Search

In 2017, the German ethics commission for automated and connected driving released 20 ethical guidelines for autonomous vehicles. It is now up to the research and industrial sectors to enhance the development of autonomous vehicles based on such guidelines. In the current state of the art, we find studies on how ethical theories can be integrated. To the best of the authors’ knowledge, no framework for motion planning has yet been published which allows for the true implementation of any practical ethical policies. This paper makes four contributions: Firstly, we briefly present the state of the art based on recent works concerning unavoidable accidents of autonomous vehicles (AVs) and identify further need for research. While most of the research focuses on decision strategies in moral dilemmas or crash optimization, we aim to develop an ethical trajectory planning for all situations on public roads. Secondly, we discuss several ethical theories and argue for the adoption of the theory “ethics of risk.” Thirdly, we propose a new framework for trajectory planning, with uncertainties and an assessment of risks. In this framework, we transform ethical specifications into mathematical equations and thus create the basis for the programming of an ethical trajectory. We present a risk cost function for trajectory planning that considers minimization of the overall risk, priority for the worst-off and equal treatment of people. Finally, we build a connection between the widely discussed trolley problem and our proposed framework.

Object detection in camera images, using deep learning has been proven successfully in recent years. Rising detection rates and computationally efficient network structures are pushing this technique towards application in production vehicles. Nevertheless, the sensor quality of the camera is limited in severe weather conditions and through increased sensor noise in sparsely lit areas and at night. Our approach enhances current 2D object detection networks by fusing camera data and projected sparse radar data in the network layers. The proposed CameraRadarFusionNet (CRF-Net) automatically learns at which level the fusion of the sensor data is most beneficial for the detection result. Additionally, we introduce BlackIn, a training strategy inspired by Dropout, which focuses the learning on a specific sensor type. We show that the fusion network is able to outperform a state-of-the-art image-only network for two different datasets. The code for this research will be made available to the public at: https://github.com/TUMFTM/CameraRadarFusionNet., Accepted at 2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF)

In motorsports, lap time simulation (LTS) is used by race engineers to evaluate the effects of setup changes on lap time and energy consumption. Many of the LTS published to date are no longer able to meet today’s requirements because more and more racing series are introducing hybrid systems to improve powertrain efficiency. In addition, some racing series have purely electric powertrains. As a result, new types of LTS are needed that can represent the current state of technology. In addition to various powertrain types and topologies, this also includes the drag reduction system as well as the simulation of energy management strategies that control the distribution of energy within the hybrid system. For use as a co-simulation together with a race simulation, yellow flags and pit lanes should also be modeled. This paper presents an LTS that covers these aspects and, thanks to an improved quasi-steady-state solver, delivers accurate results within a short computing time. Particular emphasis was placed on easy parametrization, based on publicly available data. Exemplary results are shown for Formula 1 and Formula E cars on different racetracks. Three different energy management strategies are compared with regard to the most efficient use of the available energy.