@inproceedings{TolksdorfBirknerTejadaetal.2024, author = {Tolksdorf, Leon and Birkner, Christian and Tejada, Arturo and Van De Wouw, Nathan}, title = {Fast Collision Probability Estimation for Automated Driving using Multi-circular Shape Approximations}, booktitle = {2024 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-4881-1}, doi = {https://doi.org/10.1109/IV55156.2024.10588731}, pages = {2529 -- 2536}, year = {2024}, language = {en} } @inproceedings{TolksdorfTejadavandeWouwetal.2023, author = {Tolksdorf, Leon and Tejada, Arturo and van de Wouw, Nathan and Birkner, Christian}, title = {Risk in Stochastic and Robust Model Predictive Path-Following Control for Vehicular Motion Planning}, booktitle = {IEEE IV 2023: Symposium Proceedings}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-4691-6}, doi = {https://doi.org/10.1109/IV55152.2023.10186708}, year = {2023}, language = {en} } @inproceedings{WeihmayrSezginTolksdorfetal.2024, author = {Weihmayr, Daniel and Sezgin, Fatih and Tolksdorf, Leon and Birkner, Christian and Jazar, Reza}, title = {Predicting the Influence of Adverse Weather on Pedestrian Detection with Automotive Radar and Lidar Sensors}, booktitle = {2024 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-4881-1}, doi = {https://doi.org/10.1109/IV55156.2024.10588472}, pages = {2591 -- 2597}, year = {2024}, language = {en} } @unpublished{TolksdorfTejadaBauernfeindetal.2026, author = {Tolksdorf, Leon and Tejada, Arturo and Bauernfeind, Jonas and Birkner, Christian and van de Wouw, Nathan}, title = {Risk Estimation for Automated Driving}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2601.15018}, year = {2026}, language = {en} } @phdthesis{Tolksdorf2026, author = {Tolksdorf, Leon}, title = {Risk-Based Motion Planning in Automated Vehicles}, publisher = {Eindhoven University of Technology}, address = {Eindhoven}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:573-65845}, pages = {xv, 175}, school = {Eindhoven University of Technology}, year = {2026}, abstract = {It is anticipated that there will be a long period where automated vehicles (AVs) and human road users share the same road network, with limited communication between them. As a result, AVs often operate with uncertain knowledge of their surroundings due to limitations in both sensing and estimation of the traffic scenario's current and future states. These limitations can be caused by factors such as noisy sensor data or lack of information about the intentions of other road users. Accounting for this uncertainty while designing motion planning and control algorithms for AVs is critical, as an AV may display hazardous behavior if it is overly confident in falsely estimated environment states or, contrarily, may act too cautiously when considering unnecessarily large safety margins in estimated states. Although safety regulations call for taking uncertainty into account, the right means to integrate uncertainty in motion planning has yet to be agreed upon. A promising way to account for uncertainty is through the concept of risk. Risk accounts for uncertainty in assessing safety by considering both the likelihood and severity of unsafe events, such as collisions. Research has shown that human drivers navigate traffic by trading off subjectively perceived risk against the potential rewards of reaching their destinations. Additionally, studies indicate that subjective risk tends to correlate with objective risk measures, while ethicists argue that risk can be used as a means to facilitate ethicality in road traffic by distributing risk fairly among road users. These relationships highlight the benefits of incorporating risk as a proxy for generating AV behavior in motion planning algorithms, by accounting for uncertainty in unsafe events. Incorporating risk in AV motion planning presents two main challenges. The first challenge is to develop a notion of risk that correctly incorporates an AV's uncertainty about the future motion of other road users, and that can be computed fast (and precisely) enough to be used in online (i.e., real-time) motion-planning algorithms. The second challenge is to develop an appropriate AV motion planning algorithm that incorporates risk and generates the desired AV behavior, facilitating ethicality. This dissertation addresses both challenges by making six main contributions. First, we introduce a suitable risk metric: the expected severity of a collision event. This metric, thus, is constituted of two terms, one accounting for the likelihood of a collision and another term considering the severity of a collision. Second, we investigate the AV behavior given different optimization-based motion planning strategies that accommodate our risk metric. We find that a stochastic model predictive control (SMPC)-based motion planner adequately balances risk with travel efficiency in the presence of varying uncertainty. \\Third, to compute risk, we provide an computationally efficient (i.e., real-time computable) algorithm to estimate risk. Here, the focus lies on estimating the probability of collision (POC), as our risk metric reduces to a POC metric when the severity term is considered constant. Based on multi-circular shape approximations of the geometries of the AV and other road users, we present an algorithm that estimates the POC with good precision, and