Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Machine Learning Methods for Enhanced Reliable Perception of Autonomous Systems

: Henne, Maximilian; Gansloser, Jens; Schwaiger, Adrian; Weiß, Gereon

Fulltext urn:nbn:de:0011-n-6422192 (2.5 MByte PDF)
MD5 Fingerprint: 7824aafc769b35cc61940fd57cefe7e3
Created on: 21.10.2021

München: Fraunhofer IKS, 2021, 34 pp.
Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und Energie StMWi
BAYERN DIGITAL II; 20-3410-2-9-8; ADA-Center
ADA Lovelace Center for Analytics, Data and Applications
Report, Electronic Publication
Fraunhofer IKS ()
machine learning; ML; autonomous system; safety critical; Deep neural networks; DNN; uncertainty; uncertainty estimation; reliability; autonomous driving; perception; object detection; Out-of-Distribution Detection

In our modern life, automated systems are already omnipresent. The latest advances in machine learning (ML) help with increasing automation and the fast-paced progression towards autonomous systems. However, as such methods are not inherently trustworthy and are being introduced into safety-critical systems, additional means are needed. In autonomous driving, for example, we can derive the main challenges when introducing ML in the form of deep neural networks (DNNs) for vehicle perception. DNNs are overconfident in their predictions and assume high confidence scores in the wrong situations. To counteract this, we have introduced several techniques to estimate the uncertainty of the results of DNNs. In addition, we present what are known as out-of-distribution detection methods that identify unknown concepts that have not been learned beforehand, thus helping to avoid making wrong decisions. For the task of reliably detecting objects in 2D and 3D, we will outline further methods. To apply ML in the perception pipeline of autonomous systems, we propose using the supplementary information from these methods for more reliable decision-making. Our evaluations with respect to safety-related metrics show the potential of this approach. Moreover, we have applied these enhanced ML methods and newly developed ones to the autonomous driving use case. In variable environmental conditions, such as road scenarios, light, or weather, we have been able to enhance the reliability of perception in automated driving systems. Our ongoing and future research is on further evaluating and improving the trustworthiness of ML methods to use them safely and to a high level of performance in various types of autonomous systems, ranging from vehicles to autonomous mobile robots, to medical devices.