Section: Bilateral Contracts and Grants with Industry

Contracts with Industry

Toyota Motors Europe

[Feb 2006 - Feb 2009] [Dec 2010 - Dec 2014]

The contract with Toyota Motors Europe is a joint collaboration involving Toyota Motors Europe, Inria and ProBayes. It follows a first successful short term collaboration with Toyota in 2005.

This contract aims at developing innovative technologies in the context of automotive safety. The idea is to improve road safety in driving situations by equipping vehicles with the technology to model on the fly the dynamic environment, to sense and identify potentially dangerous traffic participants or road obstacles, and to evaluate the collision risk. The sensing is performed using sensors commonly used in automotive applications such as cameras and lidar.

This collaboration has been extended for 4 years and Toyota provides us with an experimental vehicle Lexus equipped with various sensing and control capabilities. Several additional connected technical contracts have been signed also.

Renault

[Jan 2010 - Feb 2013]

This contract is linked to the PhD Thesis of Stephanie Lefèvre. The objective is to develop technologies for collaborative driving as part of a Driving Assistance Systems for improving car safety. Both vehicle perception and communications are considered in the scope of this study. An additional short-term contract (3 months) has also been signed in november 2012.

PROTEUS

[November 2009 - October 2013]

PROTEUS (“Robotic Platform to facilitate transfer between Industries and academics”) is an ANR project involving 6 industrial and 7 academic partners. This projects aims to develop a software platform which helps to share methods and softwares between academics and industries in the field of mobile robotics.

The project works on three main aspects :

• Specification of different scenarios and its associated formalism.

• Definition of a domain specific language (DSL) to specify and execute the given scenarios.

• Setting up 4 robotic challenges to evaluate the capacity and the usability of the platform.

The contribution of e-Motion to PROTEUS is first to provide its expertise on mobile robotics to develop the DSL and next to provide a simulation environment with its platform “CycabTK”.

Juan Lahera-Perez has been recruited as engineer to work on this project with Amaury Nègre.

Delta Drone

[9 May 2012 - 9 November 2012]

This is a collaboration between our lab and the company Delta Drone. The goal of this collaboration is the exploitation of our competences in visual inertial navigation in order to make a drone able to perform autonomous navigation in GPS denied environment. This would have a strong impact on many civilian applications (e.g., surveillance, rescue mission, building inspection, etc.) During 2012, our effort has been focused on the first important step which must be accomplished in order to perform any task: the hovering. To this regard, we introduced a new method to localize a micro aerial vehicle (MAV) in GPS denied environments and without the usage of any known pattern. This makes possible to perform hovering in an unknown and GPS denied environment. The method has successfully been implemented on the platform available in our lab. This is a Pelican from Ascending Technologies equipped with an Intel Atom processor board (1.6 GHz, 1 GB RAM).

IRT-Nano Perfect (2012-2014, and 2015-2017)

Perfect is a project supported by ANR in the scope of the IRT (Technological Research Institute) Nano-electronic driven by the CEA (Nuclear Energy Agency). The partners of the project are the CEA-LETI LIALP laboratory, ST-Microelectronics and Inria. The goal of this project is to propose integrated solutions for “Embeeded Bayesian Perception for dynamic environments” and to develop integrated open platforms. During the first phase of the project (2012-2014), the focus is on the domain of transportation (both vehicle and infrastructure); health and smart home sectors will also be considered in the second phase (2015-2017).

FUI Permobile (2013-2015) – submitted

Permobile is a project submitted to the 15th FUI call for project. The consortium of the project puts together research labs, large industrial partners and local small and medium companies. The objective of Permobile is to create electronic solutions (both hardware and software) for an embedded system for mobile perception in dynamic environments. This system is intended to anticipate potential collisions which may occur for the mobile platform (car, bus, aerial drone…).

The starting point is the current perception system developed in the e-Motion team for automotive applications, which is currently implemented on a standard PC (CPU+GPU) architecture. Permobile intends to improve the perception capability and to reduce the size, cost and electrical consumption of the system through the integration on the mobile technologies. A first stage consists in using current mobile technologies, while the second stage proposes to develop an innovative mobile board incorporating multiple mobile CPU/GPU processors. Demonstrators based on real mobile platforms (bus and aerial drone) will be developed to assess the realism and the efficiency of the approach developed in the project.

The partners of the project include both experts in software (Inria, Probayes), hardware (CEA LETI, Calao systems, ST-Ericsson), and final users of the technology (Delta-Drone, SEMITAG).