Skip to main content
EURAXESS

MSCA-COFUND-CLEAR-Doc-PhD Position#CD22-62: AI-based Energy-efficient Localisation on Embedded Devices with Multi-sensor Fusion

14/10/2022

Job Information

Organisation/Company
Université Gustave Eiffel
Department
AME-GEOLOC
Research Field
Computer science
Technology
Technology » Transport technology
Computer science » Digital systems
Mathematics
Engineering
Engineering » Systems engineering
Researcher Profile
First Stage Researcher (R1)
Country
France
Application Deadline
Type of Contract
Temporary
Job Status
Full-time
Hours Per Week
35
Is the job funded through the EU Research Framework Programme?
H2020 / Marie Skłodowska-Curie Actions COFUND
Marie Curie Grant Agreement Number
101034243
Is the Job related to staff position within a Research Infrastructure?
No

Offer Description

With the recent developments in hardware systems and wireless communication technologies, there is an increasing number of portable and wearable devices with wireless connection capabilities in our daily life. These connected devices contain embedded systems with specific algorithms performing different tasks. For example, smartwatches record daily activities and count steps; Internet-of-Things (IoT) tags can track items or pets; different wearable medical devices also exist to monitor health in real-time and to send alerts in urgent situations. However, these devices have limited battery capacity, limited bandwidth, and limited computational power to enable acceptable performances at low cost. Although much research work addresses Artificial Intelligence (AI)-based positioning algorithms in the current literature [1-2], very few investigates the energy consumption [3] and computation power of these AI models from a real-time implementation point of view. Today, the design of AI-based positioning algorithms in an energy-efficient way has become a crucial question.

The main objective of the PhD thesis is to propose energy-efficient, sample-efficient and hardware-efficient solutions to embed localization algorithms in wearable devices by introducing green AI techniques. The impact of energy consumption, as well as the computational cost, in the whole process chain of the AI-based localization algorithm will be studied and evaluated together with the localization performances.

The target application of this PhD thesis will be a multisensory fusion localization system with AI-based anomaly detection, which aims at providing more reliable positioning information for hazard prevention or emergency intervention. The first stage of the PhD thesis is to develop a baseline positioning algorithm that fuses data from several sensors. The sensors will be the classical ones embedded in smartphones such as GNSS, Inertial Measurement Unit and 5G signals. In the second stage, an AI-based anomaly detection algorithm especially for GNSS and 5G signals will be developed to improve the positioning accuracy. Pre-labeled (Line-of-Sight/Non-Line-of-Sight) GNSS data and 5G data already exist respectively in the GEOLOC laboratory and the Fraunhofer Institute for Integrated Circuits IIS. They will support the basic training database for AI. Transfer learning or meta-learning techniques will be used to adapt the AI model to the specific context of smart devices. During this second stage, the AI computational cost in terms of different sample rates as well as the model performance will be evaluated. The objective is to find the trade-off between the power consumption and the model performance for implementing the AI-based positioning algorithm with anomaly detection in real time. Possible AI model compression techniques, which are the expertise of the Fraunhofer Institute for Integrated Circuits IIS, will also be explored to improve the efficiency of the AI model while reducing energy consumption. Finally, the proposed complete scheme will be implemented into embedded devices and tested in both controlled and real conditions. By reducing the energy consumption of the AI-based connected devices and improving their reliability in case of hazard or emergency prevention, this PhD topic aims at contributing to the target challenge 3 of the CLEAR-doc program: “develop the digital city and make it a catalyst for social, environmental and economic performance” in the framework of the United Nation (UN)’s Sustainable Development Goals (SDG).

The PhD student will be co-supervised by researchers from the GEOLOC Laboratory of the University Gustave Eiffel in France and the Fraunhofer Institute for Integrated Circuits IIS in Germany. GEOLOC laboratory has expertise in AI-based multisensory (GNSS/MIMU) fusion positioning algorithms [4-5] and measurement anomaly detection [6]. GEOLOC possesses IMU-based positioning devices as well as reference positioning systems for vehicles and pedestrians. The Fraunhofer Institute for Integrated Circuits IIS has expertise in AI-based hybrid positioning and information fusion [7-8]. They have access to optical reference systems and 5G and Ultra-Wideband (UWB) positioning systems as well as different embedded devices. A specific measurement hall (1.400 m²) and an outdoor area (10.000 m²) can be used to collect reference data together with measurement data from multisensors. The PhD student will spend 18 months in each institution.

Required skills: signal processing, artificial intelligence, multisensory fusion positioning, state estimation, python, matlab

[1] Kone, Y., Zhu, N., Renaudin, V., & Ortiz, M. (2020). Machine learning-based zero-velocity detection for inertial pedestrian navigation. IEEE Sensors Journal, 20(20), 12343-12353.

[2] Feigl, T., Kram, S., Woller, P., Siddiqui, R. H., Philippsen, M., & Mutschler, C. (2019, September). A bidirectional LSTM for estimating dynamic human velocities from a single IMU. In 2019 International Conference on Indoor Positioning and Indoor Navigation (IPIN) (pp. 1-8). IEEE.

