The rise of advanced driver assistance systems and partially automated driving functions leads to the need of virtual simulation to assess these systems and their effects. This especially refers, but is not limited, to safety effects in traffic. There are various methods and tools for prospective evaluation of safety systems with respect to traffic safety. Implementing the methodology by creating and maintaining the openPASS platform will support reliability and transparency of results obtained by simulation.
In the last few years, the "Robocar" community of enthusiasts that build autonomous scaled vehicles (mostly 1:10) has grown significantly and the level of functionality that is achieved is amazing. Many of these projects use ROS/Python and start with available open source platforms. At itemis, we decided to build our vehicle based on other technologies that we see in production at our customers, such as C++ and Eclipse hosted communication frameworks.
Environment perception is an important aspect of reliable and safe autonomous driving for automated vehicles. Typical AD software stacks provide localization, object detection and tracking using and array of sensor data. Sensor data is complemented with other information arriving from V2X connectivity, passenger behavior, person-to-device mapping and other networked data such as the urban context, degradation of traffic etc.
Work in the field of automated driving and autonomous mobility requires many multi-faceted processes incorporating a variety of software tools. In particular, any software that will be used in a vehicle must undergo rigorous testing, increasingly including vehicle and traffic simulation, as part of the verification and validation (V&V) strategy.
One challenge the Bosch Autonomous Driving division faces is the toolchain for developing autonomous driving solutions becoming more complex by every level of automation. Well established tools are not well integrated for the use cases and it is easy to detect gaps in the overall toolchain. Instead of solving these challenges alone, wasting lots of money on the path, the Bosch division together with partners from the industry and related domains build up a community to solve the toolchain challenge together in the OpenADx ecosystem.