International Journal of Humanoid Robotics

Stair climbing is still a challenging task for humanoid robots, especially in unknown environments. In this paper, we address this problem from perception to execution. Our first contribution is a real-time plane-segment estimation method using Lidar data without prior models of the staircase. We then integrate this solution with humanoid motion planning. Our second contribution is a stair-climbing motion generator where estimated plane segments are used to compute footholds and stability polygons. We evaluate our method on various staircases. We also demonstrate the feasibility of the generated trajectories in a real-life experiment with the humanoid robot HRP-4.

The paper presents a creative design approach focused at simplifying the control of biped humanoid robots locomotion in a domestic scenario. The creative design approach is the result of intensive studies aimed at optimizing dynamic balance ZMP-based control on fully-actuated biped platforms. The innovative solution proposed in this paper is applied to the realization of a novel humanoid robot, ROLLO, which is based on the implementation of a passive flexible structure constituting the robotic legs, and of wheeled feet. The unconventional use of the cylindrical helical springs in the flexible structure of the legs allows obtaining a biped robot able to achieve an alternate leg motion having only two active motors and remaining in a standing position also when the motors are not active.

Detecting affordances on objects is one of the main open problems in robotic manipulation. This paper presents a new method to represent and localize grasp affordances as bounded curved contact patches (paraboloids) of the size of the robotic hand. In particular, given a three-dimensional (3D) point cloud from a range sensor, a set of potential grasps is localized on a detected object by a fast contact patch fitting and validation process. For the object detection, three standard methods from the literature are used and compared. The potential grasps on the object are then refined to a single affordance using their shape (size and curvature) and pose (reachability and minimum torque effort) properties, with respect to the robot and the manipulation task. We apply the proposed method to a circular valve turning task, verifying the ability to accurately and rapidly localize grasp affordances, under significant uncertainty in the environment. We experimentally validate the method with the humanoid robot COMAN on 10 circular control valves fixed on a wall, from five different viewpoints and robot poses for each valve. We compare the reliability of the introduced local grasp affordances method to the baseline that relies only on object detection, illustrating the superiority of ours for the valve turning task.

To predict the 3D walking pattern of a human, a detailed upper body model that includes the spine, shoulders, and neck must be made, which is challenging because of the coupling relations of degrees of freedom (DOF) in these body sections. The objective of this study was to develop a discomfort function for including a high DOF upper body model during walking. A multi-objective optimization (MOO) method was formulated by minimizing dynamic effort (DE) and the discomfort function simultaneously. The discomfort function is defined as the sum of the squares of deviation of joint angles from their neutral angle positions. The neutral angle position is defined as a relaxed human posture without actively applied external forces. The DE is the sum of the joint torque squared. To illustrate the capability of including a high DOF upper body, backward walking is used as an example. By minimizing both DE and the discomfort function, a 3D whole-body model with a high DOF upper body for walking was simulated successfully. The proposed MOO is a promising human performance measure to predict human motion using a high DOF upper body with full range of motion. This has been demonstrated by simulating backward walking, lifting, and ingress motions.

The passive dynamic walker is well known for its success in human mimicry; however, the torso, an important part of humans and human-like biped robot, is usually ignored in the model. In this paper, a fully passive torso is coupled to the passive dynamic walker via two hip torsional springs. The performances of the walker are studied by means of numerical simulation, and the benefits brought by the torso are revealed. Comparisons with the walker without a torso are performed. On a regular slope, the gait's existence and specifications are studied with respect to the slope angle and the spring coefficient. An interesting dynamical phenomenon of having two stable walking cycles is observed, and the differences between them are presented via a parametric study. The ranges of stable walking slopes and gait performances are significantly improved. On an irregular slope, the disturbance rejection ability (DRA) is measured for three types of disturbances. The slope range of stable gait with strong DRA is significantly extended. The walker with a torso is more flexible by adjusting the slope angle, the spring coefficient and its initial state. The unique properties of our model can be utilized to design humanoid robots and walking enhancing equipment.

As robots get closer to humans, higher requests to robots are put forward. Human-like motion is one of those important issues, especially for humanoid service robots, advanced industrial robots and assistive robots. In this paper, a motion-decision algorithm is proposed and applied to human-like motion planning of robotic arms. The algorithm consists of two parts: intelligent decision and calculation of the joint trajectory. The former includes two parts: the hierarchical planning strategy (HPS) and the Bayesian decision. The HPS reflects the general rules of human arm movements and the robotic arms using the HPS can simulate the movements of human arms accurately. The Bayesian decision is used to make robotic arms choose an appropriate mode of motion. The calculation of the joint trajectory builds a motion framework of robotic arms to generate human-like movements. The human performance measures (HPMs) in different planning hierarchies are proposed. Finally, the validity of the proposed algorithm is verified by experiments.

The paper studies the control design of an exoskeleton robot based on electromyography (EMG). An EMG-based motion detection method is proposed to trigger the rehabilitation assistance according to user intention. An adaptive control scheme that compensates for the exoskeleton's dynamics is employed, and it is able to provide assistance tailored to the human user, who is supposed to participate actively in the training process. The experiment results verify the effectiveness of the control method developed in this paper.

With the limitations of the artificial intelligence, automatic control and sensor technologies, the dexterous hand in unstructured environments to achieve fully autonomous operations is still very difficult. This paper proposed a master–slave control method for dexterous hands with the combination of the data glove and the micro-stepper motor. The hardware of this method included CyberGloveII device, personal computer (PC), integrated control board (ICB), and YWZ dexterous hand (a multi-fingered robot hand with 20 active degrees of freedom (DOFs)). By the CyberGloveII device, we gained human finger joints motion data in real-time firstly, which were preprocessed by a shaking elimination algorithm to ensure the motion stability of the dexterous hand. Then, the motion data were mapped to the dexterous hand joints, respectively. A communication protocol was designed to transfer the motion data between the PC and the ICB. The motion data were transmitted into the ICB through a serial interface driving the corresponding dexterous hand joints. The experimental results showed that this method is feasible, can achieve the open-loop control of dexterous hands, and has excellent movement accuracy, real-time and stability.

FastSLAM is a well-known solution to the simultaneous localization and mapping (SLAM) problem. In FastSLAM, a nonparametric filter is used for the mobile robot pose (position and orientation) estimation, and a parametric filter is used for the feature location's estimation. The performance of the conventional FastSLAM degrades over time due to the particle depletion and unknown statistic noises. In this paper, intelligent FastSLAM (IFastSLAM) is proposed. In this approach, an evolutionary filter (EF) searches stochastically along with the state space for the best robot's pose estimation and an adaptive fuzzy unscented Kalman filter (AFUKF) is used for the feature location's estimation. In AFUKF, a fuzzy inference system (FIS) supervises the performance of the unscented Kalman filter with the aim of reducing the mismatch between the theoretical and actual covariance of the innovation sequences in order to get better consistency. We demonstrate the proposed algorithm with simulations and real-world experiments. The results show that the proposed method is effective, and its performance outperforms conventional FastSLAM.