Li Shipei
ABSTRACT
Aiming at the problem of grasping objects under different lighting conditions and positions, A method based on supervised learning under the guidance of vision to accurately recognize objects is put forward, Firstly, the center of the object is determined through the diagonal center, and the pixel coordinate of the object center is converted into the terminal coordinate of the robot through camera calibration and hand-eye calibration. Then, the programming is carried out on the robot instructor to obtain a grasping route through path planning.Through many experiments and analyses, it is proved that the supervised learning method of directional gradient histogram and support vector machine can precisely locate the target, which has certain reference value for robot grasping.
- Cao Wenxiang(2011). Research status and development trend of industrial robot.Machinery manufacturing, 49(2):41--43.Google Scholar
- Lu Quanji(2014). Research on visual grasping application of manipulator based on HALCON.Optical instruments, 36(6):492--498.Google Scholar
- Xie Chunsheng(2014). Robot vision algorithm based on object color and size features. Mechanical science and technology, 33(11).Google Scholar
- Huang Lingtao(2019). Research on robot grasping system. Journal of agricultural machinery, 50(01):390--399.Google Scholar
- Chen hong(2014). Separation technology of mushroom based on machine vision. Journal of agricultural machinery, 45(1):281--287.Google Scholar
- LingJing(2000). Research on visual servo system of robot.Control theory and application, 17(4): 476--481.Google Scholar
- Shi F Y, Cheng S X(2005). Automatic seeded region growing forcolor image segmentation. Image and Vision Computing, 23(10): 877 886.Google ScholarDigital Library
- Qiu Zhaowen (2004). A new image color feature extraction method. Journal of Harbin Institute of Technology, 36(12): 1699--1701.Google Scholar
- Chen Weiyi (2004). Ellipse extraction based on Hough transform and deformation curve technique. Microelectronics and computers, 21(9): 91--95.Google Scholar
- Chen Yi(2013), Recent Development and future research issues. The International Journal of Advanced Manufacturing Technology, 66(9-12): 1489--1497.Google ScholarCross Ref
- Meng Xiaoqiao(2002), A new method of camera self - calibration based on circle point.Journal of software, 13(5):957--965.Google Scholar
- Jain A(2010). an assistive mobile manipulator that autonomously fetches objects from flat surfaces. Autonomous Robots, 28(1):45--64.Google ScholarDigital Library
- Duan Feng(2002). Overview of machine vision technology and its applications. Automation expo, 19(3): 59--61.Google Scholar
- Li Song(2005). Open source computer vision library OpenCV application. Computer application and software,(8): 134--136.Google Scholar
- Luo Jiajia(2005). Research on robot motion simulation based on MATLAB. Journal of xiamen university, 44(5): 640--644.Google Scholar
Index Terms
- Cooperative Robot Grasping Based On Supervised Learning
Recommendations
Supervised fuzzy reinforcement learning for robot navigation
A novel method for combination of supervised learning and fuzzy reinforcement learning (FRL) is proposed.Supervised learning is used for initialization of value (worth) of each candidate action of fuzzy rules in critic-only based FRL algorithms.The ...
Neural network-based approaches for mobile robot navigation in static and moving obstacles environments
Mobile robots can travel by acquiring the information using sensor-actuator control techniques from surrounding and perform several tasks. Due to the ability of traversing, mobile robots are used in different application for different places. In the ...
Towards Imitation Learning of Grasping Movements by an Autonomous Robot
GW '99: Proceedings of the International Gesture Workshop on Gesture-Based Communication in Human-Computer InteractionImitation learning holds the promise of robots which need not be programmed but instead can learn by observing a teacher. We present recent efforts being made at our laboratory towards endowing a robot with the capability of learning to imitate human ...
Comments