Doctorant PhD Thesis CIFRE "Sensor data fusion architectures (early, middle, late) to increase [...]

Company AMPERE SOFTWARE TECHNOLOGY Job Description

Thesis subject description

The introduction of advanced driver-assistance systems (ADAS) has considerably enhanced the driving experience by providing automation of driving tasks, like lane keeping assist, contextual cruise control, automated emergency braking, etc. Safety and driving comfort are at the center of these changes. The reliability of ADAS features strongly relies on the robustness of the perception system beneath it. Perception system fuses information from different sensors (e.g., front camera, front radar, side radars, sonar, …) in order to obtain a reliable description of the world environment.

There are plenty of multi-sensor fusion architectures proposed in the literature (in particular, late fusion, early fusion, mid-fusion, hybrid fusion). The main differences are the latent spaces in which data fusion is performed and the complexity of the sensor specific treatment, which inherently impacts both sensor fusion performances and complexity. The general tendency in the literature seems to spotlight deep raw-data fusion.

In this thesis, we would like to investigate the different approaches for sensor data fusion along with next generation of sensor data fusion with a focus on AD L2+ and L3 use cases. The main challenges will be to correlate a sensor fusion architecture with both a software and hardware/electronic architecture implementation and their constraints (memory, computational power, data flow, latencies) in order to meet AD performances and AEB critical uses cases (and in particular the most challenging use cases from NCAP 2029). The focus will be on quantifying the gain or necessity to have more complex sensor fusion algorithms to tackle specific AD uses cases. Concrete examples and demonstrations will be developed both in simulation (with real driving data) and in a prototype vehicle.

This thesis will rely on Ampere facilities and experience both in electronic/hardware/software vehicle architecture and perception system.

Your missions

A PhD thesis allows you to develop several skills to enable you to carry independent research and, at the same time, to develop the know-how on key technologies. You shall have the opportunity to formulate novel solutions whilst making the most of our prototype platforms and driving data.You will need to gain a strong understanding of sensor data fusion and principles of machine learning & deep learning from the autonomous drive perspective and gain critical thinking to formulate the problem, propose solutions, and test them.

Your profile

You should be completing or have Bac+5-level degree: an engineering diploma or a Master of Science in Engineering (Electrical Engineering, Signal Processing, Computer Science, Machine Learning, …). You are very much interested in perception systems and sensor data fusion along with self-learning algorithms (machine learning and deep learning). It is very important to be curious, willing to learn new techniques. You will have the opportunity to formulate your own ideas, to test them on Renault driving database or in Renault prototype vehicles. Strong technical background in signal processing, fundamentals of machine learning & deep learning, programming (C, Python) and scripting skills are required.

A working knowledge of the English language is required. You will have to interact with team members and several Renault divisions, at different levels.

Job Family Transverse Contract Duration 36 months

Renault Group is committed to creating an inclusive working environment and the conditions for each of us to bring their passion, perform to the full and grow, whilst being themselves.
We find strength in our diversity and we are engaged to ensure equal employment opportunities regardless of race, colour, ancestry, religion, gender, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, etc. If you have a disability or special need requiring layout of the workstation or work schedule, please let us know by completing this form.

In order to follow in real time the evolution of your applications and to stay in touch with us, we invite you to create a candidate account. This will take you no more than a minute and will also make it easier for you to apply in the future.

By submitting your CV or application, you authorise Renault Group to use and store information about you for the purposes of following up your application or future employment. This information will only be used by Renault Group companies as described in the Group privacy policy.

#J-18808-Ljbffr