Next-gen ADAS focuses on urban driving
With the next generation of ADAS, techniques such as machine learning or neural networks enter the cars. Higher processing power and sensor resolution as well as larger memories makes it possible that techniques hitherto restricted to stationary systems will run in future vehicles.
Daimler introduced a software technology called ‘scene labelling’ that helps camera-based driver assistance systems to better detect critical situations and thus enable them to take action sooner and with higher precision. The technique classifies unknown situation and thus automatically identifies objects relevant to the ADAS, from bicyclists to pedestrians or wheelchair users. The developers “showed” the ADAS thousands of images of cities in which 25 object classes were labelled manually, such as vehicles, pedestrians, roads, sidewalks, buildings or even trees. With this image material as input, machine learning techniques enabled the ADAS to correctly classify completely unknown new camera images and to make driving decisions on this basis. These algorithms are running on Deep Neural Networks, powerful computers that are neurally linked, similar to the connection of neurons in the human brain. Thus, the system is comparable to human vision.
Besides scene labelling, Daimler showed a radar-based vehicle with capabilities that exceed today’s vehicle radar systems: It can resolve not only dynamic objects but static ones as well. It also utilises what Daimler calls micro Doppler that provides a signature of moving objects and thus unambiguously identifies pedestrians and cyclists.
A third Daimler test vehicle was equipped with a system that can detect and identify the intentions of pedestrians and cyclists. Based on features such as head posture, body position the system predicts if the person detected will cross the street or stay on the sidewalk. The system can reduce the reaction time by the one critical second that decides over crash or no crash, Daimler claims.
Opel showed a system that tackles similar problems as Daimler: It can identify pedestrians who suddenly run between to parked cars onto the road – a situation that is as day-to-day as it is dangerous. The sensors and algorithms enable Opel’s test vehicles not only to detect the person but at the same time avoid collisions by direct braking and steering intervention. With another test vehicle Opel addressed traffic management and better traffic flow: Through a modified WiFi link, the car received data from the traffic management infrastructure and from fellow vehicles. Based on these data, the vehicle optimises its speed when approaching an intersection. This helps the driver to approach traffic lights at the optimum speed, in ideal cases he does not even need to stop – he only arrives at the traffic light in the moment when it turns green. This approach increases safety and reduces fuel consumption, Opel says.
A similar technology as Daimler has supplier Bosch. The company utilises its series production stereo front camera as sensor to detect objects on a collision course. The system also predicts their trajectory – or, in other words, it predicts where they are heading for and initiates the corresponding countermeasures. The time horizon for the prediction is about one second, which gives the driver or the ADAS significantly more time to brake or dodge. In addition, it supports the driver when turning the wheel in what the system has calculated as the appropriated direction. The system also supports drivers on specific narrow passages in that it computes an ideal trajectory, taking into consideration moving objects on both sides of the street and of course on the street as well.
The findings from these projects are fed into future developments towards automated driving, Bosch said.
The German aerospace centre DLR which also performs research in the automotive segment demonstrated an application example for vehicle-to-infrastructure communication: It equipped the traffic lights of a crossroad with connectivity equipment to exchange data with cars. In case an emergency or police vehicle arrives in urgent mission, this vehicle can switch the traffic light to green (and the other ones to red). The function applies only to the specific lane where the emergency vehicle is approaching. With current technology, such a feature requires that the traffic management centre switches the respective traffic light manually.