International Journal of Humanoid Robotics

We evaluate the ability of locally present participants to localize an avatar head’s gaze direction rapidly in hosted telepresence. We performed a controlled user study to test two potential solutions to indicate a remote user’s gaze. We analyze the influence of the user’s distance to the avatar and display technique on localization accuracy. Furthermore, we examine the effect of the avatar head’s rotation around the pitch and yaw axes on the localization accuracy. Our experimental results suggest that all these factors have a significant effect on the localization accuracy with different extent. The results also verified that people had a better perceptive and localizing ability when interacting with a 3D AR-displayed avatar. In addition, participants preferred to interact with a 3D avatar displayed using a simulated AR technique instead of with a 2D avatar displayed in a tablet because of its high realism. Our findings motivate the need for 3D avatar display in the further design of telepresence systems.

Gait development for bipedal/humanoid robots has been a field of study with a lot of attention for several years and is becoming increasingly important as robots slowly become part of our daily lives. Therefore, it is expectable that robots should adopt human-like behaviors in order to make their interactions with humans more natural and studies have been made involving robots that have a natural, human-like gait. However, very few focus on scenarios with slippery floors. In this paper, the humanoid robot NAO is used and the effects of a human-based walking pattern on the robot’s balance when walking on floors with different slipperiness degrees were analyzed. The simulations are done having the robot equipped with specially developed shoes that enable the measurement of the friction coefficient. From that analysis, an algorithm that automatically adapts the gait parameters to the floor’s slipperiness was developed, in order to prevent the robot from suffering unexpected disturbances and possibly falling over. This paper focusses on preventing balance disturbances, instead of correcting them.

The prime challenge in a humanoid robot is its stability on two feet due to the presence of an underactuated system. In this paper, the complete dynamics of the humanoid robot has been described in essence of torque calculation at the end effectors. Presence of various restraints in humanoid robot motion makes the task of stabilization an even humongous one. Therefore, to neutralize these constraints, whole-body control (WBC) has been proposed to consider the free-floating base and to ensure the stability of the humanoid robot. Dynamic modeling of the humanoid robot is performed based on the Langrage–Euler formalism to obtain the maximum torque at the joints. This approach is utilized to formulate the torque equation and solve the problem of stabilization. WBC deals with the limitation of attainment of well nimble dynamics behavior operated at high speeds. The simulated annealing approach is preferred to tune WBC to get efficient stabilization and eliminate the earlier limitation. In addition, the zero-moment point (ZMP) criterion is taken care of as it affects the stability of the humanoid robot aggressively. Simulations on V-REP are carried out to understand the torque behavior at each joint. To validate the simulation results, the experiments are carried out on the NAO humanoid robot in real experimental conditions. The experimental and simulation results are compared through torque versus time graphs, and they both show good agreement with deviation under 4% between them. The proposed technique is then compared with various previously implemented techniques which confirm the robustness and efficiency of the proposed methodology.

Exoskeleton for motion assistance has obtained more and more attention due to its advantages in rehabilitation and assistance for daily life. This research designed an estimation method of human joint torque by the kinetic human–machine interaction between the operator’s elbow joint torque and the output of exoskeleton. The human elbow joint torque estimation was obtained by back propagation (BP) neural network with physiological and physical input elements including shoulder posture, elbow joint-related muscles activation, elbow joint position, and angular velocity. An elbow-powered exoskeleton was developed to verify the validity of the human elbow joint torque estimation. The average correlation coefficients of estimated and measured three shoulder joint angles are 97.9%, 96.2%, and 98.1%, which show that estimated joint angles are consistent with the measured joint angle. The average root-mean-square error between estimated elbow joint torque and measured values is about 0.143Nm. The experiment results proved that the proposed strategy had good performance in human joint torque estimation.

Biped humanoid robots that operate in real-world environments need to be able to physically recognize different floors to best adapt their gait. In this work, we describe the preparation of a dataset of contact forces obtained with eight force tactile sensors for determining the underlying surface of a walking robot. The data is acquired for four floors with different coefficient of friction, and different robot gaits and speeds. To classify the different floors, the data is used as input for two common computational intelligence techniques (CITs): Artificial neural network (ANN) and extreme learning machine (ELM). After optimizing the parameters for both CITs, a good mapping between inputs and targets is achieved with classification accuracies of about 99%.

Although there are several popular and capable humanoid robot designs available in the kid-size range, they lack some important characteristics: affordability, being user-friendly, using a wide-angle camera, sufficient computational resources for advanced AI algorithms, and mechanical robustness and stability are the most important ones. Recent advances in 3D printer technology enables researchers to move from model to physical implementation relatively easy. Therefore, we introduce a novel fully 3D printed open platform humanoid robot design named ARC. In this paper, we discuss the mechanical structure and software architecture. We show the capabilities of the ARC design in a series of experimental evaluations.