1A1-K08 視覚・近接覚を統合したロボットハンドによる対象物把持に関する研究 : 近接フィードバックを活用するための視覚情報の検討(ロボットハンドの機構と把持戦略(1))

1P1-N-088 家庭用サービスロボット向けエンドエフェクタの開発 : 多指多関節ロボットハンド(ロボットハンドの機構と把握戦略2,生活を支援するロボメカ技術のメガインテグレーション)

This paper presents a back-drivable two-fingered four-degree of freedom hand that can generate a large grasping force of 120N. All fingers are 98 mm in length and the weight of the hand is 1.2kg. The hand can generate a large grasp force with a new force-magnification mechanism and all joints can perform a high speed motion of larger than 750deg/s with a high-speed driving mechanism. The force-magnification mechanism installed in our previous hands need a non-backdrivable element, which loses compliance. The new force-magnification mechanism is connected to the high-speed driving mechanism only when it is activated. Therefore the high-speed driving mechanism can be back driven maintaining high compliance.

One of the problems on robots that work at human enviroments is manipulation ability. In this research, we focus on manipulation of slippery objects. When robots has to manipulate oily dishes, for example, utilization of slip information is important. The purpose of this research is realizing robot manipulation of such objects by using slip and contact force information. This paper proposes a estimation method of falling time and planning method of trajectory by using slip information. We also performed preliminary experiments on the methods.

This paper presents the impedance control of force instuction -type This control suppresses the excessive power and vibration This is effective for a rigid body and a exible object

It is important to realize the robot handling soft objects. In this paper, we treat a string as an example of soft objects. Humans can create various figures with a string; we aim to develop a robot system that can do such a thing. We employ the string figures as the task. We propose a framework with which a robot can play string figures with a human. Concretely, we develop a description method that can represent a variety of procedures of string figures to be played by a robot and a human pair. In order to implement this framework on a dual-arm robot, we also develop a method to decide centers of loops to be picked up using camera images. This paper demonstrates the experimental results with a dual-arm robot Hiro-NX.

In this article we describe a general-purpose robotic grasping system for use in unstructured environments. Using computer vision and a compact set of heuristics, the system automatically generates the robot arm and hand motions reqrsired for grasping an unmodeled object. The utility of such a system is most evident in environ ments where the robot will have to grasp and manipulate a variety of unknown objects, but many of these manipu lation tasks may be relatively simple. Examples of such domains are planetary exploration and astronaut assis tance, undersea salvage and rescue, and nuclear waste site clean-up. This work implements a two-stage model of grasping: stage one is an orientation of the hand and wrist and a ballistic reach toward the object; stage two is hand preshaping and adjustment. Visual features are first extracted from the unmodeled object. These features and their relations are used by an expert system to generate a set of valid reach/grasps for the object. These grasps are then used in driving the robot hand and arm to bring the fingers into contact with the object in the desired configu ration. Experimental results are presented to illustrate the functioning of the system.

Robot grasping under the instruction of natural language has attracted increasing attention in various applications for its advantages in enabling natural and smooth human-robot interaction. At present, mainstream algorithms mainly solve problems of utilizing simple natural language instructions to guide the robot arm to perform some specific grasping. However, for two natural language instructions with different temporal logic and the same semantics, it is usually difficult for the robot to achieve semantic disambiguation, which further leads to the failure of the grasping task. In order to address this problem, we propose a new natural language instruction disambiguation method for robot grasping by combining sentence vector similarity calculation model and sentence temporal logic model. Firstly, the word vector is obtained through the Skip-gram model in Word2vec and a sentence vector is constructed. The semantic similarity of the sentence is then calculated by using the proposed cost function. Based on the semantic similarity of the sentence, the correct temporal logic form of the sentence is then extracted according to the temporal adverbial priority to further guide the grabbing process of the robot arm. The experimental results show that our method can successfully realize the semantic disambiguation for natural language instructions with different temporal logics and the same semantics, and further guide the robot arm to complete more complicated tasks than previous tasks.

