Unifying Representations and Large-Scale Whole-Body Motion Databases for Studying Human Motion

2016 ◽  
Vol 32 (4) ◽  
pp. 796-809 ◽  
Author(s):  
Christian Mandery ◽  
Omer Terlemez ◽  
Martin Do ◽  
Nikolaus Vahrenkamp ◽  
Tamim Asfour
Keyword(s):  
Large Scale ◽  
Human Motion ◽  
Body Motion ◽  
Whole Body

scholarly journals Simulation of Disturbance Recovery Based on MPC and Whole-Body Dynamics Control of Biped Walking

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2971 ◽  
Author(s):  
Xuanyang Shi ◽  
Junyao Gao ◽  
Yizhou Lu ◽  
Dingkui Tian ◽  
Yi Liu
Keyword(s):  
Large Scale ◽  
Center Of Mass ◽  
Biped Robot ◽  
Optimization Method ◽  
Stability Control ◽  
Body Motion ◽  
Whole Body ◽  
Human Beings ◽  
Foot Placement ◽  
Body Dynamics

Biped robots are similar to human beings and have broad application prospects in the fields of family service, disaster rescue and military affairs. However, simplified models and fixed center of mass (COM) used in previous research ignore the large-scale stability control ability implied by whole-body motion. The present paper proposed a two-level controller based on a simplified model and whole-body dynamics. In high level, a model predictive control (MPC) controller is implemented to improve zero moment point (ZMP) control performance. In low level, a quadratic programming optimization method is adopted to realize trajectory tracking and stabilization with friction and joint constraints. The simulation shows that a 12-degree-of-freedom force-controlled biped robot model, adopting the method proposed in this paper, can recover from a 40 Nm disturbance when walking at 1.44 km/h without adjusting the foot placement, and can walk on an unknown 4 cm high stairs and a rotating slope with a maximum inclination of 10°. The method is also adopted to realize fast walking up to 6 km/h.

Whole-Body Human-to-Humanoid Motion Imitation

2013 ◽  
Vol 479-480 ◽  
pp. 617-621
Author(s):  
Hsien I Lin ◽  
Zan Sheng Chen
Keyword(s):  
Degrees Of Freedom ◽  
Humanoid Robot ◽  
Optimal Solution ◽  
Human Motion ◽  
Body Motion ◽  
Upper Body ◽  
Whole Body ◽  
Nao Robot ◽  
Novel Approach ◽  
Intuitive Method

Human-to-Humanoid motion imitation is an intuitive method to teach a humanoid robot how to act by human demonstration. For example, teaching a robot how to stand is simply showing the robot how a human stands. Much of previous work in motion imitation focuses on either upper-body or lower-body motion imitation. In this paper, we propose a novel approach to imitate human whole-body motion by a humanoid robot. The main problem of the proposed work is how to control robot balance and keep the robot motion as similar as taught human motion simultaneously. Thus, we propose a balance criterion to assess how well the root can balance and use the criterion and a genetic algorithm to search a sub-optimal solution, making the root balanced and its motion similar to human motion. We have validated the proposed work on an Aldebaran Robotics NAO robot with 25 degrees of freedom. The experimental results show that the root can imitate human postures and autonomously keep itself balanced.

Dynamic locomotion synchronization of bipedal robot and human operator via bilateral feedback teleoperation

2019 ◽  
Vol 4 (35) ◽  
pp. eaav4282 ◽  
Author(s):  
Joao Ramos ◽  
Sangbae Kim
Keyword(s):  
Sagittal Plane ◽  
Frontal Plane ◽  
Humanoid Robots ◽  
Human Locomotion ◽  
Human Motion ◽  
Body Motion ◽  
Human Operator ◽  
Whole Body ◽  
Physical Endurance ◽  
Bipedal Robot

