Method and apparatus for positioning vehicle, electronic device and storage medium

1. A method for positioning a current vehicle, the method comprising:

acquiring an identification element and non-identification elements of the current vehicle, both the identification element and non-identification elements representing environmental information of the current vehicle;

matching the identification element of the current vehicle with position elements in a high-definition map to determine an initial position of the current vehicle;

using at least one position element in the high-definition map to perform observational constraints on the non-identification elements of the current vehicle to acquire position elements corresponding to the non-identification elements of the current vehicle;

adjusting the initial position of the current vehicle using the position elements corresponding to the non-identification elements of the current vehicle to obtain a target position of the current vehicle; and

moving the current vehicle based at least in part on the target position of the current vehicle;

wherein the using at least one position element in the map to perform observational constraints on the non-identification elements of the current vehicle to acquire position elements corresponding to the non-identification elements of the current vehicle, includes:

selecting a non-identification element in the non-identification elements of the current vehicle as a current non-identification element, and determining at least one position element corresponding to the current non-identification element in the map based on the current non-identification element; and

either performing point and point observational constraints on the current non-identification element and the corresponding position element, in response to that the current non-identification element is a point element and the corresponding position element is a point original element, to acquire the position element corresponding to the current non-identification element; or

performing point and line observational constraints on the current non-identification element and the corresponding position element, in response to that the current non-identification element is a line element and the corresponding position element is a point original element, or, the current non-identification element is a point element and the corresponding position element is a point and line element, to acquire the position element corresponding to the current non-identification element; and

repeatedly performing above operations until the position elements corresponding to the non-identification elements of the current vehicle are acquired.

2. The method according to claim 1 , wherein the acquiring the identification element and non-identification elements of the current vehicle, comprises:

collecting environment images of the current vehicle in four directions using four fisheye sensors provided on the current vehicle; wherein, the four fisheye sensors on the current vehicle are respectively provided in the four directions of front, rear, left, and right of the current vehicle;

stitching the environment images of the current vehicle in the four directions collected using the fisheye sensors into a surround-view fisheye image; and

inputting the surround-view fisheye image into a deep neural network, and outputting the identification element and the non-identification elements of the current vehicle through the deep neural network.

3. The method according to claim 1 , wherein the matching the identification element of the current vehicle with position elements in the high-definition map to determine the initial position of the current vehicle, comprises:

determining at least one reference initial position in the high-definition map based on the identification element of the current vehicle; and

calculating a matching degree between the identification element of the current vehicle and each of the at least one reference initial position, and determining a reference initial position having a highest matching degree as the initial position of the current vehicle.

4. The method according to claim 1 , further comprising:

collecting inertial measurement data and wheel speed data of the current vehicle using an inertial measurement unit sensor and a wheel speed sensor provided on the current vehicle; and

adjusting the target position of the current vehicle using the inertial measurement data and the wheel speed data of the current vehicle, to obtain a final position of the current vehicle.

5. An electronic device, comprising:

at least one processor; and

a memory, communicatively connected to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor, the instructions, when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:

acquiring an identification element and non-identification elements of a current vehicle, both the identification element and non-identification elements representing environmental information of the current vehicle;

matching the identification element of the current vehicle with position elements in a high-definition map to determine an initial position of the current vehicle;

using at least one position element in the high-definition map to perform observational constraints on the non-identification elements of the current vehicle to acquire position elements corresponding to the non-identification elements of the current vehicle;

adjusting the initial position of the current vehicle using the position elements corresponding to the non-identification elements of the current vehicle to obtain a target position of the current vehicle; and

moving the current vehicle based at least in part on the target position of the current vehicle;

wherein the using at least one position element in the map to perform observational constraints on the non-identification elements of the current vehicle to acquire position elements corresponding to the non-identification elements of the current vehicle, includes:

selecting a non-identification element in the non-identification elements of the current vehicle as a current non-identification element, and determining at least one position element corresponding to the current non-identification element in the map based on the current non-identification element; and

performing point and point observational constraints on the current non-identification element and the corresponding position element, in response to that the current non-identification element is a point element and the corresponding position element is a point original element, to acquire the position element corresponding to the current non-identification element; or,

performing point and line observational constraints on the current non-identification element and the corresponding position element, in response to that the current non-identification element is a line element and the corresponding position element is a point original element, or, the current non-identification element is a point element and the corresponding position element is a point and line element, to acquire the position element corresponding to the current non-identification element; and

repeatedly performing above operations until the position elements corresponding to the non-identification elements of the current vehicle are acquired.

