Automated Vehicle System Degradation


Guaranteeing safety plays a critical role on the widespread of autonomous vehicles. Although the state-of-the-art autonomous vehicles operate very well in sound conditions, in severe weather conditions, where the sensor information is limited, or in situations where the other traffic participants do not obey traffic regulations, maintaining safety evolves to a challenging problem. The idea behind the EU Horizon 2020 RobustSENSE project (Robust and Reliable Environment Sensing and Situation Prediction for Advanced Driver Assistance Systems and Automated Driving) is to develop an holistic processing architecture and ensure the operational safety of an autonomous vehicle. My task in this project involved a new architecture concept and design to increase robustness and reliability.

Sunglare on fish-eye cam.

An exemplary situation highlighting the benefits of 'sensor performance assessment'. Object detection probability for the front left fish-eye camera highly decreases consider- ing the relative position of the sun provided by 'Environment Condition Assessment'.

Snow in Karlsruhe.

The utilization of an 'Environment Condition Assessment' module can help to activate deblurring algorithms.

RobustSENSE system architecture

RobustSENSE architecture.

An automated vehicle system architecture that benefits from redundancy, interdependencies and disparity through the utilization of performance assessment modules and an Environment Condition Assessment module.

Understanding and Planning layer

Understanding and Planning layer.

The Understanding and Planning layer consists of Scene Understanding, Situation Prediction, Behavioral Planning and Trajectory Planning modules which process and enrich the environment model.

The Performance Assessment units employ metrics reflecting quality of the obtained results. If the quality values are low, the whole module is switched into a degraded operation mode.

The System Performance Assessment module continuously evaluates the performance status of the whole vehicle by processing its inputs from the Data Fusion and Understanding and Planning layers to create an awareness of the system's performance and to be able to react by either function degradation or component adaptation.

Automated Driving with ROS

ROS System Architecture

The multi-server ROS system acts as one integrated system for peripheral devices like sensors and actuators. The modular and extendible structure of ROS allows for adapting the system to short-term modifications that makes it especially powerful for prototyping purposes.

Publications on this topic

Name Material
Ömer Şahin Taş, Stefan Hörmann, Bernd Schäufele, Florian Kuhnt. Automated Vehicle System Architecture with Performance Assessment.. In IEEE Intelligent Transportation Systems Conference (ITSC), 2017.
André-Marcel Hellmund, Sascha Wirges, Ömer Şahin Taş, Claudio Bandera, Niels Ole Salscheider. Robot Operating System: A Modular Software Framework for Automated Driving. In Proceedings of the IEEE Intelligent Transportation Systems Conference (ITSC), 2016.
Ömer Şahin Taş, Florian Kuhnt, Marius Zöllner, Christoph Stiller. Functional System Architectures towards Fully Automated Driving. In Proceedings of the IEEE Intelligent Vehicles Symposium (IV), 2016.