When EPFL researchers fused the data from two intelligent vehicles, the result was a wider field of view, extended situational awareness and greater safety.
Intelligent vehicles get their intelligence from cameras, Light Detection and Ranging (LIDAR) sensors, and navigation and mapping systems. But there are ways to make them even smarter. Researchers at EPFL are working to improve the reliability and fault tolerance of these systems by combining the data they gather with that from other vehicles. This can, for example, extend the field of view of a car that is behind another car. Using simulators and road tests, the team has developed a flexible software framework for networking intelligent vehicles so that they can interact.
“Today, intelligent vehicle development is focused on two main issues – the level of autonomy and the level of cooperation,” says Alcherio Martinoli, who heads EPFL’s Distributed Intelligent Systems and Algorithms Laboratory (DISAL). Over the past several years, his team has been working on cooperation issues, which have yet to garner much attention from the automotive industry. As part of his PhD thesis, Milos Vasic has developed cooperative perception algorithms, which extend an intelligent vehicle’s situational awareness by fusing data from onboard sensors with data provided by cooperative vehicles nearby.
The researchers used the cooperative perception algorithms as the basis for the software framework. For example, in a scenario in which one car overtakes another car on a two-lane road, they developed an assistance system that assesses the risk of the overtaking manoeuver. The risk assessment factors in the probability of an oncoming car in the opposite lane as well as kinematic conditions such as driving speeds, the distance required to overtake and the distance to the oncoming car. Cooperative perception means that an intelligent vehicle can combine its own data with that of another vehicle – such as the one it wants to overtake, which has a wider field of view. In this way, the decision whether or not to overtake can be made safely. According to Vasic, “cooperative perception makes overtaking safer and more fluid.”
Seeing two pedestrians instead of one
At first, the team used a simulator to test their algorithms under various scenarios, both with and without cooperative vehicles nearby. Then, with help from Groupe PSA, they took their project on the road. Two Citroen C-Zero electric cars were retrofitted with a Mobileye camera, an accurate localization system, a router to enable Wi-Fi communication, a computer to run the software and an external battery to power everything. “These were not autonomous vehicles,” says Martinoli, “but we made them intelligent using off-the-shelf equipment.”
Success did not come easily, however. One of the difficulties in fusing data from the two vehicles involved relative localization. The cars needed to be able to know precisely where they are in relation to each other as well to objects in the vicinity. If a single pedestrian does not appear to both cars to be in the same exact spot, there is a risk that, together, they will see two figures instead of one. By using other signals, particularly those provided by the LIDAR sensors and cameras, the researchers were able to correct flaws in the navigation system and adjust their algorithms accordingly. This exercise was all the more challenging as the data had to be processed in real time while the vehicles were in motion. “Because of this, the project also helped improve the accuracy of localization more generally,” Vasic says. Although the tests involved only two vehicles, the longer-term goal is to create a network between multiple vehicles as well with the roadway infrastructure.
In addition to driving safety and comfort, cooperative networks of this sort could eventually be used to optimize a vehicle’s trajectory, save energy and improve traffic flows. The team is aware, however, that many questions – which are beyond the scope of their research – remain unanswered. To begin with, there is the issue of liability in the case of an accident. Determining liability – which already involves the owner, car manufacturer and software designer or supplier – becomes even more complicated when vehicles cooperate. “The answers to these issues will play a key role in determining whether autonomous vehicles are accepted,” adds Martinoli.
Learn more: Two intelligent vehicles are better than one
The Latest on: Networked intelligent vehicles
- In Chinese first, Seeland launches pilot operation of its autonomous commuter vehicleon November 30, 2019 at 9:38 pm
forming an advanced community intelligent cooperative transportation network in China. It enables the efficient cooperation among people, vehicles, roads and environment. Hachi Auto can carry ...
- Seedland Launches Pilot Operation of China’s First Autonomous Commuter Vehicle: Hachi Autoon November 30, 2019 at 7:17 pm
Another great feature of Hachi Auto is that it is connected with the Smart Life System of the Seedland communities, forming an advanced community intelligent cooperative transportation network in ...
- Roundup of major Chinese OEMs’ intelligent connectivity strategieson November 29, 2019 at 1:41 am
Changan is seeking to complete the transformation from traditional automobile manufacturer to intelligent mobility technology company. Changan Automobile said it would no longer produce non-networked ...
- 5G Network Investment Opportunities Are Starting To Take Shapeon November 28, 2019 at 4:04 am
Image Source: Qualcomm The traditional concepts of autonomous vehicles, industrial IoT ... the 5G space with products designed to help service providers deploy the networks in a cost-efficient manner.
- The Surprising Way Artificial Intelligence Is Transforming Transportationon November 27, 2019 at 11:20 am
Developments in 5G networks, autonomous vehicles, and artificial intelligence are poised to transform the way we drive and the safety of our roads. 5G will have a positive impact on road maintenance ...
- Autonomous Vehicle Market Size: Global Industry Demand, Growth & Revenue, Opportunity 2019 to 2024on November 27, 2019 at 6:18 am
Artificial Intelligence technologies power self-driving vehicle systems. Creators of self-driving vehicle use a huge amount of data from image recognition systems, along with neural networks and ...
- Chinese Spy Defects to Australia Offering a Trove of Security and Intelligence Informationon November 27, 2019 at 6:04 am
He had been charged with fraudulently obtaining loans to buy luxury vehicles and at least one of his car dealerships had collapsed ... Zhao reportedly told the Australian Security Intelligence ...
- Smart CCTV Networks Are Driving an AI-Powered Apartheid in South Africaon November 24, 2019 at 6:34 pm
“But when you have people in an intimidating vehicle with bullet-proof vests and big guns ... Eventually, the Vumacam network would cover “the whole of Johannesburg” with an “intelligent software ...
- The FCC's new automotive connectivity standard opens the door for mobile network operators to capitalize on partnerships with automakerson November 22, 2019 at 7:18 am
The FCC will reallocate most of the 5.9 GHz band that was previously reserved for Dedicated Short-Range Communications automotive safety applications.
- Tech your ride: Electric vehicles, improved safety features and AI at 2019 LA Auto Showon November 21, 2019 at 9:39 am
Spotlighted at AutoMobility LA: emerging innovations such as new connectivity options, artificial intelligence, electrification, ridesharing platforms and semi- and fully-autonomous vehicles. Here's a ...
via Google News and Bing News