[3] A. Saylam, R. O. Cikmazel, N. Kelesoglu, M. Nakip and V. Rodoplu, ""Energy-Efficient Indoor Positioning for Mobile Internet of Things Based on Artificial Intelligence,"" 2021 Innovations in Intelligent Systems and Applications Conference (ASYU), 2021, pp. 1-6.

[4] Kone Y, Zhu N, Renaudin V. Zero velocity detection without motion pre-classification: Uniform ai model for all pedestrian motions (UMAM)[J]. IEEE Sensors Journal, 2021, 22(6): 5113-5121.

[5] Al Abiad N, Kone Y, Renaudin V, et al. Smartstep: A Robust STEP Detection Method Based on SMARTphone Inertial Signals Driven by Gait Learning[J]. IEEE Sensors Journal, 2022, 22(12): 12288-12297.

[6] Zhu, N., Betaille, D., Marais, J., & Berbineau, M. (2020). GNSS integrity monitoring schemes for terrestrial applications in harsh signal environments. IEEE Intelligent Transportation Systems Magazine, 12(3), 81-91.

[7] Stahlke, M., Kram, S., Mutschler, C., & Mahr, T. (2020, June). NLOS detection using UWB channel impulse responses and convolutional neural networks. In 2020 International Conference on Localization and GNSS (ICL-GNSS) (pp. 1-6). IEEE.

[8] Niitsoo, A., Edelhäußer, T., Eberlein, E., Hadaschik, N., & Mutschler, C. (2019). A deep learning approach to position estimation from channel impulse responses. Sensors, 19(5), 1064.

Requirements

Research Field
Computer science
Education Level
Bachelor Degree or equivalent
Research Field
Mathematics
Education Level
Bachelor Degree or equivalent
Research Field
Engineering
Education Level
Bachelor Degree or equivalent
Skills/Qualifications
  • At the time of the deadline, applicants must be in possession or finalizing their Master’s degree or equivalent/postgraduate degree.
  • At the time of recruitment, applicants must be in possession of their Master’s degree or equivalent/postgraduate degree which would formally entitle to embark on a doctorate.
Specific Requirements
  • Required skills: signal processing, artificial intelligence, multisensory fusion positioning, state estimation, python, matlab
Languages
FRENCH
Level
Basic
Languages
ENGLISH
Level
Excellent

Additional Information

Benefits
  • High-quality doctoral training rewarded by a PhD degree, delivered by Université Gustave Eiffel
  • Access to cutting-edge infrastructures for research & innovation.
  • Appointment for a period of 36 months based on a salary of 2 700 € (gross salary per month).
  • Job contract under the French labour legislation in force, respecting health and safety, and social security: 35 hours per week contract, 25 days of annual leave per year.
  • International mobility will be mandatory
  • An international environment supported by the adherence to the European Charter & Code.
  • Access to dedicated CLEAR-Doc trainings with a strong interdisciplinary focus, together with a Career development Plan.
Eligibility criteria

Applicants must fulfil the following eligibility criteria:

  • At the time of the deadline, applicants must be in possession or finalizing their Master’s degree or equivalent/postgraduate degree.
  • At the time of recruitment, applicants must be in possession of their Master’s degree or equivalent/postgraduate degree which would formally entitle to embark on a doctorate.
  • At the time of the deadline, applicants must be in the first four years (full-time equivalent research experience) of their research career (career breaks excluded) and not yet been awarded a doctoral degree. Career breaks refer to periods of time where the candidate was not active in research, regardless of his/her employment status (sick leave, maternity leave etc). Short stays such as holidays and/or compulsory national service are not taken into account.
  • At the time of the deadline, applicants must fulfil the transnational mobility rule: incoming applicants must not have resided or carried out their main activity (work, studies, etc.) in France for more than 12 months in the 3 previous years.

One application per call per year is allowed.

Applicants must be available full-time to start the programme on schedule (November 1st 2023).

Application rules are enforced by the French doctoral system which specifies a standard duration of 3 years for a full-time PhD together with the MSCA standards and the OTM-R European rules as follows.

Citizens of any nationality may apply to the programme.

There is no age limit.

Selection process

Please refer to the Guide for Applicants available on the CLEAR-Doc website: https://clear-doc.univ-gustave-eiffel.fr/how-to-apply/useful-documents/

Additional comments

The First step before applying is contacting the PhD supervisor. You will not be able to apply without an acceptation letter from the PhD supervisor.

International mobility planned: International mobility planned at Fraunhofer Institute for Integrated Circuits-IIS (Germany).

Please contact the PhD supervisor for any additional detail on job offer.

There are no restrictions concerning the age, gender or nationality of the candidates. Applicants with career breaks or variations in the chronological sequence of their career, with mobility experience or with interdisciplinary background or private sector experience are welcome to apply.

Support service is available during every step of the application process by email: clear-doc@univ-eiffel.fr

Website for additional job details

Work Location(s)

Number of offers available
1
Company/Institute
Université Gustave Eiffel
Country
France
City
Bouguenais
Postal Code
44340
Street
Allée des Ponts et Chaussées
Geofield

Contact

Website
E-Mail
ni.zhu@univ-eiffel.fr
christopher.mutschler@iis.fraunhofer.de