Lane-level digital maps are crucial to advanced driver assistance systems (ADAS) and autonomous driving, since they can simplify driving tasks and enhance system performance by providing strong priors about the driving environment. However, the high cost of current map generation systems prevents their benefits to normal commercial cars as they usually depend on specialized sensors and need great manual postprocessing. In this paper, a low-cost solution is proposed for automatic generation of a precise lane-level map by using conventional sensors that have been already installed in contemporary cars. It mainly consists of two modules, i.e., road orthographic image generation and lane graph construction. First, the global map is divided into fixed local segments based on the road network topology. With the reference of the local map segments, the bird's eye view images of the road surface are accumulated by fusing GPS, INS, and visual odometry and subsequently integrated into synthetic orthographic images. Next, the driving lane information is extracted from the road orthographic images and a large amount of vehicle trajectories. Such information is then used to construct a lane graph of the map based on the sophisticated lane models we proposed without manual processing. Experiments show promising results of the automatic map generation of the real-world roads, which substantiated the effectiveness of the proposed approach. Such a system can offer increased value and promote the automation level for today's commercial cars without being supplemented additional sensors.

Comprehensive situational awareness is paramount to the effectiveness of advanced driver assistance systems (ADASs) used in daily urban traffic, particularly for the unmarked roads, which cannot fulfill the requirements of conventional ADAS systems. This paper proposed a stereovision-based multimodal ADAS system designed for expanding the usability of ADAS functions, including lane-keeping assist, adaptive cruise control, and precrash system, to normal urban scenarios with unmarked roads. At first, the physical road boundary and vehicle candidates are detected. Subsequently, the contextual information between the host vehicle, the road, and the other vehicles are correlated for both low-level object detection improvement and high-level road structure estimation. Finally, the required ADAS elements are generated based on the correlation results with respect to the system functionalities. Experimental results in various typical but challenging scenarios have substantiated the effectiveness of the proposed system, which could help increase the value of the existing ADAS system without major modifications or expense.

Lane-level digital maps can simplify driving tasks for robotic cars as well as enhance performance and reliability for advanced driver assistance systems (ADAS) by providing strong priors about the driving environment. In this paper, we present a system for automatic generation of precise lane-level maps by using conventional low-cost sensors installed in most of current commercial cars. It mainly consists of two modules, i.e. road orthographic image generation and lane graph construction. First, we divide the global map into fixed local segments based on the road network topology. According to the local map segments, we accumulate the bird's eye view images of the road surface by fusing GPS, INS and visual odometry, and subsequently integrate them into synthetic orthographic images with the reference of the local map segments. Furthermore, the information of the driving lanes is extracted from the orthographic images and a large amount of vehicle trajectories, which is used to construct the lane graph of the map based on the lane models we proposed. Such a system can offer increased value as well as promote the automation level for today's commercial cars without being supplemented additional sensors. Experiments show promising results of the automatic map generation of the real-world roads, which substantiated the effectiveness of the proposed approach.

Comprehensive situational awareness is paramount to the effectiveness of higher-level functions of the advanced driver assistance systems (ADAS) used in daily urban traffic, in which, the host vehicle have to interact with other cars. This paper addresses a multimodal advanced driver assistance system, which we call CADAS (Contextual ADAS), designed for expanding the usability of current ADAS functions, including LKA, ACC, and PCS, to normal urban streets, particularly for non-marking roads. In the proposed system, the relational contexts between the host vehicle, the road and other vehicles are employed for both the low level object detection improvement and the high level scene understanding and decision making. Experimental results in various typical but challenging scenarios show the effectiveness of the proposed system.

This paper proposes a novel technique to generate accurate road ortho-images using low-cost sensors (single frequency GPS, speed sensor and MEMS yaw rate gyro). Ortho-images are data incorporated into accurate digital maps. Our proposal should contribute to reduction in production costs of accurate digital maps. The most striking feature of our proposal is vehicle trajectory estimation using GPS Doppler, for road image mosaicing. We realize accurate trajectory and heading angle estimation by integrating GPS Doppler and yaw-rate gyro. This enables creation of ortho-images with a combination of devices less expensive than the conventionally used ones. A comparison with commercial road ortho-images shows that our proposed technique can realize the same level of accuracy.

