Balance Of Humanoid Robot Research Articles

Deep-reinforcement-learning-based gait pattern controller on an uneven terrain for humanoid robots

Although conventional gait pattern control in humanoid robots is typically performed on flat terrains, the roads that people walk on every day have bumps and potholes. Therefore, to make humanoid robots more similar to humans, the movement parameters of these robots should be modified to allow them to adapt to uneven terrains. In this study, to solve this problem, reinforcement learning (RL) was used to allow humanoid robots to engage in self-training and automatically adjust their parameters for ultimate gait pattern control. However, RL has multiple types, and each type has its own benefits and shortcomings. Therefore, a series of experiments were performed, and the results indicated that proximal policy optimization (PPO), combining advantage actor-critic and trust region policy optimization, was the most suitable method. Hence, an improved version of PPO, called PPO2, was used, and the experimental results indicated that the combination of deep RL with data preprocessing methods, such as wavelet transform and fuzzification, facilitated the gait pattern control and balance of humanoid robots.

Dynamic Balancing of Humanoid Robot with Proprioceptive Actuation: Systematic Design of Algorithm, Software, and Hardware.

For humanoid robots, maintaining a dynamic balance against uncertain disturbance is crucial, and this function can be achieved by coordinating the whole body to perform multiple tasks simultaneously. Researchers generally accept hierarchical whole-body control (WBC) to address this function. Although experts can build feasible hierarchies using prior knowledge, real-time WBC is still challenging because it often requires a quadratic program with multiple inequality constraints. In addition, the torque tracking performance of the WBC algorithm will be affected by uncertain factors such as joint friction for a large transmission ratio proprioceptive-actuated robot. Therefore, the balance control of physical robots requires a systematic solution. In this study, a robot control system with high computing power and real-time communication ability, UBTMaster, is implemented to achieve a reduced WBC in real time. Based on these, a whole-body control scheme based on task priority for the dynamic balance of humanoid robots is implemented. After realizing the joint friction model identification, finally, a variety of balancing scenarios are tested on the Walker3 humanoid robot driven by the proprioceptive actuators to verify the effectiveness of the proposed scheme. The Walker3 robot exhibits excellent balance when multiple external disturbances occur simultaneously. For example, the two feet of the robot are subjected to tilt and displacement perturbations, respectively, while the torso is subjected to external shocks simultaneously. The experimental results show that the dynamic balance of the robot under multiple external disturbances can be achieved by using strictly hierarchical real-time WBC with a systematic design.

Optimization of the ground reaction force for the humanoid robot balance control

Optimization of the ground reaction force for the humanoid robot balance control

Reproducing Human Arm Strategy and Its Contribution to Balance Recovery Through Model Predictive Control.

The study of human balance recovery strategies is important for human balance rehabilitation and humanoid robot balance control. To date, many efforts have been made to improve balance during quiet standing and walking motions. Arm usage (arm strategy) has been proposed to control the balance during walking motion in the literature. However, limited research exists on the contributions of the arm strategy for balance recovery during quiet standing along with ankle and hip strategy. Therefore, in this study, we built a simplified model with arms and proposed a controller based on nonlinear model predictive control to achieve human-like balance control. Three arm states of the model, namely, active arms, passive arms, and fixed arms, were considered to discuss the contributions of arm usage to human balance recovery during quiet standing. Furthermore, various indexes such as root mean square deviation of joint angles and recovery energy consumption were verified to reveal the mechanism behind arm strategy employment. In this study, we demonstrate to computationally reproduce human-like balance recovery with and without arm rotation during quiet standing while applying different magnitudes of perturbing forces on the upper body. In addition, the conducted human balance experiments are presented as supplementary information in this paper to demonstrate the concept on a typical example of arm strategy.

Perancangan Reaction Wheel Inverted Pendulum Sebagai Alat Peraga Sistem Kontrol Berbasis Sistem Kontrol PID

A control system will be easier to understand if demo devices are available that can be used as learning media. Reaction wheel inverted pendulum is an under-actuation device so that the existence of a controller is absolutely necessary. This will be very interesting if used as a teaching aid of a control system. One application of this reaction wheel inverted pendulum is for the humanoid robot balance system. In this research project the physical design of the teaching aids and the design of the controller are carried out. The design starts from designing mechanical part first, starting from the dimensions and shape of the tool to the needs of the motor. Furthermore, a controller is designed that can balance the device automatically. The controller used is based on Arduino. The test results show that the reaction wheel inverted pendulum demo device can work quite well even though there is some drawback.

