In prior research, a method was introduced for traversability perception in autonomous mobile robots, utilizing a Growing Neural Gas with Different Topologies (GNG-DT). The traversability refers to the points at which an autonomous mobile robot can traverse. GNG-DT traditionally relied on pre-set parameters like slope angle and surface roughness to estimate traversability. To address this limitation, an estimation technique leveraging supervised learning is proposed. Using the proposed method, it is shown that the robot performance-based traversability can be estimated using supervised learning. In addition, the robot can avoid obstacles using self-learned traversability. The current study advances this work by introducing a self-learning approach for estimating traversability, enabling self-supervised learning in perceptual systems.

One of the most important capabilities of an autonomous robot is to recognize a 3D space of the surrounding environment in real-time from a 3D point cloud measured by a 3D distance sensor. The area in which the robot can travel is limited by a robot embodiment such as a mechanism of the robot. Therefore, the traversability estimation method helps the robot to travel safely and reduces the calculation cost of the path planning. This paper proposes Growing Neural Gas (GNG) based traversability estimation method by utilizing a topological structure learned from the 3D point cloud data. However, the conventional GNG cannot preserve the geometric information of the 3D point cloud if the input vector is composed of the multiple properties. Therefore, this paper apply GNG with Different Topologies (GNG-DT) that learn the multiple topological structures according to the number of properties. This paper proposes a GNG-DT based traversability estimation method by redefining the property of the GNG-DT. We conduct several experiments in both simulation and real environment to verify the effectiveness of our proposed method.

We have developed a CT guided needle puncture robot (Zerobot) to assist in interventional radiology surgery. Currently, Zerobot is operated remotely, and the next goal is to perform automatic needle puncture surgery. There is a challenge that automatic detection of puncture needle from CT images for first step of automatic puncture surgery. Because there is the case that the form of puncture needle is curved, it is necessary to detect the needle from CT image instead of estimating the needle position from arm of Zerobot. First, the method detects ROI with ResNet. Next, difference of the CT value is calculated for each pixel in the ROI, and a linear approximation is performed for to detect the needle shape. Images from animal experiments were used to evaluate the learner and image processing. We confirmed that the proposed method can detect needles in a single image and in multiple images.

An autonomous mobile robot needs many tasks such as self-localization, collision detection, and path planning to a target position in an unknown environment. Therefore, the robot needs to build environmental maps with different resolutions in each workspace. In addition, the robot requires the path planning capability in the unknown environment for applying the robot to various domains such as a disaster site and commercial construction. This research proposes a Growing Neural Gas based topological environmental map building method from a metric map with a high-resolution map for using self-localization. Our proposed method enables us to build the topological map with occupancy information of the metric map and simultaneously preserve the geometric feature of the map. Next, the path planning method in unknown environments is proposed by utilizing the topological map, and the sub-goal selection of the topological map is proposed by utilizing the contour node information for realizing the path planning in an unknown environment. Finally, we conducted several experiments to evaluate our proposed method and discuss its effectiveness.

Recently, the demand to manipulate deformable objects such as a string and cloth by robots is growing. The reason is that it has the possibility of making our lives more convenient in many domains. The manipulation of deformable objects, however, is more difficult than that of rigid objects, because deformable objects have diversity of shape and behavior. Therefore, our research group has been focusing on the string shape operation. This paper describes planning method of string untying operation based on knot theory and algorithms to generate the motion of a manipulator. The novel contribution of our planning method is automatic selection of optimal shape operation based on cost function. At final, the results of string untying experiments are reported.

This paper explores a strong stability system, which regulates safety for generalized minimum variance control (GMVC). GMVC is one of the control methods for application in industry and the controller is designed by generalized output to make the closed-loop system stable. Once the generalized output is designed, the derived controller cannot be re-designed without changing the closed-loop characteristic. For safe applications in industry, it is desirable that both of the closed-loop system and the controller are stable. That is, the strong stability system, which means that both of the closed-loop system and the controller are stable, is desirable to develop the applications. Although authors have proposed the extended GMVC design methods and the strong stability systems by using coprime factorization, there is a problem that the degree of controller may be higher than the conventional method because stable polynomial is needed in order to obtain coprime factorization. Therefore this paper directly extends GMVC without coprime factorization, and a strong stability system regulating safety is studied from the view point of the quantity of feedback signal. Some numerical examples are shown in order to check the characteristic of the proposed method.

