Testing the reliability of monocular obstacle detection methods in a simulated 3D factory environment

Journal of Intelligent Manufacturing, vol. 33, pp. 2157–2165

Abstract

Abstract Automated driving in public traffic still faces many technical and legal challenges. However, automating vehicles at low speeds in controlled industrial environments is already achievable today. A reliable obstacle detection is mandatory to prevent accidents. Recent advances in convolutional neural network-based algorithms hypothetically allow the replacement of distance measuring laser scanners with common monocameras. In this paper, we present a photorealistic 3D simulated factory environment for testing vision-based obstacle detecting algorithms preceding field tests on the safety–critical system. We further test two obstacle detection methods employing state-of-the-art semantic segmentation and depth estimation in a range of challenging test scenarios. Both models performed well under common factory settings. Some edge cases, however, lead to vehicle crashes.

Authors 4

1. Marius Wenning corresponding Aachen Werkzeugmaschinenlabor

   RWTH Aachen University

   Affiliation as printed

   Werkzeugmaschinenlabor, RWTH Aachen University, Aachen, Germany

2. Anton Akira Backhaus Aachen Werkzeugmaschinenlabor

   RWTH Aachen University

   Affiliation as printed

   Werkzeugmaschinenlabor, RWTH Aachen University, Aachen, Germany

3. Tobias Adlon Aachen Werkzeugmaschinenlabor

   RWTH Aachen University

   Affiliation as printed

   Werkzeugmaschinenlabor, RWTH Aachen University, Aachen, Germany

4. Peter Burggräf Aachen Werkzeugmaschinenlabor

   RWTH Aachen University

   Affiliation as printed

   Werkzeugmaschinenlabor, RWTH Aachen University, Aachen, Germany