Robot positioning method and apparatus, intelligent robot, and storage medium
Provided are a robot positioning method and apparatus, an intelligent robot, and a storage medium. The method includes: configuring a camera and various sensors on a robot so that the robot may acquire an image collected by the camera and various sensing data collected by the various sensors (step 101 ); next extracting semantic information contained in the collected image (step 102 ) and identifying, according to the semantic information, a scenario where the robot is currently identified (step 103 ); finally, determining a current position of the robot according to target sensing data corresponding to the scenario where the robot is located (step 104 ). In the method, the sensing data used during determining the pose of the robot is not all the sensing data, but is the target sensing data corresponding to the scenario. Therefore, the basis for determining the pose is more targeted, thus further improving the accuracy of the pose.
1. A robot positioning method, comprising:
acquiring an image collected by a camera on a robot and various sensing data collected by various sensors on the robot, wherein the various sensors comprise: a movement speed meter, a movement angle meter, and a laser sensor;
processing the image to obtain an environmental brightness value corresponding to the image according to a grayscale value of each pixel point in the image;
extracting semantic information contained in the image by using a pre-trained semantic recognition model provided in the robot, wherein the semantic information comprises an object contained in the image;
recognizing, according to the semantic information, a scenario where the robot is located; and
determining a pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image;
wherein, in response to the environmental brightness value corresponding to the scenario being not within a preset value range, the determining the pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image comprises:
determining a first pose according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter,
mapping the first pose to a pre-established raster map to obtain a second pose, the raster map being established according to historical sensing data collected by the laser sensor, and
determining the second pose as the pose of the robot; and
wherein, in response to the environmental brightness value corresponding to the scenario being within the preset value range, the determining a pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image comprises:
mapping the first pose to a pre-established visual feature map to obtain a third pose, the visual feature map being established according to historical images collected by the camera, and the first pose being determined according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter; and
fusing the second pose with the third pose to determine a fusion result as a pose of the robot, the second pose being determined according to the first pose and the raster map.
2. The method according to claim 1 , further comprising:
determining a navigation path according to the pose of the robot and a target position input by a user, so that the robot moves to the target position according to the navigation path.
3. The method according to claim 1 , wherein the scenario corresponds to a building of a preset structure contained in the image;
the determining a pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image comprises:
determining a first pose according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter;
mapping the first pose to a pre-established visual feature map to obtain a fourth pose, the visual feature map being established according to historical images collected by the camera; and
determining the fourth pose as a pose of the robot.
4. The method according to claim 1 , wherein the scenario corresponds to a crowd contained in the image;
the determining a pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image comprises:
determining a pose of the robot according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter.
5. The method according to claim 1 , wherein the scenario where the robot is located is a scenario where the raster map may not be used;
the determining a pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image comprises:
determining a first pose according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter;
determining a fifth pose according to the images collected by the camera; and
fusing the first pose with the fifth pose to determine a fusion result as a pose of the robot.
6. A robot positioning apparatus, comprising:
an acquisition module configured to acquire an image collected by a camera on a robot and various sensing data collected by various sensors on the robot, wherein the various sensors comprise: a movement speed meter, a movement angle meter, and a laser sensor;
an extraction module configured to process the image to obtain an environmental brightness value corresponding to the image according to a grayscale value of each pixel point in the image, and extract semantic information contained in the image by using a pre-trained semantic recognition model provided in the robot, wherein the semantic information comprises-an object contained in the image;
a recognition module configured to recognize, according to the semantic information, a scenario where the robot is located; and
a pose determination module configured to determine a pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image;
wherein, in response to the environmental brightness value corresponding to the scenario being not within a preset value range, the pose determination module is further configured to:
determine a first pose according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter;
map the first pose to a pre-established raster map to obtain a second pose, the raster map being established according to historical sensing data collected by the laser sensor; and
determine the second pose as a pose of the robot; and
wherein, in response to the environmental brightness value corresponding to the scenario being within the preset value range, the pose determination module is further configured to:
map the first pose to a pre-established visual feature map to obtain a third pose, the visual feature map being established according to historical images collected by the camera, and the first pose being determined according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter; and
fuse the second pose with the third pose to determine a fusion result as a pose of the robot, the second pose being determined according to the first pose and the raster map.
7. An intelligent robot, comprising a processor and a memory, wherein the memory is configured to store one or more computer instructions which, when executed by the processor, implements:
acquire an image collected by a camera on a robot and various sensing data collected by various sensors on the robot, wherein the various sensors comprise: a movement speed meter, a movement angle meter, and a laser sensor;
process the image to obtain an environmental brightness value corresponding to the image according to a grayscale value of each pixel point in the image;
extract semantic information contained in the image by using a pre-trained semantic recognition model provided in the robot, wherein the semantic information comprises an object contained in the image;
recognize, according to the semantic information, a scenario where the robot is located; and
determine a pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image;
wherein, in response to the environmental brightness value corresponding to the scenario being not within a preset value range the determine the pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image comprises:
determining a first pose according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter;
mapping the first pose to a pre-established raster map to obtain a second pose, the raster map being established according to historical sensing data collected by the laser sensor; and
determining the second pose as a pose of the robot; and
wherein, in response to the environmental brightness value corresponding to the scenario is within a preset value range;
the determine the pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image comprises:
mapping the first pose to a pre-established visual feature map to obtain a third pose, the visual feature map being established according to historical images collected by the camera, and the first pose being determined according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter; and
fusing the second pose with the third pose to determine a fusion result as the pose of the robot, the second pose being determined according to the first pose and the raster map.
8. A non-statutory computer-readable storage medium for storing a computer instruction which, when executed by one or more processors, causes the one or more processors to at least execute the following actions:
acquiring an image collected by a camera on a robot and various sensing data collected by various sensors on the robot, wherein the various sensors comprise: a movement speed meter, a movement angle meter, and a laser sensor;
processing the image to obtain an environmental brightness value corresponding to the image according to a grayscale value of each pixel point in the image;
extracting semantic information contained in the image by using a pre-trained semantic recognition model provided in the robot, wherein the semantic information comprises an object contained in the image;
recognizing, according to the semantic information, a scenario where the robot is located; and
determining a pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image;
wherein, in response to the environmental brightness value corresponding to the scenario being not within a preset value range, the determining the pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image comprises:
determining a first pose according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter;
mapping the first pose to a pre-established raster map to obtain a second pose, the raster map being established according to historical sensing data collected by the laser sensor; and
determining the second pose as the pose of the robot; and
wherein, in response to the environmental brightness value corresponding to the scenario being within a preset value range the determining the pose of the robot according to target sensing data, corresponding to the scenario, in the various sensing data, and the environmental brightness value corresponding to the image comprises:
mapping the first pose to a pre-established visual feature map to obtain a third pose, the visual feature map being established according to historical images collected by the camera, and the first pose being determined according to the sensing data collected by the movement speed meter and the sensing data collected by the movement angle meter; and
fusing the second pose with the third pose to determine a fusion result as the pose of the robot, the second pose being determined according to the first pose and the raster map.