Description
This is a large, rich dataset derived from the interactions of large trucks and smaller 4WD vehicles in an industrial setting. The data were collected by a fleet of 13 vehicles operating in a surface mine during a period of 3 years. The dataset includes information about the vehicles’ state (e.g. position, speed and heading) as well as details of their peer-to-peer radio communications.
The data spans a period of 3 years with a resolution of 1 hertz. To the best of our knowledge, no other publicly-available dataset comes close to this level of detail over such a large time frame. The research possibilities and applications that that these data enable are unprecedented.
This dataset has already been used to examine map creation, analysis of safety, inference of driver intent and failure analysis of wireless network antennas.
Podcast
Listen to two of the authors talking about this dataset at the ITS Podcast.
Citation
When using this dataset please cite:
- J. Ward, S. Worrall, G. Agamennoni, and E. Nebot, “The Warrigal Dataset: Multi-Vehicle Trajectories and V2V Communications,” Intelligent Transportation Systems Magazine, IEEE, vol. 6, iss. 3, pp. 109-117, 2014. doi:10.1109/MITS.2014.2315660
[BibTeX] [Abstract]
Intelligent Transportation Systems rely on understanding, predicting and affecting the interactions between vehicles. Development of such systems must be based upon data derived from actual interactions if they are to be effective when used in real world applications. Increasingly, systems are being developed that are based on radio communication of state and intent between vehicles. Understanding of how these interactions occur is also necessary to creating robust systems. In order to test and compare new techniques, approaches and algorithms it is necessary to have a rich dataset to experiment with. This paper presents a detailed dataset useful for members of the Intelligent Transportation Systems community. It contains vehicle state information, vehicle-to-vehicle communications and road maps at high temporal resolution for large numbers of interacting vehicles over a long time period. This data set has already been used for a number of Intelligent Transportation Systems projects such as road mapping, driver intent prediction and collision avoidance among others.
@Article{ward2014warrigal, Title = {The Warrigal Dataset: Multi-Vehicle Trajectories and V2V Communications}, Author = {Ward, J. and Worrall, S. and Agamennoni, G. and Nebot, E.}, Journal = {Intelligent Transportation Systems Magazine, IEEE}, Year = {2014}, Month = {Fall}, Number = {3}, Pages = {109-117}, Volume = {6}, Abstract = {Intelligent Transportation Systems rely on understanding, predicting and affecting the interactions between vehicles. Development of such systems must be based upon data derived from actual interactions if they are to be effective when used in real world applications. Increasingly, systems are being developed that are based on radio communication of state and intent between vehicles. Understanding of how these interactions occur is also necessary to creating robust systems. In order to test and compare new techniques, approaches and algorithms it is necessary to have a rich dataset to experiment with. This paper presents a detailed dataset useful for members of the Intelligent Transportation Systems community. It contains vehicle state information, vehicle-to-vehicle communications and road maps at high temporal resolution for large numbers of interacting vehicles over a long time period. This data set has already been used for a number of Intelligent Transportation Systems projects such as road mapping, driver intent prediction and collision avoidance among others.}, Doi = {10.1109/MITS.2014.2315660}, ISSN = {1939-1390}, Keywords = {collision avoidance;intelligent transportation systems;radiocommunication;road vehicles;V2V communication;collision avoidance;driver intent prediction;intelligent transportation systems;multivehicle trajectory;radio communication;road mapping;road maps;robust system;temporal resolution;vehicle state information;vehicle-to-vehicle communication;warrigal dataset;Acceleration;Antennas;Electric vehicles;Global Positioning System;Intelligent vehicles;Traffic safety;Trajectory} }
Publications
Publications using this dataset include:
- G. Agamennoni, J. I. Nieto, and E. M. Nebot, “Robust and accurate road map inference,” in Robotics and Automation (ICRA), 2010 IEEE International Conference on, 2010, pp. 3946-3953. doi:10.1109/ROBOT.2010.5509778
[BibTeX] [Abstract]
Over the last ten years, electronic vehicle guidance systems have become increasingly popular. However, their performance is subject to the availability and accuracy of digital road maps. Most current digital maps are still inadequate for advanced applications in unstructured environments. Lack of detailed up-to-date information and insufficient accuracy and refinement of the road geometry are among the most important shortcomings. The massive use of inexpensive GPS receivers, combined with the rapidly increasing availability of wireless communication infrastructure, suggests that large volumes of data combining both modalities will be available in a near future. The approach presented here draws on machine learning techniques to process logs of position traces to consistently build a detailed and accurate representation of the road network and, more importantly, extract the actual paths followed by vehicles. Experimental results with data from large mining operations are presented to validate the algorithm.
