Skip to main content

Job Offer

PhD

PhD: Positioning Integrity Monitoring for Connected Mobility in Multimodal Transport Context

Specialty of the thesis

Signal Processing, Computer Engineering, Navigation, Statistics

PhD supervisor

Valérie RENAUDIN (UGE/AME/GEOLOC)

PhD advisor

Ni ZHU (UGE/AME/GEOLOC)

Keywords

Integrity monitoring, multisensory fusion (GNSS/INS/Magnetometer/Barometer), positioning, protection level, artificial intelligence, mobility, vulnerable users

Context

The location-based interconnected devices are rapidly increasing nowadays, which has covered a variety of market segments. They are no longer limited to traditional mass-market applications for daily pedestrian navigation or entertainment, but has already extended to other reliability or security-critical applications. That is to say, for instance, some mobility information, such as travelers' trajectories, can help automate the household travel survey (Enquête Ménages Déplacement). Moreover, some recently emerged positioning applications are dedicated to vulnerable users (handicapped people, children, aged people, etc) for supporting their daily life or assisting health monitoring. For these kinds of applications, the information extracted from the estimated Position, Velocity and Time (PVT) can be used as a basis of decision-making of government macro-control (such as urban planning, transport line optimization, electronic voting) or launch the emergency service for vulnerable users. This brings benefits for the society thanks to their easy access and huge amount but at the same time, some concerns arise due to the problems caused by the no qualified positioning information. Therefore, knowing the certainty of the information provided by the positioning system is essential, which is the problematic targeted by the concept of positioning integrity.

Positioning integrity is a measure of trust, which can be placed in the correctness of the information supplied by the complete system. More concretely, on the one hand, it can detect and exclude faulty measurements and one the other hand, it can provide a positioning uncertainty indicator, i.e., Protection Level (PL). In the current literature, the discussions about positioning integrity monitoring issue are mostly limited to applications in mono-mode transport context, such as aircraft [1], terrestrial vehicles [2, 3] or Unmanned Aerial Vehicle (UAV) [4]. However, for the mass-market applications dedicated to travelers or vulnerable users, the mono-transport mode is far from enough since positioning information is required in different environments for different modes of transport. Few research works address the problematic of integrity monitoring in a multimodal context. Therefore, the objective of this thesis is to design an integrity monitoring scheme in multimodal transport context to meet the requirement of accuracy and reliability.

The first challenge to be solved in this thesis is to categorize the position-based applications and then define the specifications and tolerance on positioning accuracy and integrity risk for different categories of applications in multimodal transport context. This is because the design of the integrity monitoring algorithm depends strongly on the targeted applications. For example, the integrity risk and the tolerance on positioning errors are different between position-based entertainment applications and location-based guidance services for the blind people. Moreover, for different transport modes, the requirements for accuracy are also different. Once the specifications are defined, the second challenge is to study the measurement error characterizations and its propagation within a positioning filter with a hybrid system, including GNSS, INS, magnetometer and barometer. The GNSSsuffers mostly from the step error (or instantaneous error) due to multipath in urban canyon and other sensors such as INS are mainly contaminated by slowly growing error (or ramp error). They should be both taken into consideration to correctly detect and exclude the measurement faults as well as estimate a PL adaptive to different transport modes for different targeted users. The last challenge is to recognition of the localization context (i.e., the environments, the transport mode, the pedestrian movement nature), which is important for multimodal transport application. The positioning context can provide

complementary information either to limit the error growth or to help the global decision-making process, for example choosing the right system dynamic model.

A promising way to solve these challenges is to combine the traditional methods with the Artificial Intelligence (AI) techniques. In the past decades, AI is proved to be highly applicable for different disciplines and some recent research work on AI-aided positioning shows encouraging results such as GNSS LOS, NLOS and multipath signals classification, Human Activity Recognition (HAR) with multiple sensor signals. However, few research addresses the topic of AI-aided integrity monitoring but some preliminary discussions about this have appeared lately [5-6].

Job Description

The expected contribution of this thesis is mainly to design an integrity monitoring system in a multimodal transport context to meet the requirement of accuracy and reliability. Based on the existing research work [2, 7, 8], the candidate will be required to:

  • Review existing integrity monitoring methods for multisensory multimodal transport positioning system
  • For different transport modes in different environments, define the specifications and tolerance on positioning accuracy and integrity risk
  • Study the measurement error characteristic and its propagation (including GNSS measurements, INS, magnetometer, barometer measurements) from the measurement space to the position space in the positioning filter (such as Extended Kalman Filter);
  • Design a multisensory fusion system with AI-aided integrity monitoring module in a multimodal context which aims at mitigating measurement faults and providing a positioning uncertainty indicator. The hybrid-AI techniques will be addressed by combining traditional learning methods with the knowledge-based feature selection especially applied in localization context recognition as well as measurement fault detection
  • Set up and carry on experimentation with the existing equipment of GEOLOC laboratory to validate and evaluate the proposed integrity monitoring system.

[1] Kropp, Victoria. Advanced receiver autonomous integrity monitoring for aircraft guidance using GNSS. Diss. Universität der Bundeswehr München, 2018.

