Trucks and buses will be equipped with nanoradars and sensors to increase safety. FIT BUT participates in their development

Truck drivers have a poor view of their immediate surroundings - blind spots cover not only the area in front of and behind the truck, but also the sides. So from July 2024, European Commission regulations require trucks and buses to have safety sensors that can detect motorcyclists, cyclists or other vulnerable road users. This will be ensured by innovative laser sensors and nano-radars, on which experts from FIT BUT have collaborated.

A child hiding behind the back of a vehicle or a cyclist riding next to a turning truck - new lidar sensor and nano-radar technologies can help drivers detect these dangerous situations. Within the framework of two projects of the TACR, experts from FIT BUT developed them together with the company Valeo, which specialises in research, development and production of assistance systems and systems for autonomous driving.

"From a regular camera, we can see some objects on the road, but we do not get information about their distance or speed of movement[PC1] . This will be made possible by the new nano-radar, which can see behind vehicles in view. The LiDAR laser sensor will then offer the driver closer information about the geometric shape of the object," explains the basic point of the safety sensors Peter Chudý from FIT BUT, who participated in the development of both technologies.

The LiDAR (Light Detection and Ranging) sensors measure the distance of objects using the reflection of a laser beam. They are active sensors that emit energy into the environment and measure the amount that is returned. While the first generation of laser sensors had four layers of scanning beam, the latest ones have more than a hundred. So they can detect even small objects on the road and alert the driver to them. The most famous car companies, including Audi, Mercedes and Honda, also include them in their assistance systems.


Detection and monitoring of pedestrians in the vicinity of the truck. A pair of experimental displays for 2D and 3D visualization of the outputs of the implemented algorithms/ Author: Valeo

But the ScaLa NFL laser sensor is also unique in its design: 'There are two ways to build a sensor - to focus the beam into a geometrically narrow space, where it can measure distant objects. Or to irradiate the entire space at once, thus monitoring a wider scene," describes developer Radek Maňásek of Valeo.

The data from the sensor then creates a so-called point cloud-an image where each point represents the distance from the reflected point. Special signal-processing software then interprets it and assigns it to a representative 3D object. It uses machine learning and its development was also the responsibility of experts from FIT BUT.

The advantage of the new laser scanner is its fast response to very close objects. "With a scanner-based sensor, where energy is concentrated in a small space, we often encounter insensitivity in smaller spaces, which normally measure up to a meter and a half. This makes them suitable in situations where the car is moving at higher speeds - for example on the motorway. Our latest LiDAR, however, can measure distances from as little as 10 cm," adds Maňásek, who worked on the sensor for three years.

LiDAR is thus able to detect whether a child or an obstacle is standing close behind a car that has been started. If the sensor is placed in an autonomous car, it can then trigger a self-driving start.

Several sensors are placed on the car to cover the entire area around the vehicle - especially blind spots. These are the biggest risks in trucks or lorries, where the driver sits very high up.

The second safety feature that the FIT BUT researchers collaborated on is a nano radar for trucks, which has several advantages over lidar or camera systems - it is not sensitive to weather, so it does not mind fog, rain or darkness. In addition to its higher durability, it can also instantly measure the speed of a road user. "It can also operate in dynamic environments and heavy traffic. A LiDAR or camera works more or less like our eyesight and sees only the obstacle, whereas a nano radar sends out an electromagnetic wave that gets under or around the car and gets data even about the shadowed object," explains Michal Mandlík, who is in charge of the development of radar technologies at Valeo.


Installation of a nanoradar (left) and one of the lidars (right) in the front of the truck/ Author: Valeo

Nanoradar thus perfectly complements the data collected from other sensors - LiDAR and front cameras. "The radar in the signal chain looks at the road users from above and in a 2D view. It identifies the truck as one rectangle with a buffer zone and the cyclist riding next to it as another. In case their routes start to cross, the driver immediately receives a signal. LiDAR, on the other hand, provides 3D information and is thus able to identify whether there is a garbage can, a person or a small obstacle in front of the truck," adds Mandlík.

Thanks to the sophisticated system, the driver can therefore obtain information from several different sensors. While lidar technology is great for getting the car moving, the nano-radars will allow perfect monitoring of the sides of the vehicle. "The advanced compositing of information from LiDAR, radar and vision sensors to increase the driver's situational awareness of the vehicle's surroundings was created by experts at FIT BUT. Sensor fusion, which results in confirmed trajectories of tracked objects, is one example of the transfer of modern aerospace technologies to the automotive industry," adds Peter Chudý.

The technologies were developed separately under two TACR projects [PC2] and can be applied to the car both together and separately. "Of course, the automotive industry is dealing with costs, and in addition to the technical aspects, the price of the resulting car will also be a decisive factor, so a lot of attention is being paid to the price of the resulting sensor. In general, the price of a laser sensor is many times higher compared to a radar sensor," he points out.

"These are two completely different technologies, but they combine into one user function and give the driver a great overview of what is happening around the car," he adds. It will then be up to the carmaker to decide which combination of sensors to equip the car with - including whether it is a highly automated or fully autonomous vehicle.