This paper deals with estimation of thermal conductivity for temperature control of an aluminum plate considering radiative heat transfer. Aiming at accurate control results, model-based control method needs true values of plant parameters. In our previous research, the nominal values of plant parameters have been used for temperature control experiment. However, for the actual environment in industrial field, physical parameters such as thermal conductivity will change. Therefore this paper reports the estimation result of thermal conductivity of aluminum plate considering radiative heat transfer through experimental data.

There is minimally invasive method called Interventional Radiology (IR) that achieves an operation by using diagnostic imaging equipment such as Computed Tomography (CT). IR has advantages that it is a minimally invasive method and it is applied widely such as lung cancer treatment, liver cancer treatment, biopsy, and so on. However, it has a problem that doctors are exposed by X-ray due to a procedure in the vicinity of the CT gantry. To solve this problem, we have developed a robot so we calling “Zerobot”. Zerobot has six DOF and controlled remotely. We previously conducted animal experiment using a rabbit to evaluate Zerobot. As a result, percutaneous puncture was impossible without epidermis cutting. Therefore, we developed a new function called instantaneously puncture that can achieve high speed and short stroke puncture like a human operator. In this paper, overview of Zerobot is described first. Then, measurement of puncture speed of a human operator is described. Furthermore, design and system structure of instantaneously puncture system is described. Finally, we present results of animal experiment using the instantaneously puncture system.

The demand is growing that a robot manipulates a deformable object. Scenarios for both of a grasping point and transfer of grasped point are required, in order to manipulate a deformable object by a robot. Therefore, it is important for a robot to recognize its form by using image information. In this paper, three-dimensional points groups of a string are obtained by a camera that has distance measure equipment. A shape model called “point chain model” is obtained from points group based on proposed algorithm. In this algorithm, first, points which are estimated to be outside of target object are removed from obtained points groups. Secondly, points groups obtained from various viewpoints are combined to reconstruct three-dimensional shape of a string. Thirdly, central axes of a string are abstracted from combined points groups. Finally, central axes are chained to construct the point chain model. Effectiveness of proposed algorithm is confirmed by experiment.

Fault detection functions with learning method of a robotic manipulator are very useful for factory automation. All production has the possibility to fail due to unexpected accidents. To reduce the fatigue of human workers, small errors automatically should be corrected by a robot system. Also a learning method is important for fault detection, because labor of system integrator should be reduced. In this paper, an external thread fastening task by a robotic manipulator is investigated. To discriminate the four states of a task, linear support vector machine methods with two feature parameters are introduced. The effectiveness of the proposed algorithm is confirmed through an experiment and recognition examination. Finally, the ability of linear SVM is compared with artificial neural network method.

The traffic congestion is growing in urban area these days due to the rapidly increasing number of automobiles. One of the traffic problem solutions is to increase the flow rate of a particular traffic artery. To make the vehicle smaller and narrower might be a good idea. We developed a new conceptual Narrow Tilting Vehicle (NTV) that has one front wheel and two rear wheels. The proposed NTV is very narrow and all three wheels can tilt to improve the stability during turning. We also derive a new switching dynamical model of the NTV. This model considers several states including normal running, temporary running with one rear wheel not on the ground and totally falling down. Based on this model, a simulation platform is established, which is useful to test different control methods and to investigate dangerous driving situations in case hurt drivers in real experiments. The effectiveness of proposed dynamical model is verified through comparison study of simulations and corresponding experiments.

There has been increasing interest in a type of underactuated mechanical systems, mobile-wheeled inverted-pendulum (MWIP) models, which are widely used in the field of autonomous robotics and intelligent vehicles. Robust-velocity-tracking problem of the MWIP systems is investigated in this study. In the velocity-control problem, model uncertainties accompany uncertain equilibriums, which make the controller design become more difficult. Two sliding-mode-control (SMC) methods are proposed for the systems, both of which are capable of handling both parameter uncertainties and external disturbances. The asymptotical stabilities of the corresponding closed-loop systems are achieved through the selection of sliding-surface parameters, which are based on some rules. There is still a steady tracking error when the first SMC controller is used. By assuming a novel sliding surface, the second SMC controller is designed to solve this problem. The effectiveness of the proposed methods is finally confirmed by the numerical simulations.

