Abstract | ||
---|---|---|
For the identification of scenarios in real-world testdrive data (scenario mining) knowledge about the road, the vehicle drives on, is required because the set of possible scenarios varies according to the road type. Since these scenarios are needed for the scenario-based validation of automated driving functions, a robust approach for road membership estimation is vital.For that purpose, the vehicle location is estimated using a particle filter and mapped on a digital map providing the required road information. But, since particle filter-based solutions lack precision in ambiguous situations, reliable road membership estimation is not possible.In this work, a map matching framework is proposed to provide high accuracy and complete trajectories of vehicle poses by utilizing particle filter for vehicle localization and a directed acyclic graph of mapped roads (DAGMaR). The presented approach is evaluated with an inner-city, a mixed and a motorway drive showing promising results. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/IOTSMS48152.2019.8939213 | 2019 Sixth International Conference on Internet of Things: Systems, Management and Security (IOTSMS) |
Keywords | Field | DocType |
map matching,scenario mining,automated driving,particle filter,monte carlo localization | Data mining,Computer science,Particle filter,Computer network,Directed acyclic graph,Monte Carlo localization,Map matching | Conference |
ISBN | Citations | PageRank |
978-1-7281-2950-1 | 0 | 0.34 |
References | Authors | |
14 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lars Klitzke | 1 | 0 | 0.34 |
Johannes Meyer | 2 | 3 | 4.82 |
Tilman Leune | 3 | 0 | 0.34 |
Carsten Koch | 4 | 0 | 0.34 |
Frank Koester | 5 | 0 | 0.34 |