付記する学位プログラム名: デザイン学大学院連携プログラム / 京都大学 / 新制・課程博士 / 博士(工学) / 甲第24607号 / 工博第5113号 / 新制||工||1978(附属図書館) / 京都大学大学院工学研究科機械理工学専攻 / (主査)教授 椹木 哲夫, 教授 小森 雅晴, 教授 泉井 一浩 / 学位規則第4条第1項該当 / Doctor of Philosophy (Engineering) / Kyoto University / DFAM

Perception for autonomous drive systems is the most essential function for safe and reliable driving. LiDAR sensors can be used for perception and are vying for being crowned as an essential element in this task. In this thesis, we present a novel real-time solution for detection and tracking of moving objects which utilizes deep learning based 3D object detection. Moreover, we present a joint solution which utilizes the predictability of Kalman Filters to infer object properties and semantics to the object detection algorithm, resulting in a closed loop of object detection and object tracking.On one hand, we present YOLO++, a 3D object detection network on point clouds only. A network that expands YOLOv3, the latest contribution to standard real-time object detection for three-channel images. Our object detection solution is fast. It processes images at 20 frames per second. Our experiments on the KITTI benchmark suite show that we achieve state-of-the-art efficiency but with a mediocre accuracy for car detection, which is comparable to the result of Tiny-YOLOv3 on the COCO dataset. The main advantage with YOLO++ is that it allows for fast detection of objects with rotated bounding boxes, something which Tiny-YOLOv3 can not do. YOLO++ also performs regression of the bounding box in all directions, allowing for 3D bounding boxes to be extracted from a bird's eye view perspective. On the other hand, we present a Multi-threaded Object Tracking (MTKF) solution for multiple object tracking. Each unique observation is associated to a thread with a novel concurrent data association process. Each of the threads contain an Extended Kalman Filter that is used for predicting and estimating an associated object's state over time. Furthermore, a LiDAR odometry algorithm was used to obtain absolute information about the movement of objects, since the movement of objects are inherently relative to the sensor perceiving them. We obtain 33 state updates per second with an equal amount of threads to the number of cores in our main workstation.Even if the joint solution has not been tested on a system with enough computational power, it is ready for deployment. Using YOLO++ in combination with MTKF, our real-time constraint of 10 frames per second is satisfied by a large margin. Finally, we show that our system can take advantage of the predicted semantic information from the Kalman Filters in order to enhance the inference process in our object detection architecture.

Nowadays, autonomous driving revolution is getting closer to reality. To achieve the Autonomous driving the first step is to develop the Advanced Driver Assistance System (ADAS). Driver-assistance systems are one of the fastest-growing segments in automotive electronics since already there are many forms of ADAS available. To investigate state of art of development of ADAS towards Autonomous Driving, we develop Systematic Mapping Study (SMS). SMS methodology is used to collect, classify, and analyze the relevant publications. A classification is introduced based on the developments carried out in ADAS towards Autonomous driving. According to SMS methodology, we identified 894 relevant publications about ADAS and its developmental journey toward Autonomous Driving completed from 2012 to 2016. We classify the area of our research under three classifications: technical classifications, research types and research contributions. The related publications are classified under thirty-three technical classifications. This thesis sheds light on a better understanding of the achievements and shortcomings in this area. By evaluating collected results, we answer our seven research questions. The result specifies that most of the publications belong to the Models and Solution Proposal from the research type and contribution. The least number of the publications belong to the Automated…Autonomous driving from the technical classification which indicated the lack of publications in this area.

Autonomous Driving and Advance Driver Assistance Systems (ADAS) are revolutionizing the way we drive and the future of mobility. Among ADAS, Traffic Sign Classification is an important technique which assists the driver to easily interpret traffic signs on the road. In this thesis, we used the powerful combination of Image Processing and Deep Learning to pre-process and classify the traffic signs. Recent studies in Deep Learning show us how good a Convolutional Neural Network (CNN) is for image classification and there are several state-of-the-art models with classification accuracies over 99 % existing out there. This shaped our thesis to focus more on tackling the current challenges and some open-research cases. We focussed more on performance tuning by modifying the existing architectures with a trade-off between computations and accuracies. Our research areas include enhancement in low light/noisy conditions by adding Recurrent Neural Network (RNN) connections, and contribution to a universal-regional dataset with Generative Adversarial Networks (GANs). The results obtained on the test data are comparable to the state-of-the-art models and we reached accuracies above 98% after performance evaluation in different frameworks

To achieve the widespread diffusion of autonomous electric buses (AEBs) and thus harness their environmental potential, a broad acceptance of new technology-based mobility concepts must be fostered. Still, there remains little known about the factors determining their acceptance, especially in the combination of vehicles with alternative fuels and autonomous driving modes, as is the case with AEBs. In this study, we first conducted qualitative research to identify relevant factors influencing individual acceptance of autonomously driven electric buses. We then developed a comprehensive research model that was validated through a survey of 268 passengers of an AEB, operated in regular road traffic in Germany. The results indicate that a mix of individual factors, social impacts, and system characteristics determine an individual’s acceptance of AEBs. Notably, it is important that users perceive AEBs, not only as advantageous, but also trustworthy, enjoyable, and in a positive social light. Our research supplements the existing corpora by demonstrating the importance of individual acceptance and incorporating it to derive policy implications.

