Ekim Yurtsever

Ekim Yurtsever, Emeç Erçelik, Mingyu Liu et al.

State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of trained models. Self-supervised training strategies can alleviate these issues by learning a general point cloud backbone model for downstream 3D vision tasks. Against this backdrop, we show the relationship between self-supervised multi-frame flow representations and single-frame 3D detection hypotheses. Our main contribution leverages learned flow and motion representations and combines a self-supervised backbone with a supervised 3D detection head. First, a self-supervised scene flow estimation model is trained with cycle consistency. Then, the point cloud encoder of this model is used as the backbone of a single-frame 3D object detection head model. This second 3D object detection model learns to utilize motion representations to distinguish dynamic objects exhibiting different movement patterns. Experiments on KITTI and nuScenes benchmarks show that the proposed self-supervised pre-training increases 3D detection performance significantly. https://github.com/emecercelik/ssl-3d-detection.git

Xingcheng Zhou, Mingyu Liu, Ekim Yurtsever et al.

The applications of Vision-Language Models (VLMs) in the field of Autonomous Driving (AD) have attracted widespread attention due to their outstanding performance and the ability to leverage Large Language Models (LLMs). By incorporating language data, driving systems can gain a better understanding of real-world environments, thereby enhancing driving safety and efficiency. In this work, we present a comprehensive and systematic survey of the advances in vision language models in this domain, encompassing perception and understanding, navigation and planning, decision-making and control, end-to-end autonomous driving, and data generation. We introduce the mainstream VLM tasks in AD and the commonly utilized metrics. Additionally, we review current studies and applications in various areas and summarize the existing language-enhanced autonomous driving datasets thoroughly. Lastly, we discuss the benefits and challenges of VLMs in AD and provide researchers with the current research gaps and future trends.

Dianwei Chen, Ekim Yurtsever, Keith Redmill et al.

Recent research in pedestrian simulation often aims to develop realistic behaviors in various situations, but it is challenging for existing algorithms to generate behaviors that identify weaknesses in automated vehicles' performance in extreme and unlikely scenarios and edge cases. To address this, specialized pedestrian behavior algorithms are needed. Current research focuses on realistic trajectories using social force models and reinforcement learning based models. However, we propose a reinforcement learning algorithm that specifically targets collisions and better uncovers unique failure modes of automated vehicle controllers. Our algorithm is efficient and generates more severe collisions, allowing for the identification and correction of weaknesses in autonomous driving algorithms in complex and varied scenarios.

Bare Luka Žagar, Tim Hertel, Mingyu Liu et al.

Deformable linear objects are vastly represented in our everyday lives. It is often challenging even for humans to visually understand them, as the same object can be entangled so that it appears completely different. Examples of deformable linear objects include blood vessels and wiring harnesses, vital to the functioning of their corresponding systems, such as the human body and a vehicle. However, no point cloud datasets exist for studying 3D deformable linear objects. Therefore, we are introducing two point cloud datasets, PointWire and PointVessel. We evaluated state-of-the-art methods on the proposed large-scale 3D deformable linear object benchmarks. Finally, we analyzed the generalization capabilities of these methods by conducting transferability experiments on the PointWire and PointVessel datasets.

Emeç Erçelik, Ekim Yurtsever, Alois Knoll

3D object detection is a core component of automated driving systems. State-of-the-art methods fuse RGB imagery and LiDAR point cloud data frame-by-frame for 3D bounding box regression. However, frame-by-frame 3D object detection suffers from noise, field-of-view obstruction, and sparsity. We propose a novel Temporal Fusion Module (TFM) to use information from previous time-steps to mitigate these problems. First, a state-of-the-art frustum network extracts point cloud features from raw RGB and LiDAR point cloud data frame-by-frame. Then, our TFM module fuses these features with a recurrent neural network. As a result, 3D object detection becomes robust against single frame failures and transient occlusions. Experiments on the KITTI object tracking dataset show the efficiency of the proposed TFM, where we obtain ~6%, ~4%, and ~6% improvements on Car, Pedestrian, and Cyclist classes, respectively, compared to frame-by-frame baselines. Furthermore, ablation studies reinforce that the subject of improvement is temporal fusion and show the effects of different placements of TFM in the object detection pipeline. Our code is open-source and available at https://github.com/emecercelik/Temp-Frustum-Net.git.

Dongfang Yang, Haolin Zhang, Ekim Yurtsever et al.

