Kentaro Hashimoto

Learn More
— A technique to recognize the shape of a grasping hand during manipulation tasks is proposed; which utilizes a 3D articulated hand model and a reconstructed 3D volume from infrared cameras. Vision-based recognition of a grasping hand is a tough problem, because a hand may be partially occluded by a grasped object and the ratio of occlusion changes along(More)
In this paper we propose a new visual servoing technique using point correspondences. This approach ensures, for known intrinsic parameters and optical axis direction, global convergence and guarantees to keep all points in the field of view of the camera during the robot control, without requiring any knowledge on the 3D model of the scene. Moreover, the(More)
To date, many control methods have been researched on the assumption that the soles of a biped walking robot contact the ground as four points. It is difficult for almost all biped robots to maintain four-point-contact on uneven terrain because they have rigid and flat soles. It means that the biped robots can lose their balance. To solve this kind of(More)
In this paper we describe how a humanoid robot can learn a representation of its own reachable space from motor experience: a Reachable Space Map. The map provides information about the reachability of a visually detected object (i.e. a 3D point in space). We propose a bio-inspired solution in which the map is built in a gaze-centered reference frame: the(More)
This paper describes a static disturbance compensation control for a biped walking vehicle. To measure forces and moments caused by a passengerpsilas motion, we use a 6-axis force/torque sensor placed under the passengerpsilas seat. When small external force acts on a robot, only a reference ZMP trajectory is changed inside a support polygon. When large(More)
This paper describes the development of a prototype biped walking wheelchair. This robot consists of two Stewart platform type legs and waist with a passenger seat. The walking control method based on ZMP criteria and virtual compliance control method for this robot were also developed. Through various experiments, the effectiveness of the developed(More)
This paper describes a walking stabilization control on a soft ground based on gait analysis for a biped humanoid robot. There are many studies on gait analysis on a hard ground, but few physiologists analyze the walking ability of human beings on a soft ground. Therefore, we conducted anthropometric measurement using VICON motion capture system on a soft(More)
The neuroscientific research shows that humans tend to stabilize their head orientation, while accomplishing a locomotor task. In order to replicate head movement behaviors found in human walk it is necessary and sufficient to be able to control the orientation (roll, pitch and yaw) of the head in space. The described behaviors can be replicated by giving(More)
This paper describes a trajectory planning method of ladder climbing for a four-limbed robot. The overall design of the four-limbed robot and the specific design of its end-effector is explained. The trajectory planning consists of two components: path planning and time planning, and the separation of these two parts are realized by arc-length(More)
  • 1