This paper describes a precision positioning technique that can be applied to vehicles in urban areas. The proposed technique mitigates Global Positioning System (GPS) multipath by means of an omnidirectional infrared (IR) camera that can eliminate the need for invisible satellites [a satellite detected by the receiver but without line of sight (LOS)] by using IR images. Some simple GPS multipath mitigation techniques, such as the installation of antennas away from buildings and using choke ring antennas, are well known. Further, various correlator techniques can also be employed. However, when a direct signal cannot be received by the antenna, these techniques do not provide satisfactory results because they presume that the antenna chiefly receives direct signals. On the other hand, the proposed technique can mitigate GPS multipath, even if a direct signal cannot be received because it can recognize the surrounding environment by means of an omnidirectional IR camera. With the IR camera, the sky appears distinctively dark; this facilitates the detection of the borderline between the sky and the surrounding buildings, which are captured in white, due to the difference in the atmospheric transmittance rate between visible light and IR rays. Positioning is performed only with visible satellites having fewer multipath errors and without using invisible satellites. With the proposed system, static and kinematic evaluations in which invisible satellites are discriminated through observation using an omnidirectional IR camera are conducted. Hence, signals are received even if satellites are hidden behind buildings; furthermore, the exclusion of satellites having large errors from the positioning computation becomes possible. The evaluation results confirm the effectiveness of the proposed technique and the feasibility of highly accurate positioning.

This paper describes a precision positioning technique that can be applied to vehicles in urban areas. The proposed technique mitigates GPS multipath by means of an omnidirectional infrared (IR) camera that can eliminate the need for invisible satellites (a satellite detected by the receiver but without LOS (Line Of Sight)) by using IR images. Some simple GPS multipath mitigation techniques such as installation of antennas away from buildings and using choke ring antennas are well known. Further, various correlator techniques can also be employed. However, when a direct signal cannot be received by the antenna, these techniques do not provide satisfactory results because they presume that the antenna chiefly receives direct signals. On the other hand, the proposed technique can mitigate GPS multipath even if a direct signal cannot be received because it can recognize the surrounding environment by means of an omnidirectional IR camera. With the IR camera, the sky appears distinctively dark; this facilitates the detection of the borderline between the sky and the surrounding buildings, which are captured in white, due to the difference in the atmospheric transmittance rate between visible light and the IR rays. Positioning is performed only with visible satellites having less multipath errors, and without using invisible satellites. With the proposed system, static and kinematic evaluations in which invisible satellites are discriminated through observation using an omnidirectional IR camera are conducted. Hence, signals are received even if satellites are hidden behind buildings; furthermore, exclusion of satellites having large errors from the positioning computation becomes possible. The evaluation results confirm the effectiveness of the proposed technique and the feasibility of highly accurate positioning.

This study discusses a unique disaster-information collection technique that involves the collaboration of a rescue system and a GIS. The proposed technique can be applied to any rescue system by saving the information collected by the robot as text files. The rescue systems can realize a simple and flexible database across networks by "MISP." Disaster information is collected effectively by different types of rescue robots and transmitted to the "spatial-temporal GIS" using MISP. Effective disaster-information analysis is achieved by the spatial-temporal GIS DiMSIS/DyLUPAs. Field experiments (collapsing house, vast disaster areas) reveal the validity of the proposed disaster-information collection system

This paper describes an autonomous mobile surveillance system usually used in a factory premises with some high-rise buildings. This system consists of a wireless LAN network, a base station and an autonomous vehicle. The vehicle is equipped with a GPS/INS navigation system using the network-based Real-Time Kinematic GPS (RTK-GPS) with Positioning Augmentation Services (PASTM, Mitsubishi Electric Corporation 2003), an Area Laser Radar (ALR), a CCD camera called slaved camera, and an Omni-Directional Vision (ODV) sensor for surveillance and reconnaissance. The vehicle switches navigation modes according to the vehicle status. It has three guidance modes, which are “Normal”, “Road tracking”, and “Crossing recognition”. A field test result shows that the vehicle can track the planned path within 0.10[m] accuracy at straight paths and within 0.25[m] for curved paths even if RTK fixed solutions are not available. Field experiments and analyses have proved that the proposed navigation method can provide good enough guidance accuracy even under poor satellite visibility and that the panorama image database with absolute position is useful for surveillance.