Deep reinforcement learning-based attitude motion control for humanoid robots with stability constraints

Purpose This paper aims to present an intelligent motion attitude control algorithm, which is used to solve the poor precision problems of motion-manipulation control and the problems of motion balance of humanoid robots. Aiming at the problems of a few physical training samples and low efficiency, this paper proposes an offline pre-training of the attitude controller using the identification model as a priori knowledge of online training in the real physical environment. Design/methodology/approach The deep reinforcement learning (DRL) of continuous motion and continuous state space is applied to motion attitude control of humanoid robots and the robot motion intelligent attitude controller is constructed. Combined with the stability analysis of the training process and control process, the stability constraints of the training process and control process are established and the correctness of the constraints is demonstrated in the experiment. Findings Comparing with the proportion integration differentiation (PID) controller, PID + MPC controller and MPC + DOB controller in the humanoid robots environment transition walking experiment, the standard deviation of the tracking error of robots’ upper body pitch attitude trajectory under the control of the intelligent attitude controller is reduced by 60.37 per cent, 44.17 per cent and 26.58 per cent. Originality/value Using an intelligent motion attitude control algorithm to deal with the strong coupling nonlinear problem in biped robots walking can simplify the control process. The offline pre-training of the attitude controller using the identification model as a priori knowledge of online training in the real physical environment makes up the problems of a few physical training samples and low efficiency. The result of using the theory described in this paper shows the performance of the motion-manipulation control precision and motion balance of humanoid robots and provides some inspiration for the application of using DRL in biped robots walking attitude control.

Analysis of Sensor-Based Real-Time Balancing of Humanoid Robots on Inclined Surfaces

An experimental and theoretical study of real-time robot balancing on inclined surfaces with electrical feedback circuitry is presented. Force sensors are experimentally shown to extend the sustainability of a stable robot posture beyond a critical surface inclination. For this purpose, the inclination feedback from the force sensors is used to adjust the robot's ankle-pitch-motor angle above the critical inclination, thus enabling the maintenance of a stable robot posture. Further, the Inverted Pendulum Model (IPM) (Hemami and Golliday, 1977, Hemami et al., 1973, and McGhee and Kuhner, 1969) is extended to the case of inclined surfaces. Through application of this extended IPM it is demonstrated, that simultaneous use of gyro-sensor data can minimize the necessary initial adjustment of the motor angle for controlled robot-body rotation, which additionally has the positive effect of reducing possible overshoots of the motor's rotation angle during feedback. Consequently, the reported feedback control improves the robot-body stability on inclined surfaces. Efficient implementation of the developed control scheme into an existing robot's electrical system is proposed.

Experimental Robot Model Adjustments Based on Force-Torque Sensor Information.

The computational complexity of humanoid robot balance control is reduced through the application of simplified kinematics and dynamics models. However, these simplifications lead to the introduction of errors that add to other inherent electro-mechanic inaccuracies and affect the robotic system. Linear control systems deal with these inaccuracies if they operate around a specific working point but are less precise if they do not. This work presents a model improvement based on the Linear Inverted Pendulum Model (LIPM) to be applied in a non-linear control system. The aim is to minimize the control error and reduce robot oscillations for multiple working points. The new model, named the Dynamic LIPM (DLIPM), is used to plan the robot behavior with respect to changes in the balance status denoted by the zero moment point (ZMP). Thanks to the use of information from force–torque sensors, an experimental procedure has been applied to characterize the inaccuracies and introduce them into the new model. The experiments consist of balance perturbations similar to those of push-recovery trials, in which step-shaped ZMP variations are produced. The results show that the responses of the robot with respect to balance perturbations are more precise and the mechanical oscillations are reduced without comprising robot dynamics.

