Vehicle navigation method, vehicle and storage medium

A vehicle, comprising:

• at least one processor;
• and
• a memory communicatively coupled to the at least one processor, wherein
• the memory stores instructions executable by the at least one processor, when the instructions are executed by the at least one processor, the at least one processor is caused to implement a vehicle navigation method comprising:
• in response to a vehicle being in a driving state, obtaining environment information corresponding to the vehicle;
• obtaining lane information corresponding to the vehicle from a lane information set based on the environment information, wherein the lane information comprises first lane information of covered areas of a high-precision map and second lane information of uncovered areas of the high-precision map;
• displaying a vehicle sign corresponding to the vehicle on a map based on the lane information, to provide navigation information for the vehicle;
• and
• control the vehicle to travel based on said navigation information when the vehicle travels through the uncovered areas of the high-precision map,
• wherein the lane information set comprises a first lane set and a second lane set, and before obtaining the environment information corresponding to the vehicle in the driving state, the vehicle navigation method further comprises:
• obtaining the first lane information corresponding to each first lane in the first lane set based on the high-precision map in the covered areas of the high-precision map;
• obtaining the second lane information corresponding to each second lane in the second lane set based on a traditional map and a neural network model in the uncovered areas of the high-precision map;
• and
• rendering the first lane information and the second lane information onto the map, wherein obtaining the second lane information corresponding to each second lane in the second lane set based on the traditional map and the neural network model in the uncovered areas of the high-precision map, comprises:
• obtaining a lane number and a lane shape information corresponding to any uncovered area of the high-precision map based on the traditional map in the uncovered areas of the high-precision map;
• obtaining a second lane subset corresponding to said any uncovered area of the high-precision map;
• obtaining a first lane width information corresponding to at least one second lane in the second lane subset using the neural network model;
• obtaining a second lane information corresponding to each second lane in the second lane subset based on the lane number, the lane shape information, and the first lane width information corresponding to the at least one second lane;
• and
• traversing the uncovered areas of the high-precision map, and obtaining the second lane information corresponding to each second lane in the second lane set,
• wherein the second lane information is determined based on the lane number and the lane shape information obtained from the traditional map in the uncovered areas of the high-precision map, and the first lane width information obtained by the neural network model,
• wherein obtaining the first lane width information corresponding to the at least one second lane in the second lane subset using the neural network model, comprises:
• obtaining high-precision map information corresponding to said any uncovered area of the high-precision map, wherein the high-precision map information corresponding to said any uncovered area of the high-precision map comprises:
• both a roadway grade and a second lane width information for a nearest covered area of the high-precision map, and
• a spacing distance from said any uncovered area of the high-precision map to the nearest covered area of the high-precision map;
• collecting a road image of said any uncovered area of the high-precision map;
• and
• obtaining the first lane width information corresponding to the at least one second lane in the second lane subset corresponding to said any uncovered area of the high-precision map using the neural network model based on the high-precision map information corresponding to said any uncovered area of the high-precision map and the road image of said any uncovered area of the high-precision map.