Projects

The Mobilitech platform is an initiative of UTBM, within the framework of the project "UTBM 2020: European Engineering Campus" aiming at the establishment on the university campus of Montbéliard, a partnership technology platform in the field of transport and mobility.

MACPOLO is a Toyota Partner Robot joint research project between Toyota Motor Corporation (TMC) and the University of Technology of Belfort-Montbéliard (UTBM). This project focuses on the development of multisensor-based active perception methods for human tracking and object recognition on the one hand, and unknown object grasping on the other. The entire research will particularly based on the context of health and social care services for the disabled and elderly people. Moreover, the lifelong learning methods will be investigated throughout the project, since the lifelong learning ability of a robot is expected to play a crucial role in long-term autonomous operation in everyday environments. In particular, we will exploit data acquired by sensors installed in the Toyota's HSR robot and the external environment, where the heterogeneous nature of the sensory data will allow mutual (enrichment) training of models for human tracking and object recognition, then for object grasping. The developed methods could also be served for semantic mapping, robot localization, and navigation in long-term.

Over the past few years, one person has been killed and close to one seriously injured every day on Level Crossings (LC). Therefore, the EU project SAFER-LC aims to improve safety and minimize risk by developing a fully integrated cross-modal set of innovative solutions and tools for the proactive management and design of LC infrastructure. EP users are responsible for developing an advanced video surveillance system for modeling and analyzing LC users' behavior including vulnerable users and their interactions with other users and to LC.

DENOSAU is a joint research project between the Groupe Renault and the University of Technology of Belfort-Montbéliard (UTBM) in France, which assesses the impact of severe weather conditions on 3D lidar data and develop new solutions that can integrate with current hardware resources, extending the state-of-the-art to achieve efficient 3D lidar data denoising. Scientifically, DENOSAU aims to address one of the most pressing problems in autonomous driving, i.e. object detection and tracking, via the study of denoising method for point cloud generated by the 3D lidar under adverse weather conditions.

3L4AV is a mobility research project between the Czech Technical University in Prague (CTU) in Czechia and the University of Technology of Belfort-Montbéliard (UTBM) in France. The research goal is to provide new methods for autonomous vehicles to improve the robustness of their perception system, in particular for dynamic objects detection and tracking in adverse conditions, such as during adverse weather and dense traffic. In this project, we will investigate machine learning methods for multisensor systems deployed in autonomous vehicles. The heterogeneous nature of the sensory data will allow mutual training of the methods of dynamic object detection and tracking. On-the-fly, lifelong learning of the objects models for detection and tracking will be achieved through exploitation of the heterogeneity and amounts of data gathered by the vehicle's sensors over long periods of time. In contrast to existing technologies which are mainly based on static models, our project will focus on development of adaptive models that are completed and refined based on the data gathered over long-time operation of the autonomous vehicle.

[Video] The SafePlatoon project addresses the platooning problem, in the case of autonomous vehicles. It possesses an innovative aspect, given by the conception of a set of extended and robust platooning capabilities. Firstly, it is engaged with mastering platoon operation aspects, with different geometric configurations: linear, triangular, front line, etc. Secondly, it also concerns the conception of platoon's dynamic adaptation capabilities : configuration changes, vehicle insertion and ejection. An important aspect of the safe platoon project is that the proposed decision and control algorithms will be verified and validated. Verification consists in proving, by applying specific methods and tools, that a set of safety properties is valid relatively to a given system. Validation relates to performing, on a simulation model or a prototype of the system, a set of test scenarios. The latter being defined so as to evaluate the conformity and the quality of the proposed approaches. The SafePlatoon project partners possess an experience in the development of platooning decision and control algorithms and in the design of experimental intelligent vehicles. They have also participated in projects devoted to platooning and/or autonomous vehicle applications for urban transportation, agriculture and the military. Those experiences will be enriched and reinforced, in the frame of the SafePlatoon project.

[Video] In compliance with the French call for tender ANR-VTT, PANsafer's main objective is to actively contribute to reduce level crossing accidents. To reach this objective, the project includes: 1) database analysis related to accidents that occurred in the most preoccupying level crossing s in France, and to determine their technical, human and organisational causes; 2) emphasis of main accident factors by identifying scenarios; 3) analysis of behaviours led by the infrastructure and its exploitation methods; 4) detection, recognition and evaluation of dangerous (or potentially) dangerous situations and setting up of a "criticality level"; 5) exploring the possibilities of new technical and organisational solutions, with a focus on the new technologies of detection of rail/road interactions environment, telecommunication and data exchange. PANsafer activities will directly allow the improvement and development of the intermodal rail/road collaboration. EPAN contributes on aspects concerning the perception of the environment by image analysis and virtual reality (3D modeling, simulation of scenarios, etc.).