Noise Reduction on the Tilt Sensor for the Humanoid Robot Balancing System Using Complementary Filter

The aim of the research is to present the design of a system which is capable for noise reduction on the reading of the tilt sensor data used in a balancing system on humanoid robots. Humanoid robot is a robot that has body construction like a human. Humanoid robots can make a movement by walking with both legs. In order to walk properly, humanoid robot needs to have a proper balancing system. The humanoid robot balancing system consists of tilt sensors, either an accelerometer or a gyroscope sensor, main processing unit and actuator in the form of servo motors on each robot’s joint. The tilt sensor is used to detect tilt angle of the robot body. When sensor gives information about the robot is in a position of tilt angle that will cause the robot to fall, the main processor will send commands to the actuators to do the balancing action so the robot will go to a balancing position. Unfortunately, the tilt angle reading value obtained from tilt sensor, still contain noise. That noise makes the reading of the tilt angle of the robot body to be inaccurate. Therefore, a filtering method is required to reduce the noise. In this research, complementary filter is used to overcome this problem. From the test result, the complementary filter is able to reduce noise on the tilt sensor data value reading. The optimum filtering result was obtained with the use of filter coefficient of 0.96 and sampling time of 50ms, where the average tilt angle error value is 0.775° on the x-axis and 0.691° on the y-axis. In another test, the robot is able to perform a balancing action based on the output of the complementary filter. So the robot was always able to maintain its position on balanced condition.

Lower-body control of humanoid robot NAO via Kinect

Humanoid robot has been concerned as it can perform some movements as human, especially imitating human motion in real time with motion tracking equipments. To imitate the human motion, there are still some challenges for the lower-body control of robot due to the physical difference between human and robot. In this paper, we propose a joint angle-based control (JAC) scheme for the lower-body control of humanoid robot to imitate human motion via Kinect sensor. Due to factors such as noise, tracking error and robot joint constrains, the motion information captured from the Kinect sensor applied to the robot directly will arise the problem of balance control. To overcome it, we optimize the joint angles in the lower-body of NAO, and define a gain factor to compensate the difference between the human motion and the robot so as to keep the balance of humanoid robot during imitation. Experimental results show that the proposed control scheme works efficiently even when the humanoid robot performs some complex movements such as standing on single foot.

Multiple Balance Strategies for Humanoid Standing Control

Full-state feedback parametric controllers are proposed for standing balance of humanoid robots in response to impulsive and constant pushes. Multiple robot models are used to approach multiple strategies in human standing balance. For each model, we design a parametric controller acting on each state variable and optimize controller parameters for different push sizes, directions, and locations. The performance of each controller is shown in response to different external pushes. By comparing the capabilities of handling disturbances in each strategy, the contributions of every joint to standing balance are also explored.

Multiple Balance Strategies for Humanoid Standing Control

Full-state feedback parametric controllers are proposed for standing balance of humanoid robots in response to impulsive and constant pushes. Multiple robot models are used to approach multiple strategies in human standing balance. For each model, we design a parametric controller acting on each state variable and optimize controller parameters for different push sizes, directions, and locations. The performance of each controller is shown in response to different external pushes. By comparing the capabilities of handling disturbances in each strategy, the contributions of every joint to standing balance are also explored.

Compliant Terrain Adaptation for Biped Humanoids Without Measuring Ground Surface and Contact Forces

This paper reports the applicability of our passivity-based contact force control framework for biped humanoids. We experimentally demonstrate its adaptation to unknown rough terrain. Adaptation to uneven ground is achieved by optimally distributed antigravitational forces applied to preset contact points in a feedforward manner, even without explicitly measuring the external forces or the terrain shape. Adaptation to unknown inclination is also possible by combining an active balancing controller based on the center-of-mass (CoM) measurements with respect to the inertial frame. Furthermore, we show that a simple impedance controller for supporting the feet or hands allows the robot to adapt to low-friction ground without prior knowledge of the ground friction. This presentation includes supplementary experimental videos that show a full-sized biped humanoid robot balancing on uneven ground or time-varying inclination.

Convex Optimization Algorithms for Active Balancing of Humanoid Robots

We show that a large class of active balancing problems for legged robots can be framed as a second-order cone programming (SOCP) problem, a convex optimization problem for which efficient and numerically robust algorithms exist. We describe this general SOCP balancing framework, show that several existing optimization-based balancing strategies reduce to special cases of this more general formulation, and investigate the computational performance of our SOCP algorithms through simulation studies involving a humanoid model.