Authors:
Sagar Pathrudkar
1
;
Guido Schroeer
2
;
Vijaya Indla
1
and
Saikat Mukherjee
1
Affiliations:
1
Siemens Technology, India
;
2
Siemens Mobility, Germany
Keyword(s):
Traffic Analytics, Semantic Data Models, Driving Behavior, Real2Sim, Simulation-Based Testing, State Space Explosion.
Abstract:
Infrastructure elements would be crucial in enabling autonomous mobility at scale to provide centrally shared insights and possibly planning and control. Infrastructure mounted multi-sensor perception systems observe traffic and generate data in object list format which typically consists of timestamped vehicle trajectories and metadata about the vehicles, ie, their type, dimensions, etc. Such data is huge in volume and its analysis is difficult due to the spatiotemporal sequential nature of the data. In this work, we present framework and algorithms to semantically model and analyze this data in the context of map geometry to gain statistics and insights at an actionable level of abstraction. We start with algorithms to process common 2D-HDmap formats to extract map features - roads, lanes, junctions, etc. We then present meaningful traffic KPIs and statistics that describe traffic patterns. We finally describe methods to abstract the traffic patterns and driving behaviors into para
metrized functions for various applications.
(More)