Registration for this competition is closed
About the competition:
The participants will be provided with data from a road construction site in Viken including GPS data from dump trucks, machine data including daily fuel consumption, and drone maps of the construction site. In addition, we have a small dataset of vibration data from a subset of dumpers, and of course public data such as weather, maps etc.
The challenge is to demonstrate how the data can be exploited for road construction to become more sustainable. Sustainability can be interpreted as directly reduced emission, but also as minimizing construction time and impact on the surroundings. The current status is that many processes are manually controlled, and could benefit from automated decision support: This can for example be obtained through:
- Reduction of idle time
- Optimal flow of dump trucks on the construction site
- Minimization of unnecessary driving
- Optimal driving style with minimal acceleration
- Automated classification of road types for improved planning
- Automated progress reports
- Automated detection of load cycles (when excavators fill the dumpers)
- …
Registration for this competition has been closed. Contact birte.hansen@nora.ai for more information.
Description of tasks:
The aim of the competition is to demonstrate how road construction can become more sustainable through use of data. Sustainability in this sense can be interpreted as directly reduced emission, but also as minimizing construction time and impact on the surroundings. At the same time, suggested improvements must be feasible and based on data that can be collected automatically.
- Develop an algorithm to improve sustainability - demonstrate the potential for improved sustainability impact from using data.
- Provide a deployment plan - describe system and data requirements as well as potential challenges for deployment. Are there any ethical issues?
- Transparency - evaluate the transparency of the developed system including explanations for how the models were trained, interpretation of predictions, risk assessment and clear guidelines for usage.
- Write a 2 pager for submission to NMI summarizing task 1, 2 and 3. Author guidelines NMI.
We recommend an exploratory approach when solving the set tasks and encourage innovation when developing solutions.
To compete for the prize money all four tasks are mandatory. Submissions of only one sub task are allowed, but will not be eligible for winning any of the prizes.
About the data:
The main data set contains data from March, April and May in 2022.
This data is no longer available.
GPS data
The GPS data is recorded from ipads in the dumpers and trucks. They report timestamp, machine ID, location, type and amount of material being moved, and where the material is being loaded and unloaded. The latter are manually recorded through the driver interacting with an app on the ipads, and hence there is some uncertainty related to when they actually record loading and unloading. The unloading is usually associated with reversing the dumper and tipping the load, and the actual location can often be inferred from the GPS track (automation of dump and load points are suggested tasks in the challenge). The data is divided into trips, where one trip contains the cycle of loading, driving the load, dumping, and driving to pick up a new load. The vehicle might return to the same loading place, or another loading location. There are two folders each containing one file per date: one for the gps pings (trips) and one for the metadata (tripsInfo) about the trips.
The trips data contains the following columns:
- TripLogId (One unique ID per trip)
- Timestamp (Time of GPS ping)
- Latitude
- Longitude
- Uncertainty (the real position should be within this radius of the recorded position. Units is meters)
The metadata contains the following columns:
- TripLogId (same ID as in the trip data)
- DumperMachineNumber (One unique number per machine)
- MachineType (Dumper or truck)
- LoadLongitude
- LoadLatitude
- DumpLongitude
- DumpLatitude
- MassTypeMaterial
- Quantity (Amount being transported in tons)
Machine data (AEMP)
In addition, we provide daily reports (called AEMP) from a set of machines with location, odometer, fuel consumption and hours used. These are only available from Skanska-owned machines whereas the GPS data are available for all machines working on the project. The only way to match machine and GPS data is via timestamps and locations.
The machine data contains the following columns:
- Datetime - Time stamp
- Make - Brand of machine
- ID - Anonymized unit id
- Latitude, Longitude - Coordinates when sending data
- Hour - Number of hours the machine has been in use given as days, hours, minutes, seconds
- FuelConsumed or FuelConsumedLast24 - Total accumulated fuel consumption or consumed within last 24 hours
- FuelUnits or FuelUnitsLast24 - Units of fuel consumption
- Odometer - Accumulated distance driven
- OdometerUnits - Units of distance driven
Vibration data
We have news regarding the vibration data. It seems that the data indeed is duplicated, and that each team must clean it themselves. Each data point occurs 7 times.
As for the data being the same for the two days, there was probably an error when we uploaded the data.
