International Journal of Humanoid Robotics

Compliance control is highly relevant to human safety in human–robot interaction (HRI). This paper presents a review of various compliance control techniques. The paper is aimed to provide a good background knowledge for new researchers and highlight the current hot issues in compliance control research. Active compliance, passive compliance, adaptive and reinforcement learning-based compliance control techniques are discussed. This paper provides a comprehensive literature survey of compliance control keeping in view physical human robot interaction (pHRI) e.g., passing an object, such as a cup, between a human and a robot. Compliance control may eventually provide an immediate and effective layer of safety by avoiding pushing, pulling or clamping in pHRI. Emerging areas such as soft robotics, which exploit the deformability of biomaterial as well as hybrid approaches which combine active and passive compliance are also highlighted.

Compliance control is highly relevant to human safety in human–robot interaction (HRI). This paper presents multi-dimensional compliance control of a humanoid robot arm. A dynamic model-free adaptive controller with an anti-windup compensator is implemented on four degrees of freedom (DOF) of a humanoid robot arm. The paper is aimed to compliment the associated review paper on compliance control. This is a model reference adaptive compliance scheme which employs end-effector forces (measured via joint torque sensors) as a feedback. The robot's body-own torques are separated from external torques via a simple but effective algorithm. In addition, an experiment of physical human robot interaction is conducted employing the above mentioned adaptive compliance control along with a speech interface. The experiment is focused on passing an object (a cup) between a human and a robot. Compliance is providing an immediate layer of safety for this HRI scenario by avoiding pushing, pulling or clamping and minimizing the effect of collisions with the environment.

This paper proposes a new technique that can be used to produce improved localization accuracy and to remove out the noises in sensing when the low-cost GPS/INS system has been used for a quad-rotor. The level of localization accuracy could be worse when the quad-rotor flies through the air by forming a curve. Also, the accuracy is influenced by the performance of GPS/INS system. The location data by the GPS/INS system include high frequency noises caused by various factors such as measurement noises and external disturbances. When the quad-rotor flies outdoor, it is possible to estimate the moving path for a short interval since the path can be assumed to be straight for a short interval. Therefore, the extended Kalman filter has been adopted to improve the localization accuracy. Also the global path can be more precisely estimated by fitting the location data obtained by the GPS/INS system to the planned path. Through the foregoing processes of the extended Kalman filter and path planning algorithm, the improved localization information can be obtained when the quad-rotor flies. Performance improvement of the proposed system has been verified based on various outdoor experiments.

The impressive manipulation capabilities of the human hand are undoubtedly related to the thumb opposition. Such a versatility is highly desirable in the context of humanoid robots, in particular when performing object manipulation. In the present case, a robotic hand with size, forces, velocity, and shape comparable to the human one, is envisioned. Unlike most robotic designs — where the fingers are modular and the thumb is simply a finger placed in opposition — the thumb benefits from an intensive functional analysis. This paper details the design method of the thumb of the Awiwi hand, the hand of the Integrated Hand Arm System project of DLR. First, several guidelines are presented that are fused and, with the help of a novel optimization method, lead to the final design. Finally, the design is evaluated by the means of biomedical tests on the realized hardware.

This paper presents a general dynamic model that describes the two-dimensional grasp by two robotic fingers with soft fingertips. We derive the system's kinematics and dynamics by incorporating rolling constraints that depend on the deformation and on the rolling distance characteristics of the fingertips' material. We analyze the grasp stability at equilibrium, and conclude that the rolling properties of the fingertips can play an important role in grasp stability, especially when the width of the grasped object is small compared to the radius of the tips. Subsequently, a controller, which is based on the fingertips' rolling properties, is proposed for stable grasping concurrent with object orientation control. We evaluate the dynamic model under the proposed control law by simulations and experiments that make use of two different types of soft fingertip materials, through which it is confirmed that the dynamic model can successfully capture the effect of the fingertips' deformation and their rolling distance characteristics. Finally, we use the dynamic model to demonstrate by simulations the significance of the fingertips' rolling properties in grasping thin objects.

