It is necessary to calibrate the hydraulic pressure of the shift control to develop an automatic transmission (AT), and this calibration process entails a subjective shift quality assessment by experienced engineers. An objective shift quality assessment methodology has been explored for a long time to replace the engineer. The most recent data-based assessment model has attained a nearly human-like performance. However, preparing the large number of data labels required for supervised learning of the model has limitations. This study proposes an unsupervised anomaly detection model for objective shift quality assessment to address data label shortages and high data labeling costs. The proposed anomaly detection model is trained to classify a normal shift and an abnormal shift using just normal shift data. It is possible to easily obtain many train datasets from ordinary vehicles, and data labeling is not required. On the basis of real vehicle shift data, multiple anomaly detection models composed of various deep neural networks are developed and assessed. The evaluation results show that training exclusively on normal shift data can detect abnormal shifts; the best area under receiver operating characteristic curve is 0.902.

This paper aims to obtain a guide of several experimental object detection architectures for pedestrian detection / vehicle detection (PD/VD) in the South Korean driving environment and to present the trade-off relationship between the mean average precision (mAP) and the frame per second (FPS) values. For these purposes, we generated a Korean vehicle black box front view dataset (KVD) to consider the actual driving environments in South Korea. We then experimented with various configurations of object detection architectures using the KVD. Next, the trade-off relationship for each architecture was summarized and analyzed. This paper presents a guide for choosing PD/VD architectures to achieve a suitable mAP-FPS balance for advanced driver assistance systems (ADAS) and autonomous navigation technologies.

The proposed study aims to address the complexities resulting from the mixing of manually driven and autonomous vehicles. First, the complexity of the driving situation was defined to evaluate a new road environment containing both types of vehicles. Assuming V2X technology, driving situation complexity (DSC) was defined by the concept of perplexity and standard deviation and calculated by measuring the driver-vehicle behaviors in a simulated driving environment. Second, according to the definition of autonomous driving proposed by the Society of Automotive Engineers International (SAE), a driver model of an autonomous vehicle was implemented using a PreScan simulator. The proportions of defined autonomous vehicles were modified and the DSCs for different scenarios, such as confluence, accident, stop, and safety sections, were measured. Then, the significance of the complexity of the driving situation, as presented by each section, was verified. In addition, the implications of the complexity were clarified by analyzing the correlation between DSC and accident risk measure (ARM), which is used to evaluate accident situations by monitoring the occurrence of accidents. Finally, the complexities of driving situations were analyzed for various mixed driving situations, including Levels 0-5 autonomous driving vehicles. Future situations were predicted to involve a mixture of manually driven and autonomous vehicles.

This paper proposes a method for multi-agent path planning on a road network in the presence of congestion. We suggest a distributed method to find paths for multiple agents by introducing a probabilistic path choice achieving global goals such as the user equilibrium or the social optimum. This approach, which shows that the global goals can be achieved by local processing using only local information, can be parallelized and sped-up using massive parallel processing. The probabilistic assignment reliably copes with the case of random choices of unidentified agents or random route changes of agents who ignore our path guidance. We provide the analytical result on convergence and running time. We demonstrate and evaluate our algorithm by an implementation using asynchronous computation on multi-core computers.

This paper proposes a method for multi-agent path planning on a road network in the presence of congestion. We suggest a distributed method to find paths for multiple agents by introducing a probabilistic path choice achieving global goals such as the social optimum. This approach, which shows that the global goals can be achieved by local processing using only local information, can be parallelized and sped-up using massive parallel processing. The probabilistic assignment reliably copes with the case of random choices of unidentified agents or random route changes of agents who ignore our path guidance. We provide the analytical result on convergence and running time. We demonstrate and evaluate our algorithm by an implementation using asynchronous computation on multi-core computers.

We present algorithms for a motion planning for multiple agents whose goals are to visit multiple locations with probabilistic guarantees for achieving the goal. Though much research has been done in stochastic shortest path algorithms, the existing algorithms focus on the single-origin single-destination problem for one agent. This paper formulates a general framework for the stochastic shortest path problem with visit node constraints designed to achieve a specific goal with multiple agents, multiple resources, and multiple destinations. The constraints are defined by a set of sequences of nodes to be visited. Given predetermined constraints, our motion planning problem consists of finding the best agents, resources, and destinations, and the path through a sequence of nodes representing them. The technique in this paper solves the problem at the same level of complexity as solving the single-origin single-destination problem by parallelization. We demonstrate the algorithm by a Web-based traffic navigation guide system and evaluate the algorithm's performance.

Traffic congestion, volumes, origins, destinations, routes, and other road-network performance metrics are typically collected through survey data or via static sensors such as traffic cameras and loop detectors. This information is often out-of-date, difficult to collect and aggregate, difficult to analyze and quantify, or all of the above. In this paper we conduct a case study that demonstrates that it is possible to accurately infer traffic volume through data collected from a roving sensor network of taxi probes that log their locations and speeds at regular intervals. Our model and inference procedures can be used to analyze traffic patterns and conditions from historical data, as well as to infer current patterns and conditions from data collected in real-time. As such, our techniques provide a powerful new sensor network approach for traffic visualization, analysis, and urban planning.

This paper presents shadow detection methods for vision-based autonomous driving in an urban environment. Shadows misclassified as objects create problems in autonomous driving applications. Real-time efficient algorithms in dynamic background settings are proposed. Without the static background assumption, which was often used in previous work to develop fast algorithms, our scheme estimates the varying background efficiently. A combination of various features classifies each pixel into one of the following categories: road, shadow, dark object, or other objects. In addition to pixel level classification, spatial context is also used to identify the shadows. Our results show that our methods perform well for autonomous driving applications and are fast enough to work in real time.

The Personal Commute Portal (PCP) is a Web-based traffic information system that provides a good driving direction and personalized route recommendation using historical and real-time traffic data obtained by a vehicular sensor network.