[2] N. ZHU, « GNSS propagation channel modeling in constrained environments: contribution to the improvement of the geolocation service quality », Thèse de doctorat, Université de Lille, 2018.

[3] Tran, Hieu Trung, and Letizia Lo Presti. "Kalman filter-based ARAIM algorithm for integrity monitoring in urban environment." ICT Express 5.1 (2019): 65-71.

[4] Maaref, Mahdi, and Zaher M. Kassas. "UAV Integrity Monitoring Measure Improvement using Terrestrial Signals of Opportunity." Proceedings of the Institute of Navigation (ION) GNSS+, September 16-20, 2019, Miami, FL, United States. (2019).

[5] Kim, Daehee, and Jeongho Cho. "Improvement of Anomalous Behavior Detection of GNSS Signal Based on TDNN for Augmentation Systems." Sensors 18.11 (2018): 3800.

[6] Gogliettino, Giovanni, Renna, Michele, Pisoni, Fabio, Di Grazia, Domenico, Pau, Danilo, "A Machine Learning Approach to GNSS Functional Safety," Proceedings of the 32nd International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2019), Miami, Florida, September 2019, pp. 1738-1752.

[7] Crespillo, O. Garcia, et al. "Innovation vs residual KF based GNSS/INS autonomous integrity monitoring in single fault scenario." Proceedings of the 30th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2017), Portland, Oregon. 2017.

[8] El-Mowafy, Ahmed, and Nobuaki Kubo. "Integrity monitoring of vehicle positioning in urban environment using RTK-GNSS, IMU and speedometer." Measurement Science and Technology 28.5 (2017): 055102

Required Skills

  • Engineering degree or Master's degree in: Signal Processing / Computer science / geomatic engineering / telecommunications / applied mathematics
  • Signal Processing
  • Applied mathematics
  • Multisensory fusion positioning
  • State estimation
  • The knowledge of machine learning will be an additional value
Contract TypePhD, 3 years full time (38h30/week) starting end of 2021 (flexible date)
LocationGEOLOC Laboratory, University Gustave Eiffel, Nantes, France
Deadline01/04/2021 23:50 - Europe/Brussels
ApplicationAttach all your materials: Your motivated application, CV, Diplomas, Note transcript by email to ni.zhu@univ-eiffel.fr et valerie.renaudin@univ-eiffel.fr

PostDoc

Engineer/postdoc in machine learning

Do you have a heart for the contribution of artificial intelligence in the construction of physical models, to address the challenges and needs of new mobility services? The inmob joint laboratory on the Nantes campus of the Gustave Eiffel University of France could be the next step in your career.

Context

Research at the Geoloc Laboratory of the Gustave Eiffel University focuses on the development of dynamic positioning methods and systems for travellers. It owns a wide range of skills in the design and programming of beaconless positioning and navigation algorithms with original testing facilities. The Okeenea Digital company is an innovative company from the Okeenea group, specialised for 26 years in the design and supply of accessibility solutions to improve mobility in situations of disability. These two organisations have joined forces in the joint laboratory inmob (disability mapping with INertial signal to facilitate MOBility) to improve the mobility of people with disabilities.

Our ambition is to design new approaches based on artificial intelligence to build physical models that describe the individual specificities of movement of people with disabilities and thus individualise the positioning approaches. This research will increase the performance of current geolocation technologies, which are still insufficient to assist a blind or hearing-impaired person throughout his or her route in complete safety without depending on a very dense network of beacons. To strengthen the labcom team and contribute to the work in artificial intelligence for improved mobility services, we are looking for a research engineer or postdoc, ideally with complementary skills in physics/mathematics and artificial intelligence.

Job Description

The successful candidate will be responsible for R&D actions in machine learning to design the models necessary for the calculation of displacement trace and improvement of the navigator in the broad sense. His/her main responsibilities include in particular:

  • The design of models to calculate the displacement vector of a person equipped with a mobile phone (inertial and GNSS satellite signals, etc.)
  • The design and maintenance of a database of signals collected by connected objects worn by people with disabilities
  • The transfer of scientific and technological bricks on an embedded system for real time
  • Participation in the steering and administration of the research programme
  • Co-supervision of the work of doctoral students and trainees
  • The publication of scientific articles

Required Skills

  • Engineering degree, Master 2 or PhD in: Signal Processing, Machine Learning, Statistics, Computer Science or any other comparable discipline
  • Strong competences in Statistics, Data Mining, Signal Processing
  • Strong programming skills in Python and TensorFlow (cpp)
  • Work experience in the use of machine learning applied to the field of physics/mathematics
  • Proven ability to integrate data on a large scale
  • Significant understanding of connected object technologies and programming under Android
  • Ability to effectively integrate research results into publications and intellectual property
  • Creativity and openness to innovation
  • Enthusiasm, responsibility and excellent collaboration skills
  • Passion for high quality data production
  • Strong oral and written skills in English
Contract Typ2 years full time (37h/week) starting mid 2021 (flexible date)
LocationGEOLOC Laboratory, University Gustave Eiffel, Nantes, France
Deadline31/01/2021 23:50 - Europe/Brussels
ApplicationAttach all your materials (Your motivated application, CV, Diplomas, List of publications and productions) in one PDF file emailed to frederic.le-bourhis@univ-eiffel.fr