Yoshinobu Ando

Picking up operation of thin objects by robot arm with two-fingered parallel soft gripper

One of the tasks which we expect executing by home service robots is a handling of thin objects like papers or plastic cards. It is a difficult task for the home service robots to pick up a thin object placed on the table, because it needs high dexterity. To achieve this motion by home service robots, we used a two-fingered parallel soft gripper with a soft nail, and constructed a sequence of picking up operation of a paper or a plastic card by a robot arm. The constructed sequence consists of sliding motion and raising motion. The robot slides a paper or a card and hooks its nail at the side of it, and raises one side of it, and picks it up like humans. In this paper, we propose a sequence of picking up operation of a paper or a plastic card on the table derived from the analysis of human motions, and confirm its availability through experiments.

Development of the Robot Power Management System Adapting to Tasks and Environments -The design guideline of the Power Control System Applied to the Distributed Control Robot

Efficient energy usage is crucial issue because energy consumption increases with the spread of RT (robot technology) application fields. Power consumption in a robot system changes according to a task and its operating environment. To adapt these conditions, we have proposed the CEPC (component for electric power control). This paper describes the electric-power design guideline of a robots subsystem and investigation on the power consumption data obtained from experiments

Research on person following system based on RGB-D features by autonomous robot with multi-Kinect sensor

In this study, we develop a person following system based on RGB-D features by autonomous robot with multi-Kinect sensor. The sensor system is composed of multiple Kinect sensors, we call it “Multi-Kinect”. Since the field of view of a single Kinect sensor is narrow, this sensor makes it wider by using three Kinect sensors. Furthermore, the system selects a person who raises hand or says “Start” as the target of following at the beginning. Then, the system can identify a person from the person location and characteristics of clothes and re-recognizes the target of following when an occlusion occurs. Herewith, a mobile robot with this sensor accomplishes a human detection and follows only the target of following even if more than two people is located around the robot.

A Mobile Robot Navigation by Means of Range Data from Ultra Wide Angle Laser Sensor and Simple Linguistic Behavior Instructions

A navigation scheme for a mobile robot is presented, where a set of linguistic instructions are formulated to command the robot to move toward destination in a corridor environment. This approach do not need a detailed model of the environment. The robot is equipped with ultra-wide-angle laser range sensor. Fundamental functions based on the surroundings information obtained from the laser range sensor: to move along the corridor without any collision with walls nor objects, and to find a crossings are provided on the robot to move in the corridor directed by the set of instructions.

Casting and Winding Manipulation with Hyper-Flexible Manipulator

Non-elastic hyper-flexible elements like tethers and ropes will have various possibilities of unconventional manipulations. In this paper, casting and winding manipulation of hyperflexible manipulators (HFM) is proposed. The HFM is modeled as an underactuated multi-link system connected by non-elastic passive joints, and simulation results with dynamic parameters heuristically determined corresponding to the experimental results show the validity of the proposed non-elastic model. The simulation results also correspond to the experimental ones with actuation at the base joint. Observations on the simulation results is derived to reveal a better casting actuation to succeed in winding to an object. Then, single swing actuation for winding is proposed and verified in simulations

A Trajectory generation of cloth object folding motion toward realization of housekeeping robot

In our research, we aim to construct a house-keeping robot system which folds laundry. And, we propose a way for folding clothes without vision sensing device. To realize this system, we prepare appropriate fixed folding motion. We analyzed cloth folding motions by human. And, we found fixed folding motion pattern for the robot. Furthermore, we generated a trajectory of folding motion which is applicable to different size of towels. We confirmed the effectiveness of our method through experiments without the use of vision sensing device.

“Tsuide task (Accompanied task)” Service Framework for user RT-service generation system

We introduced robot technology (RT) Ontology for human-robot interactive space design. In this interactive space, the robot provides appropriate services to the user according to situations. For this purpose, we defined “Main task” as a task which user requests to the robot, and “Tsuide task (Accompanied task)” as an essential task accompanied with the “Main task” to complete it in our system. We focus on the development of the system for identifying and defining “Tsuide task” that is set from the intention of user and main tasks by referring RT Ontology. RT Ontology is an infrastructure technology for structuring space information. Our system acquires relationship information from RT Ontology, and set “Tsuide task” in the “Tsuide task” Service Framework. The availability of the proposed framework was confirmed through experiments of five cases. In this paper, we describe the structure and process of “Tsuide task” Service Framework which we have constructed for identifying and defining “Tsuide task”.

Physical agent system: concept and implementation

In this paper, we propose the concept of the PAS (physical agent system) and its implementation. The PAS is the tele-operated autonomous robot system that acts as AGENT, and is used to support human collaboration activities over distant places using robots. The PAS consists of the autonomous mobile robot equipped with a CCD-camera, a laser-pointer and an arm. The mobile robot is controlled by the distributed microprocessor system to allow flexible system configuration and adoption of various effectors and sensors. The camera and laser-pointer system is used as active vision system to measure the distance to the object pointed by the laser beam keeping the object in the view. The mobile robot is driven by crawler. It is equipped with ultra-sonic sensors and PSDs to detect obstacles around the robot along the directed path. Using these sensors, the mobile robot autonomously avoids the obstacles keeping the goal pointed by the laser beam. Another feature of the PAS is the system description using XML (extensible markup language) to achieve flexible configuration and to adopt various devices by defining functions and specifications of the subsystems such as effectors, sensors and operation devices.

A study of towel folding by a robot arm - Spreading and vertex detection using image processing

In this study, we aim to construct a sequence of towel folding operations by a robot arm. In this paper, we propose the methods for spreading a towel and detecting the grasp positions. For the easy spreading of the towel, we propose how to put the towel on the table. The proposed method lifts one vertex of the towel, and detects the shadow part by using a camera image for recognizing the overlapped condition of the towel. For the folding motion of the towel, we set the vertices of the towel edges as grasping positions. So, we propose the way to detect the vertices of the towel correctly by generating a rectangle which includes all feature points of the towel by using image processing.

A study of intelligent drawer with RFID tag information reading system for Intelligent Space

People store many things in drawer cases. However, they sometimes forget the places of the stored things. As a solution of this problem, we propose a managing system which server stores and informs the place of the stored things by using the idea of “Intelligent Space”. Home service robot is able to use this system for getting information of stored things and bring them to the user. The system consists of drawer case, RFID tag, tag antenna and tag reader. RFID tag is attached to the stored things. Tag antenna reads RFID tag data and gets information of the things. In this system, reliability of RFID tag reading is especially important. However, the stored things in the drawer case are vary and the positions and orientations of the attached RFID tags are different according to the posture and the shape of the stored things. It is necessary to be read RFID tags of various positions and orientations in this system. In this paper, we consider the method to read RFID tags of various positions and orientations. Especially, we consider reading the vertical RFID tags in regard to tag antennas. We made a prototype model of drawer case, and evaluated it through experiments.