Internship : Open Research & Development internship position available at Inria GRA on Advanced Perception and Control for Autonomous Vehicles
Inria
Montbonnot-Saint-Martin, 38330
Internship : Open Research & Development internship position available at Inria GRA on Advanced Perception and Control for Autonomous Vehicles
Le descriptif de l’offre ci-dessous est en Anglais
Type de contrat : Stage
Contrat renouvelable : Oui
Niveau de diplôme exigé : Bac + 5 ou équivalent
Fonction : Stagiaire de la recherche
A propos du centre ou de la direction fonctionnelle
The Inria Grenoble – Rhône-Alpes research center groups together almost 600 people in 22 research teams and 7 research support departments.
Staff is present on three campuses in Grenoble, in close collaboration with other research and higher education institutions (Université Grenoble Alpes, CNRS, CEA, INRAE, …), but also with key economic players in the area.
Inria Grenoble – Rhône-Alpes is active in the fields of high-performance computing, verification and embedded systems, modeling of the environment at multiple levels, and data science and artificial intelligence. The center is a top-level scientific institute with an extensive network of international collaborations in Europe and the rest of the world.
Contexte et atouts du poste
The Inria research team Chroma is involved in several academic and industrial projects in the field of Autonomous Vehicles. The proposed R&D work has to be performed in the scope of a multi-annual project of the French IRT Nanoelec, in cooperation with the CEA and several industrial companies such as Renault or Toyota. The main objective is to develop, to experimentally validate and to demonstrate the capabilities of an Embedded Perception and Decision-making system in the context of Mobile Robotics and Autonomous Vehicles applications. Several well published and patented results have already been obtained in the scope of this project. Exploitation licenses of the current version of the software CMCDOT have already been sold to industrial companies, see illustration video at https://hal.inria.fr/medihal-01963296v1
Mission confiée
A Research & Development intern position is available at Inria Grenoble Rhône-Alpes, potentially leading to a R&D engineer or PhD position, in the scope of the above-mentioned project. The current objective of the project is to further develop and expand our embedded perception and navigation system for autonomous mobile vehicles, with an emphasis on real world experiments performed using an automated Renault Zoé vehicle and some other industrial mobile robots. Different evolutions are to be developed, such as new capabilities for reasoning at the semantic level, by combining the current Dynamic Occupancy Grid approaches with Deep Learning approaches, integration of new sensors in the framework, or hardware-specific adaptations for new embedded device architecture. The specific R&D subject will be decided according to the applicant's interests and skills.
The recruited intern will work within a team of 4 engineers already working on the project, with occasional interactions with some PhD students, other engineers and researchers of the Chroma team. He will develop his skills in the team fields of expertise, including perception, control, on-line trajectory planning for safe navigation in dynamic environments, learning semantic information using deep learning approaches or parallel computing development (GPU, FPGA).
Most implementations and the experimentations will be performed using the ROS framework, Nvidia GPUs and the experimental platform of the IRT nanoelec (which includes an automated Renault Zoé vehicle), or the new offroad robot. The recruited intern will also contribute to the improvement of the experimental platform, and he will participate to some scientific publications, industrial conferences or various demonstrations.
Principales activités
According to the profile, the activities of the recruited intern will consist on some of the following :
- Develop perception software on embedded parallel architectures (Nvidia Jetson, FPGA).
- Develop experimental platforms, test and integrate new sensors.
- Propose and develop new semantic detection methods, and their integration in the current framework.
- Write documentation, reports, and participate in scientific paper writting.
- Run tests using simulation tools and experimental plateforms.
- Participate in presentations and demonstrations with the automated vehicles in industrial or research events.
Compétences
- Experience or Education in Computer Science, Robotics or closely related fields.
- Good theoretical and practical background in one of the following domains: Robotics, Multi-sensors Perception, Scene Understanding, Parallel computing, Deep Learning and/or Decision-making for safe navigation.
- Good skills in C/C++.
The following qualifications would be an advantage:
- Experience using the Robotics library ROS
- Familiarity with CUDA and Boost libraries, or FPGAs
- Good skills in Linux, system management, python.
- Theoretical knowledge of Bayesian models
- Experience on Deep Learning
- Ability to work as a teammate with other researchers
- Reasonable French and English skills (written and spoken)
Avantages
- Partial reimbursement of public transport costs
- Leaves
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
Rémunération
- Internship bonus of 4,05 € per hours