CommonRoad: Composable benchmarks for motion planning on roads
Open accessThe DOI matches its Crossref record; 51 of the 52 references it cites were found in a registry or an index.
Abstract
Numerical experiments for motion planning of road vehicles require numerous components: vehicle dynamics, a road network, static obstacles, dynamic obstacles and their movement over time, goal regions, a cost function, etc. Providing a description of the numerical experiment precise enough to reproduce it might require several pages of information. Thus, only key aspects are typically described in scientific publications, making it impossible to reproduce results - yet, re-producibility is an important asset of good science. Composable benchmarks for motion planning on roads (CommonRoad) are proposed so that numerical experiments are fully defined by a unique ID; all information required to reconstruct the experiment can be found on the CommonRoad website. Each benchmark is composed by a vehicle model, a cost function, and a scenario (including goals and constraints). The scenarios are partly recorded from real traffic and partly hand-crafted to create dangerous situations. We hope that CommonRoad saves researchers time since one does not have to search for realistic parameters of vehicle dynamics or realistic traffic situations, yet provides the freedom to compose a benchmark that fits one's needs.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“With the exception of nuPlan and CommonRoad [12], all datasets focus on prediction (motion forecasting).”
From Towards learning-based planning: The nuPlan benchmark for real-world autonomous driving (2024) · cites this paper as [12]
In the citing paper
“However, CommonRoad [12] does not provide a real world dataset as the basis for the simulation, instead resorting to a small number of manually crafted scenarios and tools to import other datasets, albeit without any sensor data.”
From Towards learning-based planning: The nuPlan benchmark for real-world autonomous driving (2024) · cites this paper as [12]
Citations
Cites
Vision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 1×
“One of the most successful automotive benchmarks is the KITTI benchmark targeting computer vision [24].”
BackgroundRajamani, R. (2012) · Mechanical Engineering Series · doi:10.1007/978-1-4614-1433-9 · Cited by 4,401
A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles
Paden, B., Cap, M., Yong, S. Z., Yershov, D., & Frazzoli, E. (2016) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2016.2578706 · Cited by 2,585 · cited 1×
“Tire slip is not considered, but the kinematic singletrack model can be used when the vehicle does not operate close to its physical capabilities [26], [35].”
BackgroundThe Open Motion Planning Library
Sucan, I. A., Moll, M., & Kavraki, L. E. (2012) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2012.2205651 · Cited by 1,616 · cited 1×
“…but the data has never been or is no longer publicly available, e.g. [13]–[15]. c) Motion planning libraries: One of the most successful motion planning libraries in robotics is the Open Motion Planning Library (OMPL) [16], which implements many of the most important sampling-based approaches.”
BackgroundOptimal paths for a car that goes both forwards and backwards
Reeds, J., & Shepp, L. (1990) · Pacific Journal of Mathematics · doi:10.2140/pjm.1990.145.367 · Cited by 1,447 · cited 1×
“We have not included Dubin or Reeds-Shepp cars since they require changing the steering angle infinitely fast (see e.g. [31]).”
BackgroundCHOMP: Gradient optimization techniques for efficient motion planning
Ratliff, N., Zucker, M., Bagnell, J. A., & Srinivasa, S. (2009) · 2009 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2009.5152817 · Cited by 992 · cited 1×
“…techniques, there also exists the Covariant Hamiltonian Optimization for Motion Planning (CHOMP) library for gradient-based optimization techniques [23]. d) Automotive benchmarks beyond motion planning: One of the most successful automotive benchmarks is the KITTI benchmark targeting computer…”
BackgroundOptimal trajectory generation for dynamic street scenarios in a Frenét Frame
Werling, M., Ziegler, J., Kammel, S., & Thrun, S. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509799 · Cited by 801 · cited 2×
“• Acceleration : [44, Sec.”
Automated vehicle control developments in the PATH program
Shladover, S. E., Desoer, C. A., Hedrick, J. K., Tomizuka, M., Walrand, J., Zhang, W.-B., McMahon, D. H., Peng, H., Sheikholeslam, S., & McKeown, N. (1991) · IEEE Transactions on Vehicular Technology · doi:10.1109/25.69979 · Cited by 786 · cited 1×
“For adaptive cruise control in particular, numerous works already exist that realize a commanded acceleration, see e.g. [27], [28].”
