DSRC and cooperative perception
The deployment of DSRC technology will enable the sharing of a multitude of information, that can potentially be used to build very accurate representations of the local environment. This information will be provided initially by intelligent public infrastructure, and in the future by smart vehicles fitted with perception capabilities.
This project focuses on the development of a general framework for cooperative data fusion to integrate data coming from different sources with their own uncertainties. These algorithms will be used to estimate and propagate estimates of position, context and associated risk for all road users and vehicles in proximity.
During the next few years we expect a significant deployment of DSRC technology in vehicles and related infrastructure. The providers of this technology have already implemented and demonstrated the operation of the technology in safety applications. These demonstrations have been based on V2X communications and a set of rules designed to address a set of risk scenarios.
It is also clear that these approaches will only have a significant impact in safety once there is a sufficiently large penetration of the technology. It is expected that it will soon be mandatory for all new vehicles to be fitted with this technology. Nevertheless, there will be a period of many years where the DSRC enabled vehicles will share the road with the existing vehicle fleet. Encouraging existing vehicles to adopt DSRC technology will allow the V2X communication network to grow more rapidly.
A more densely connected V2X network will provide a greater opportunity for implementing smart safety technologies and assist/enhance autonomous operations. To facilitate this early growth, it is essential to provide new innovative uses of DSRC technology to encourage members of the existing fleet to access the vehicular network by retrofitting/incorporate their vehicles with this new technology.
This project aims at developing the fundamental cooperative framework to enable a number of commercial applications of this technology. These applications will be able to operate from day one by providing safety benefit in low DSRC penetration markets and will become essential components for the deployment of autonomous vehicles.
This project aims at the:
1. Development of fundamental multi-vehicle cooperative framework that can enable a number of commercial applications of DSRC technology.
2. Development of consistent and efficient data fusion algorithms that can operate across four vehicle scenarios:
- Single extended object tracking from a stationary object
- Multiple extended object tracking from a stationary platform
- Multiple extended object tracking from a moving platform
- Cross-platform data fusion (fusing posed estimates of multiple targets associated with uncertainty from multiple inhomogeneous platforms)
These scenarios cover most typical V2X interactions.
3. Demonstration of safety/automation benefit in low DSRC penetration environments.
Ongoing, this page will be a living record of this project. As it continues, matures, hits milestones, etc., we’ll add information, links, images, interviews and more. Watch this space!