International Journal of Humanoid Robotics

A new torso structure for a humanoid robot has been proposed. The structural characteristics and functions of human torso have been considered to gain inspirations for design purposes. The proposed torso structure consists of six revolute units divided into two basic categories connected in a serial chain mechanism. The proposed torso structure shows more advantages compared to traditional humanoid robots in terms of high degrees of freedom (DOFs), high stiffness, self-locking capabilities, as well as easy-to-control features. Bionic optimization design based on objective function method has been implemented on structural design for better motion performances. A 3D model has been elaborated and simulated in SolidWorks and ADAMS environments for structural design and kinematic simulation purposes, respectively. Simulation results show that the new bionic torso structure is able to well imitate movements of human torso.

This paper presents a novel trajectory planning optimization process for a mobile robot to capture a mobile sound source (MSS) efficiently. The sound source can be an arbitrary object for the mobile robot to follow, such as a human being. The mobile robot is equipped with a microphone array so that it can obtain the location and direction of the MSS. During the capturing process, the location and direction of the MSS need to be known in advance so that an optimal path for capturing the sound source can be generated based upon a single or a double curvature path. Also a path predictive algorithm is used to estimate the moving path of the sound source. The conventional Kalman filter is used to realize an efficient prediction process for the mobile robot to capture the sound source quickly and accurately. The validity of the proposed algorithm has been demonstrated through its application in real experiments.

In this paper, effects of employing toe-off and heel-contact gait phases on the performance of bipedal robots traversing stairs are examined. The main goal is to demonstrate the hypothesis that employing toes and heels during walking up and down stairs improves the gait performance in terms of actuating joint torques and energy consumption. For this purpose, a comprehensive dynamics model for a 3D biped robot is developed and the inverse dynamics solutions during various walking phases are presented. To realize walking up and down stairs, a zero moment point (ZMP)-based pattern generation routine in the task space is proposed. In this routine, first, trajectories for the feet and the pelvis in the task space are designed to realize the desired task and preserve the feasibility constraints. Then, consistent with the topology of walking, suitable trajectory for the toe joint is generated. To examine the effects of heel-contact and toe-off gait phases, three walking topologies for walking up stairs and four walking topologies for walking down stairs, depending on the use of toe-off and heel-contact motions, are considered. For these topologies, the optimization procedure is conducted to yield the optimal patterns. Finally, the obtained patterns are compared in terms of energy consumption and joint torques, while obtained results show a significant improvement in the gait performance in terms of considered cost functions.

Haptic exploration and grasp planning by dexterous robot hand are usually two independent research areas. In this paper, the determination of optimal grasp configurations after haptic exploration of unknown objects is discussed. The haptic exploration information is used to select initial grasp points and the corresponding robot configurations, which greatly improve the efficiency of grasp planning process. The feasible searching regions on the object are obtained under the constrains of manipulability and robot kinematics. Then, the optimization method based on KNN search is applied to find the optimal grasp positions in feasible searching regions. The selected optimal grasp points set can achieve high grasp quality under the constrains of robot kinematics and manipulability. The optimization method combines multiple grasp quality metrics, which is fast and feasible in optimal grasp points searching. Experiments validate the feasibility and effectivity of the proposed method.

Currently, as the requirements for simple implementations in the motor control technologies increase, System-on-Chip (SoC) device such as Zynq All Programmable SoC was devised to meet those requirements. Because this CPU and FPGA can be assembled into one SoC device, we can consolidate motor-control functions and additional processing tasks into a single SoC device. The control algorithms, networking and other tasks, are off-loaded to the programmable logic that can include multiple control cores and multiple control system. This SoC system with a single chip can allow the hardware design with a single chip, hence, we can implement to control the motor to be simpler, more reliable, and less expensive. In this paper, in order to implement motor controller, we apply latest All Programmable SoC technologies for humanoid robot or industrial device that is integrated with FPGA technologies and embedded processor technologies. We also propose the structure of motor controller that decentralizes the function of motor driver from previous typical motor driver into FPGA and level of embedded processor by using All Programmable SoC for humanoid robot or industrial device. We verify the possibilities of applying the novel implemented motor controller in Zynq EPP (Extensible Processing Platform) which is one kind of All Programmable SoC made by Xilinx. To do this, we perform velocity control and position control with digital PI controller on the BLDC motor.

Human-likeness of an anthropomorphic arm is mainly exhibited by the main arm consisting of shoulder and elbow joints as well as upper arm and forearm. In this paper, we focus on a 4-DOF anthropomorphic arm and propose a novel approach to generate human-like motion, considering human physiological and psychological factors. According to the features of musculoskeletal system of human upper limb, the 3-DOF shoulder joint is simplified with two rotations: one is about a fixed axis through shoulder center and the other is about the axis of humerus. In addition with elbow joint and a special rotation about the shoulder-wrist line, they constitute the basic motion primitives (MPs) which are macroscopic compared with the joint space but microscopic compared with the Cartesian space. Therefore, planning motion based on MPs combines intuitiveness and flexibility. Two basic kinds of motion planning, point-to-point motion planning and linear trajectory planning, are conducted. The different psychological concerns, i.e., predicting the next step of configuration and relieving the brain burden, are taken into account. Simulations are performed to verify the feasibility and validation of the proposed approach. Comparisons between simulation results with the proposed method and that with traditional joint and Cartesian space methods prove the improvement in human-likeness.

The use of Robot-Assisted Therapy (RAT) in healthcare interventions has increasingly received research attention. However, a lot of RAT studies are conducted under Wizard of Oz (WoZ) techniques in which the robots are teleoperated or pre-programmed. The trend of RAT is moving towards (partially) autonomous control in which the robot behavior control architecture plays a significant role in creating effective human–robot interaction by engaging and motivating human users into the therapeutic processes. This paper describes the state-of-the-art of the autonomous behavior control architectures currently developed for social robots in healthcare interventions, considering both clinical and exploratory studies. We also present certain requirements that an architecture used in RAT study should acquire, which provide roboticists and therapists an inspiration to orient their designs and implementations on the basis of their targeted RAT applications.