Most of the recent automated driving systems assume the accurate functioning of localization. Unanticipated errors cause localization failures and result in failures in automated driving. An exact localization failure detection is necessary to ensure safety in automated driving; however, detection of the localization failures is challenging because sensor measurement is assumed to be independent of each other in the localization process. Owing to the assumption, the entire relation of the sensor measurement is ignored. Consequently, it is difficult to recognize the misalignment between the sensor measurement and the map when partial sensor measurement overlaps with the map. This paper proposes a method for the detection of localization failures using Markov random fields with fully connected latent variables. The full connection enables to take the entire relation into account and contributes to the exact misalignment recognition. Additionally, this paper presents localization failure probability calculation and efficient distance field representation methods. We evaluate the proposed method using two types of datasets. The first dataset is the SemanticKITTI dataset, whereby four methods are compared with the proposed method. The comparison results reveal that the proposed method achieves the most accurate failure detection. The second dataset is created based on log data acquired from the demonstrations that we conducted in Japanese public roads. The dataset includes several localization failure scenes. We apply the failure detection methods to the dataset and confirm that the proposed method achieves exact and immediate failure detection.

As represented by automated driving systems, the complexity of in-vehicle systems is rapidly increasing. The process related to the design, implementation, and validation of the system has become complicated. To reduce this complexity, a function description method suitable for the development of an automated driving system and an interpreter for directly executing this function description in software are proposed. To describe the function logically and strictly, the description sentence is based on an ontology model for traffic context. The description is also based on one-time predicate logic to enable verification by a theorem prover. By using this method, the behaviors of the automated driving system are directory linked with the description of the function definition.

This paper presents a comparison of driving behavior modeling methods based on hidden Markov models (HMMs) with driver's eye-gaze measurement and ego-vehicle localization. Original HMMs are sometimes insufficient to model real-world scenarios. To overcome these limitations, extended HMMs have been proposed, e.g., autoregressive input-output HMMs (AIOHMMs). This paper first details AIOHMMs and presents ways to use them for driving behavior modeling. We compare the performance for behavior modeling and maneuver discrimination for six types of HMMs. The driving data for this work was gathered in our university campus with a car-like vehicle. Experimental results suggest that the hidden states can properly represent the average of the driving actions when the driving behaviors are accurately modeled by the HMMs. It is also suggested that surrounding and past information can be used to flexibly model the relationship between driving actions and related information.

An autonomous driving service in urban areas is still a challenging problem. It is necessary to simultaneously solve tactical planning problems and operation planning problems, such as a scenario for passing through an intersection with oncoming vehicles. To realize the service by using a centralized management system, it is necessary to guide thousands of vehicles in real-time. Therefore, efficiency and robustness are required for the management system. In this study, we propose a centralized path planning system to make tactical level decisions to manage the path plans of multiple vehicles based on Dynamic Map. The proposed system selects an operational-level planner to generate a detailed motion plan for each vehicle based on a decision-making algorithm. Then, the conflicts of motion plans between vehicles are detected and resolved by using a spatio-temporal reservation map on Dynamic Map. We report the results of simulation tests of10,000 hours to evaluate the efficiency and robustness of the proposed system using the map data of an existing city.

This paper presents a longitudinal and lateral motion planning method for driver assistance systems in urban scenarios. We proposed a Bayesian network based motion planner to generate the trajectory, including the positions and velocities to path through multiple traffic participants. To design the probabilistic models which represent a lane keeping maneuver and an obstacle avoidance maneuver, we collect and analyze natural driving data. Then, it is difficult to collect collision data in the real world. Therefore, we analyze the inverse collision probability from safety driving trajectories of expert drivers. The proposed method generates the optimal trajectory plan by using the global optimization algorithm named Belief Propagation. Finally, we show the evaluation experiment that compares the difference between the trajectories generated by the proposed method and natural driving data.

This paper proposes a driving safety evaluation method based on the parameter analysis of a driver model. Since the driving abilities, such as reaction, recognition and judgment time decrease with aging, it is difficult for elderly drivers to avoid the traffic accidents instantly. Therefore, the proactive safety driving is important for the elderly drivers to prevent the accidents. Then, the safety evaluation criteria of a driving behavior are useful to encourage the driver to keep proactive safety driving. And these criteria are useful to develop an advanced driver assistance system for elderly drivers. To evaluate the driving behavior, we use the parameters of a risk potential model which is the driver model to represent the speed and course control around the risk factors. Since the risk potential model represents the driving behavior by using a small number of the parameters, we make the assumption that the parameters are highly abstract the driving behavior and it is useful for analyzing the safety level of the driver. To evaluate the assumption experimentally, we collect the actual driving data of elderly, general and normative drivers for analyzing the parameters of the risk potential model and the safety level of the driver. Finally, the results show that the parameters of the risk potential model can be used to indicate the features of the driving behavior of the elderly drivers.

In unsignalized intersections with poor visibility, proactive driving with hazard anticipation is required in order to avoid collisions with other traffic participants from a blind corner. However, for elderly drivers and novice drivers, it is difficult to recognize potential hazardous area and difficult to select an appropriate speed to pass the intersections safely. To assist such drivers, a driver model which can recommend the appropriate speed by learning driving data of expert drivers based on a statistical approach is useful for a driver assistance system. The proposed method automatically estimates parameters of the driver model from the actual driving data by defining risk potential functions for representing braking behaviors while passing through intersections, oncoming vehicles and pedestrians. To evaluate the proposed method, the driving data of instructors of a driving school are collected. The results show that the accuracy (RMSE) of the estimated braking behavior model is 2.5 km/h against the actual data.

This paper proposes an interactive 3D animation system specifically aiming efficient control of human motion. However there are various commercial products for creating movies and game contents, those are still difficult to deal with for non-professional users. To ease the creation process and encourage to utilize 3D animation for the general users, e.g., in the field of such as education, medicine and so on, we propose a system using Kinect. The data of skeleton models of human motion estimated by Kinect is processed to generate Motion Graph and finally restructure the data automatically for 3D character models. We also propose an efficient 3D animation viewing system based on touch interface for tablet device, which enables intuitive control of multiple motions of the human activity. To evaluate the effectiveness of the method, we implemented a prototype system and created several 3D animations.

Recently importance of tablet devices with touch interface increases significantly, because they attract not only mobile phone users, but also people of all generations including small kids to elderly people. One key technology on those devices is 3D graphics; some of them exceed the ability of desktop PCs. Although currently 3D graphics are only used for game applications, it also has a great potential for other purposes. For example, an interactive 3D animation system for tablet devices has been developed recently and attracts many people. With the system, multiple 3D animations are played depending on view direction and user's gesture input. However, the system still has two critical issues: the first one is a complicated process for data creation, and the other is a conflict on several gestures overlapped at the same position. In the paper, the first issue is solved by using a realtime range sensor and the second one is solved by considering the relationship between the 3D object and the input 2D gesture. The effectiveness of the system was proved by making the real system and creating and manipulating the actual 3D animations.