6. The electronic device according to claim 5 , wherein the acquiring the identification element and non-identification elements of the current vehicle, comprises:

collecting environment images of the current vehicle in four directions using four fisheye sensors provided on the current vehicle; wherein, the four fisheye sensors on the current vehicle are respectively provided in the four directions of front, rear, left, and right of the current vehicle;

stitching the environment images of the current vehicle in the four directions collected using the fisheye sensors into a surround-view fisheye image; and

inputting the surround-view fisheye image into a deep neural network, and outputting the identification element and the non-identification elements of the current vehicle through the deep neural network.

7. The electronic device according to claim 5 , wherein the matching the identification element of the current vehicle with position elements in the high-definition map to determine the initial position of the current vehicle, comprises:

determining at least one reference initial position in the high-definition map based on the identification element of the current vehicle; and

calculating a matching degree between the identification element of the current vehicle and each of the at least one reference initial position, and determining a reference initial position having a highest matching degree as the initial position of the current vehicle.

8. The electronic device according to claim 5 , wherein the operations further comprise:

collecting inertial measurement data and wheel speed data of the current vehicle using an inertial measurement unit sensor and a wheel speed sensor provided on the current vehicle; and

adjusting the target position of the current vehicle using the inertial measurement data and the wheel speed data of the current vehicle, to obtain a final position of the current vehicle.

9. A non-transitory computer readable storage medium, storing computer instructions, the computer instructions, when executed by a computer, cause the computer to perform operations, the operations comprising:

acquiring an identification element and non-identification elements of a current vehicle, both the identification element and non-identification elements representing environmental information of the current vehicle;

matching the identification element of the current vehicle with position elements in a high-definition map to determine an initial position of the current vehicle;

using at least one position element in the high-definition map to perform observational constraints on the non-identification elements of the current vehicle to acquire position elements corresponding to the non-identification elements of the current vehicle;

adjusting the initial position of the current vehicle using the position elements corresponding to the non-identification elements of the current vehicle to obtain a target position of the current vehicle; and

moving the current vehicle based at least in part on the target position of the current vehicle;

wherein the using at least one position element in the map to perform observational constraints on the non-identification elements of the current vehicle to acquire position elements corresponding to the non-identification elements of the current vehicle, includes:

selecting a non-identification element in the non-identification elements of the current vehicle as a current non-identification element, and determining at least one position element corresponding to the current non-identification element in the map based on the current non-identification element; and

performing point and point observational constraints on the current non-identification element and the corresponding position element, in response to that the current non-identification element is a point element and the corresponding position element is a point original element, to acquire the position element corresponding to the current non-identification element; or,

performing point and line observational constraints on the current non-identification element and the corresponding position element, in response to that the current non-identification element is a line element and the corresponding position element is a point original element, or, the current non-identification element is a point element and the corresponding position element is a point and line element, to acquire the position element corresponding to the current non-identification element and repeatedly performing above operations until the position elements corresponding to the non-identification elements of the current vehicle are acquired.

10. The non-transitory computer readable storage medium according to claim 9 , wherein the acquiring the identification element and non-identification elements of the current vehicle, comprises:

collecting environment images of the current vehicle in four directions using four fisheye sensors provided on the current vehicle; wherein, the four fisheye sensors on the current vehicle are respectively provided in the four directions of front, rear, left, and right of the current vehicle;

stitching the environment images of the current vehicle in the four directions collected using the fisheye sensors into a surround-view fisheye image; and

inputting the surround-view fisheye image into a deep neural network, and outputting the identification element and the non-identification elements of the current vehicle through the deep neural network.

11. The non-transitory computer readable storage medium according to claim 9 , wherein the matching the identification element of the current vehicle with position elements in the high-definition map to determine the initial position of the current vehicle, comprises:

determining at least one reference initial position in the high-definition map based on the identification element of the current vehicle; and

calculating a matching degree between the identification element of the current vehicle and each of the at least one reference initial position, and determining a reference initial position having a highest matching degree as the initial position of the current vehicle.

12. The non-transitory computer readable storage medium according to claim 9 , wherein the operations further comprise:

collecting inertial measurement data and wheel speed data of the current vehicle using an inertial measurement unit sensor and a wheel speed sensor provided on the current vehicle; and

adjusting the target position of the current vehicle using the inertial measurement data and the wheel speed data of the current vehicle, to obtain a final position of the current vehicle.