In this paper, we propose a Learning from Demonstration approach for robotic grasping with compliant arms. The compliance in the robot arm for safety often causes a problem in grasping. In our approach, we construct a recurrent neural network, given the estimation of the target object position and random initial joint angles of the robot arm, that can produce the whole trajectories for grasping the target object. In order to generate smooth and stable trajectories and to decrease the number of human demonstrations, we propose a data augmentation method to increase the training data and utilize the trajectory planning technique using cubic splines for smooth and stable trajectories. Specifically, the two arms of the robot are trained respectively, and a support vector machine is used to decide which arm needs to be used for grasping the target object. The evaluation results show that our recurrent model not only has a good prediction for the final joint configurations, but also generates smooth and stable trajectory. Moreover, the model is robust to the changes in the initial joint state which means that even though the initial joint configuration is affected by disturbances, the model can still generate trajectories leading to the final joint configurations for grasping the object. Finally, we tested the proposed learning method on the Pepper robot which can successfully grasp randomly placed object on the workbench. Compared to traditional methods which need to avoid singular configurations as well as to secure accurate localization, our method turns out to be robust and efficient and can be applied to cluttered environment.

This paper presents an integrated system that combines learning, a natural-language interface, and robotic grasping to enable the transfer of grasping skills from nontechnical users to robots. The system consists of two parts: a natural-language interface for grasping commands and a learning system. This paper focuses on the learning system and testing of the entire system in a small usability study. The learning system presented consists of two phases. In the first phase, the system learns to predict the next command, which the user is planning to issue based on command sequences recorded during previous grasping sessions. In the second phase, the system predicts the user's current state and moves the robot's gripper to the intended target endpoint to attempt to grasp the object. Using eight nontechnical users and a 5-degree-of-freedom (DOF) robot arm, a usability study was conducted to observe the impact of the learning system on user performance and satisfaction during a grasping operation. Experimental results show that the system was effective in learning users' grasping intentions, which allowed it to reduce the average time to grasp an object. In addition, participants' feedback from the usability study was generally positive toward having an adaptive robotics system that learns from their commands.

Control barrier functions have been demonstrated to be a useful method of ensuring constraint satisfaction for a wide class of controllers. However, the existing results are mostly restricted to continuous-time systems. Mechanical systems, including robots, are typically second-order systems in which the control occurs at the force/torque level. These systems have actuator, velocity, and position constraints (i.e., relative degree two) that are vital for safety and/or task execution. Additionally, mechanical systems are typically controlled digitally as sampled-data systems. The contribution of this article is twofold. The first contribution is the development of novel, robust control barrier functions that ensure constraint satisfaction for sampled-data systems in the presence of model uncertainty and allows for satisfaction of actuator constraints. The second contribution is the application of the proposed method to the challenging problem of robotic grasping in which a robotic hand must ensure that an object remains inside the grasp while manipulating it to the desired reference trajectory. A grasp constraint satisfying controller is proposed that can admit the existing nominal manipulation controllers from the literature while simultaneously ensuring no slip, no overextension (e.g., singular configurations), and no rolling off of the fingertips. Simulation and experimental results validate the proposed control for the robotic hand application.

The Robot Grasping and Manipulation Competition, held during the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) in Daejeon, South Korea was sponsored by the IEEE Robotic and Automation Society (RAS) Technical Committee (TC) on Robotic Hands Grasping and Manipulation (RHGM) [1]. This competition was the first of a planned series of grasping and manipulation-themed events of increasing difficulty that are intended to spur technological developments and advance test methods and benchmarks so that they can be formalized for use by the community. The coupling of standardized performance testing with robot competitions will promote the use of unbiased evaluation methods to assess how well a robot system performs in a particular application space. A strategy is presented for a series of grasping and manipulation competitions that facilitate objective performance benchmarking of robotic assembly solutions. This strategy is based on test methods that can be used for more rigorous assessments and comparison of systems and components outside of the competition regime. While competitions have proven to be useful mechanisms for assessing the relative performance of robotic systems with measures of success, they often lack a methodical measurement science foundation. Consequently, scientifically sound and statistically significant metrics, measurement, and evaluation methods to quantify performance are missing. Using performance measurement methods in a condensed format will accommodate competition time limits while introducing the methods to the community as tools for benchmarking performance in the developmental and deployment phases of a robot system. The particular evaluation methods presented here are focused on the mechanical assembly process, an application space that is expected to accelerate with the new robot technologies coming to market.

