Robot embedded computing terminal integrating high-precision navigation positioning and deep learning
A technology of navigation and positioning and deep learning, applied in vehicle position/route/altitude control, instruments, two-dimensional position/channel control and other directions, which can solve the problem of lack of deep learning platform support, lack of environmental intelligence perception, and low hardware integration. and other problems, to achieve the effects of rich interfaces, overcoming inaccurate monocular ranging, real-time path planning and navigation
Active Publication Date: 2022-03-15
中山赛伯坦智能科技有限公司 +2
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, current robots generally require three industrial computers for positioning, driving, and core computing to complete basic tasks. Therefore, existing robot embedded platforms generally have insufficient computing power, low hardware integration, lack of deep learning platform support, and lack of environment. Intellisense and other limitations
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0022] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.
[0023] The present invention designs a high-precision integrated intelligent robot embedded device, which provides various interfaces for accessing various sensor devices, and realizes the access of multi-source sensor data. The whole setup satisfies the acquisition, processing and output of multiple signals, and has continuous high-precision multi-sensor fusion adaptive positioning and deep learning capabilities.
[0024] A highly integrated embedded robot development device based on Beidou positioning provided by the embodiment of the present invention has ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention is a robot embedded computing terminal integrating high-precision navigation positioning and deep learning, which is characterized in that it includes an integrated core processing unit Jetson chip, FPGA chip, embedded ARM module and various sensors, and the sensors include GNSS satellite navigation module, IMU inertial navigation module, laser radar and camera, the core processing unit Jetson chip is connected to camera and laser radar, FPGA chip is respectively connected to GNSS satellite navigation module and IMU inertial navigation module, embedded ARM module; embedded ARM module is connected Control the robot's servo motors. The invention can support the solution of real-time high-precision positioning results, and realize the environment perception and task planning of the robot.
Description
technical field [0001] The invention describes a highly integrated intelligent robot development device based on high-precision Beidou positioning, which belongs to the field of embedded robot development. Background technique [0002] The multi-source sensor information fusion processing on the robot is the key to the robot's autonomous perception, precise control and task planning. Due to the characteristics of small size, low power consumption and high integration level of the embedded platform, the embedded platform has become the mainstream research and development platform of the robot. However, current robots generally require three industrial computers for positioning, driving, and core computing to complete basic tasks. Therefore, existing robot embedded platforms generally have insufficient computing power, low hardware integration, lack of deep learning platform support, and lack of environment. IntelliSense and other limitations. Contents of the invention [0...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G05D1/02
CPCG05D1/0088G05D1/0231G05D1/0246G05D1/027G05D1/0278
Inventor 郭迟董巍张艺芬陈梁代永红崔竞松郭文飞左文炜
Owner 中山赛伯坦智能科技有限公司