Seungsu Kim

Stable whole-body motion generation for humanoid robots to imitate human motions

This work presents a methodology to generate dynamically stable whole-body motions for a humanoid robot, which are converted from human motion capture data. The methodology consists of the kinematic and dynamical mappings for human-likeness and stability, respectively. The kinematic mapping includes the scaling of human foot and Zero Moment Point (ZMP) trajectories considering the geometric differences between a humanoid robot and a human. It also provides the conversion of human upper body motions using the method in [1]. The dynamic mapping modifies the humanoid pelvis motion to ensure the movement stability of humanoid whole-body motions, which are converted from the kinematic mapping. In addition, we propose a simplified human model to obtain a human ZMP trajectory, which is used as a reference ZMP trajectory for the humanoid robot to imitate during the kinematic mapping. A human whole-body dancing motion is converted by the methodology and performed by a humanoid robot with online balancing controllers.

Human-like Arm Motion Generation for Humanoid Robots Using Motion Capture Database

During the communication and interaction with a human using motions or gestures, a humanoid robot needs to not only look like a human but also behavior like a human to avoid confusions in the communication and interaction. Among human-like behaviors, arm motions of the humanoid robot are essential for the communication with people through motions. In this work, a mathematical representation for characterizing human arm motions is first proposed. The human arm motions are characterized by the elbow elevation angle that is determined using the position and orientation of human hands. That representation is mathematically obtained using an approximation tool, response surface method (RSM). Then, a method to generate human-like arm motions in real time using the proposed representation is presented. The proposed method was evaluated to generate human-like arm motions when the humanoid robot was asked to move its arms from a point to another point including the rotation of hand. An example motion was performed using the KIST humanoid robot, MAHRU

Catching Objects in Flight

We address the difficult problem of catching in-flight objects with uneven shapes. This requires the solution of three complex problems: accurate prediction of the trajectory of fastmoving objects, predicting the feasible catching configuration, and planning the arm motion, and all within milliseconds. We follow a programming-by-demonstration approach in order to learn, from throwing examples, models of the object dynamics and arm movement. We propose a new methodology to find a feasible catching configuration in a probabilistic manner. We use the dynamical systems approach to encode motion from several demonstrations. This enables a rapid and reactive adaptation of the arm motion in the presence of sensor uncertainty. We validate the approach in simulation with the iCub humanoid robot and in real-world experiments with the KUKA LWR 4+ (7-degree-of-freedom arm robot) to catch a hammer, a tennis racket, an empty bottle, a partially filled bottle, and a cardboard box.

Learning motion dynamics to catch a moving object

In this paper, we consider a novel approach to control the timing of motions when these are encoded with autonomous dynamical systems (DS). Accurate timing of motion is crucial if a robot must synchronize its movement with that of a fast moving object. In previous work of ours [1], we developed an approach to encode robot motion into DS. Such a time-independent encoding is advantageous in that it offers robustness against violent perturbation by adapting on the fly the trajectory while ensuring high accuracy at the target. We propose here an extension of the system that allows to control the timing of the motion while still benefitting from all the robustness properties deriving from the time-independent encoding of the DS. We validate the approach in experiments where the iCub robot learns from human demonstrations to catch a ball on the fly.

Estimating the non-linear dynamics of free-flying objects

This paper develops a model-free method to estimate the dynamics of free-flying objects. We take a realistic perspective to the problem and investigate tracking accurately and very rapidly the trajectory and orientation of an object so as to catch it in flight. We consider the dynamics of complex objects where the grasping point is not located at the center of mass. To achieve this, a density estimate of the translational and rotational velocity is built based on the trajectories of various examples. We contrast the performance of six non-linear regression methods (Support Vector Regression (SVR) with Radial Basis Function (RBF) kernel, SVR with polynomial kernel, Gaussian Mixture Regression (GMR), Echo State Network (ESN), Genetic Programming (GP) and Locally Weighted Projection Regression (LWPR)) in terms of precision of recall, computational cost and sensitivity to choice of hyper-parameters. We validate the approach for real-time motion tracking of 5 daily life objects with complex dynamics (a ball, a fully-filled bottle, a half-filled bottle, a hammer and a pingpong racket). To enable real-time tracking, the estimated model of the objects dynamics is coupled with an Extended Kalman Filter for robustness against noisy sensing.

Whole-body motion imitation using human modeling

The purpose of this study is to develop a methodology that enables a humanoid robot to imitate a whole body motion of a human. In the communication and interaction with a human being with motions and gestures, a humanoid robot needs not only to look like a human but to behave as a human does to make sure the meanings of motions and gestures. To act like a human, the humanoid robot has to imitate the kinematical and dynamical movement of human. For this, a methodology for a humanoid robot to imitate human whole body motions, is presented. Human motions are acquired from a motion capture system. The proposed methodology first converts the captured motions into the motions for a humanoid robot considering kinematical differences between human and robot. In addition, the methodology proposes a simplified human model to analyze a human ZMP trajectory using an optimization scheme. The methodology computes a stable ZMP trajectory for the humanoid robot based the ZMP trajectory of this simplified human model. From the computed ZMP trajectory, the whole body motion for the humanoid robot is generated through this off-line process. A human whole body motion, a dancing motion, is converted to examine the developed methodology.

Regenerating human-like arm motions of humanoid robots for a movable object

A method to regenerate a new human-like arm motion by modifying and scaling a human arm motion is presented. The humanoid robot may not obtain all the necessary human-like motions from motion capture data. When the robot communicates with a person, the robot has to keep attention to the person by aligning the direction of the motion. The robot needs to modify human arm motions and regenerate new human-like arm motions without loosing the original meanings. The developed method modifies and scales the wrist trajectory of a human arm motion and reproduces the human-like arm. The motion of drawing multiple circles with a various radius and direction is examined.

Balloon burster: A CORBA-based visual servoing for humanoid robot in a distributed environment

This paper proposes CORBA-based visual servoing system of humanoid robot. To effectively control the humanoid robot which is connected to network, it needs to define necessary services for visual servoing as distribution object, and realize them in the middleware. For realizing it following services should be addressed. Naming service for searching a necessary service with unique name assigned to each object, image service for supplying image obtained from stereo camera. In the experiment, we show the result of balloon tracking and bursting that the robot tracks balloons as target objects in the real time, and if a balloon stop for a certain time, then the robot bursts the balloon.

A service framework of humanoid in daily life

This paper presents a service framework of a humanoid robot for the coordinated task execution. To execute given tasks, various sub-systems of the robot need to be coordinated effectively. The goal of our paper is to develop the service framework which makes it possible to execute various tasks in daily life environments. A script is used as a tool for describing tasks to easily regulate actions of the sub-systems while the robot is performing the task. The performance of the presented framework is experimentally demonstrated as follows: A humanoid robot, as the platform of the task execution, recognizes the designated object. The object pose is calculated by performing model-based object tracking using a particle filter with back projection-based sampling. An approach proposed by Kim et al. [1] is used to solve a human-like arm inverse kinematics and then the control system generates smooth trajectories for each joint of the humanoid robot. The results of our implementation show the robot can execute the task efficiently in human workspaces, such as an office or home.