Autonomous surveying of underfloor voids
The present disclosure provides a method of processing depth data and image data from a robotic device having a camera and a depth measurement device mounted to a chassis of the robotic device to generate a data set representative of a three-dimensional map of an environment in which the robotic device is located. The camera is arranged to generate image data relating to the environment. The depth measurement device is arranged to generate depth data relating to the environment. The method comprises generating image data and depth data at a first location of the robotic device in the environment, whereby to generate a first data set comprising a plurality of data points. The method further comprises moving the robotic device to at least a second location in the environment. The method further comprises generating image data and depth data at the second location, whereby to generate a second data set comprising a plurality of data points. The method further comprises associating each data point of the first data set with the spatially nearest point of the second data set, if any, within a predefined distance from the first data point. The method further comprises replacing data points from the first data set with the associated data points from the second data set by reference to the distance of the data point from the location of the robotic device when the data point was generated.
1. A method of processing depth data and image data from a robotic device having a camera and a depth measurement device mounted to a chassis of the robotic device to generate a data set representative of a three-dimensional map of an environment in which the robotic device is located, wherein the camera is adapted to generate image data relating to the environment, and the depth measurement device is adapted to generate depth data relating to the environment, the method comprising:
generating first image data and first depth data at a first location of the robotic device in the environment to generate a first data set of first data set data points,
moving the robotic device to at least a second location in the environment,
generating second image data and second depth data at the second location to generate a second data set of second data set data points,
associating each of the first data set data points with the second data set points that are within a predefined distance from the respective first data set data points, and
replacing each of the first data set data points with the associated second set data points based on a distance of the first and second data set data points from the robotic device when the respective data points were generated.
2. A method as claimed in claim 1 further comprising:
adding to the first data set data points each of the second data set data points that are not associated with any of the first set data set points.
3. A method as claimed in claim 1 , wherein the first set data points are replaced with the associated data points from the second data set data points when the second data set data points are closer to the robotic device than the first set data points when the respective data points were generated.
4. A method as claimed in claim 1 , wherein the robotic device is adapted to move autonomously from the first location to the second location.
5. A method as claimed in claim 4 , wherein the second location is calculated by selecting a candidate second location from a number of candidate locations based on an expected increase in information relating to the environment achievable at each candidate location.
6. A method as claimed in claim 5 , wherein the second location is calculated based on the expected increase in information in combination with a distance to each candidate location.
7. A method as claimed in claim 4 , wherein the second location is calculated by selecting a candidate second location from a number of candidate locations based on a distance of each candidate location from the first location.
8. A method as claimed in claim 1 , wherein the depth measurement device is adapted to generate depth data relating to a forward direction and to a rearward direction of the robotic device.
9. A method as claimed in claim 8 , wherein the depth measurement device is adapted to rotate about an axis substantially perpendicular to the forward direction and the rearward direction.
10. A method as claimed in claim 1 , wherein the depth measurement device is a laser rangefinder.
11. A robotic device having a camera and a laser rangefinder mounted to a chassis of the robotic device and a data processing apparatus configured to control the robotic device to carry out the method of claim 1 .
12. A method of processing depth data and image data from a robotic device having a camera and a depth measurement device mounted to a chassis of the robotic device to generate a data set representative of a three-dimensional map of an environment in which the robotic device is located, wherein the camera is adapted to generate image data relating to the environment, and the depth measurement device is adapted to generate depth data relating to the environment, the method comprising:
receiving a first data set of first data set data points having image data and depth data from a first location of the robotic device in the environment,
receiving a second data set of second data set data points having image data and depth data at a second location of the robotic device in the environment,
associating each of the first data set data points with the second data set data points that are within a predefined distance from the first data point, and
replacing each of the first data set data points with the associated data points from the second data set data points based on a distance of the first and second data set data points from robotic device when the respective data points were generated.
13. A method as claimed in claim 12 further comprising:
adding to the first data set data points each of the second data set data points that are not associated with any of the first data set data points.
14. A method as claimed in claim 12 , wherein the first data set data points are replaced with the associated data points from the second data set data points when the second data set data points are closer to the robotic device than the first set data points when the respective data points were generated.
15. A non-transitory computer-readable storage medium comprising computer-readable instructions, which, when executed by a general purpose data processing apparatus, causes the general purpose data processing apparatus to carry out the method of claim 12 .