Diagnostic Mechanism and Robustness of Safety Relevant Automotive Deep Convolutional Networks

Robert Krutsch, Rolf Schlagenhaft; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 61-68

In this paper we investigate functional safety aspects for a road labeling application, a common task in the autonomous driving algorithmic stack. We introduce computationally light safety checks that reduce the error space significantly, train a CNN on the Cityscape dataset that reaches 93% mean IU and use Monte Carlo simulations to assess the impact of single event upset random hardware faults. The results show that the networks based on convolution and ReLU have some intrinsic robustness and that together with additional constraints strong function safety claims can be made. We compare also the diagnostic coverage between floating point and fixed point implementation of CNNs and summarize key safety features needed to achieve a high diagnostic coverage.