Despite remarkable progress in artificial intelligence, autonomous humanoid robots are still far from matching human-level manipulation and locomotion proficiency in real applications. Proficient robots would be ideal first responders to dangerous scenarios such as natural or man-made disasters. When handling these situations, robots must be capable of navigating highly unstructured terrain and dexterously interacting with objects designed for human workers. To create humanoid machines with human-level motor skills, in this work, we use whole-body teleoperation to leverage human control intelligence to command the locomotion of a bipedal robot. The challenge of this strategy lies in properly mapping human body motion to the machine while simultaneously informing the operator how closely the robot is reproducing the movement. Therefore, we propose a solution for this bilateral feedback policy to control a bipedal robot to take steps, jump, and walk in synchrony with a human operator. Such dynamic synchronization was achieved by (i) scaling the core components of human locomotion data to robot proportions in real time and (ii) applying feedback forces to the operator that are proportional to the relative velocity between human and robot. Human motion was sped up to match a faster robot, or drag was generated to synchronize the operator with a slower robot. Here, we focused on the frontal plane dynamics and stabilized the robot in the sagittal plane using an external gantry. These results represent a fundamental solution to seamlessly combine human innate motor control proficiency with the physical endurance and strength of humanoid robots.

WHOLE-BODY MOTION GENERATION OF ANDROID ROBOT USING MOTION CAPTURE AND NONLINEAR CONSTRAINED OPTIMIZATION

2013 ◽  
Vol 10 (02) ◽  
pp. 1350003 ◽  
Author(s):  
JUNG-YUP KIM ◽  
YOUNG-SEOG KIM
Keyword(s):  
Constrained Optimization ◽  
Motion Capture ◽  
Optimization Technique ◽  
Human Motion ◽  
Body Motion ◽  
Whole Body ◽  
Motion Generation ◽  
Nonlinear Constrained Optimization ◽  
Gimbal Lock ◽  
Android Robot

This paper describes a whole-body motion generation scheme for an android robot using motion capture and an optimization method. Android robots basically require human-like motions due to their human-like appearances. However, they have various limitations on joint angle, and joint velocity as well as different numbers of joints and dimensions compared to humans. Because of these limitations and differences, one appropriate approach is to use an optimization technique for the motion capture data. Another important issue in whole-body motion generation is the gimbal lock problem, where a degree of freedom at the three-DOF shoulder disappears. Since the gimbal lock causes two DOFs at the shoulder joint diverge, a simple and effective strategy is required to avoid the divergence. Therefore, we propose a novel algorithm using nonlinear constrained optimization with special cost functions to cope with the aforementioned problems. To verify our algorithm, we chose a fast boxing motion that has a large range of motion and frequent gimbal lock situations as well as dynamic stepping motions. We then successfully obtained a suitable boxing motion very similar to captured human motion and also derived a zero moment point (ZMP) trajectory that is realizable for a given android robot model. Finally, quantitative and qualitative evaluations in terms of kinematics and dynamics are carried out for the derived android boxing motion.

scholarly journals Robots that look like humans: A brief look into humanoid robotics

2018 ◽  
Author(s):  
Eiichi Yoshida
Keyword(s):  
Degrees Of Freedom ◽  
Large Scale ◽  
Humanoid Robots ◽  
Pattern Generation ◽  
Human Robot Interaction ◽  
Cognitive Robotics ◽  
Body Motion ◽  
Upper Body ◽  
Whole Body ◽  
Robot Interaction

This article provides a brief overview of the technology of humanoid robots. First, historical development and hardware progress are presented mainly on human-size full-body biped humanoid robots, together with progress in pattern generation of biped locomotion. Then, «whole-body motion» – coordinating leg and arm movements to fully leverage humanoids’ high degrees of freedom – is presented, followed by its applications in fields such as device evaluation and large-scale assembly. Upper-body humanoids with a mobile base, which are mainly utilized for research on human-robot interaction and cognitive robotics, are also introduced before addressing current issues and perspectives.

WHOLE-BODY DYNAMIC BEHAVIOR AND CONTROL OF HUMAN-LIKE ROBOTS

2004 ◽  
Vol 01 (01) ◽  
pp. 29-43 ◽  
Author(s):  
O. KHATIB ◽  
L. SENTIS ◽  
J. PARK ◽  
J. WARREN
Keyword(s):  
Dynamic Behavior ◽  
Dynamic Models ◽  
Dynamic Control ◽  
Human Motion ◽  
Body Motion ◽  
Whole Body ◽  
Control Framework ◽  
Generalized Framework ◽  
Space Formulation ◽  
Body Dynamic

With the increasing complexity of humanoid mechanisms and their desired capabilities, there is a pressing need for a generalized framework where a desired whole-body motion behavior can be easily specified and controlled. Our hypothesis is that human motion results from simultaneously performing multiple objectives in a hierarchical manner, and we have analogously developed a prioritized, multiple-task control framework. The operational space formulation10 provides dynamic models at the task level and structures for decoupled task and posture control.13 This formulation allows for posture objectives to be controlled without dynamically interfering with the operational task. Achieving higher performance of posture objectives requires precise models of their dynamic behaviors. In this paper we complete the picture of task descriptions and whole-body dynamic control by establishing models of the dynamic behavior of secondary task objectives within the posture space. Using these models, we present a whole-body control framework that decouples the interaction between the task and postural objectives and compensates for the dynamics in their respective spaces.

