arXiv subjects

Ömer Şahin Taş

Publications and source records attributed to Ömer Şahin Taş.

9 recordsLinked to original sources

arXiv2026

Generative AI for Autonomous Driving: A Review

Generative AI (GenAI) is rapidly advancing the field of Autonomous Driving (AD), extending beyond traditional applications in text, image, and video generation. We explore how generative models can enhance automotive tasks, such as static map creation, dynamic scenario generation, trajectory forecasting, and vehicle motion planning. By examining multiple generative approaches ranging from Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) to Generative Transformers (GTs) and Diffusion Models (DMs), we highlight and compare their capabilities and limitations for AD-specific applications. Additionally, we discuss hybrid methods integrating conventional techniques with generative approaches, and emphasize their improved adaptability and robustness. We also identify relevant datasets and outline open research questions to guide future developments in GenAI. Finally, we discuss five core challenges: safety, interpretability, realtime capabilities, training and benchmarking. We also present recommendations for image generation, dynamic scenario generation, and planning.

cs.CV↗

arXiv2026

Mosaic: An Extensible Framework for Composing Rule-Based and Learned Motion Planners

Safe and explainable motion planning remains a central challenge in autonomous driving. While rule-based planners offer predictable and explainable behavior, they often fail to grasp the complexity and uncertainty of real-world traffic. Conversely, learned planners exhibit strong adaptability but suffer from reduced transparency and occasional safety violations. We introduce Mosaic, a framework for structured decision-making that integrates both paradigms through arbitration graphs. By decoupling trajectory verification and selection from the generation of trajectories by individual planners, every decision becomes transparent and traceable. This separation lets verification and trajectory selection contribute independently: centralized verification acts as a safety floor, reducing at-fault collisions from 25 for each standalone planner to 16. In contrast, per-step trajectory selection acts as a performance ceiling, combining the complementary strengths of a rule-based and a learned planner. In experimental evaluation on nuPlan, Mosaic achieves 95.56 CLS-NR and 94.18 CLS-R on the Val14 closed-loop benchmark, setting a new state of the art. On the interPlan benchmark, focused on highly interactive and out-of-distribution scenarios, Mosaic scores 54.10 CLS-R, outperforming its best constituent planner by 22.8% -- all without retraining or requiring additional data. The code is available at github.com/KIT-MRT/mosaic.

cs.RO↗

arXiv2026

Creating Impactful Autonomous Driving Datasets: A Strategic Guide from Research Gap to Benchmark

Well-designed autonomous driving datasets have fundamentally shaped research progress, yet existing literature primarily describes what datasets contain rather than how to strategically design impactful ones. This is especially limiting for small and medium-sized labs and startups that cannot afford to misallocate scarce resources. We argue that impactful dataset creation begins with a diagnosis: whether a research question is blocked by a data problem or an evaluation problem, and proceeds by selecting the minimal data operator(s) that closes the resulting gap, recording new data only when no cheaper operator(s) suffices. We analyze the evolution of major autonomous driving (AD) datasets through this lens and distill a strategic framework spanning gap identification, operator choice, sensor suite design, and annotation strategy. We ground the framework in a running case study of our KITScenes dataset family. The datasets are available at: https://kitscenes.com/

cs.CV↗

arXiv2026

The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset

Existing autonomous driving datasets have enabled major progress, but fall short in sensor fidelity, map completeness, or geographic diversity. We present KITScenes Multimodal, a European dataset built around high-fidelity sensors and maps. Our fully synchronized sensor suite combines high-resolution global-shutter cameras, long-range lidar beyond 400m, 4D imaging radar, and redundant GNSS/INS localization. Our HD maps are, to our knowledge, the most complete of any sensor dataset, validated through autonomous driving trials on open-source software. For the first time in a public dataset, all driving-relevant traffic elements, such as traffic lights, are mapped in 3D to a reprojection-accurate level with full topological connectivity. Recorded in cities with irregular street layouts and mixed traffic modes, our dataset complements existing datasets by broadening the available geographic diversity. We also introduce four benchmarks, each advancing spatial learning for embodied AI: online HD map construction, long-range depth estimation, novel view synthesis, and end-to-end driving. Project page: https://kitscenes.com/

