Designing a Roadside Sensor Infrastructure to Support Automated Driving

Abstract

Automation of complex traffic scenarios is expected to rely on input from a roadside infrastructure to complement the vehicles' environment perception. We here explore design requirements for a prototypical setup of virtual vision or RADAR sensors along one roadside. Explicitly, we analyze the road coverage and the probability of vehicle occlusions, with the objective of evaluating the completeness of information that is captured by the sensor field. Simulation case studies are performed based on real traffic data acquired at the German Autobahn 9 near Munich. Our findings indicate how the sensor network should be designed in terms of sensor range, orientation and opening angle, in order to enable effective traffic detection. The achieved degree of completeness suggests that such a setup could be used to support automated vehicles to a substantial extent.

A Plausibility-Based Fault Detection Method for High-Level Fusion Perception Systems

“…This scenario of highway surveillance by a network of Radar sensors is guided by long-term observations within the KoRA9 project [7], [15]. In our setup, a four-lane road segment of about 600m is monitored by 12 Radars at a separation of 50m, where we discard the first and last sensor for the statistics to minimize finite size effects, see Fig.…”

“…The adopted highway traffic model features various vehicle classes such as cars, trucks, buses, and generates speed, lane, and type distributions based on realistic highway statistics [33]. Vehicle maneuvers such as overtaking are neglected here since they do not impact the observation quality significantly, see also [7]. Fig.…”

“…Uncertainties are handled within the Dempster-Shafer (DS) theory of evidence [13], [14]. Besides an instantaneous plausibility assessment, we provide with statistical metrics Figure 1: An example experiment performed in the KoRA9 project, see also [7]. (Left) Object tracks accumulated over time at a highway test segment.…”

Optimized sensor placement for dependable roadside infrastructures

“…We illustrate our method for the following scenarios. 1) Scenario 1 -Multi-lane highway: Similar to the setup in [24], the scenario of a four-lane motorway to be monitored by mid-range radar sensors is considered. In the case of right-hand side road traffic, the lanes to the right (the bottom in Fig.…”

Analysis of the Impact of Road Safety Barriers on Reducing the Risk of Dangerous Road Accidents and Their Consequences

“…Aktualnie, zapewnienie bezpieczeństwa ruchu drogowego, zwłaszcza autonomicznych pojazdów, proponuje się realizować poprzez nieprzerwany nadzór drogowy siecią odpowiedniej konfiguracji wirtualnej wizji lub czujników radarowych, wzdłuż jednego pobocza drogi [14]. W ostatnich latach zyskały wysoki priorytet ochrony bezpieczeństwa; pojazdowe systemy wczesnego ostrzegania VANET (Vehicular ad-hoc networks), WiMAX (World interoperability for microwave access), Android, AES (Advanced encryption standard).…”