Papers by Atsushi Yamashita
Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006.
Sensing in underwater environments meets the difficulty that, when a camera is set in air behind ... more Sensing in underwater environments meets the difficulty that, when a camera is set in air behind a watertight glass plate, image distortion occurs by refraction of light at the boundary surface between air and water. It has also the problem that air bubble noises sometimes disturb image processing. This paper proposes a robust sensing method, which is realized by "three-dimensional measurement that took refraction of light into account" and "accurate extraction of measurement object from bubble noises by image processing", in underwater environments.
Recent Advances in Mobile Robotics, 2011
Then, line features should be utilized for environment measurement, because non-texture objects o... more Then, line features should be utilized for environment measurement, because non-texture objects often have straight-lines. As examples of previous works using lines, a method for precise camera movement estimation by using stereo camera (Chandraker et al., 2009), a method for buildings reconstruction by using orthogonal lines (Schindler, 2006) and so on (Bartoli & Sturm, 2005; Smith et al., 2006; Mariottini & Prattichizzo, 2007) have been proposed. However, there is a prerequisite on previous line detections of them. A method must obtain a vanishing point (Schindler, 2006) or a pair of end points of the straight-line (Smith et al., 2006). Some of previous line detection is only for a normal camera (Chandraker et al., 2009). Alternatively, some previous methods obtain line correspondences by hand (Bartoli & Sturm, 2005; Mariottini & Prattichizzo, 2007). We propose a method for straight-line extraction and tracking on distorted omnidirectional images. The method does not require a vanishing point and end points of straight-lines. These straight-lines are regarded as infinite lines in the measurement process (Spacek, 1986). Therefore, the proposed method can measure straight-lines even if a part of the line is covered by obstacles during its tracking. Our proposed method measures feature points together with straight-lines. If only straightlines are used for camera movement estimation, a non-linear problem must be solved. However, camera movement can be estimated easily by a linear solution with point correspondences. Moreover, although few numbers of straight-lines may be extracted from textured objects, many feature points will be extracted from them. Therefore, we can measure the environment densely by using both feature points and straight-lines. The process of our proposed method is mentioned below (Fig. 2). First, feature points and straight-lines are extracted and tracked along an acquired omnidirectional image sequence. Camera movement is estimated by point-based Structure from Motion. The estimated camera movement is used for an initial value for line-based measurement. Fig. 2. Procedure of our proposed method. Image sequence acquisition Feature point tracking Straight-line tracking Point-based measurement Line-based measurement Camera rotation & line direction Camera translation & line location Result qualification Modeling www.intechopen.com Three-Dimensional Environment Modeling Based on Structure from Motion with Point and Line Features by Using Omnidirectional Camera 53 The proposed line-based measurement is divided into two phases. At the first phase, camera rotation and line directions are optimized. Line correspondence makes it possible to estimate camera rotation independently of camera translation (Spacek, 1986). Camera rotation can be estimated by using 3-D line directions. At the second phase, camera translation and 3-D line location are optimized. The optimization is based on Bundle adjustment (Triggs et al., 1999). Some of measurement results have low accuracy. The proposed method rejects such results. Measurement results of feature points and straight-lines are integrated. Triangular meshes are generated from the integrated measurement data. By texture-mapping to these meshes, a three-dimensional environment model is constructed.
IEICE Transactions on Information and Systems, 2007
In this paper, we proposed a new region extraction method using chroma key with a two-tone checke... more In this paper, we proposed a new region extraction method using chroma key with a two-tone checker pattern background. This method solves the problem in conventional chroma key techniques that foreground objects become transparent if they have the same color with the background. The method utilizes the adjacency condition between two-tone regions of the background and the geometrical information of the background grid lines. Experimental results show that the foreground objects can be segmented exactly from the background regardless of the colors of the foreground objects.
