Navigation method of wheeled mobile robot based on ihdr autonomous learning framework
A mobile robot, navigation method technology, applied in two-dimensional position/channel control and other directions, can solve problems such as poor adaptability, inability to adapt to complex, changeable and unknown environments, etc., to achieve improved efficiency and success rate, intelligent high degree of effect
Active Publication Date: 2017-11-10
WUHAN UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This mathematical model-based navigation method requires the robot to re-plan in the new environment, which is reflected in: ① cannot adapt to the complex, changeable and unknown environment; ② task is specific, only for a certain task has a good performance, not Can develop new abilities; therefore poor adaptability
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
[0035] The mobile robot manually trains the robot's "walking" behavior, stores the corresponding learning mechanism, and then moves autonomously in the same environment without human control. Attached below Figure 1-5 The present invention is described in detail:
[0036] The present invention communicates with the upper computer through the handle controller to control the robot to move forward, backward, left, and right through the motion control card, and collects some image information and depth information that the robot "sees" through the kincet sensor, and then uses the IHDR algorithm to establish the IHDR tree structure. The autonomous learning framework stores the learned "knowledge" in the knowledge base, and finally, without human intervention, the robot can retrieve the IHDR tree structure in real time to obtain the corresponding motion data and feed it back to the robot to realize the autonomous movement of the robot; including The main steps are as follows:
...
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 relates to a navigation method for a wheeled mobile robot based on an IHDR autonomous learning framework. It includes the following steps: first guide the robot to move, and in the process, the robot collects the image information and speed value at the current moment in real time through the kinect sensor and the handle control quantity; then uses the IHDR algorithm to establish a mapping relationship between image input and speed value output, and A large amount of collected data is stored in the robot in the form of a "knowledge" tree structure; finally, under the condition of no human intervention, the robot can search the knowledge base according to the current image information, so as to realize autonomous navigation. This method can make the robot have the same way of thinking as human beings, which embodies a cognitive ability, rather than the traditional way of navigating through mathematical models, and has a higher degree of intelligence.
Description
technical field [0001] The invention belongs to the technical field of navigation of wheeled mobile robots, and relates to a method for obtaining image information based on kinect and enabling the robot to have autonomous navigation through artificial training. Background technique [0002] With the development of sensor technology, more and more sensors are carried on the robot. For example, how far the robot is from the obstacle in front is measured by the sick laser rangefinder; the image information is obtained by the kinect sensor, and the SLAM (Simultaneous Localization and Mapping, real-time simultaneous positioning and map construction) algorithm is used for three-dimensional composition; the digital compass Know the relative coordinates where the robot is located, the azimuth angle it has turned, etc. The development of these sensor technologies makes robots more and more intelligent, and more and more functions can be realized. However, robot navigation is still ...
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
Inventor 吴怀宇李威凌钟锐陈洋张琴丽牛洪芳
Owner WUHAN UNIV OF SCI & TECH