Descripció del projecte
Multiple object tracking is an important challenging task for the automotive industry. The goal of this project is to develop a general-purpose framework that is able to solve this problem for different applications, such as autonomous vehicles as well as traffic monitoring on open road tests. Furthermore, this system shall be able to process inputs from different configurations and sensors such as frontal lidars, 360-degree lidars, cameras, radars, GPS (Global Positioning System) and IMU (Inertial Measurement Unit). The initial proposal is to exploit filtering and optimization techniques together with track management logic to combine the information from each sensor in a robust and interpretable way. Since this is a modular approach, there are many potential applications depending on the sensors used, but one of the main goals of the project is to build a reference perception system that can be mounted easily on a car, so that it can be used to evaluate and validate the performance of the sensors in the car, the perception, and the ADAS/AV functions implemented.
The project will be carried in cooperation with the following two institutions:
-Institut de Robòtica i Informàtica Industrial (IRI) in the Universitat Politècnica de Catalunya.
-IDIADA
The scientific advisor in IRI will be Dr. Antonio Agudo Martínez.
The responsible for part of the company will be Xavier Sallert.
