108 Yet, to what extent do the training data actually reflect the operational domains of the ADAS? This is often of secondary importance. In order to reduce the systems’ susceptibility to errors, only the quantity of data has been kept constantly increasing up to now. This results in unnecessarily complex, lengthy and inefficient development processes. ARRK Engineering has therefore developed an approach that allows to correct or remove data that is inaccurate or distorts reality and to train the Neural Networks in a targeted, reliable and at the same time resource-efficient manner. Well-known OEMs are leading the way, mobility start-ups are following suit and consumers want it: more and more vehicles are being equipped with level 2 and level 3 driver-assistance systems. Thus, every day, numerous road users rely on lane keeping assists or autosteer (LKA/LCA), automated parking and adaptive cruise control (ACC). The general safety on the roads – and thus the safety of all road users – depends to a large extent on the proper functioning of these systems. To ensure this, their neuronal networks are trained with the help of huge data sets. Huge data sets: the vicious cycle of the mass The more complex the functionalities of different ADAS, the more attention needs to be paid to the collection of the training data. In order to cover all possible traffic situations, the data sets have been expanded more and more in recent years, focusing primarily on mass, i.e. the sheer number of recording hours or of annotated objects in different weather and lighting conditions. However, this inevitably increases the proportion of data that is inaccurate or simply unsuitable for a particular operational domain. To ensure that the newly developed ADAS remain their reliability, their quality deficit has in turn been compensated for with quantity – a vicious cycle. This has already led to very long development process with many iteration loops, in which the training of the neural networks alone takes several weeks. To escape this dilemma, the automotive industry needs to shift the focus towards quality, instead of of relying on quantity of data sets. Therefore, the machine learning specialists at ARRK Engineering have developed an approach to validate the processes with regard to an operational domain and to correct them if necessary. In this way, of NN can be made more efficient and, more importantly, the functional safety of the ADAS can be increased. Example of ACC: Analyzing the data sets with regard to trajectory planning The ADAS function ACC automatically controls the acceleration and breaking of a vehicle, always maintaining sufficient distance to other road users and obstacles. To do this, the system calculates the so-called time-to-collision (TTC) for each detected object. If it drops below a defined threshold value, the vehicle reacts accordingly with deceleration. Thereby applies: The greater the speed difference between the vehicle itself and an object in front of it, the shorter the TTC and the earlier the ACC must react. Due to this correlation, on motorways, for example, the system needs to reliably detect objects at a significantly greater distance, Machine Learning Inferior data sets can increase the risk of accidents in driverassistance systems Is quantity really the best solution for training highly functional ADAS? By Václav Diviš, Senior Expert Machine Learning at ARRK Engineering Advanced driver-assistance systems (ADAS) are nowadays not only a standard accessory in new cars, but also an important milestone on the road to autonomous driving. The more the technical assistants are supposed to be able to do independently, the better the neural networks on which the systems are based have to be trained for this. Consequently, the data sets used continue to grow. Image: © Scharfsinn/Shutterstock The ADAS function ACC keeps the vehicle in the lane at a certain speed, always ensuring sufficient distance to other road users and obstacles.
RkJQdWJsaXNoZXIy MjUzMzQ=