Method and apparatus for planning a path for a mobile object
A method for planning a path for a mobile object is disclosed. The method includes: generating a plurality of costmap layers based at least on locations of the obstacles in a navigation area, current locations and/or current planned paths of other mobile objects in the navigation area, and historical locations of other mobile objects in the navigation area; generating a master costmap based on the plurality of costmap layers; and planning a path to a target location based on the master costmap. An apparatus for planning a path for a mobile object is also disclosed. A controller for a mobile object, a mobile object and a computer-readable storage medium are also disclosed.
1 . A method for planning a path for a mobile object and operating the mobile object, comprising:
generating a plurality of costmap layers based at least on (i) locations of obstacles in a navigation area, (ii) current planned paths of other mobile objects in the navigation area, and (iii) historical locations of the other mobile objects in the navigation area;
generating a master costmap based on the plurality of costmap layers;
planning a path to a target location based on the master costmap; and
operating the mobile object, based on the planned path, to navigate to the target location and to avoid the obstacles in the navigation area and the other mobile objects in the navigation area,
wherein a first costmap layer of the plurality of costmap layers is generated based on a static map of the navigation area,
wherein a second costmap layer of the plurality of costmap layers is generated based on current locations of obstacles detected by the mobile object during the navigation,
wherein a third costmap layer of the plurality of costmap layers is generated based on current locations of the other mobile objects in the navigation area and the current planned paths of the other mobile objects,
wherein a fourth costmap layer of the plurality of costmap layers is generated based on the historical locations of the other mobile objects over a predefined time period,
wherein the costmap layers of the plurality of costmap layers are assigned different weight values when generating the master costmap,
wherein (i) the third costmap layer is assigned a higher weight value than the fourth costmap layer when the other mobile objects are able to share their current planned paths, and (ii) the fourth costmap layer is assigned a higher weight value than the third costmap layer when the other mobile objects cannot share their current planned paths,
wherein a density map is generated based on the historical locations of the other mobile objects over the predefined time period,
wherein the fourth costmap layer is generated based on the density map, and
wherein the density map is a density distribution representing historical movement patterns of the other mobile objects over the predefined time period.
2 . The method of claim 1 , wherein:
the current locations of the obstacles are detected by one or more on-board sensors of the mobile object during navigation, and
the one or more on-board sensors are selected from the following group: ultrasonic sensor; radar; LiDAR; and camera.
3 . The method of claim 1 , wherein the current locations of the other mobile objects and the current planned paths of the other mobile objects are obtained based on an ultra-wideband (“UWB”) system.
4 . A controller for a mobile object, comprising:
a processor; and
a non-transitory memory having stored thereon a computer program which, when executed by the processor, carries out the steps of the method of claim 1 .
5 . A non-transitory computer-readable storage medium having stored thereon a computer program, wherein:
the computer program, when executed by a processor, carries out the steps of the method of claim 1 .
6 . The method of claim 1 , wherein a density value of a grid cell of the density map is calculated and continuously updated by normalizing a number of the historical locations of the other mobile objects over the predefined time period assigned to the grid cell by a number of times that the grid cell has been sampled.
7 . An apparatus for planning a path for a mobile object and operating the mobile object, comprising:
a controller configured to implement:
a costmap layer generation module configured to generate a plurality of costmap layers based at least on (i) locations of obstacles in a navigation area, (ii) current planned paths of other mobile objects in the navigation area, and (iii) historical locations of the other mobile objects in the navigation area;
a master costmap generation module configured to generate a master costmap based on the plurality of costmap layers; and
a path planning module configured to plan a path to a target location based on the master costmap,
wherein the controller is configured to operate the mobile object, based on the planned path, to navigate to the target location and to avoid the obstacles in the navigation area and the other mobile objects in the navigation area,
wherein a first costmap layer of the plurality of costmap layers is generated based on a static map of the navigation area,
wherein a second costmap layer of the plurality of costmap layers is generated based on current locations of obstacles detected by the mobile object during the navigation,
wherein a third costmap layer of the plurality of costmap layers is generated based on current locations of the other mobile objects in the navigation area and the current planned paths of the other mobile objects,
wherein a fourth costmap layer of the plurality of costmap layers is generated based on the historical locations of the other mobile objects over a predefined time period,
wherein the costmap layers of the plurality of costmap layers are assigned different weight values when generating the master costmap,
wherein (i) the third costmap layer is assigned a higher weight value than the fourth costmap layer when the other mobile objects are able to share their current planned paths, and (ii) the fourth costmap layer is assigned a higher weight value than the third costmap layer when the other mobile objects cannot share their current planned paths,
wherein a density map is generated based on the historical locations of the other mobile objects over the predefined time period,
wherein the fourth costmap layer is generated based on the density map, and
wherein the density map is a density distribution representing historical movement patterns of the other mobile objects over the predefined time period.
8 . The apparatus of claim 7 , wherein:
the current locations of the obstacles are detected by one or more on-board sensors of the mobile object during navigation, and
the one or more on-board sensors are selected from the following group: ultrasonic sensor; radar; LiDAR; and camera.
9 . The apparatus of claim 7 , wherein the current locations of the other mobile objects and the current planned paths of the other mobile objects are obtained based on an ultra-wideband (“UWB”) system.
10 . A mobile object, comprising:
the apparatus for planning a path for a mobile object of claim 7 or the controller of claim 4 ; and
one or more on-board sensors.
11 . The mobile object of claim 10 , wherein the mobile object further comprises at least one ultra-wideband (“UWB”) tag.
12 . The apparatus of claim 7 , wherein a density value of a grid cell of the density map is calculated and continuously updated by normalizing a number of the historical locations of the other mobile objects over the predefined time period assigned to the grid cell by a number of times that the grid cell has been sampled.