A self-driving vehicle scheduling method and device

Abstract

The present application provides a method and device for dispatching autonomous vehicles, wherein the method includes: obtaining the travel demand information of a passenger, wherein the travel demandinformation of the passenger includes a start point, an end point, and a ride time; planning a travel route and generating travel route information based on a pre-trained route planning model and according to the travel demand information, the weather information corresponding to the ride time, an actual traffic condition or estimated traffic condition corresponding to the ride time, and the state information of the autonomous vehicle corresponding to the ride time, wherein the travel route information carries a ride route, transfer sites, and transfer vehicles corresponding to respective transfer sites; and dispatching the autonomous vehicles based on the travel route information and the current position information of the passenger. The method and device dispatch the autonomous vehicleswith different driving abilities to carry the passenger in different sections so as to realize the long-distance travel demand of the passenger.

Description

technical field [0001] The present application relates to the technical field of automatic driving technology, and in particular, to a method and device for automatic driving vehicle scheduling. Background technique [0002] Self-driving vehicles, also known as unmanned vehicles, computer-driven vehicles, or wheeled mobile robots, are intelligent vehicles that realize unmanned driving through computer systems. Self-driving vehicles rely on artificial intelligence, visual computing, radar, surveillance devices and global positioning systems to work together to allow computers to operate motor vehicles automatically and safely without human intervention. [0003] However, due to the different hardware and software used in the manufacturing process of self-driving vehicles, there will be differences in the self-driving capabilities of different vehicles, such as the installation position of sensors, the sensitivity of sensing, and the automatic driving model used. , vehicle co...

AI Technical Summary

Problems solved by technology

[0003] However, due to the different hardware and software used in the manufacturing process of self-driving vehicles, there will be differences in the self-driving capabilities of different vehicles, such as the installation position of sensors, the sensitivity of sensing, and the automatic driving model used. , vehicle control methods, etc. are all different; these differences will cause some self-driving vehicles to drive only in a certain local traffic scene, or only in a specific scene; another example: a certain self-driving vehicle uses Take a certain street as the training data to train the automatic driving model. The vehicle can only drive on this street when applying the automatic driving model to achieve automatic driving; if it is driving on other streets, it may be because the vehicle cannot correctly identify other streets. Buildings, landmarks, driving rules, etc. on the road cause traffic accidents

This also leads to the fact that self-driving vehicles can only drive in traffic scenarios that match their self-driving capabilities.

However, the current urban traffic environment is complex, and everyone’s travel distance is also different. When the travel distance exceeds the traffic scene that matches the driving ability of the self-driving vehicle, the self-driving vehicle cannot complete the travel task.

[0004] Under such differentiated and heterogeneous conditions, the current self-driving vehicles cannot meet the long-distance travel needs of users

Images