Cooperative intelligent transport systems reduce accidents involving cyclists
Networking and automation of vehicles offer a great opportunity to also increase the safety of cyclists. In Salzburg (Austria), researchers validated wireless communication channels between different vehicles, bicycles and infrastructure under real-world conditions.
Road accidents involving bicycles are steadily increasing. In 2015, the road accident statistics of Statistics Austria recorded 6,901 road accidents involving bicycles; in 2021, the figure was already 9,578. The accidents with other vehicles involved mostly occurred in a turning situation in an intersection, with the bicycle predominantly going straight ahead. In addition, there are a large number of near-accidents that do not appear in any accident statistics.
New technological developments in the field of vehicle communication by means of ITS-G5, bicycle localisation, vehicle environment perception by means of camera and lidar sensor technology as well as with cameras created the basis for cooperative solution approaches for the detection and avoidance of collision risks. Vulnerable road users such as cyclists should not only be recognised, but actively involved in collision avoidance. “Therefore, with our research project Bike2CAV, we intended to make these risks easier to assess so that measures can be taken even before something happens,” says project manager Cornelia Zankl from Salzburg Research.
This should bring added value on several levels: Cyclists will be warned of collisions at an early stage in order to recognise dangerous situations and avoid accidents. Connected vehicles and driver assistance systems can detect cyclists more reliably through improved detection quality as well as active communication, and these can react at an early stage. Municipalities and infrastructure operators receive objective assessments of risk zones at traffic junctions and can defuse them preventively.
- Autonomous driving: Algorithm allocates risks fairly
- Smartphone magnet sensor protects pedestrians, cyclists
- Retrofit turning assistant creates safety for pedestrians and cyclists
In the research project, several solution approaches were analysed in order to be able to select suitable and safe methods. The most promising methods were tested and tried out in three scenarios at two test intersections in rural and urban areas.
A networked, automated vehicle and a networked research bicycle were used in the experiments at the test intersections equipped with smart sensor technology. A continuous chain of different data processing methods was tested, from the self-localisation and detection of road users, through the detection of collision risks and the generation and transmission of warning messages, to communication with cyclists and other road users.
The preliminary conclusion: The research project has demonstrated the high complexity of the technical implementation of cooperative systems. Some central results were achieved in the defined focus areas of the project.
The researchers succeeded in a semi-automated derivation of interaction zones in intersection areas based on statistical accident probabilities. “An important finding was that cyclists often use the infrastructure at the studied urban intersection differently than intended. This is probably due to the fact that the planning primarily follows the needs of motor vehicle traffic,” says Martin Loidl from the University of Salzburg.
A highly accurate self-localisation of cyclists is central for a reliable detection of collision risks. In addition to two GNSS receivers installed in the Holoscene Bike, the accuracy of a smartphone and that of a high-precision sensor mounted on the helmet were also investigated. The researchers’ goal was to achieve less than 50 cm deviation with 99.9 percent reliability. This was not fully achieved – the researchers only achieved 0.5 metres lateral deviation at 95 per cent reliability in rural environments; and only two metres lateral deviation at 95 per cent reliability in urban environments.
The approach of also equipping bicycles with V2X technology proved to be advantageous in order to enable automated vehicles to actively recognise via ITS-G5 in addition to passive recognition via environmental sensors. Although such bicycles are not yet available on the market, a proof-of-concept prototype could be tested in the project.
Detection of cyclists by infrastructure and V2X communication
Extensive sensor technology is used to visually detect and track cyclists through the infrastructure. A camera-based AI detection system for the recognition and classification of motor vehicles and pedestrians was extended to the recognition of cyclists. In addition, the design of the message format “collective perception message” for the transmission of information from detected road users was successfully tested for V2X communication. Based on machine learning methods, an intention recognition of cyclists was implemented, thus enabling a better path prediction and determination of collision risks.
Warning concepts for cyclists
The requirements for non-deflective warnings of collision risks between a vehicle and cyclists were identified in a co-creation process with lead users. Different warning modes – acoustic, visual and tactile – were designed and tested using a navigation app on the smartphone, vibration on the handlebars and acoustic signals in the helmet. The results showed that cyclists found auditory warnings particularly helpful, especially in situations where a vehicle was approaching from behind. In all tested scenarios, risky situations with collision risk could be simulated and collision warnings could be generated.
“In summary, we can confirm that collision risks can be detected cooperatively with the chosen approach. However, the connection of different data sources and the processing of the large amounts of data still turned out to be very complex. The tests carried out were successful on a prototype level, but further developments and optimisations are still required for real use,” summarises project manager Cornelia Zankl.
Video (in German): https://www.youtube.com/watch?v=5c1c_UY0eTQ
Related articles:
Autonomous driving: Algorithm allocates risks fairly
Smartphone magnet sensor protects pedestrians, cyclists
Retrofit turning assistant creates safety for pedestrians and cyclists
Technology aims at preventing “dooring” accidents
Intelligent bicycle gets connected
Connecting vehicles to smart infrastructure reduces CO2 emissions
For the sake of safety: Autonomous cars develop social skills
Vodafone launches cloud-based V2X platform for connected road traffic
Automotive GNSS module enables sub-meter accuracy
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
