Sensor Fusion in Autonomous Vehicles Webinar: Data for Free and Automated Parking

The October 27 webinar focuses on exciting new developments in sensor fusion for autonomous vehicles. Many current autonomous vehicle applications employ sensor fusion techniques relying on high-performance sensors that may come at some additional cost to equip a commercially available vehicle. But what can you get for free? Secondly, the relative low cost of radar makes it an attractive solution for some positioning applications, notably in this case automated parking in enclosed garages.

The webinar is sponsored by NovAtel.

GNSS/INS Sensor Fusion with On-Board Vehicle Sensors

The first presentation in this webinar focuses on the exploitation of lower-cost sensors already available on most modern vehicles. These sensors include low-resolution odometry (DMI) and consumer grade IMUs currently used for dynamic stability control and wheel slip detection. A novel approach for combining vehicle speed, steering angles, transmission settings and multiple odometry inputs demonstrates achievable results while operating under a GNSS-denied environment. The test trajectory mimics a typical parking structure with many corners and short straight segments. The only a priori information required for the filter is the wheel track and wheelbase (separation of wheels). A 90% performance improvement compared to the stand-alone GNSS/INS solution is logged during GNSS outages up to 30 minutes. The use of the extra input to the filter can improve protection levels of the positioning system to allow for more frequent engagement of the autonomous navigation system.

[Image above: Map View of 30-Minute GNSS Outage Performance, Mixed Driving Test, courtesy NovAtel]

Radar-based Multi-Floor Localization for Automated Valet Parking

The webinar’s second presentation demonstrates an integrated radar-based localization system that supports driving automation level 4 applications with a focus on automated valet parking in degraded visual environments in covered parking garages. The system integrates automotive radars and dead reckoning technologies supported by high-definition (HD) maps to offer decimeter-level positioning accuracy. Radar-based localization system was tested and validated in single and multi-floor underground parking lots. In the first case, the vehicle travels on a single floor and performs a parking maneuver on the far end of an underground parking location, then returns to the initial point. In the second case, the vehicle starts on the lower floor of a multi-floor parking building, then travels to the upper-floor before returning to the initial floor and performing a reverse parking maneuver. In both scenarios, the localization solution was consistent with the stringent requirements of driving automation level 4 applications.


Ryan Dixon is the Sensor Fusion and Autonomy Lead in NovAtel’s Applied Research group. In this role he is responsible for exploring sensor fusion methods and relating them to autonomy applications. Prior to this he was Chief Engineer of the SPAN GNSS/INS products group at NovAtel, responsible for the dedicated team maintaining and enhancing NovAtel’s inertial product portfolio.

Aboelmagd Noureldin received bachelor’s and Masters degrees in engineering physics from Cairo University and a Ph.D. in electrical and computer engineering from The University of Calgary. He is currently a Cross-Appointment Professor with the Departments of Electrical and Computer Engineering, Royal Military College of Canada, Queen’s University, Kingston, Ontario, Canada.

Source link