cs.CV↗

arXiv2026

FlowDrive: moderated flow matching with data balancing for trajectory planning

Learning-based planners are sensitive to the long-tailed distribution of driving data. Common maneuvers dominate datasets, while dangerous or rare scenarios are sparse. This imbalance can bias models toward the frequent cases and degrade performance on critical scenarios. To tackle this problem, we compare balancing strategies for sampling training data and find reweighting by trajectory pattern an effective approach. We then present FlowDrive, a flow-matching trajectory planner that learns a conditional rectified flow to map noise directly to trajectory distributions with few flow-matching steps. We further introduce moderated, in-the-loop guidance that injects small perturbation between flow steps to systematically increase trajectory diversity while remaining scene-consistent. On nuPlan and the interaction-focused interPlan benchmarks, FlowDrive achieves state-of-the-art results among learning-based planners and approaches methods with rule-based refinements. After adding moderated guidance and light post-processing (FlowDrive*), it achieves overall state-of-the-art performance across nearly all benchmark splits. Our code is available at https://github.com/einsteinguang/flow_drive_planner.

cs.RO↗

arXiv2025

Optimal Control of Hybrid Systems via Measure Relaxations

We propose an approach to trajectory optimization for piecewise polynomial systems based on the recently proposed graphs of convex sets framework. We instantiate the framework with a convex relaxation of optimal control based on occupation measures, resulting in a convex optimization problem resembling the discrete shortest-paths linear program that can be solved efficiently to global optimality. While this approach inherits the limitations of semidefinite programming, scalability to large numbers of discrete modes improves compared to the NP-hard mixed-integer formulation. We use this to plan trajectories under temporal logic specifications, comparing the computed cost lower bound to a nonconvex optimization approach with fixed mode sequence. In our numerical experiments, we find that this bound is typically in the vicinity of the nonconvex solution, while the runtime speedup is significant compared to the often intractable mixed-integer formulation. Our implementation is available at https://github.com/ebuehrle/hpoc.

math.OC↗

arXiv2024

Decision-theoretic MPC: Motion Planning with Weighted Maneuver Preferences Under Uncertainty

Continuous optimization based motion planners require specifying a maneuver class before calculating the optimal trajectory for that class. In traffic, the intentions of other participants are often unclear, presenting multiple maneuver options for the autonomous vehicle. This uncertainty can make it difficult for the vehicle to decide on the best option. This work introduces a continuous optimization based motion planner that combines multiple maneuvers by weighting the trajectory of each maneuver according to the vehicle's preferences. In this way, the planner eliminates the need for committing to a single maneuver. To maintain safety despite this increased complexity, the planner considers uncertainties ranging from perception to prediction, while ensuring the feasibility of a chance-constrained emergency maneuver. Evaluations in both driving experiments and simulation studies show enhanced interaction capabilities and comfort levels compared to conventional planners, which consider only a single maneuver.

cs.RO↗

arXiv2021

Efficient Sampling in POMDPs with Lipschitz Bandits for Motion Planning in Continuous Spaces

Decision making under uncertainty can be framed as a partially observable Markov decision process (POMDP). Finding exact solutions of POMDPs is generally computationally intractable, but the solution can be approximated by sampling-based approaches. These sampling-based POMDP solvers rely on multi-armed bandit (MAB) heuristics, which assume the outcomes of different actions to be uncorrelated. In some applications, like motion planning in continuous spaces, similar actions yield similar outcomes. In this paper, we utilize variants of MAB heuristics that make Lipschitz continuity assumptions on the outcomes of actions to improve the efficiency of sampling-based planning approaches. We demonstrate the effectiveness of this approach in the context of motion planning for automated driving.

cs.RO↗

arXiv2020

Decision-Time Postponing Motion Planning for Combinatorial Uncertain Maneuvering

Motion planning involves decision making among combinatorial maneuver variants in urban driving. A planner must consider uncertainties and associated risks of the maneuver variants, and subsequently select a maneuver alternative. In this paper we present a planning approach that considers the uncertainties in the prediction and, in case of high uncertainty, postpones the combinatorial decision making to a later time within the planning horizon. With our proposed approach, safe but at the same time not overconservative motion is planned.

cs.RO↗