Neural Networks for Real-Time, Probabilistic Obstacle Detection

Title data

Werner, Tobias ; Bloeß, Josua ; Henrich, Dominik:
Neural Networks for Real-Time, Probabilistic Obstacle Detection.
In: Ferraresi, Carlo ; Quaglia, Giuseppe (ed.): Advances in Service and Industrial Robotics : Proceedings of the 26th International Conference on Robotics in Alpe-Adria-Danube Region, RAAD 2017. - Cham : Springer , 2017 . - pp. 306-313
ISBN 978-3-319-61276-8
DOI: https://doi.org/10.1007/978-3-319-61276-8_34

Related URLs

Project information

Abstract in another language

Recent research suggests intrinsically safe robots, such as through soft limbs or artificial skins, to enable close-quarter human-robot collaboration. Intrinsically safe robots allow for risk-minimized instead of collision-free path planning. Risk-minimized path planning can integrate non-binary knowledge—including obstacle probabilities, robot speed, or data age—into the choice of a robot path. In this contribution, we propose a novel approach to probabilistic obstacle detection on color images that is specifically suited for use in real-time risk-minimized path planning. Our approach enhances an existing neural network for object detection by incorporating spatial coherence via a second neural network and an optimization step inspired by simulated annealing. Finally, a bias towards false-positive obstacle detection allows us to avoid the Sleeping Person Problem for online learning. In our experiments, we show that a GPGPU implementation of our approach can process Full HD images at a soft real-time rate of 15 Hz. We conclude that our probabilistic obstacle detection is fit for use in real-time risk-minimized path planning.