POSITIONING METHOD, DEVICE, MEDIUM AND EQUIPMENT
The present disclosure relates to a method, apparatus, medium, and device for positioning. When a predetermined switching condition is satisfied, a positioning result obtained by using a different positioning algorithm based on positioning data collected by a further selected sensor to position a movable object can be used as the positioning result of the movable object. When a autonomous driving vehicle leaves an area with high satellite signal quality and enters an area with low satellite signal quality, a positioning result of the vehicle obtained based on positioning data collected by a further selected sensor, which is different from a GPS receiver, can be used as the positioning result of the vehicle. In this way, when positioning the vehicle, the GPS positioning data with low positioning accuracy can be directly discarded, thereby effectively improving the accuracy of vehicle positioning.
1 - 12 . (canceled)
13 . A positioning method, comprising:
positioning a movable object by using a first positioning algorithm based on positioning data collected by at least one first sensor to obtain a first positioning result;
positioning the movable object by using a second positioning algorithm based on positioning data collected by at least one second sensor to obtain a second positioning result;
selecting one of the first positioning result and the second positioning result as a target positioning result; and
selecting another one of the first positioning result and the second positioning result as the target positioning result in response to a current condition of the movable object satisfying a predetermined switching condition.
14 . The method of claim 13 , wherein the at least one first sensor comprises at least one of a satellite positioning system receiver and an inertial navigation sensor, the at least one second sensor has at least one different sensor from the at least one first sensor, and the at least one second sensor comprises at least one of a vision sensor, a laser sensor, and an inertial navigation sensor.
15 . The method of claim 14 , wherein said positioning the movable object by using the first positioning algorithm based on the positioning data collected by the at least one first sensor to obtain the first positioning result comprises:
positioning the movable object based on a satellite signal collected by the satellite positioning system receiver to obtain a satellite positioning result;
positioning the movable object based on acceleration data collected by the inertial navigation sensor to obtain an inertial navigation positioning result; and
performing weighted filtering and fusion on the satellite positioning result and the inertial navigation positioning result to generate the first positioning result.
16 . The method of claim 14 , wherein said positioning the movable object by using the second positioning algorithm based on the positioning data collected by the at least one second sensor to obtain the second positioning result comprises:
positioning the movable object based on image data collected by the vision sensor to obtain a vision positioning result;
positioning the movable object based on point cloud data collected by the laser sensor to obtain a laser positioning result;
positioning the movable object based on acceleration data collected by the inertial navigation sensor to obtain an inertial navigation positioning result; and
performing weighted filtering and fusion on the inertial navigation positioning result, the vision positioning result, and the laser positioning result to generate the second positioning result.
17 . The method of claim 14 , wherein the predetermined switching condition comprises a first switching condition, and the first switching condition is a combination of one or more of:
satellite signal quality obtained by the movable object being lower than a specified value, and
the movable object arriving at a specified position on a pre-loaded map.
18 . The method of claim 17 , wherein said selecting the one of the first positioning result and the second positioning result as the target positioning result comprises:
determining, while the first positioning result is selected as the target positioning result, whether the current condition of the movable object satisfies the first switching condition, and
said selecting another one of the first positioning result and the second positioning result as the target positioning result in response to the current condition of the movable object satisfying the predetermined switching condition comprises:
selecting the second positioning result as the target positioning result in response to the current condition of the movable object satisfying the first switching condition.
19 . The method of claim 18 , wherein said selecting the second positioning result as the target positioning result in response to the current condition of the movable object satisfying the first switching condition comprises:
determining, in response to the current condition of the movable object satisfying the first switching condition, whether a first positioning error corresponding to the second positioning result converges or not; and
selecting the second positioning result as the target positioning result in response to the first positioning error converging.
20 . The method of claim 19 , wherein said determining, in response to the current condition of the movable object satisfying the first switching condition, whether the first positioning error converges or not comprises:
determining, in response to the current condition of the movable object satisfying the first switching condition, whether the first positioning error converges or not at a current time point; or
determining, in response to the current condition of the movable object satisfying the first switching condition, whether the first positioning error converges or not within a defined time length.
21 . The method of claim 14 , wherein the predetermined switching condition comprises a second switching condition, and the second switching condition is a combination of one or more of:
satellite signal quality obtained by the movable object being higher than a defined value, and
the movable object arriving at a defined position on a pre-loaded map.
