Cooperative Perception for Networked Intelligent Vehicles

The goal of this collaborative research is to improve driver safety and overall traffic fluidity using innovative intelligent vehicle technology.

This project focuses on the development of novel cooperative perception algorithms for intelligent vehicles operating in realistic traffic scenarios. Scientific challenges are concerned with designing an efficient sensory system, as well as designing perception and sensor fusion algorithms that involve V2X communication. In terms of algorithmic validation, we will work both with real vehicles, provided by PSA Peugeot-Citroën, and simulation tools at various abstraction levels.

This project was featured in the EPFL news.

Team and Collaborators

Sponsors and Research Period

This project was sponsored by PSA (Peugeot Citroën Automobiles SA), from September 2012 to August 2017.

Related Student Projects and Internships

DISAL-MP33: Johannes Brakker Løje, Gaussian Process Labeled Multi-Bernoulli Filter for Tracking in Dynamic Environments

DISAL-MP32: Romain Michael Desarzens, Multiple Extended Target Tracking Based on PHD Filter and Gaussian Processes

DISAL-SP85: Jonathan Gan, A Collaborative Fusion and Tracking Algorithm Based on a Sequential Monte Carlo Probability Hypothesis Density Filter

DISAL-SP79: Raphaël Lüthi, Object Classification in Urban Environments by Means of Machine Learning Techniques

DISAL-SP88: David Rivollet, Cooperative Localization Based on Topology Matching

DISAL-SP89: Loïc Veyssière, Comparison of Centralized and Distributed Fusion Architectures in a Sensor Network

DISAL-SP66: Gael Lederrey, Collaborative Sensing and Decision Making for Intelligent Vehicle Maneuvers

DISAL-SP55: Titus Cieslewski, Feature-Based Localization for Autonomous Vehicles

DISAL-SP59: Luca Brusatin, Detection and Classification Using Data from an Automotive Laser Range-Finder

Videos

Publications