• 센서학회지
• /
• 제33권1호
• /
• pp.18-23
• /
• 2024

Humanoid robots, designed to interact in human environments, require stable mobility to ensure safety. When a humanoid robot falls, it causes damage, breakdown, and potential harm to the robot. Therefore, fall detection is critical to preventing the robot from falling. Prevention of falling of a humanoid robot requires an operator controlling a crane. For efficient and safe walking control experiments, a system that can replace a crane operator is needed. To replace such a crane operator, it is essential to detect the falling conditions of humanoid robots. In this study, we propose falling detection methods using Convolution Neural Network (CNN) model. The image data of a humanoid robot are collected from various angles and environments. A large amount of data is collected by dividing video data into frames per second, and data augmentation techniques are used. The effectiveness of the proposed CNN model is verified by the experiments with the humanoid robot MAX-E1.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.77-79
• /
• 2004

Because robot hardware architecture generally is consisted of a few sensors and motors connected to the central processing unit, this type of structure is led to time consuming and unreliable system. For analysis, one of the fundamental difficulties in real-time system is how to be bounded the time behavior of the system. When a distributed control network controls the robot, with a central computing hub that sets the goals for the robot, processes the sensor information and provides coordination targets for the joints. If the distributed system supposed to be connected to a control network, the joints have their own control processors that act in groups to maintain global stability, while also operating individually to provide local motor control. We try to analyze the architecture of network-based humanoid robot's leg part and deal with its application using the CAN(Controller Area Network) protocol.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.548-550
• /
• 2006

This paper deals with the implementation of a small humanoid robot controller on the basis of Real Time Operating System(RTOS) and the FPGA. This controller was adapted to the humanoid robot with 25 DOFs, which are 12 DOFs in each leg, 8 DOFs in each arm, 3 DOFs in waist, and 2 DOFs in head. The robot actuators were used DX-117 servo motors that have all of the controller components in one module in order to simplify the control structure. In addition, the main controller is FPGA of Virtex4-FX from Xilinx, and ported on VxWorks that is kind of RTOS. It is essential to install this RTOS on the complex control system and to do control activity at the multitasking environments. This paper suggested the method of distributing the computational load in the humanoid robot controller using the FPGA and RTOS concepts. All of the control process was verified through the real action of the humanoid.

• 제어로봇시스템학회논문지
• /
• 제16권2호
• /
• pp.107-113
• /
• 2010

In this paper, a prototype of cooperative work model for multi-robots system is introduced and the evolutionary approach is applied to generate the motions for the cooperative works of multi-robots system using genetic algorithm. The cooperative tasks can be performed by a humanoid robot and a mobile robot to deliver objects from shelves. Generation of the humanoid motions such as pick up, rotation, and place operation for the cooperative works are evolved. Modeling and computer simulation for the cooperative robots system are executed in Webots environments. Experimental results show the feasible and reasonable solutions for humanoid cooperative tasks are obtained.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권2호
• /
• pp.121-130
• /
• 2012

This paper proposes an intuitive real-time robot control system using human body movement. Recently, it has been developed that motion generation for humanoid robots with reflecting human body movement, which is measured by a motion capture. However, in the existing studies about robot control system by human body movement, the detailed structure information of a robot, for example, degrees of freedom, the range of motion and forms, must be examined in order to calculate inverse kinematics. In this study, we have proposed Associative Motion Generation as humanoid robot motion generation method which does not need the detailed structure information. The associative motion generation system is composed of two neural networks: nonlinear principal component analysis and Jordan recurrent neural network, and the associative motion is generated with the following three steps. First, the system learns the correspondence relationship between an indication and a motion using training data. Second, associative values are extracted for associating a new motion from an unfamiliar indication using nonlinear principal component analysis. Last, the robot generates a new motion through calculation by Jordan recurrent neural network using the associative values. In this paper, we propose a real-time humanoid robot control system based on Associative Motion Generation, that enables user to control motion intuitively by human body movement. Through the task processing and subjective evaluation experiments, we confirmed the effective usability and affective evaluations of the proposed system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1539-1543
• /
• 2004