that is guaranteed not to under-approximate it. The algorithm is shown to execute significantly faster than standard Monte Carlo sampling, while being tailored for optimization-based motion planning strategies. In our SMPC-based motion planning strategy, it is shown to generate smooth, reproducible trajectories under varying levels of uncertainty. Fourth, we extend our POC algorithm to risk estimation. Here, we propose a severity estimation method that allows us to consider different collision constellations, as literature shows that those are associated with different levels of harm to the passengers of vehicles. The resulting risk estimation algorithm leverages the advantages of the POC estimation algorithm, i.e., its particular suitability for optimization-based motion planning strategies, while allowing for the flexible integration of severity functions to represent different collision types. Furthermore, we provide an extension of our risk metric to estimate the risk from the perspective of each road user in the driving scene, as we argue that risk is asymmetric between pairs of road users, i.e., dependent on the perspective. Fifth, given our proposed SMPC-based motion planning strategy, the AVs behavior can be tuned such that it minimizes its own risk (egoistic perspective), the risk other road users face (altruistic perspective), and a balance of both (collective perspective). To evaluate safety and driving behavior for each of these risk metrics, we performed simulations on a database containing a wide variety of real-world and artificial traffic scenarios. The results show that a collective perspective balances the overall risk of all road users with the AV's driving behavior in a favorable manner, and constitutes a suitable approach to facilitate ethicality in road traffic. Lastly, we use our proposed risk metric as part of the decision-making process on emergency maneuvers, i.e., emergency steering and emergency braking, for an AV designed to evade collisions with late-detected pedestrians. In simulations, we show that this metric outperforms deterministic risk estimation by choosing the appropriate evasive maneuver more frequently. In experimental testing, we verified the real-world applicability of this metric in an AV testbed designed for collision avoidance by having a pedestrian dummy walk out from a sight obstruction when the AV approaches. We find that risk is beneficial in deciding on accident avoidance maneuvers. The contributions introduced in this thesis show that risk, and thus uncertainty, can be systematically incorporated in AV algorithms for motion planning and decision-making. We demonstrate that our risk metric is beneficial to the avoidance capabilities of low-automation safety systems. Furthermore, the proposed algorithms are computationally efficient, allowing for real-time optimization-based motion planning, which allows highly automated vehicles to navigate smoothly through road traffic. We show that risk-based AV behavior generation enables balancing the AV's interests in safety and travel efficiency for all road users, and thus, facilitates ethicality.}, language = {en} } @techreport{TolksdorfSchoriesCastellsetal.2023, author = {Tolksdorf, Leon and Schories, Lars and Castells, Jacint and Gragopoulos, Ioannis and Karoui, Mouna and Weihmayr, Daniel and Smit, Robin and Gloger, Timm and Mayrargue, Sylvie and Stoll, Johann and Blum, Kristin and Munoz Sanchez, Manuel and Mannoni, Valerian and Denis, Benoit}, title = {D3.8 Verification Report for Demos 2, 3 and 4}, url = {https://www.safe-up.eu/deliverables}, pages = {111}, year = {2023}, language = {en} } @unpublished{KernTolksdorfBirkner2025, author = {Kern, Tobias and Tolksdorf, Leon and Birkner, Christian}, title = {Comparison of Localization Algorithms between Reduced-Scale and Real-Sized Vehicles Using Visual and Inertial Sensors}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2507.11241}, year = {2025}, language = {en} } @unpublished{TolksdorfTejadaBirkneretal.2025, author = {Tolksdorf, Leon and Tejada, Arturo and Birkner, Christian and van de Wouw, Nathan}, title = {Collision Probability Estimation for Optimization-based Vehicular Motion Planning}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2505.21161}, year = {2025}, language = {en} } @techreport{LoefflerGlogerSilvasetal.2021, author = {L{\"o}ffler, Christian and Gloger, Timm and Silvas, Emilia and Mu{\~n}oz S{\´a}nchez, Manuel and Tolksdorf, Leon and Weihmayr, Daniel and Labenski, Volker and Koebe, Markus and Stoll, Johann and Vogl, Carina and Watanabe, Hiroki and Smit, Robin}, title = {D3.3 Vehicle demonstrator for trajectory planning and control for combined automatic emergency braking and steering manoeuvres including system for VRU detection, motion planning and trajectory control to enhance real world performance}, url = {https://www.safe-up.eu/resources}, pages = {45}, year = {2021}, language = {en} } @techreport{LoefflerGlogerTolksdorfetal.2021, author = {L{\"o}ffler, Christian and Gloger, Timm and Tolksdorf, Leon and Weihmayr, Daniel and Vogl, Carina and Watanabe, Hiroki and Stoll, Johann and Labenski, Volker and Koebe, Markus}, title = {D3.2 Demo 2 Vehicle demonstrator for object detection in adverse weather conditions}, url = {https://www.safe-up.eu/resources}, pages = {25}, year = {2021}, language = {en} }