The iLoc workshop aims to address the localization integrity requirements of automated vehicles. The concept of integrity is defined as “a measure of trust which can be placed in the correctness of the information supplied by the total system”. In particular, it is a critical performance indicator for the navigation of highly automated vehicles (e.g., SAE L3 and above). To guarantee the safe driving of an AV in varying environments, measures of the localization information gathered from different sensors, such as LiDAR, IMU and GNSS, are required. Continuously and reliably estimating a vehicle’s position in varying driving environments is essential for autonomous driving and safe operation. However, dynamic and complex traffic environments make high-integrity localization very challenging in the vehicular domain. In our 2nd iLoc workshop, we want to emphasize the importance of integrity in ITS and address the scientific challenges in managing localization integrity for vehicle navigation in complex traffic environments, including its use as part of perception tasks.

Research Questions of Interest:

• What are the leading factors for high-integrity localization for AVs, e.g., road geometry, vehicle dimension, sensor accuracy, environmental factors, vehicle motion, and other road users?
• Which multi-sensor architectures and data fusion methods are best suited for autonomous driving?
• How to estimate the uncertainty and integrity risks applicable to model-based and data-driven approaches to localization?
• How can maps be used to increase localization integrity?
• How to combine a vehicle kinematic model and road geometry to improve integrity estimation? Is the sequence of AV’s maneuver tasks of driving from position A to B well defined?
• What are the integrity metrics needs for AVs? That is, in longitudinal, lateral, vertical (e.g., multi-level road interchanges), orientation (pitch, roll, and yaw angles).
• Are there any emergent standards applicable to the estimation of integrity in the Intelligent Transportation field?
• How to verify experimentally the system localization integrity when considering low risks? E.g., down to 10e-5 or below, and under numerous driving conditions?

Topics of Interest:

• Uncertainty propagation and updates while an AV drives in different environments.
• Novel algorithm and requirement definition for integrity, continuity, availability, and accuracy evaluation for intelligent transportation
• Map reference with its own integrity measure, including 2D digital map, high-definition map, 3D map/3D city model, even more precise survey map with both dynamic and static objects.
• Quantification and representation of the models’ aleatoric (or statistical) and epistemic (or systematic) uncertainties for both environmental perception and localization.
• Uncertainty estimation of LiDAR point clouds registration and imagery data processing in e.g., probabilistic and deep learning-based models.
• State-of-the-art deep learning multi-modal data fusion for e.g., GNSS, LiDAR point clouds, images, 3D map localization information with integrity estimation.

The ITSC 2023 conference will be held at the Euskalduna Conference Centre located in the center of Bilbao, Bizkaia, Spain.

Workshop room

0D.2

Getting there

You can get to the Euskalduna Congress Centre building by following these instructions:

By underground (metro):

The nearest stop is San Mamés (exit for Sabino Arana). From the exit, walk down Calle Sabino Arana towards the end of the street. The Euskalduna Conference Centre is in the other side of the roundabout. It is about a ten-minute walk.

By tram:

The nearest stop is Euskaduna, which is right by the Conference Centre building. It is about a one-minute walk.

By bus:

• Bilbobus: LINES 56, 62 and 28 stop in Gran Via 74/85, close to the Euskalduna Roundabout which is about a three-minute walk). Website for Bilbobus
• Bizkaibus (if coming from other municipalities of Bizkaia): Several lines stop at Bilbao Intermodal Bus station, which is at 8 minute walk from the venue, getting to the Sabino Arana avenue and going downwards. Website for Bizkaibus
• Bizkaibus (coming from the AIRPORT): Line A3247 can be used for getting from the airport to Bilbao City Centre. Buses depart every 20 minutes from the airport (3€ ride) and they stop in city centre (Moyua Square) but they also have stops in Gran Vía 79 (4 minutes from Euskalduna) and Bilbao Intermodal (8 minutes from Euskalduna) Status of the bus can be checked in real time.

By car:

The congress centre has its own parking.

By train:

• Renfe: Abando station has a link to the underground (you should take any underground train from the platform for trains bound for Plentzia) and the Abando tram stop is right near there (take a tram bound for Basurto). Should you wish to walk from this station to the Bizkaia Aretoa building, the journey would take just over 20 minutes.

• FEVE: La Concordia Station (also known as ‘Estación de Santander’) is next door to Abando Station, and therefore the same routes mentioned above can be used to reach the Bizkaia Aretoa building from here.

Arrivals at Bilbao Intermodal:

It is possible to walk to the Congress Centre from Bilbao Intermodal in about 10 minutes or else to take the tram bound for Atxuri from the San Mamés tram stop.

Airport Transfers:

• The airport is a short 25-minute drive from the heart of downtown Bilbao.
• Car rental companies offer on-site pickup options.
• Taxi service is available at the curb on the terminal just outside of Baggage Claim. The average taxi fare is about €30, although it could be increased on Sundays or night services.
• Uber and similar services do not operate in Bilbao
• Regional Bus Line A3247 can be used for getting from the airport to Bilbao City Centre. Buses depart every 20 minutes from the airport (3€ ride, last departure at 0:00, buy tickets in the “Bizkaibus” kiosk inside the terminal) and they stop in city centre (Moyua Square) but they also have stops in Gran Vía 79 (4 minutes from Euskalduna) and Bilbao Intermodal (8 minutes from Euskalduna) Status of the bus can be checked in real time.