Date: Thursday 22 March 2018
Time: 13:20 - 13:50
Location / Room: Saal 2
Chair:
Ayse Coskun, Boston University, US
During the last years a lot of prototypes for automated/autonomous driving vehicles have been presented to the public. Depending on the use case car manufacturers or tech companies have used an evolutionary or a revolutionary approach. While the evolutionary way should be more reasonable applied for owned cars due to cost restraints and the need for the functionality to work more or less by "something everywhere", the revolutionary approach following the strategy "everything somewhere" seems to be the better solution for fleets of autonomous cabs or shuttles. Although we have seen a lot of functional concepts for both approaches to automation, there are still some big challenges to be solved. On one hand the whole automation function has to be designed redundantly to ensure a sufficient functional safety level. In this context the use of Artificial Intelligence based networks could be a solution in particular neuronal networks based on deep learning. On the other hand there is still the question "how good is good enough" having in mind that perfectly working systems cannot be realized and how can the necessary verification/validation process be implemented. The public funded project PEGASUS is working to provide first answers. However: do we have considered all impacts of automated mobility?
| Time | Label | Presentation Title Authors |
|---|---|---|
| 13:20 | 11.0.1 | KEYNOTE SPEAKER Author: Thomas Form, Head of Electronics and Vehicle Research, Volkswagen AG, and co-ordinator of the Pegasus research project on safety of automated driving, DE Abstract During the last years a lot of prototypes for automated/autonomous driving vehicles have been presented to the public. Depending on the use case car manufacturers or tech companies have used an evolutionary or a revolutionary approach. While the evolutionary way should be more reasonable applied for owned cars due to cost restraints and the need for the functionality to work more or less by "something everywhere", the revolutionary approach following the strategy "everything somewhere" seems to be the better solution for fleets of autonomous cabs or shuttles. Although we have seen a lot of functional concepts for both approaches to automation, there are still some big challenges to be solved. On one hand the whole automation function has to be designed redundantly to ensure a sufficient functional safety level. In this context the use of Artificial Intelligence based networks could be a solution in particular neuronal networks based on deep learning. On the other hand there is still the question "how good is good enough" having in mind that perfectly working systems cannot be realized and how can the necessary verification/validation process be implemented. The public funded project PEGASUS is working to provide first answers. However: do we have considered all impacts of automated mobility? |
| 13:50 | End of session | |
| 15:30 | Coffee Break in Exhibition Area
On all conference days (Tuesday to Thursday), coffee and tea will be served during the coffee breaks at the below-mentioned times in the exhibition area (Terrace Level of the ICCD). Lunch Breaks (Großer Saal + Saal 1)On all conference days (Tuesday to Thursday), a seated lunch (lunch buffet) will be offered in the rooms "Großer Saal" and "Saal 1" (Saal Level of the ICCD) to fully registered conference delegates only. There will be badge control at the entrance to the lunch break area. Tuesday, March 20, 2018
Wednesday, March 21, 2018
Thursday, March 22, 2018
|