22 . The method of claim 21 , wherein said selecting the one of the first positioning result and the second positioning result as the target positioning result comprises:
determining, while the second positioning result is selected as the target positioning result, whether the current condition of the movable object satisfies the second switching condition, and
said selecting another one of the first positioning result and the second positioning result as the target positioning result in response to the current condition of the movable object satisfying the predetermined switching condition comprises:
selecting the first positioning result as the target positioning result in response to the current condition of the movable object satisfying the second switching condition.
23 . The method of claim 22 , wherein said selecting the first positioning result as the target positioning result in response to the current condition of the movable object satisfying the second switching condition comprises:
determining, in response to the current condition of the movable object satisfying the second switching condition, whether a second positioning error corresponding to the first positioning result converges or not; and
selecting the first positioning result as the target positioning result in response to the second positioning error converging.
24 . The method of claim 23 , wherein said determining, in response to the current condition of the movable object satisfying the second switching condition, whether the second positioning error converges or not comprises:
determining, in response to the current condition of the movable object satisfying the second switching condition, whether the second positioning error converges or not at a current time point; or
determining, in response to the current condition of the movable object satisfying the second switching condition, whether the second positioning error converges or not within a defined time length.
25 . A non-transitory computer readable storage medium comprising instructions which, when executed by a processor of a computing device, cause the computing device to carry out a method comprising:
positioning a movable object by using a first positioning algorithm based on positioning data collected by at least one first sensor to obtain a first positioning result;
positioning the movable object by using a second positioning algorithm based on positioning data collected by at least one second sensor to obtain a second positioning result; and
selecting one of the first positioning result and the second positioning result as a target positioning result; and
selecting another one of the first positioning result and the second positioning result as the target positioning result in response to a current condition of the movable object satisfying a predetermined switching condition.
26 . The storage medium of claim 25 , wherein the at least one first sensor comprises at least one of a satellite positioning system receiver and an inertial navigation sensor, the at least one second sensor has at least one different sensor from the at least one first sensor, and the at least one second sensor comprises at least one of a vision sensor, a laser sensor, and an inertial navigation sensor.
27 . The storage medium of claim 26 , wherein said positioning the movable object by using the first positioning algorithm based on the positioning data collected by the at least one first sensor to obtain the first positioning result comprises:
positioning the movable object based on a satellite signal collected by the satellite positioning system receiver to obtain a satellite positioning result;
positioning the movable object based on acceleration data collected by the inertial navigation sensor to obtain an inertial navigation positioning result; and
performing weighted filtering and fusion on the satellite positioning result and the inertial navigation positioning result to generate the first positioning result.
28 . The storage medium of claim 26 , wherein said positioning the movable object by using the second positioning algorithm based on the positioning data collected by the at least one second sensor to obtain the second positioning result comprises:
positioning the movable object based on image data collected by the vision sensor to obtain a vision positioning result;
positioning the movable object based on point cloud data collected by the laser sensor to obtain a laser positioning result;
positioning the movable object based on acceleration data collected by the inertial navigation sensor to obtain an inertial navigation positioning result; and
performing weighted filtering and fusion on the inertial navigation positioning result, the vision positioning result, and the laser positioning result to generate the second positioning result.
29 . The storage medium of claim 26 , wherein the predetermined switching condition comprises a first switching condition, and the first switching condition is a combination of one or more of:
satellite signal quality obtained by the movable object being lower than a specified value, and
the movable object arriving at a specified position on a pre-loaded map.
30 . The storage medium of claim 29 , wherein said selecting the one of the first positioning result and the second positioning result as the target positioning result comprises:
determining, while the first positioning result is selected as the target positioning result, whether the current condition of the movable object satisfies the first switching condition, and
said selecting another one of the first positioning result and the second positioning result as the target positioning result in response to the current condition of the movable object satisfying the predetermined switching condition comprises:
selecting the second positioning result as the target positioning result in response to the current condition of the movable object satisfying the first switching condition.
31 . The storage medium of claim 30 , wherein said selecting the second positioning result as the target positioning result in response to the current condition of the movable object satisfying the first switching condition comprises:
determining, in response to the current condition of the movable object satisfying the first switching condition, whether a first positioning error corresponding to the second positioning result converges or not; and
selecting the second positioning result as the target positioning result in response to the first positioning error converging.
32 . A positioning device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor is configured to, when executing the program, perform a method composing:
positioning a movable object by using a first positioning algorithm based on positioning data collected by at least one first sensor to obtain a first positioning result;
positioning the movable object by using a second positioning algorithm based on positioning data collected by at least one second sensor to obtain a second positioning result; and
selecting one of the first positioning result and the second positioning result as a target positioning result; and
selecting another one of the first positioning result and the second positioning result as the target positioning result in response to a current condition of the movable object satisfying a predetermined switching condition.