Predicting vulnerable road user behavior is an essential prerequisite for deploying Automated Driving Systems (ADS) in the real-world. Pedestrian crossing intention should be recognized in real-time, especially for urban driving. Recent works have shown the potential of using vision-based deep neural network models for this task. However, these models are not robust and certain issues still need to be resolved. First, the global spatio-temproal context that accounts for the interaction between the target pedestrian and the scene has not been properly utilized. Second, the optimum strategy for fusing different sensor data has not been thoroughly investigated. This work addresses the above limitations by introducing a novel neural network architecture to fuse inherently different spatio-temporal features for pedestrian crossing intention prediction. We fuse different phenomena such as sequences of RGB imagery, semantic segmentation masks, and ego-vehicle speed in an optimum way using attention mechanisms and a stack of recurrent neural networks. The optimum architecture was obtained through exhaustive ablation and comparison studies. Extensive comparative experiments on the JAAD pedestrian action prediction benchmark demonstrate the effectiveness of the proposed method, where state-of-the-art performance was achieved. Our code is open-source and publicly available.

Haolin Zhang, Dongfang Yang, Ekim Yurtsever et al.

Learned pointcloud representations do not generalize well with an increase in distance to the sensor. For example, at a range greater than 60 meters, the sparsity of lidar pointclouds reaches to a point where even humans cannot discern object shapes from each other. However, this distance should not be considered very far for fast-moving vehicles: A vehicle can traverse 60 meters under two seconds while moving at 70 mph. For safe and robust driving automation, acute 3D object detection at these ranges is indispensable. Against this backdrop, we introduce faraway-frustum: a novel fusion strategy for detecting faraway objects. The main strategy is to depend solely on the 2D vision for recognizing object class, as object shape does not change drastically with an increase in depth, and use pointcloud data for object localization in the 3D space for faraway objects. For closer objects, we use learned pointcloud representations instead, following state-of-the-art. This strategy alleviates the main shortcoming of object detection with learned pointcloud representations. Experiments on the KITTI dataset demonstrate that our method outperforms state-of-the-art by a considerable margin for faraway object detection in bird's-eye-view and 3D. Our code is open-source and publicly available: https://github.com/dongfang-steven-yang/faraway-frustum.

Dongfang Yang, Ekim Yurtsever, Vishnu Renganathan et al.

Social distancing has been proven as an effective measure against the spread of the infectious COronaVIrus Disease 2019 (COVID-19). However, individuals are not used to tracking the required 6-feet (2-meters) distance between themselves and their surroundings. An active surveillance system capable of detecting distances between individuals and warning them can slow down the spread of the deadly disease. Furthermore, measuring social density in a region of interest (ROI) and modulating inflow can decrease social distancing violation occurrence chance. On the other hand, recording data and labeling individuals who do not follow the measures will breach individuals' rights in free-societies. Here we propose an Artificial Intelligence (AI) based real-time social distancing detection and warning system considering four important ethical factors: (1) the system should never record/cache data, (2) the warnings should not target the individuals, (3) no human supervisor should be in the detection/warning loop, and (4) the code should be open-source and accessible to the public. Against this backdrop, we propose using a monocular camera and deep learning-based real-time object detectors to measure social distancing. If a violation is detected, a non-intrusive audio-visual warning signal is emitted without targeting the individual who breached the social distancing measure. Also, if the social density is over a critical value, the system sends a control signal to modulate inflow into the ROI. We tested the proposed method across real-world datasets to measure its generality and performance. The proposed method is ready for deployment, and our code is open-sourced.

Ekim Yurtsever, Linda Capito, Keith Redmill et al.

Automated driving in urban settings is challenging. Human participant behavior is difficult to model, and conventional, rule-based Automated Driving Systems (ADSs) tend to fail when they face unmodeled dynamics. On the other hand, the more recent, end-to-end Deep Reinforcement Learning (DRL) based model-free ADSs have shown promising results. However, pure learning-based approaches lack the hard-coded safety measures of model-based controllers. Here we propose a hybrid approach for integrating a path planning pipe into a vision based DRL framework to alleviate the shortcomings of both worlds. In summary, the DRL agent is trained to follow the path planner's waypoints as close as possible. The agent learns this policy by interacting with the environment. The reward function contains two major terms: the penalty of straying away from the path planner and the penalty of having a collision. The latter has precedence in the form of having a significantly greater numerical value. Experimental results show that the proposed method can plan its path and navigate between randomly chosen origin-destination points in CARLA, a dynamic urban simulation environment. Our code is open-source and available online.

