This paper proposes a character segmentation method using a fully convolutional network (FCN) and a post-processing phase. The network is trained with five-channel images that indicate five kinds of zones within the bounding box for each character-the top half, bottom half, left half, right half, and center. The post-processing step reconstructs the bounding boxes for characters from the five-channel image of the FCN output. The proposed method possesses the following advantages: (1) It is possible to process input images including multiple text lines directly; in other words, a text line segmentation process is unnecessary. (2) It does not rely upon character recognition. (3) It is robust to variations in the sizes of characters and the gaps between characters and also to cursive characters or character overlap. In the experiment of character segmentation, the accuracy ratio was 95% for real images of historical handwritten official documents written in Japanese.

The challenge of this work is to study the design and development of human-robot collaboration (HRC) in cellular manufacturing. Based on the concept of human collaborative design, four main design factors are being identified and developed in an active HRC prototype production cell for cable harness assembly. Human collaborative design aims to optimize the system design for the advantage of collaboration between human and robots based on human considerations. Task modeling approach is developed to study and analyze the task in order to identify the collaboration tasks to develop the collaboration planning. In the collaboration safety development, five safety designs, cover both hardware and control design, are proposed and developed in the prototype system. Risk assessment is conducted to verify the safety design. Two main experiments were conducted as preliminary study to investigate mental workload in HRC. A multimodal information support system is developed in the study of man-machine interface in this work to provide a comprehensive human-robot interface to facilitate human operator. The system performance evaluation had proven the improvement of prototype production cell with HRC design for cellular manufacturing.

The purpose of this work is to conduct human factors studies in the development of an information support system for human-robot collaborative cellular manufacturing system. Multimedia technologies are being utilized to enhance the support system to function as operational information support and interface between human operator and robot system. In the study, five experiments were carried out in both system hardware and support information developments to investigate the human factors design of the support system. In the information display approach study, comparison of information presentation ability among paper manual, LCD TV and projector was conducted. Similar information was displayed in different visual areas by vertical and horizontal LCD TV configurations to study the effect on human visual working area. The comparison experiment on image, text and voice formats had resulted varying modality effectiveness of information. Different information formats require different human cognitive processes even though the information contents are similar. The investigation on multimedia displays in five combinations of information elements was performed in multimedia display design study. The information support system is implemented in a human-robot collaborative prototype production cell. The cable harness assembly experiment had proven the effectiveness of the information support system in guiding the operators on the assembly operation and also to collaborate well with the robot system.

This paper proposes a visual tracking method which is robust to occlusion. This paper also integrates the visual tracking method and visual servo control into a vision-based control method with occlusion handling. The proposed method chooses a set of correctly extracted image features, and it then obtains an estimate of all the image features from the correctly extracted image features. The estimation procedure makes it possible to track image features even when occlusion occurs. The method has low computational complexity, since the image Jacobian is used for the image feature selection and estimation. In addition, even when the controller fails to track a moving image feature, it can find the failed image feature without a global search over the entire image plane. As a result, it can track the failed image feature again quickly.

This paper proposes an assistant and training system for controlling an unmanned helicopter. The unmanned helicopter does not have any sensors which measure its position or posture. Stationary cameras are placed on the flight field. The helicopter is controlled by using a visual servo technique as follows. An operator steers the helicopter using sticks on a hand-held input device. The sticks make reference signals. The assistant system designs control signals such that the helicopter tracks the reference signals. The proposed system has the following four functions: automatic takeoff and landing, control channel selection, flight in a desired area, and automatic motion generation. They enables beginners to control an unmanned helicopter. The system provides real actions of unmanned helicopters. This is the main difference from flight simulators.

In this paper, methods for detecting obstacles on a plane using a relative disparity map (RDMap) are proposed and discussed. The RDMap, which was formerly introduced by the author Umeda, is relative to a plane that is observed at first as the reference. It has an interesting feature that a plane in real 3D space also becomes a plane in the map, and has homogeneous characteristics compared to an ordinary range image. The proposed methods work even when the pose of the sensor changes significantly, which is the case in humanoid walking. First, a method to detect planar regions and obstacles by fitting a plane to the RDMap and a method to obtain the pose parameters from the RDMap are introduced. Fundamental experiments are then conducted to verify that a plane in real 3D space becomes a plane in the RDMap and that obstacles can be detected using the residual sum of squares for the fitted plane, and measurement errors in pose parameters are then evaluated. Finally, an experimental system with a humanoid and a small range image sensor is constructed, and it is demonstrated that the humanoid can detect obstacles on a plane by the proposed methods while walking.

This paper proposes a switched visual feedback control method for a micro helicopter under occlusions. Two stationary cameras are placed on the ground. They track four black balls attached to rods connected to the bottom of the helicopter. The control input is computed by using the errors between the positions of the tracked objects and pre-specifled reference values for them. The multi-camera configuration is redundant for helicopter control, but it enables us to design a switched controller which is robust against occlusions. An occlusion occurs when an object moves across in front of a camera or when the background color happens to be similar to the color of a tracked object. Multi-camera systems are suitable for designing a robust controller under occlusions, since even when a tracked object is not visible in a camera view, other cameras may track it. The authors have proposed a camera selection approach: If an occlusion is detected in a camera view then the other camera is used to control the helicopter. This paper presents another switched visual feedback control method for a micro helicopter under occlusions. This is called the image feature selection approach. This paper assumes that at most one tracked object is occluded at each time to simplify notations, although we can draw general conclusions. The errors between the positions of the tracked objects and pre-specifled references are used to compute the control input, when all the tracked objects are visible. If one of the tracked objects is invisible, then the controller uses the errors given by the other three tracked objects. The position of the occluded object is also estimated by using the other three tracked objects.