No description available.

Sensors, as a crucial part of autonomous driving, are primarily used for perceiving the environment. The recent deep learning development of different sensors has demonstrated the ability of machines recognizing and understanding their surroundings. Automotive radar, as a primary sensor for self-driving vehicles, is well-known for its robustness against variable lighting and weather conditions. Compared with camera-based deep learning development, Object detection using automotive radars has not been explored to its full extent. This can be attributed to the lack of public radar datasets. In this thesis, we collect a novel radar dataset that contains radar data in the form of Range-Azimuth-Doppler tensors along with the bounding boxes on the tensor for dynamic road users, category labels, and 2D bounding boxes on the Cartesian Bird-EyeView range map. To build the dataset, we propose an instance-wise auto-annotation algorithm. Furthermore, a novel Range-Azimuth-Doppler based multi-class object detection deep learning model is proposed. The algorithm is a one-stage anchor-based detector that generates both 3D bounding boxes and 2D bounding boxes on Range-AzimuthDoppler and Cartesian domains, respectively. Our proposed algorithm achieves 56.3% AP with IOU of 0.3 on 3D bounding box predictions, and 51.6% with IOU of 0.5 on 2D bounding box predictions. Our dataset and the code can be found at https://github.com/ZhangAoCanada/RADDet.git.

This thesis is concerned with model predictive control (MPC) within the field of autonomous driving. MPC requires a model of the system to be controlled. Since a vehicle is expected to handle a wide range of driving conditions, it is crucial that the model of the vehicle dynamics is able to account for this. Differences in road grip caused by snowy, icy or muddy roads change the driving dynamics and relying on a single model, based on ideal conditions, could possibly lead to dangerous behaviour. This work investigates the use of Gaussian processes for learning a model that can account for varying road friction coefficients. This model is incorporated as an extension to a nominal vehicle model. A double lane change scenario is considered and the aim is to learn a GP model of the disturbance based on previous driving experiences with a road friction coefficient of 0.4 and 0.6 performed with a regular MPC controller. The data is then used to train a GP model. The GPMPC controller is then compared with the regular MPC controller in the case of trajectory tracking. The results show that the obtained GP models in most cases correctly predict the model error in one prediction step. For multi-step predictions, the results vary more with some cases showing an improved prediction with a GP model compared to the nominal model. In all cases, the GPMPC controller gives a better trajectory tracking than the MPC controller while using less control input.

Semi-autonomous driving is an emerging – though not unprecedented – technology which cannot necessarily be seen as safe and reliably accident-free. Insurance companies thus play an important role as influential stakeholders in the negotiation and implementation processes around this new technology. They can either push the technology (e.g. by offering beneficial, promotional insurance models for semi-autonomous car owners) or constrain it (e.g. by providing restrictive insurance models or no insurance cover at all). Insurers face questions concerning ethical or societal consequences on various levels: not only when it comes to promoting the technology – whose impact is not yet certain and may range from saving to endangering lives – but also with respect to insurance models such as “pay as you drive”, which may involve discriminatory elements. The concept of responsible research and innovation (RRI) is well suited to accompanying and guiding insurers, policy makers and other stakeholders in this field through a responsible negotiation process that may prove beneficial for everyone. Part of the RRI approach is to make stakeholders aware of “soft” factors such as the ethical, societal or historical factors which influence innovation and of the need to include these aspects in their activities responsibly.

The aim of the thesis is to develop a method to identify driving lanes based on aerial images and existing spatial data. The proposed method uses up to date available data in which it identifies road surface marking (RSM). Polygons classified as RSM are further processed to obtain their vector line representation as the first partial result. While processing RSM vectors further, borders of driving lanes are modelled as the second partial result. Furthermore, attempts were done to be able to automatically distinguish between solid and broken lines for a higher amount of information contained in the resulting dataset. Proposed algorithms were tested in 20 case study areas and results are presented further in this thesis. The overall correctness as well as the positional accuracy proves effectivity of the method. However, several shortcomings were identified and are discussed as well as possible solutions for them are suggested. The text is accompanied by more than 70 figures to offer a clear perspective on the topic. The thesis is organised as follows: First, Introduction and Literature review are presented including the problem background, author's motivation, state of the art and contribution of the thesis. Secondly, technical and legal requirements of RSM are presented as well as theoretical concepts and...