Ekim Yurtsever, Yongkang Liu, Jacob Lambert et al.

Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipeline, limiting their availability and robustness. To address these issues, we introduce a novel deep learning based action recognition framework for classifying dangerous lane change behavior in short video clips captured by a monocular camera. We designed a deep spatiotemporal classification network that uses pre-trained state-of-the-art instance segmentation network Mask R-CNN as its spatial feature extractor for this task. The Long-Short Term Memory (LSTM) and shallower final classification layers of the proposed method were trained on a semi-naturalistic lane change dataset with annotated risk labels. A comprehensive comparison of state-of-the-art feature extractors was carried out to find the best network layout and training strategy. The best result, with a 0.937 AUC score, was obtained with the proposed network. Our code and trained models are available open-source.

Mingyu Liu, Ekim Yurtsever, Jonathan Fossaert et al.

Autonomous driving has rapidly developed and shown promising performance due to recent advances in hardware and deep learning techniques. High-quality datasets are fundamental for developing reliable autonomous driving algorithms. Previous dataset surveys either focused on a limited number or lacked detailed investigation of dataset characteristics. To this end, we present an exhaustive study of 265 autonomous driving datasets from multiple perspectives, including sensor modalities, data size, tasks, and contextual conditions. We introduce a novel metric to evaluate the impact of datasets, which can also be a guide for creating new datasets. Besides, we analyze the annotation processes, existing labeling tools, and the annotation quality of datasets, showing the importance of establishing a standard annotation pipeline. On the other hand, we thoroughly analyze the impact of geographical and adversarial environmental conditions on the performance of autonomous driving systems. Moreover, we exhibit the data distribution of several vital datasets and discuss their pros and cons accordingly. Finally, we discuss the current challenges and the development trend of the future autonomous driving datasets.

Mingyu Liu, Ekim Yurtsever, Marc Brede et al.

Accurate and effective 3D object detection is critical for ensuring the driving safety of autonomous vehicles. Recently, state-of-the-art two-stage 3D object detectors have exhibited promising performance. However, these methods refine proposals individually, ignoring the rich contextual information in the object relationships between the neighbor proposals. In this study, we introduce an object relation module, consisting of a graph generator and a graph neural network (GNN), to learn the spatial information from certain patterns to improve 3D object detection. Specifically, we create an inter-object relationship graph based on proposals in a frame via the graph generator to connect each proposal with its neighbor proposals. Afterward, the GNN module extracts edge features from the generated graph and iteratively refines proposal features with the captured edge features. Ultimately, we leverage the refined features as input to the detection head to obtain detection results. Our approach improves upon the baseline PV-RCNN on the KITTI validation set for the car class across easy, moderate, and hard difficulty levels by 0.82%, 0.74%, and 0.58%, respectively. Additionally, our method outperforms the baseline by more than 1% under the moderate and hard levels BEV AP on the test server.

Zhihao Zhang, Ekim Yurtsever, Keith A. Redmill

Developing an automated driving system capable of navigating complex traffic environments remains a formidable challenge. Unlike rule-based or supervised learning-based methods, Deep Reinforcement Learning (DRL) based controllers eliminate the need for domain-specific knowledge and datasets, thus providing adaptability to various scenarios. Nonetheless, a common limitation of existing studies on DRL-based controllers is their focus on driving scenarios with simple traffic patterns, which hinders their capability to effectively handle complex driving environments with delayed, long-term rewards, thus compromising the generalizability of their findings. In response to these limitations, our research introduces a pioneering hierarchical framework that efficiently decomposes intricate decision-making problems into manageable and interpretable subtasks. We adopt a two step training process that trains the high-level controller and low-level controller separately. The high-level controller exhibits an enhanced exploration potential with long-term delayed rewards, and the low-level controller provides longitudinal and lateral control ability using short-term instantaneous rewards. Through simulation experiments, we demonstrate the superiority of our hierarchical controller in managing complex highway driving situations.

Zhihao Zhang, Chengyang Peng, Minghao Zhu et al.