IEEE Transactions on Robotics and Automation, 2003
In this paper, we propose a motion-planning method of multiple mobile robots for cooperative tran... more In this paper, we propose a motion-planning method of multiple mobile robots for cooperative transportation of a large object in a three-dimensional environment. This task has various kinds of problems, such as obstacle avoidance and stable manipulation. All of these problems cannot be solved at once, since it would result in a dramatic increase of the computational time. Accordingly, we divided the motion planner into a global path planner and a local manipulation planner, designed them, and integrated them. The aim was to integrate a gross motion planner and a fine motion planner. Concerning the global path planner, we reduced the dimensions of the configuration space (C-space) using the feature of transportation by mobile robots. We used the potential field to find the solution by searching in this smaller-dimension reconstructed C-space. In the global path planner, the constraints of the object manipulation are considered as the cost function and the heuristic function in the search. For the local manipulation planner, we developed a manipulation technique, which is suitable for mobile robots by position control. We computed the conditions in which the object becomes unstable during manipulation and generated each robot's motion, considering the robots' motion errors and indefinite factors from the planning stage. We verified the effectiveness of our proposed motion planning method through simulations.
The Journal of The Institute of Image Information and Television Engineers, 2007
Transactions of the JSME (in Japanese), 2015
This paper describes a development of bird's-eye view system for teleoperation. Emergent disaster... more This paper describes a development of bird's-eye view system for teleoperation. Emergent disaster recoveries are important when natural disaters occur. Unmanned construction is used to recover from natural disasters such as landslide and pyroclastic flow. This construction method has no risk of secondary disaster because workers teleoperate construction machines at remote site. However, traditional unmanned construction is an inefficient way because captured images from a camera mounted on a construction machine usually has blind spots. We propose an easy calibration method to create bird's-eye view images which can reduce blind spots from multiple cameras. Our method helps workers understand environment easily and operate construction machines safely. We evaluate working efficiency by integrating our bird's-eye view system into actual unmanned constuction systems under actual field conditions.
Advances in Intelligent Systems and Computing, 2013
In this paper, we propose a mobile robot system which has functions of person following and auton... more In this paper, we propose a mobile robot system which has functions of person following and autonomous returning. The robot realizes these functions by analyzing information obtained with camera and laser range finder. Person following is performed by using HOG features, color information, and shape of range data. Along with person following, a map of the ambient environment is generated from the range data. Autonomous returning to the starting point is performed by applying a potential method to the generated map. We verified the validity of the proposed method by experiment using a wheel mobile robot in an indoor environment.
Proceedings of the 4th Asia International Symposium on Mechatronics, 2010
It is necessary for a biped robot to recognize a surrounding environment when moving to the desti... more It is necessary for a biped robot to recognize a surrounding environment when moving to the destination. This paper presents a method for path planning and obstacle avoidance for the biped robot. In our approach, the robot obtains color information and distance information of objects from images captured by a stereo camera system. Then, the robot generates a 2D grid map which locates floor regions, bump regions, obstacle regions and unmeasured regions. The robot decides its path by using the 2D grid map. Experimental results show the effectiveness of the proposed method.
Journal of the Japan Society for Precision Engineering, 2007
The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec), 2019
This paper proposes a novel motion planning method that can deal with changes in rough terrain ef... more This paper proposes a novel motion planning method that can deal with changes in rough terrain efficiently. Previous studies on motion planning in rough terrain did not consider significant changes in the environment. To solve this problem, we propose an efficient re-planning method. The re-planning method is characterized by using search tree repeatedly as long as it is still valid. Reusing search tree enables limiting the re-planning region, which leads to the shorter planning time. After re-planning, the re-planned path is deformed to shorten the length of the path. Experimental results show that the proposed method can generate a collision-free path against a significant environmental change and perform the re-planning within a short time.
The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec), 2018
This paper proposes a method to visualize running stability of robots in its surrounding terrain.... more This paper proposes a method to visualize running stability of robots in its surrounding terrain. The stability should be evaluated by taking account of the physical interaction between a robot and terrain. In this study, the dynamics of the robot behavior in the terrain is calculated in advance with a dynamic simulator, and the stability is assessed by our proposed criterion that can evaluate the tumble risk in a term. The calculated stability is visualized to the teleoperation operator, and therefore, a safe path can be chosen to move. In experiments, the validity of the proposed method was performed by testing additionally in an actual environment after the simulation.