For a shorter period in April 2023 we also recorded vibration data from the ipads. These are recorded at 15 Hz and contain three-dimensional vibration data as described in the Apple Core Motion documentation here https://developer.apple.com/documentation/coremotion/getting_raw_accelerometer_events.
These vibration data have not been analyzed in detail before. The transmission of vibration data takes up a significant amount of the available bandwidth to be feasible for all machines at all times. Hence, any practical use of these data will require either (pre-)processing on the ipads (computational limitations) or reduction in data to be submitted (lower frequency or fewer variables).
The vibration data is given in hdf files, they can be read using for instance pandas.read_hdf funtion. The name of the file gives the TripLogId of the data. If there is several files for one TripLogId there is an added _{number} to the filename. The following columns are not relevant: EventId', 'RetryCount', 'AppVersion', 'DumperId', 'Heading, "TrackingEventID", "MagneticFiled","Type"
For better understanding of the variables in these data, click here.
Drone data
We also provide drone data from the unloading area where the mass is being dumped. They are created with the commercial ArcGIS Site Scan software and consist of ortho-mosaic image data (tiff file format), point clouds (LAZ data format), mesh data (slpk file format), digital terrain models (tiff image with altitude information) and digital surface model (tiff image with altitude information). These data can for example be used to develop automated progress reports.One file is provided with a single day of data and one with all available data for the period (>20 Gb)
Open data
In addition, all public data can be used to accompany the provided data, including data from other countries.
Examples include maps (for example Open Streetmap or NVE’s theme maps https://kartkatalog.nve.no/#kart) or weather (met.no)
Reasonable assumptions about the construction site
- Excavators have almost infinite mass to move. Very likely that they will contribute to the same task over many days.
- The long term plan is not digitally available
- No one will use the system if you have to type a lot of extra information manually
Submission Guidelines & Evaluation:
Each team should submit a visual presentation (type of video max 3 min, website, slides, flyer) and a jupyter notebook or similar which demonstrates the algorithm. The notebook needs to be submitted both as executable code where the path to the raw data is set at the top and as a pdf with all outputs.
The jury will evaluate the submissions based on the novelty and innovation of the algorithm, feasibility of implementing the algorithm and the sustainable impact of the algorithm. The jury will also review the 2 page paper (including references) describing the results of the competition. To compete for the prize awards all tasks are mandatory. Submission of only one sub-task is allowed, but will not be eligible for winning any of the prizes. The tasks encourage an exploratory and innovative approach - there are no wrong answers per se!
Once you are ready to submit, please email birte.hansen@nora.ai and she will provide a drive folder for you to upload your files.
If you have any questions, please email Birte Hansen (birte.hansen@nora.ai).
An overview article over the RoadAI Competition and datasets is published in the Nordic Machine Intelligence Journal.
Prize:
The winning team will be announced at the NordicAIMeet, which will take place in Copenhagen 2023.
1st prize:
- 35 000 NOK
- Appointed mentors from Skanska and Startuplab to commercialize idea
2nd prize:
- 15 000 NOK
Important dates:
- June 1st - Kick off webinar
- 14th of August - Q&A webinar
- 10th of September - submission deadline
- 2-3 October - Nordic AI Meet
Registration for this competition has been closed. Contact birte.hansen@nora.ai for more information.
RoadAI Partners
- Skanska
- SINTEF
- NORA.ai
- NEMONOOR
- Nordic Machine Intelligence Journal
- Posten
- Norwegian AI Cloud
- Ditio
RoadAI Team
- Lars Horn, Chief Digital Advisor, Skanska
- Signe Riemer-Sørensen, Research Manager and Senior Researcher, SINTEF Digital
- Helga Margrete Bodahl Holmestad, Research Scientist, SINTEF Digital,
- Katarzyna Michalowska, PhD Fellow, SINTEF Digital
- Heidi Dahl, Senior Data Scientist, Posten
- Bjørn Jostein Singstad, Researcher, Oslo University Hospital and University of Oslo. Responsible for Nordic Machine Intelligence Journal
- Sabry Razick, Chief Engineer, Scientific Computing Services University of Oslo, Norwegian AI Cloud
- Jacob Christian Døskeland, CTO, Ditio
Contact:
For any questions, please contact Birte Hansen (birte.hansen@nora.ai)