There has been an increasing interest in a kind of underactuated mechanical systems, mobile wheeled inverted pendulum (MWIP) models, which are widely used in the field of autonomous robotics and intelligent vehicles. Robust velocity tracking problem of MWIP systems is investigated in this study. In the velocity control problem, model uncertainties accompany uncertain equilibriums, which make the controller design become more difficult. A sliding mode control (SMC) method based on a novel sliding surface is proposed for the systems, which are capable of handling both parameter uncertainties and external disturbances. By assuming the specially designed sliding surface, the proposed SMC controller is capable of eliminating the steady velocity tracking error. The asymptotical stability of the closed-loop system is achieved through selecting sliding surface parameters in terms of some rules. The effectiveness of the proposed methods is finally confirmed by numerical simulations.

A three-wheeled omni-directional cane robot is designed for aiding the elderly walking. Possible move modes are analyzed and a corresponding hybrid model is constructed to describe walking behavior. A concept called intentional direction is presented to denote the moving intention of a human. Based on experiments and some assumptions, dynamic model of intentional direction is obtained as well as its online estimation method. A new admittance control scheme is presented based on intentional direction, which provides natural and intuitive human machine interface. Experiment results show the effectiveness of the design.

As one of dynamics-based control of biped walking, some researchers presented the control method to take advantage of robot dynamics directly by use of point-contact state between a robot and the ground. We proposed passive dynamic autonomous control (PDAC) previously (2004) as one of point-contact methods. PDAC expresses the robot dynamics as a 1-dimensional autonomous system based on the two concepts: 1) point-contact 2) virtual constraint (proposed by Grizzle et al. (2001) and Westervelt et al. (2004)). We actually realized 3D dynamic walking by means of proposed method, however stability is not proved and the convergence domain is not clear. Thus, this paper finds the convergence domain of the previously proposed controller and proves the stability by the Liapunov theory. Finally, the correctness of stability proof is confirmed by the numerical simulation.

This paper proposes the control method of biped walking with heel-off motion. Heel-off motion made it possible to avoid the problem for the impact shock at foot-contact to break the stabilization of walking. The 3D motion is separated into lateral and sagittal motion and each motion is designed individually under the assumption that each motion is possible to be treated independently each other. We adopt the approximate 1-mass model in both planes and derive the dynamics based on these models. It is assumed that the lateral motion is relevant to heel-off motion. On the other hand, in the sagittal plane, there are two phases: 1) the center of rotation (contact point) is ankle joint. 2) the center of rotation is toe. In phase 2), heel-off motion is designed to diminish the impact shock at foot-contact. By applying PDAC to the dynamics, phase around the contact point can be derived. By means of this phase of dynamics, it is possible to inspect heel-off motion analytically. We design the stabilizing controller for each plane and confirm the convergency of dynamics with the numerical simulation

In this paper we propose a remote touch screen (RTS) as an application for flexible tactile array units. RTS is a combination of a flexible tactile display, a camera, a conventional touch screen and a monitor. While the user may press a button shown on the monitor under the touch screen in a conventional touch monitor configuration, in RTS, the user may press a button that is felt and shown. For visual guidance the user's hand motion is captured by an overhead camera, and is merged with the screen menu image and shown on the monitor. For tactual guidance, a tactile pattern is provided at the center of the button locations shown on the monitor. Hence the user's button pressing motion is visually as well as tactually guided in RTS configuration. To confirm the effectiveness of tactile display units in RTS, experiments were performed with and without the tactile display units

There are many deformable objects such as papers, clothes, and ropes in life space of a person. Robots need skills to manipulate deformable objects, in order to take active parts in such space. However, it is difficult for robots to manipulate deformable objects well and possibility of failure to operate deformable objects cannot be denied. Therefore, shape recognition method for deformable object manipulation is required, that has hyper degrees of freedom structures. Thus in this paper, we propose a description method of conditions of ropes using a topological model and knot theory. And, we also propose a recognition method to obtain the structure of rope from sensor information through the CCD cameras when a robot manipulates a rope. The effectiveness of recognition method against a method using three-dimensional data is verified through an experiment