The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec), 2015
Yusuke TANAKA ， the University of T()kyo， tanaka ◎robot ． t． u − tokyo ． ac ． jp Ybnghoon JI ， th... more Yusuke TANAKA ， the University of T()kyo， tanaka ◎robot ． t． u − tokyo ． ac ． jp Ybnghoon JI ， the University of Tokyo ， ji ◎ robot ． t． u − tokyo ． ac ． jp Atsushi YAMASHITA ， the University of Tokyo ， yamashita ◎ robot ． t． u − tokyo ． ac ． jp Hajime ASAMA ， the University of Tokyo ， asama ◎robot ． t． u − tokyo ． ac ． jp This paper describes a novel rough terrain traversability analysis method br a mobile robot navigation ． We focused on the scenario of mobile robot operation in disaster environnlent with limited sensor data． The proposed method enables mobile robots to analyze terrain traversability ofsurrounding area and select safe course direction in spite of the limited sensor data acquisition area ． Terrain traversability analysis and oourse direction judgment are realized based on feature value calculation of terrain， fUzzy inference and veCtor field histogram ． The experilllental results show that the proposed method can select safe course direction of the mobile robot successfully ． Key Wotxts ： r)lobile robot ， Course direction judgment ， Terrain traversability analysis
The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec), 2003
The Journal of The Institute of Image Information and Television Engineers, 2008
TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C, 2006
Transactions of the Japan Society of Mechanical Engineers Series C, 2006
Lecture Notes in Computer Science, 2011
There are individual differences in color vision. It is difficult for a person with defective con... more There are individual differences in color vision. It is difficult for a person with defective cones in the retina to recognize the difference of specific colors. We propose a presentation method of color information by using a projector-camera system. The system projects border lines or color names on real object surfaces when they have specific color combinations. Registration of projected images and real objects is made by using projected markers. Effectiveness of the proposed method is verified through experiments.
Advances in intelligent systems and computing, 2013
In this paper, we propose a method for a mobile robot to avoid obstacles in its environment using... more In this paper, we propose a method for a mobile robot to avoid obstacles in its environment using an omni-directional camera. The method makes an environment map consisting of 3D edge points obtained from omnidirectional camera images and estimates the locations of planes by analysing these 3D edge points so that the robot can avoid walls as obstacles. The method has the advantage that it can generate a 3D map in environments constructed by textureless planes. Experimental results show the effectiveness of the proposed method.
2011 IEEE International Conference on Robotics and Biomimetics, 2011
A lot of plumbings such as gas pipes and water pipes exist in public utilities, factories and so ... more A lot of plumbings such as gas pipes and water pipes exist in public utilities, factories and so on. The use of an omni-directional camera which can take images of 360 in surroundings at a time is effective for pipe inspection. However, shape measurement is difficult only with the omnidirectional camera. Therefore, in this paper, we propose a reconstruction method of a piping shape by using a rangefinder construted with an omni-directional camera and an omni-directional laser. The rangefinder is mounted on an earthworm robot. Our method calculates 3-D coordinates by the light section method. By integrating the 3-D coordinates with the information of camera motion estimated by the structure from motion technique, the shape of the pipe is reconstructed. The validity of the proposed method is shown through experiments.
TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C, 2013
Bottom-up processes have received much attention in unsupervised and developmental learning resea... more Bottom-up processes have received much attention in unsupervised and developmental learning research domain. In contrast, effectiveness of top-down deeming on acquisition of adaptive behavior is discussed in this paper. Successful experience in the past, or a skill that could be expected to be reused successfully in a novel environment is stored in memory. Then abstract environment recognition via geometric transformation invariance is introduced to measure the reproducibility of executed skill in a novel environment. Additionally, reproducibility of skill in the environment is utilized to make up intrinsic motivation that drives the agent to active conceptualization of search space. It enables the agent to relativize current skill execution robustly in diverse environments. Useful characteristics of top-down deeming process are implemented on reinforcement learning and discussed through simulation experiments in grid world. The results demonstrate acceleration of learning progress by active conceptualization of environment. Additionally, it is shown by experiments for scaled environment that subjective anticipation could bring in consistent strategy of exploration and exploitation. Eligibility trace is also introduced for skill utility problem and it is shown that the traces regarding actions and skills could preserve learning performance for diverse skill settings.
Uploads
Papers by Atsushi Yamashita