This paper proposes a novel inflatable robotic arm on a mobile platform. To date, inflatable structures have been utilized for robotic arms to provide the workforce in the welfare and nursing care fields. In these fields, inflatable robots, which is lightweight, soft and compactable, is suitable to perform daily tasks near humans and things because of safe contact. In our research group, an inflatable robotic arm consisting of inflatable links, inflatable actuators and a gripper with pleated sheet structures have been developed.In this paper, the robotic arm is utilized in combination with a mobile platform in order to realize practical daily tasks. As an example of the task, a fetch-and-give task is demonstrated. The posture of the robotic arm and the position of the mobile platform is measured by a motion capture system. The whole system is controlled based on the visual information. Finally, it is confirmed that the inflatable robot has sufficient performance for a daily task in living space.

One of the major challenges in robotics consists in developing successful control strategies for robotic grasping devices. In this scenario, one of the most interesting approaches regards the exploitation of surface electromyography(sEMG). In this work, we propose a novel sEMG-based <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">minimally supervised</i> regression approach capable of performing nonlinear fitting without the necessity for point-by-point training data labelling. The proposed method exploits a differentiable version of the Dynamic Time Warping (DTW) similarity – referred to as soft-DTW divergence – as loss function for a flexible neural network architecture. This is a different paradigm with respect to state-of-the-art approaches in which sEMG-based control of robot hands is mainly realized using supervised or unsupervised machine learning based regression. An experimental session was carried out involving 10 healthy subjects in an offline experiment for systematic and statistical evaluations, and an online experiment for the evaluation of the control of a robot hand. The reported results demonstrate that the proposed soft-DTW neural network can be trained by means of a labelling that does not require to be temporally aligned with the sEMG training dataset, while reporting performances comparable with a standard mean square error(MSE)-based neural network. Also, the subjects were able to successfully control a robot hand for grasping motions and tasks with error levels comparable to state-of-the-art regression approaches.

Introduction We can easily manipulate a variety of objects with our hands. When exploring an object, we gather rich sensory information through both haptics and vision. The haptic and visual information obtained through such exploration is, in turn, key for realizing dexterous manipulation. Reproducing such codevelopment of sensing and adaptive/dexterous manipulation by a robotic hand is one of the ultimate goals of robotics, and further, it would be essential for understanding human object recognition and manipulation. Although many robotic hands have been developed, their performance is by far inferior to that of human hands. One reason for this performance difference may be due to differences in grasping strategies. Historically, research on robotic hands has mainly focused on pinching manipulation (e.g. Nagai and Yoshikawa, 1993) because the analysis was easy with point-contact conditions. Based on the analysis, roboticists applied control schemes using force/touch sensors at the fingertips (Kaneko et al ., 2007; Liu et al ., 2008). Since the contact points are restricted to the fingertips, it is easy for the robot to calculate how it grasps an object (e.g. a holding polygon) and how large it should exert force based on friction analysis. However, the resultant grasping is very brittle since a slip of just one of the contacting fingertips may lead to dropping the object.

One of the main goal of researchers and inventors is to provide existing systems with the vision to extend their capabilities to an extent that they can perceive their environment and perform vision based tasks. Robots make up a large section of these systems. One of the primary tasks performed by the robots, especially industrial robots, is the pick and place operation. The robot is provided with pick and place position and orientation information which is fixed for a particular task. The conventional method is to jog the robot arm and end-effector with robot’s teach pendant, verify visually the jogged position and finally recording it. These positions are then used to plan the robot motion to perform pick-place operation on given object. This method has a limited scope because of long programming time. Also, if the shape, size and orientation of the object to be picked and placed varies, one has to repeat the process all over again. The task of identifying the object and pick-placing it can be achieved by using basic computer vision algorithms. This paper discusses the strategies that can be implemented to grasp the objects of simple geometry (rectangular and triangular prisms, and cylinder) with a two finger jaw attached to a 5 degrees of freedom open-chain articulated robotic arm, with help of a 2D vision camera mounted on the robot. The robot attached camera identifies the required shape object from a given set of objects and calculates the nearest possible inverse kinematic solution to perform pick-place operation considering the object’s shape, size and orientation.