@InProceedings{Agamennoni09, Title = {Robust and accurate road map inference}, Author = {Agamennoni, G. and Nieto, J.I and Nebot, E.M.}, Booktitle = {Robotics and Automation (ICRA), 2010 IEEE International Conference on}, Year = {2010}, Month = {May}, Pages = {3946-3953}, Abstract = {Over the last ten years, electronic vehicle guidance systems have become increasingly popular. However, their performance is subject to the availability and accuracy of digital road maps. Most current digital maps are still inadequate for advanced applications in unstructured environments. Lack of detailed up-to-date information and insufficient accuracy and refinement of the road geometry are among the most important shortcomings. The massive use of inexpensive GPS receivers, combined with the rapidly increasing availability of wireless communication infrastructure, suggests that large volumes of data combining both modalities will be available in a near future. The approach presented here draws on machine learning techniques to process logs of position traces to consistently build a detailed and accurate representation of the road network and, more importantly, extract the actual paths followed by vehicles. Experimental results with data from large mining operations are presented to validate the algorithm.}, Doi = {10.1109/ROBOT.2010.5509778}, ISSN = {1050-4729}, Keywords = {Global Positioning System;cartography;data mining;driver information systems;learning (artificial intelligence);GPS receivers;data mining;digital road maps;electronic vehicle guidance systems;machine learning techniques;road geometry;road map inference;wireless communication infrastructure;Availability;Data mining;Global Positioning System;Information geometry;Machine learning;Navigation;Roads;Robustness;Vehicles;Wireless communication} }
- G. Agamennoni, S. Worrall, J. Ward, and E. Nebot, “Robust non-linear smoothing for vehicle state estimation,” in Intelligent Vehicles Symposium (IV), 2013 IEEE, 2013, pp. 156-162. doi:10.1109/IVS.2013.6629464
[BibTeX] [Abstract]
This paper presents a robust, non-linear smoothing algorithm and develops the theory behind it. This algorithm is extremely robust to outliers and missing data and handles state-dependent noise. Implementing it is straightforward as it consists mainly of two sub-routines: (a) the Rauch-Tung-Striebel recursions, or Kalman smoother; and (b) a backtracking line search strategy. The computational load grows linearly with the number of data because the algorithm preserves the underlying structure of the problem. Global convergence to a local optimum is guaranteed, under mild assumptions.
@InProceedings{Agamennoni13, Title = {Robust non-linear smoothing for vehicle state estimation}, Author = {Agamennoni, G. and Worrall, S. and Ward, J. and Nebot, E.}, Booktitle = {Intelligent Vehicles Symposium (IV), 2013 IEEE}, Year = {2013}, Month = {June}, Pages = {156-162}, Abstract = {This paper presents a robust, non-linear smoothing algorithm and develops the theory behind it. This algorithm is extremely robust to outliers and missing data and handles state-dependent noise. Implementing it is straightforward as it consists mainly of two sub-routines: (a) the Rauch-Tung-Striebel recursions, or Kalman smoother; and (b) a backtracking line search strategy. The computational load grows linearly with the number of data because the algorithm preserves the underlying structure of the problem. Global convergence to a local optimum is guaranteed, under mild assumptions.}, Doi = {10.1109/IVS.2013.6629464}, ISSN = {1931-0587}, Keywords = {convergence;road vehicles;search problems;smoothing methods;state estimation;Kalman smoother;Rauch-Tung-Striebel recursions;backtracking line search strategy;global convergence;robust nonlinear smoothing algorithm;state-dependent noise;vehicle state estimation;Approximation methods;Convergence;Global Positioning System;Robot sensing systems;Robustness;Smoothing methods;Vehicles} }
- M. Shan, S. Worrall, and E. Nebot, “Probabilistic Long-Term Vehicle Motion Prediction and Tracking in Large Environments,” Intelligent Transportation Systems, IEEE Transactions on, vol. 14, iss. 2, pp. 539-552, 2013. doi:10.1109/TITS.2012.2224657
[BibTeX] [Abstract]
Vehicle position tracking and prediction over large areas is of significant importance in many industrial applications, such as mining operations. In a small area, this can easily be achieved by providing vehicles with a constant communication link to a control center and having the vehicles broadcast their position. The problem dramatically changes when vehicles operate within a large environment of potentially hundreds of square kilometers and in difficult terrain. This paper presents algorithms for long-term vehicle motion prediction and tracking based on a multiple-model approach. It incorporates a probabilistic vehicle model that includes the structure of the environment. The prediction algorithm evaluates the vehicle position using acceleration, speed, and timing profiles built for the particular environment and considers the probability that the vehicle will stop. A limited number of data collection points distributed around the field are used to update the vehicle position estimate when in communication range, and prediction is used at points in between. A particle filter is used to estimate the vehicle position using both positive and negative information (whether communication is possible) in the fusion stage. The algorithms presented are validated with experimental results using data collected from a large-scale mining operation.
