Highly advanced artificial intelligence (AI) and convolutional neural network (CNN) technology has made the automatic detection of a range of objects possible. Still, it will never be possible to fully eliminate erroneous classifications—one reason the reliability of automatic image processing must continue to improve. The correct classification of objects is a matter of life or death in autonomous driving, and this requires a deeper understanding of decision-making processes within the neural networks. Gaining a better grasp of these mechanisms is the only way to reduce misclassification to a minimum and comply with the ISO 26262 and ISO/PAS 21448 safety standards for the reduction of, for example, unknown or unsafe scenarios. That's why, as part of its research activities, ARRK Engineering has developed the foundations of a framework for better understanding how CNNs work, and ultimately improving their object classification capabilities. This framework makes it easy to identify and eliminate vulnerabilities in a CNN, thus minimizing the risk of errors and accidents caused by incorrect classifications.
There is a strong push in the automotive industry to develop better advanced driver assistance systems (ADASs) with the help of, for instance, new hardware with more efficient and robust sensors or more powerful algorithms. In the ample research being conducted in this area, the recognition rate in automatic image processing is of central importance. "What's key to autonomous driving is that the algorithms for object recognition work fast and yield a minimal error rate," explains Václav Diviš, senior engineer for ADAS & Autonomous Driving at ARRK Engineering. "But it will only be possible to develop optimal safety features for autonomous driving once we have understood neural networks down to the last detail. The ISO 26262 and ISO/PAS 21448 standards provide the general framework for this, and it will be especially important to ensure the development processes and evaluation metrics are uniform." To achieve this goal, ARRK Engineering has established an evaluation framework for machine learning in the form of software as part of its research activities. This software will enable deeper insight into the recognition process of neural networks. From there, it will be possible to optimize algorithms and improve automatic object recognition. The experiment also served to gain a better understanding of how neural networks work.
Training the neural network
The first step was to select a reliable generative adversarial network (GAN) architecture, consisting of two neural networks—one generator and one discriminator—to provide a basis for the framework and to augment the dataset. In this phase, the used dataset comprised more than 1,000 photos of pedestrians. "Additional images were generated using the GAN to extend the dataset," Diviš explains. "The GAN's generator synthesis an image and the discriminator assessed the quality of this image. The interaction between these two neural networks allowes us to extract the features from the original objects, generate new image and extend the original dataset relatively easily." Then, the classification network was trained on the original dataset and the test results were evaluated. To achieve the best possible results, ARRK used state-of-the-art architectures for all elements in the experiment.
"The generalization of the object represents a challenge in image processing. The basic question is: What defines pedestrian?" says Diviš. "This can be easily answered by humans, since we generalize inductively. Neural networks, on the other hand, work deductively and require numerous examples to identify a specific object." Furthermore is important to observe "corner cases"—special cases in which pedestrians are not recognized, because of a pedestrian's unusual posture, an obtrusion blocking a sensor's view, or poor lighting due to weather conditions. Datasets typically lack suitable image material to classify these exceptional cases, but thanks to the GAN structure that has been established, ARRK has managed to supplement the dataset with computer-generated images and thus mitigate this problem.
Optimization of object classification processes
ARRK then began with comprehensive tests to gain a deeper understanding of the processes that underlie CNN training, focusing particularly on the filtering of object attributes as well as the depiction of regions of interest (ROI) in the image area being examined. The emergence of these kernel weights and the resulting ROI are essential for finding evaluation metrics and thus automated object classification. In their analyses, experts looked at a number of processes that occur in neural networks and examined approaches to understand the neurons' flow of information. "Some neurons are more associated with the identification of pedestrians and produce stronger responses than others," explains Diviš. "That's why we've tested a range of scenarios in which we deactivated certain neurons to see how they influence decision-making processes. We could confirm that not every neuron responsible for identifying pedestrians needs to be activated, and in fact not removing some neurons can even lead to quicker and better results." The framework that was created can be used to analyze these types of changes.
All of this allows the stability of algorithms to be sustainably increased, which will serve to make autonomous driving safer. Precautions could be taken, for example, to reduce the risk of an "adversary attack"—the external deployment of a malicious code disguised as a neutral image to compromise the neural network. This code generates a disturbance and influences the decisions of certain neurons, making it impossible to correctly recognize objects. The effects of these types of external disruptions could be reduced by removing inactive neurons, as this would provide fewer targets to attack in the neural network. "We will never be able to guarantee correct object classification 100 percent of the time," says Diviš. "In the automotive industry, our job is to identify and better understand vulnerabilities in neural networks. Only by doing so can we take efficient counteractive measures and ensure maximum safety." A system's object classification capabilities can also be improved immensely through the evaluation and combination of various data collected by sensors such as cameras, lidar, and radar.
(Further information can be found at www.arrk-engineering.com )
What are ISO 26262 and ISO/PAS 21448?
ISO 26262 is an automotive industry standard that relates to functional safety. It classifies measures to counteract potential risks posed by vehicle features according to so-called automotive safety integrity levels (ASIL) The five-point scale (QM, A, B, C, D) defines various process requirements for the development of the product: with ASIL QM, standard quality assurance in the development process is sufficient, while ASIL A requires additional risk reduction measures through monitoring diagnostics and plausibility functions. Products with the greatest potential risk—and thus the highest safety requirements—are classified as ASIL D.
ISO/PAS 21448 imposes additional guidelines for design, verification and validation measures in autonomous driving that are required for achieving "safety of the intended functionality" (SOTIF). Proper situational awareness derived from complex sensors, and the associated processing algorithms plays a key role here.
ARRK Engineering is part of the international ARRK Group and specializes in all services relating to product development. With our expertise in Electronics & Software, CAE, Materials, Acoustics, Composites, Bodywork, Drive, Chassis, Interior & Exterior, Optical Systems, Passive Safety and Thermomanagement, we develop integrated and independent products for our customers, supporting them with our many years' experience as strategic development partners. Together with our ARRK sister companies, we work to implement product developments, from virtual development to prototypes and small series production. The ARRK Engineering Division operates worldwide from sites in Germany, Romania, the UK, Japan, and China. The Engineering Division is headquartered at P+Z Engineering GmbH in Germany. ARRK Engineering employs over 1,200 staff members.