We propose a new tactile sensor utilizing piezoelectric vibration. This tactile sensor has a high sensitivity, wide measurement range, pressure resistance, flexibility, and self-sensing function. This tactile sensor comprises two piezoelectric materials. One is used for the vibration of the sensor element and the other is used for the measurement of the change in mechanical impedance induced by an external force. We achieved the wide measurement range by implementing two ideas. One was to apply the external force to the sensor element through an elastic body and the other was to use two or more modes of vibration. Moreover, for the elastic body, it is preferable to use a material whose elasticity and viscosity are easily changed by an external force, such as a gel. In this study, first, this tactile sensor was analyzed, and then its characteristics were derived. The analytical results qualitatively corresponded to the experimental results. Next, a prototype tactile sensor was fabricated and evaluated. The evaluation results showed that this tactile sensor can measure a pressure of 2.5 Pa or less and a pressure of 10 kPa or more and its pressure resistance is 1 MPa or more

The essential challenge in the future ubiquitous networks is to make information available to people not only at any time, at any place, and in any form, but with the right thing at the right time in the right way by inferring the users' situations. Several psychological experiments show that there are some associations between each user's situations including the user's emotions and each user's task selection. Utilizing those results, this article presents a situation-based task selection mechanism that enables a life-supporting robot system to perform tasks based on the user's situation. Stimulated by interactions between the robot and the user, this mechanism constructs and updates the association between the user's situation and tasks so that the robot can adapt to the user's behaviors related to the robot's tasks effectively. For the user adaptation, Radial Basis Function Networks (RBFNs) and associative learning algorithms are used. The proposed mechanism is applied to the CRF3 (Character robot face 3) system to prove its feasibility and effectiveness. © 2006 Wiley Periodicals, Inc. Int J Int Syst 21: 973–1004, 2006.

In this paper, grasping strategy using deformation of soft finger is addressed. Soft fingers, which are made of macromolecular and have large elastic deformation, have gotten a lot of attention. Soft fingers have a peculiarity that high friction force, which stabilizes a grasping condition, is generated by expansion of contact area between tip of soft finger and grasping object. However, until now nobody focuses on the fact that deformation of soft finger enables multi-fingered hand to generate force to manipulate a object which has high aspect ratio and restricted by environment. Accordingly, we focus on a task to pick up a thin plate on a floor using deformation of soft finger. The effectiveness of grasping strategy is confirmed by experiments.

We propose a novel tactile sensor, of which sensitivity and sensing range is adjustable. This sensor is a mechanical resonator sensor using a piezoelectric bimorph which measures elastic deformation of media by external force. The sensor is robust and has self-sensing capability. We derived the relationship between sensor output and spring constant at each vibration mode by the piezoelectric analysis and vibration analysis. The validity of sensor was demonstrated by experiment. As an application, a robot fingertip with tactile sensor was fabricated and evaluated.

In this paper we propose a method to insert a long peg into a tandem shallow hole using search trajectory generation without force feedback. Automation of the assembly in a factory progressed in recent years. However the many processes where workers should assemble products by themselves still remain now. We call these processes "difficult assembly". The difficult assembly has the feature that a mating part has a unique shape. The RCC (Remote Center Compliance) is an effective method for assembly, but it is no longer useful on the condition that mating parts are complex. The RCC device has no durability since it is a product made from rubber, in addition a force sensor is expensive. If a robot could accomplish the assembly task without using those devices there is a advantage in terms of expense and durability. In our approach, the manipulator system inserts a long peg into the hole with switching the trajectory generation methods depending on the task condition.

This paper proposes a new type of rough terrain vehicle with the interconnected suspension expected to be used to detaining action. This interconnected suspension was proposed and based on posture control of rough terrain vehicle. This suspension has 4 leg-cylinders interconnected and by employing 2 AC motors it can control its posture readily. This suspension makes rough terrain vehicle simple in mechanism. By using this kind of interconnected suspension, the rough terrain vehicle can control its posture smoothly when it walks on rough terrain. In order to compensate the response delay time and improve the control system, we use preview control and the effect was proved in our research. The rough terrain vehicle can control its impact load on every wheel with the interconnected suspension. This kind of suspension can distribute impact load among wheels due to interconnecting every leg-cylinder. In our research, the reduction of impact load on vehicle wheels was proved by experiments. By making good use of the advantages of the interconnected suspension, it is possible that the rough terrain vehicle is actually applied to executing some special tasks such as demining action.

We propose a flexible object manipulation system by a dual manipulator system. Flexible objects like rope or paper have shapes of irregular form, even if the manipulator goes to the same position. We use a flexible object model and vision sensor to recognize flexible object form, and we use a force sensor and vision sensor to confirm the task execution. The dual manipulator system tied a cylindrical object with rope in an experiment.