This paper describes platform overview, system integration and dynamic walking control of the humanoid robot, KHR-2 (KAIST Humanoid Robot - 2). We have developed KHR-2 since 2003. KHR-2 has totally 41 DOF (Degree Of Freedom). Each arm including a hand has 11 DOF and each leg has 6 DOF. Head and trunk also has 6 DOF and 1 DOF respectively. In head, two CCD cameras are used for eye. In order to control all joints, distributed control architecture is adopted to reduce the computation burden of the main controller and to expand the devices easily. The main controller attached its back communicates with sub-controllers in real-time by using CAN (Controller Area Network) protocol. We used Windows XP as its OS (Operating System) for fast development of main control program and easy extension of peripheral devices. And RTX, HAL(Hardware Abstraction Layer) extension program, is used to realize the real-time control in Windows XP environment. We present about real-time control of KHR-2 in Windows XP with RTX and basic walking control algorithm. Details of the KHR-2 are described in this paper.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.43-43
• /
• 2000

In this paper, we introduce a case study of developing a miniature humanoid robot that has 16 degrees of freedom and is able to perform statically stable walking. The developed humanoid robot is 37cm tall and weighs 1,200g. RC servo motors are used as actuators. The robot can walk forward and turn to any direction on even surface. It equipped with a small digital camera, so it can transmit vision data to a remote host computer via wireless modem. The robot can be operated in two modes; One is a remote-controlled mode, in which the robot behaves according to the command given by a human operator through the user-interface program running on a remote host computer, the other is a stand-alone mode, in which the robot behaves autonomously according to the pre-programmed strategy. The user-interface program also contains a robot graphic simulator that is used to produce and verify the robot's gait motion. In our walking algorithm, the ankle joint is mainly used lot balancing the robot. The experimental results shows that the developed robot can perform statically stable walking on even surface.

• 제어로봇시스템학회논문지
• /
• 제20권3호
• /
• pp.356-363
• /
• 2014

This paper covers improvement of the humanoid robot platform HUBO2, known as the HUBO2+. As a necessity of the growth of the humanoid platform, a robust, reliable and user friendly platform is needed. From this standpoint, HUBO2+ is the most improved humanoid robot platform in the HUBO series. The mechanical design has been changed to increase the movable range and to stop joint compulsion. Additionally, all of the electrical parts are re-designed to be un-breakable in an unexpected situation. A smart power controller with robot status check panel is attached on the back. Additionally, a diagnosis tool, the HUBO-i, has been developed. Moreover, each joint motor controller of HUBO2+ has a Protection Function and a PODO system is provided for handling the robot easily.

• 전기학회논문지
• /
• 제60권1호
• /
• pp.161-166
• /
• 2011

This paper addresses the vision based autonomous walking control system. To handle the obstacles which exist beyond the field of view(FOV), we used the 3d panoramic depth image. Moreover, to decide the avoidance direction and walking motion of a humanoid robot for the obstacle avoidance by itself, we proposed the vision based path planning using 3d panoramic depth image. In the vision based path planning, the path and walking motion are decided under environment condition such as the size of obstacle and available avoidance space. The vision based path planning is applied to a humanoid robot, URIA. The results from these evaluations show that the proposed method can be effectively applied to decide the avoidance direction and the walking motion of a practical humanoid robot.

• 제어로봇시스템학회논문지
• /
• 제6권5호
• /
• pp.404-414
• /
• 2000

This paper addresses the development of a 3-fingered humanoid robot hand system and a real-time grasp synthesis of multifingered robot hands to find grasp configurations which satisfy the force closure condition of arbitrary shaped objects. We propose a fast and efficient grasp synthesis algorithm for planar polygonal objects, which yields the contact locations on a given polygonal object to obtain a force closure grasp by the multifingered robot hand. For an optimum grasp and real-time computation, we develop the preference and the hibernation process and assign physical constraints of the humanoid hand to the motion of each finger. The preferences consist of each sublayer reflecting the primitive preference similar to the conditional behaviors of humans for given objectives and their arrangements are adjusted by the heuristics inspired from human's grasping behaviors. The proposed method reduces the computational time significantly at the sacrifice of global optimality, and enables the grasp posture to be changable within two-finger and three-finger grasps. The performance of the presented algorithm is evaluated via simulation studies to obtain the force-closure grasps of polygonal objects with fingertip grasps. The architecture suggested is verified through experimental implementation to our robot hand system by solving the 2- or 3-finger grasp synthesis.