@Article{Shan2013, Title = {Probabilistic Long-Term Vehicle Motion Prediction and Tracking in Large Environments}, Author = {Mao Shan and Worrall, S. and Nebot, E.}, Journal = {Intelligent Transportation Systems, IEEE Transactions on}, Year = {2013}, Month = {June}, Number = {2}, Pages = {539-552}, Volume = {14}, Abstract = {Vehicle position tracking and prediction over large areas is of significant importance in many industrial applications, such as mining operations. In a small area, this can easily be achieved by providing vehicles with a constant communication link to a control center and having the vehicles broadcast their position. The problem dramatically changes when vehicles operate within a large environment of potentially hundreds of square kilometers and in difficult terrain. This paper presents algorithms for long-term vehicle motion prediction and tracking based on a multiple-model approach. It incorporates a probabilistic vehicle model that includes the structure of the environment. The prediction algorithm evaluates the vehicle position using acceleration, speed, and timing profiles built for the particular environment and considers the probability that the vehicle will stop. A limited number of data collection points distributed around the field are used to update the vehicle position estimate when in communication range, and prediction is used at points in between. A particle filter is used to estimate the vehicle position using both positive and negative information (whether communication is possible) in the fusion stage. The algorithms presented are validated with experimental results using data collected from a large-scale mining operation.}, Doi = {10.1109/TITS.2012.2224657}, ISSN = {1524-9050}, Keywords = {control engineering computing;mining industry;mobile communication;off-road vehicles;particle filtering (numerical methods);sensor fusion;traffic engineering computing;acceleration profiles;communication range;control center;fusion stage;industrial applications;large-scale mining operation;particle filter;probabilistic long-term vehicle motion prediction;probabilistic long-term vehicle motion tracking;speed profiles;timing profiles;vehicle position tracking;Acceleration;Correlation;Motion segmentation;Roads;Timing;Tracking;Vehicles;Long-term motion prediction;negative information;particle filtering;statistical model;vehicle tracking} }
- J. Ward, S. Worrall, G. Agamennoni, and E. Nebot, “Vehicle operation safety monitoring using context based metrics: A case study,” in Intelligent Vehicles Symposium Workshops (IV Workshops), 2013 IEEE, 2013, pp. 19-24. doi:10.1109/IVWorkshops.2013.6615220
[BibTeX] [Abstract]
This paper presents results of the deployment of vehicle safety systems developed by the Intelligent Vehicles and Safety Systems Group at the Australian Centre for Field Robotics. The technology was deployed within an active mine site in Australia undergoing standard open-cut mining operations. Data were collected from the vehicles and analysed in order to assess the overall safety and performance of the vehicle operations within the mine. Metrics calculated include distributions of vehicle paths along stretches of road for driving line analysis, and statistics around vehicle events such as overspeed and proximity to other vehicles.
@InProceedings{Ward13, Title = {Vehicle operation safety monitoring using context based metrics: A case study}, Author = {Ward, J. and Worrall, S. and Agamennoni, G. and Nebot, E.}, Booktitle = {Intelligent Vehicles Symposium Workshops (IV Workshops), 2013 IEEE}, Year = {2013}, Month = {June}, Pages = {19-24}, Abstract = {This paper presents results of the deployment of vehicle safety systems developed by the Intelligent Vehicles and Safety Systems Group at the Australian Centre for Field Robotics. The technology was deployed within an active mine site in Australia undergoing standard open-cut mining operations. Data were collected from the vehicles and analysed in order to assess the overall safety and performance of the vehicle operations within the mine. Metrics calculated include distributions of vehicle paths along stretches of road for driving line analysis, and statistics around vehicle events such as overspeed and proximity to other vehicles.}, Doi = {10.1109/IVWorkshops.2013.6615220}, Keywords = {Global Positioning System;automated highways;data analysis;road safety;road vehicles;safety systems;Australian Centre for Field Robotics;GPS;Intelligent Vehicles and Safety Systems Group;active mine site;context based metrics;data analysis;driving line analysis;open-cut mining operations;vehicle events;vehicle operation safety monitoring system;vehicle paths;Global Positioning System;Measurement;Monitoring;Roads;Safety;Standards;Vehicles} }
Download
Demonstration MatLab scripts. Includes instructions for use.
