Định vị cho robot dùng bộ lọc kalman và vật mốc

• Tác giả: Hoàng Anh Lê, Văn Thuyên Ngô
• Ngôn ngữ: vie
• Ký hiệu phân loại: 332.175 General banking services
• Thông tin xuất bản: Khoa học và Công nghệ, 2012
• Mô tả vật lý: 66-71
• Bộ sưu tập: Metadata
• ID: 632155

Tóm tắt

To follow a desired trajectory in a working environment, a mobile robot must be able to localize itself. This paper presented a localization algorithm for mobile robots based on recognition of artificial landmarks with a camera. The path finding algorithm A. was applied to find an optimal path for the robot to move from its initial position to its goal without colliding with obstacles. A geometric method was used to determine the position of the robot from the coordinate of artificial landmarks in the environment. The Kalman filter combines the estimation of robot internal states based on its kinematic model and external sensory information to better estimate the robot positions. The algorithm has been implemented on a real mobile robot platform with two differential drive wheels, a Kinect camera and computer vision functions in OpenCV library. The experimental results showed that the robot can use its estimated position to follow its desired trajectory closely. The Kalman filter provided a better estimation of robot positions.