From human motion capture to humanoid locomotion imitation Application to the robots HRP-2 and HOAP-3

Robotica ◽  
2010 ◽  
Vol 29 (2) ◽  
pp. 325-334 ◽  
Author(s):  
Luc Boutin ◽  
Antoine Eon ◽  
Said Zeghloul ◽  
Patrick Lacouture
Keyword(s):  
Motion Capture ◽  
Human Locomotion ◽  
Inverse Kinematic ◽  
Human Motion ◽  
Simulation Software ◽  
Body Motion ◽  
Whole Body ◽  
Human Gait ◽  
Reference Trajectory ◽  
Double Support

SUMMARYThis paper presents a method to generate humanoid gaits from a human locomotion pattern recorded by a motion capture system. Thirty seven reflective markers were fixed on the human subject skin in order to get the subject whole body motion. To reproduce the human gait, especially the toes and heel contacts, the front and back edges of the robot's feet are used as support at the start and the end of the double support phase. The balance of the robot is respected using the zero moment point (ZMP) criterion and confirmed by the simulation software OPENHRP (General Robotics, Inc®). First, the feet trajectory as well as the ZMP reference trajectory are defined from the motion of the robot controlled as a marionette with the measured human joint angles. Then a specific inverse kinematic (IK) algorithm is proposed to find the humanoid robot's joint trajectories respecting the constraints of balance, floor contacts, and joint limits. The studied motion presented in this paper is a human walking trajectory containing a start, a movement in a straight line, a stop, and a quarter turn. The method was developed to be easily used for human-like robots of different sizes, masses, and structures and has been tested on the robot HRP-2 (AIST, Kawada Industries, Inc®) and on the small-sized humanoid robot HOAP-3 (Fujitsu Automation Ltd®).

scholarly journals sEMG-Based Continuous Estimation of Finger Kinematics via Large-Scale Temporal Convolutional Network

2021 ◽  
Vol 11 (10) ◽  
pp. 4678
Author(s):  
Chao Chen ◽  
Weiyu Guo ◽  
Chenfei Ma ◽  
Yongkui Yang ◽  
Zheng Wang ◽  
...  
Keyword(s):  
Motion Estimation ◽  
Motion Control ◽  
Large Scale ◽  
Human Motion ◽  
Kernel Size ◽  
Continuous Motion ◽  
Convolutional Network ◽  
Continuous Estimation ◽  
Discrete Motion ◽  
Precision Rate

Since continuous motion control can provide a more natural, fast and accurate man–machine interface than that of discrete motion control, it has been widely used in human–robot cooperation (HRC). Among various biological signals, the surface electromyogram (sEMG)—the signal of actions potential superimposed on the surface of the skin containing the temporal and spatial information—is one of the best signals with which to extract human motion intentions. However, most of the current sEMG control methods can only perform discrete motion estimation, and thus fail to meet the requirements of continuous motion estimation. In this paper, we propose a novel method that applies a temporal convolutional network (TCN) to sEMG-based continuous estimation. After analyzing the relationship between the convolutional kernel’s size and the lengths of atomic segments (defined in this paper), we propose a large-scale temporal convolutional network (LS-TCN) to overcome the TCN’s problem: that it is difficult to fully extract the sEMG’s temporal features. When applying our proposed LS-TCN with a convolutional kernel size of 1 × 31 to continuously estimate the angles of the 10 main joints of fingers (based on the public dataset Ninapro), it can achieve a precision rate of 71.6%. Compared with TCN (kernel size of 1 × 3), LS-TCN (kernel size of 1 × 31) improves the precision rate by 6.6%.

Sign in / Sign up

Export Citation Format

Share Document