This paper presents the effect of robotics assisted language learning (RALL) on the vocabulary learning and retention of Iranian English as foreign language (EFL) junior high school students in Tehran, Iran. After taking a vocabulary pre-test, 46 beginner level female students at the age of 12, studying in their first year of junior-high participated in two groups of RALL (30 students) and non-RALL (16 students) in this study. The textbook used was the English book (Prospect-1) devised by the Iranian Ministry of Education for 7th graders, and the vocabulary taught and tested (pre-test and post-test) were taken from this book. Moreover, the treatment given by a teacher accompanied by a humanoid robot assistant in the RALL group took about five weeks in which half of the book was covered, and the non-RALL group was taught in a traditional method. Finally, the teacher administered the post-test and delayed post-test whose results of repeated measures ANOVA and Two Ways ANOVA indicated that there was a significant difference regarding participants' vocabulary gain and retention in RALL group comparing to non-RALL group. In addition, the teacher reported the students' positive reaction to RALL in learning vocabulary. Overall, the results revealed that RALL has been very influential in creating an efficient and pleasurable English learning environment. This study has some implications for technology-based education, language teaching, and social robotics fields.

In this paper, a method to find curvilinear path features is proposed. These features are defined as centers and radiuses of circles that best fit to the curvature parts of the curvilinear path. In our previous research, we proposed a hierarchical layered paradigm for humanoid robot to learn how to walk in the curvilinear path. This model consists of four layers and each one has a specific purpose and is responsible to provide some feedbacks for the lower layer. In this study, we focus on the first layer which is high level decision unit responsible to provide some feedbacks and parameters for the lower layer using robot sensory inputs. The ultimate goal is that robot learn to walk in the curvilinear path and to reach this goal, the first step is to find robot position in the environment. In this work, Monte Carlo localization method is used for robot localization. Then we used artificial potential field to generate a path between robot and a goal. Finally, we proposed an algorithm that search the circles that best fit to the curvature parts of the path. Finding these features would help the learning process for lower layers in the learning model. We used robot camera as the only sensor to identify landmarks and obstacles for robot localization, path planning and finding curvilinear path features.

In this paper, a control system for humanoid robot walking is approximately optimized by means of reinforcement learning. Given is a 18 DOF humanoid whose gait is based on replaying a simple trajectory. This trajectory is translated into a reactive policy. A neural network whose input represents the robot state learns to produce appropriate output that additively modifies the initial control. The learning algorithm applied is actor–critic with experience replay. In 50 min of learning, the slow initial gait changes to a dexterous and fast walking. No model of the robot dynamics is engaged. The methodology in use is generic and can be applied to optimize control systems for diverse robots of comparable complexity.

This paper proposes an object based vision (O-BV) system to implement visual servoing for autonomous mobile manipulators using two charge-coupled device (CCD) cameras. Conventional stereo vision (C-SV) system estimates the depth based on the disparity between two camera images for the same object. However, the disparity is not an effective cue for a small disparity at a long distance. To resolve this problem, in the proposed O-BV system, the individual camera tracks the object independently, and the angles of the two cameras are used to estimate the distance to the object. This depth estimation technique is applied for an autonomous mobile robot to approach to a target object precisely. The O-BV system is experimentally compared to the C-SV system in terms of computing time and depth estimation accuracy. Also the two cameras which are attached on the top of the autonomous mobile manipulator have been utilized for the mobile manipulator to approach to a target object precisely through the visual servoing. Through the experiments, it is demonstrated that the fast and precise depth estimation is a critical factor for the successful visual servoing.

In this paper, a novel underactuated prosthetic finger with a compliant driving mechanism is proposed. The underactuated finger is based on linkage mechanism and spring elements within the compliant driving mechanism. The proposed finger mechanism is able to obtain human-like operations. The feasibility of the mechanism is verified through suitable kinematic and static analysis. The structure parameters and the coefficient of the springs are calculated according to the requirements of human-like operations. Finally, we experimentally validate the reasonability of design results and demonstrate that the finger grasps objects in diverse ways.