Track planning method and device based on reinforcement learning and storage medium
A technology of trajectory planning and reinforcement learning, which is applied in neural learning methods, neural architectures, biological neural network models, etc. It can solve the problems of finding the balance point of the cost function, the accuracy of path planning results is low, and the weight is not enough to cover all scenarios, etc. problems, to avoid excessive dependence, enhance applicability, and improve accuracy
Inactive Publication Date: 2021-08-17
前海七剑科技(深圳)有限公司
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, in the process of evaluating the trajectory with the cost function, various cost functions check and balance each other. It is difficult to find the balance between the cost functions in different scenarios. Excessive reliance on the calibrated weights is not enough to cover all scenarios. As a result, the accuracy of path planning results is low
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
[0025] Embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary, and are only for explaining the present application, and should not be construed as limiting the present application.
[0026] In the description of the present application, several means more than one, and multiple means more than two. Greater than, less than, exceeding, etc. are understood as not including the original number, and above, below, within, etc. are understood as including the original number. If the description of the first and second is only for the purpose of distinguishing the technical features, it cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated tech...
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 discloses a track planning method and device based on reinforcement learning and a storage medium. The trajectory planning method based on reinforcement learning provided by the invention comprises the steps of obtaining a cost function; obtaining an original action value function; performing initialization processing on the original action value function according to the cost function to obtain a pre-training action value function; obtaining a reward function; training the pre-training action value function according to the reward function to obtain a target action value function; obtaining trajectory planning data according to the target action value function. According to the track planning method based on reinforcement learning, the accuracy of a path planning result is improved.
Description
technical field [0001] The present application relates to but not limited to the field of artificial intelligence, and in particular relates to a trajectory planning method, device and storage medium based on reinforcement learning. Background technique [0002] In the field of artificial intelligence, the lattice planning algorithm of self-driving vehicles decomposes the three-dimensional trajectory problem into two two-dimensional trajectory problems based on the frenet coordinate system, that is, the three-dimensional problem between "longitudinal trajectory, horizontal trajectory, and time" is decomposed into "longitudinal ST trajectories, transverse SL trajectories" between two-dimensional problems. In the ST diagram and SL diagram, the initial and final states of the vehicle are sampled respectively, polynomial fitting is performed for each final state, and the trajectory is evaluated with a cost function, and the trajectory with the lowest cost function is selected. ...
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 IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 顾林坤谭敏波
Owner 前海七剑科技(深圳)有限公司