BackgroundA system for learning statistical motion patterns
Hu, W., Xiao, X., Fu, Z., Xie, D., Tan, T., & Maybank, S. (2006) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2006.176 · Cited by 544 · cited 1×
“Another class of works provides results on recorded data, but the data has never been or is no longer publicly available, e.g. [13]–[15]. c) Motion planning libraries: One of the most successful motion planning libraries in robotics is the Open Motion Planning Library (OMPL) [16], which implements…”
BackgroundPunzo, V., Borzacchiello, M. T., & Ciuffo, B. (2011) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2010.12.007 · Cited by 484 · cited 1×
“One of the most popular datasets of recorded traffic participants is from the Next Generation Simulation (NGSIM) program [10], [11].”
Background
Research works printed but not linked: 5
- dillmann, 2004, Benchmarks for robotics research, Deliverable KA 1 10 of the EU project EURON
- nowak, 2010, Benchmarks for mobile manipulation and robust obstacle avoidance and navigation, Deliverable D3 1 of EU Project Best Practice in Robotics (BRICS)
- pfeiffer, 2007, Action plan and recommendation on benchmarks for mobile manipulation and service robots, Deliverable D4 3 of the EU project Robot Standards and Reference Architectures (RoSta)
- 2011, MSC Software, 2 MacArthur Place, Santa Ana, CA 92707, Adams/Tire Help
- werling, 2010, Optimal trajectory generation for dynamic street scenarios in a frenet frame, Proc of the IEEE International Conference on Robotics and Automation, 987
Cited by
A Survey of Autonomous Driving: Common Practices and Emerging Technologies
Yurtsever, E., Lambert, J., Carballo, A., & Takeda, K. (2020) · IEEE Access · doi:10.1109/access.2020.2983149 · Cited by 1,889
“are referred to sources for details of the datasets. DDD17 [89] around 12 hours of driving data is recorded. The LiVi-Set [281] is a new dataset that has lidar, image and driving behavior. CommonRoad [294] is a new benchmark for motion-planning. Naturalistic driving data is another type of dataset that concentrates on…”
BackgroundA Review of Motion Planning for Highway Autonomous Driving
Claussmann, L., Revilloud, M., Gruyer, D., & Glaser, S. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2913998 · Cited by 670
“thanks to the open source scenario library developed by [196]”
BackgroundNuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclesPreprint
Caesar, H., Kabzan, J., Tan, K. S., Fong, W. K., Wolff, E. M., Lang, A., Fletcher, L., Beijbom, O., & Omari, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.11810 · Cited by 789
Survey on Scenario-Based Safety Assessment of Automated Vehicles
Riedmaier, S., Ponn, T., Ludwig, D., Schick, B., & Diermeyer, F. (2020) · IEEE Access · doi:10.1109/access.2020.2993730 · Cited by 481
“The Commonroad Framework [44], which includes not only scenarios but also models and cost functions, seems to be a good starting point for benchmarking.”
BackgroundDawson, C., Gao, S., & Fan, C. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3232542 · Cited by 269
“We use the single-track car model from the CommonRoad benchmarks [89].”
MethodInfluential
Metadata
- Authors
- Althoff, M., Koschi, M., & Manzinger, S.
- Venue
- 2017 IEEE Intelligent Vehicles Symposium (IV)
- Publisher
- IEEE
- Published
- 2017-06
- Pages
- 719-726
- ISSN
- 1931-0587 (ISSN-L)
- OpenAlex
- W2740508249
- Cited by
- 443
- References
- 52
- Citations by year
- 2026: 29 · 2025: 87 · 2024: 86 · 2023: 60 · 2022: 47 · 2021: 49 · 2020: 38 · 2019: 18 · 2018: 23 · 2017: 6
- FWCI
- 6.80
- Type
- conference paper
- Language
- en
- Open access
- green
- mediatum.ub.tum.de
- Licence
- other-oa
- Locations
- IEEE Intelligent Vehicles Symposium (publishedVersion)
- mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robotic Path Planning Algorithms
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Engineering › Control and Systems Engineering › Traffic control and management
- Keywords
- reproducibility, vehicle dynamics modeling, dynamic obstacles, cost function, autonomous driving
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: CommonRoad: Composable benchmarks for motion planning on roads. https://app.cochat.ai/papers/10.1109/ivs.2017.7995802
- The paper
- Althoff, M., Koschi, M., & Manzinger, S. (2017). CommonRoad: Composable benchmarks for motion planning on roads. 2017 IEEE Intelligent Vehicles Symposium (IV). https://doi.org/10.1109/ivs.2017.7995802
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.