Autonomous driving in dense, dynamic environments requires decision-making systems that can exploit both spatial structure and long-horizon temporal dependencies while remaining robust to uncertainty. This work presents a novel framework that integrates multi-channel bird's-eye-view occupancy grids with transformer-based sequence modeling for tactical driving in complex roundabout scenarios. To address the imbalance between frequent low-risk states and rare safety-critical decisions, we propose the Uncertainty-Weighted Decision Transformer (UWDT). UWDT employs a frozen teacher transformer to estimate per-token predictive entropy, which is then used as a weight in the student model's loss function. This mechanism amplifies learning from uncertain, high-impact states while maintaining stability across common low-risk transitions. Experiments in a roundabout simulator, across varying traffic densities, show that UWDT consistently outperforms other baselines in terms of reward, collision rate, and behavioral stability. The results demonstrate that uncertainty-aware, spatial-temporal transformers can deliver safer and more efficient decision-making for autonomous driving in complex traffic environments.

Zhihao Zhang, Chengyang Peng, Ekim Yurtsever et al.

Automated vehicle control using reinforcement learning (RL) has attracted significant attention due to its potential to learn driving policies through environment interaction. However, RL agents often face training challenges in sample efficiency and effective exploration, making it difficult to discover an optimal driving strategy. To address these issues, we propose guiding the RL driving agent with a demonstration policy that need not be a highly optimized or expert-level controller. Specifically, we integrate a rule-based lane change controller with the Soft Actor Critic (SAC) algorithm to enhance exploration and learning efficiency. Our approach demonstrates improved driving performance and can be extended to other driving scenarios that can similarly benefit from demonstration-based guidance.

Mert Koc, Ekim Yurtsever, Keith Redmill et al.

Avoiding unseen or partially occluded vulnerable road users (VRUs) is a major challenge for fully autonomous driving in urban scenes. However, occlusion-aware risk assessment systems have not been widely studied. Here, we propose a pedestrian emergence estimation and occlusion-aware risk assessment system for urban autonomous driving. First, the proposed system utilizes available contextual information, such as visible cars and pedestrians, to estimate pedestrian emergence probabilities in occluded regions. These probabilities are then used in a risk assessment framework, and incorporated into a longitudinal motion controller. The proposed controller is tested against several baseline controllers that recapitulate some commonly observed driving styles. The simulated test scenarios include randomly placed parked cars and pedestrians, most of whom are occluded from the ego vehicle's view and emerges randomly. The proposed controller outperformed the baselines in terms of safety and comfort measures.

Ekim Yurtsever, Dongfang Yang, Ibrahim Mert Koc et al.

Driving simulators play a large role in developing and testing new intelligent vehicle systems. The visual fidelity of the simulation is critical for building vision-based algorithms and conducting human driver experiments. Low visual fidelity breaks immersion for human-in-the-loop driving experiments. Conventional computer graphics pipelines use detailed 3D models, meshes, textures, and rendering engines to generate 2D images from 3D scenes. These processes are labor-intensive, and they do not generate photorealistic imagery. Here we introduce a hybrid generative neural graphics pipeline for improving the visual fidelity of driving simulations. Given a 3D scene, we partially render only important objects of interest, such as vehicles, and use generative adversarial processes to synthesize the background and the rest of the image. To this end, we propose a novel image formation strategy to form 2D semantic images from 3D scenery consisting of simple object models without textures. These semantic images are then converted into photorealistic RGB images with a state-of-the-art Generative Adversarial Network (GAN) trained on real-world driving scenes. This replaces repetitiveness with randomly generated but photorealistic surfaces. Finally, the partially-rendered and GAN synthesized images are blended with a blending GAN. We show that the photorealism of images generated with the proposed method is more similar to real-world driving datasets such as Cityscapes and KITTI than conventional approaches. This comparison is made using semantic retention analysis and Frechet Inception Distance (FID) measurements.

Ekim Yurtsever, Jacob Lambert, Alexander Carballo et al.

Automated driving systems (ADSs) promise a safe, comfortable and efficient driving experience. However, fatalities involving vehicles equipped with ADSs are on the rise. The full potential of ADSs cannot be realized unless the robustness of state-of-the-art improved further. This paper discusses unsolved problems and surveys the technical aspect of automated driving. Studies regarding present challenges, high-level system architectures, emerging methodologies and core functions: localization, mapping, perception, planning, and human machine interface, were thoroughly reviewed. Furthermore, the state-of-the-art was implemented on our own platform and various algorithms were compared in a real-world driving setting. The paper concludes with an overview of available datasets and tools for ADS development.