Obstacle trajectory prediction and model training method
A technology for predicting models and obstacles, applied in measurement devices, biological neural network models, nuclear methods, etc., can solve the problem of long time consumption, and achieve the effect of improving the trajectory effect.
Active Publication Date: 2020-11-10
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF7 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the more information acquired, the greater the amount of calculation required for unmanned equipment, and the longer it takes to predict the trajectory of obstacles
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
[0059] In order to make the purpose, technical solution and advantages of this specification clearer, the technical solution of this specification will be clearly and completely described below in conjunction with specific embodiments of this specification and corresponding drawings. Apparently, the described embodiments are only some of the embodiments in this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this specification.
[0060] In the field of unmanned driving, unmanned equipment needs to plan its own trajectory in real time during operation to avoid obstacles in the surrounding environment and achieve safe driving. In the surrounding environment where the unmanned device is located, obstacles can include static obstacles and dynamic obstacles. Therefore, in order to better plan the trajectory of the unmann...
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 an obstacle trajectory prediction and model training method and device, and unmanned equipment can determine the current driving scene, determine the prediction duration of theprediction trajectory of each obstacle required for planning the trajectory of the unmanned equipment, and predict the trajectory of each obstacle in each preset information type according to the driving scene, the prediction duration and the like.Selecting at least one information type, acquiring information of the information type of each obstacle for each selected information type, determiningcharacteristics of each obstacle corresponding to the information type according to the acquired information, and determines a prediction trajectory of the obstacle in the prediction duration according to the current position of the obstacle and the determined characteristics of each information type for each obstacle. According to the present specification, the information type can be selected,the trajectory effect of predicting the obstacle is improved based on the information of the selected information type, and the calculation power consumed for predicting the obstacle trajectory by theunmanned device and the accuracy relationship of the obstacle trajectory can be balanced.
Description
technical field [0001] This description relates to the field of unmanned driving technology, in particular to a method and device for predicting obstacle trajectories and model training. Background technique [0002] At present, when the unmanned equipment is running, it can predict the trajectory of obstacles in the surrounding environment, based on the predicted trajectory of each obstacle, reasonably plan its own future trajectory, and pre-judge and adjust the control amount. [0003] Usually, unmanned equipment can obtain information such as historical trajectories of obstacles, electronic maps, traffic lights, weather, and pedestrian attitudes, and predict the trajectory of obstacles based on the obtained information. The more precise the trajectory, the longer the time period for reliable predictions. However, the more information acquired, the greater the amount of computation required by the unmanned device, and the longer it takes to predict the trajectory of the o...
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 Applications(China)
IPC IPC(8): G01C21/34G01C21/30G06N3/04G06N20/10G06N20/00
CPCG01C21/343G01C21/3446G01C21/30G06N20/00G06N20/10G06N3/044G06N3/045
Inventor 樊明宇任冬淳周浩夏华夏朱炎亮钱德恒杨旭
Owner BEIJING SANKUAI ONLINE TECH CO LTD