite

The Global Positioning System (GPS) provides an accurate navigation solution in the open sky. However, in some environments such as urban areas or in the presence of signal jamming, GPS signals cannot be easily tracked since they could be harshly attenuated or entirely blocked. This often requires the GPS receiver to go into a signal re-acquisition phase for the corresponding satellite. To avoid the intensive computations necessary for the signal re-lock in a GPS receiver, a robust signal-tracking mechanism that can hold and/or rapidly re-lock on the signals and keep track of their dynamics becomes a necessity. This paper augments a vector-based GPS signal tracking system with a Reduced Inertial Sensor System (RISS) to produce a new ultra-tight GPS/INS integrated system that enhances receivers’ tracking robustness and sensitivity in challenging navigation environments. The introduced system is simple, efficient, reliable, yet inexpensive. To challenge the proposed method with real jamming conditions, real experiment work was conducted inside the Anechoic Chamber room at the Royal Military College of Canada (RMC). The Spirent GSS6700 signal simulator was used to generate GPS signals, and an INS Simulator is used for simulating the inertial measurement unit (IMU) to generate the corresponding trajectory raw data. The NEAT jammer, by NovAtel, was used to generate real jamming signals. Results show a good performance of the proposed method under real signal jamming conditions.

show abstract

Section: Figure 2 a Block Diagram Of Vector Tracking Systemsmentioning

confidence: 99%

“…The bandwidth reduction, in turn, improves the anti-jamming performance of the receiver and, hence, increases the post correlated signal strength. In addition, due to lower bandwidths, the accuracy of the raw measurements is likewise increased [19].…”

Section: Ultra-tight Gps/ins Integration and Rissmentioning

confidence: 99%

An Efficient Ultra-Tight GPS/RISS Integrated System for Challenging Navigation Environments

2020

View full text Add to dashboard Cite

show abstract

“…Meanwhile, there is a small amount of research using AI in tightly-coupled and ultratightly-coupled multi-sensor integration. Examples of tightlycoupling are the integration of inertial sensor and GNSS [30] and visual sensors [33], while an example of ultra-tightlycoupling is that uses inertial sensors to aid GNSS receiver design [49]. Different from [20], the paper [49] applies AI to predict the corrections of the raw measurements (e.g., Doppler observations) instead of the corrections of the navigation states.…”

Section: Artificial-intelligence-enhanced Multi-sensor Information Fu...mentioning

confidence: 99%

“…Examples of tightlycoupling are the integration of inertial sensor and GNSS [30] and visual sensors [33], while an example of ultra-tightlycoupling is that uses inertial sensors to aid GNSS receiver design [49]. Different from [20], the paper [49] applies AI to predict the corrections of the raw measurements (e.g., Doppler observations) instead of the corrections of the navigation states. Regardless of the integration modes, most research ideas are to use AI to maintain system performance when the external measurement is not available.…”

Section: Artificial-intelligence-enhanced Multi-sensor Information Fu...mentioning

confidence: 99%

“…This relationship is key to achieve appropriate sensor selection and system performance prediction in advance. 8) The AI-based inertial-motion-tracking module can be used to assist other sensors, such as reducing the mismatch rates of visual odometry [33] and predicting the correction of GNSS measurements [49]. 9) The use of unsupervised AI methods can eliminate the need for labeled training data, which is essential for traditional methods but time-costly and labor-intensive.…”

Section: A Benefitsmentioning

confidence: 99%

See 1 more Smart Citation

Inertial Sensing Meets Artificial Intelligence: Opportunity or Challenge?

Li,

Chen,

Niu

et al. 2020

Preprint

View full text Add to dashboard Cite

The inertial navigation system (INS) has been widely used to provide self-contained and continuous motion estimation in intelligent transportation systems. Recently, the emergence of chip-level inertial sensors has expanded the relevant applications from positioning, navigation, and mobile mapping to locationbased services, unmanned systems, and transportation big data. Meanwhile, benefit from the emergence of big data and the improvement of algorithms and computing power, artificial intelligence (AI) has become a consensus tool that has been successfully applied in various fields. This article reviews the research on using AI technology to enhance inertial sensing from various aspects, including sensor design and selection, calibration and error modeling, navigation and motion-sensing algorithms, multi-sensor information fusion, system evaluation, and practical application. Based on the over 30 representative articles selected from the nearly 300 related publications, this article summarizes the state of the art, advantages, and challenges on each aspect. Finally, it summarizes nine advantages and nine challenges of AI-enhanced inertial sensing and then points out future research directions.

show abstract

Inertial Sensing Meets Machine Learning: Opportunity or Challenge?

Chen

Niu

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Neural network assisted ultra-tightly coupled GPS/INS integration for seamless navigation

Cited by 4 publications

References 12 publications

An Efficient Ultra-Tight GPS/RISS Integrated System for Challenging Navigation Environments

An Efficient Ultra-Tight GPS/RISS Integrated System for Challenging Navigation Environments

Inertial Sensing Meets Artificial Intelligence: Opportunity or Challenge?

Inertial Sensing Meets Machine Learning: Opportunity or Challenge?

Contact Info

Product

Resources

About