Systems and methods for vehicle motion control with interactive object annotation
Systems and methods for vehicle motion control with interactive object annotation are provided. A method can include obtaining data indicative of a plurality of objects within a surrounding environment of the autonomous vehicle. For example, the plurality of objects can include at least at one problem object encountered by the autonomous vehicle while navigating a planned route. The method can include determining a group of objects of the plurality of objects. For example, the group of objects can include the problem object and one or more other objects in proximity to the problem object. The method can include determining a classification update to be applied to the group of objects. The method can include applying the classification update to the group of objects. The method can include providing data indicative of the classification update for the group of objects to the autonomous vehicle for use in motion planning.
1. A computer-implemented method, the method comprising:
obtaining, from an autonomous vehicle and by a computing system comprising one or more computing devices that are remote from the autonomous vehicle, data describing a plurality of objects within a surrounding environment of the autonomous vehicle, the data indicating that at least one of plurality of objects is a problem object encountered by the autonomous vehicle while navigating a planned route;
determining, by the computing system, a group of objects of the plurality of objects, the group of objects including the problem object and one or more other objects in proximity to the problem object;
determining, by the computing system, a common classification update to be applied to the group of objects;
applying, by the computing system, the common classification update to the group of objects; and
providing, by the computing system, data indicative of the common classification update for the group of objects to the autonomous vehicle for use in motion planning.
2. The computer-implemented method of claim 1 , wherein the problem object has been detected by the autonomous vehicle with incorrect object classification data.
3. The computer-implemented method of claim 1 , wherein the common classification update to be applied to the group of objects comprises:
an indication that the group of objects are static and the autonomous vehicle should pass on the left of the group of objects;
an indication that the group of objects are static and the autonomous vehicle should pass on the right of the group of objects; or
an indication that the group of objects are not static objects.
4. The computer-implemented method of claim 1 , wherein the common classification update facilitates the autonomous vehicle generating motion planning to navigate past the group of objects and continue along the planned route.
5. The computer-implemented method of claim 1 , wherein the group of objects comprises one or more of:
construction objects in a construction zone of a roadway;
foreign object debris in the roadway;
parked emergency vehicles in the roadway; or
an unknown class object in close proximity to the autonomous vehicle.
6. The computer-implemented method of claim 1 , wherein an original classification of each object included in the group of objects is stored along with the common classification update for each object included in the group of objects.
7. The computer-implemented method of claim 1 , further comprising:
providing, by the computing system, data indicative of the plurality of objects for display, wherein the data indicative of the plurality of objects comprises data indicative of the problem object along with the one or more other objects in proximity to the problem object within the plurality of objects.
8. The computer-implemented method of claim 7 ,
wherein determining, by the computing system, the group of objects of the plurality of objects comprises receiving a first user input selection of the problem object and one or more of the other objects in proximity to the problem object from the plurality of objects displayed; and
wherein determining, by the computing system, the common classification update to be applied to the group of objects comprises receiving a second user input comprising an indication of the common classification update to be applied to the group of objects.
9. The computer-implemented method of claim 8 , wherein the one or more other objects in proximity to the problem object are selected based at least in part on one or more predefined rules.
10. The computer-implemented method of claim 8 further comprising:
in response to receiving an indication of the common classification update to be applied to the group of objects, providing, by the computing system, a request for confirmation of the common classification update to be applied to the group of objects; and
receiving, by the computing system, data indicating confirmation of the common classification update to be applied to the group of objects before applying the common classification update to the group of objects.
11. The computer-implemented method of claim 1 , further comprising:
providing, by the computing system, the plurality of objects to a model that is configured to determine the group of objects comprising the problem object from the plurality of objects and determine the common classification update for the group of objects.
12. A computing system, comprising:
one or more processors; and
one or more memories including instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, the operations comprising:
obtaining, from an autonomous vehicle, data describing a plurality of objects within a surrounding environment of the autonomous vehicle, the data indicating that at least one of the plurality of objects is a problem object encountered by the autonomous vehicle while navigating a planned route;
determining a group of objects of the plurality of objects, the group of objects including the problem object and one or more other objects in proximity to the problem object;
determining a common classification update to be applied to the group of objects;
applying the common classification update to the group of objects; and
providing data indicative of the common classification update for the group of objects to the autonomous vehicle for use in motion planning.
13. The computing system of claim 12 , wherein the problem object has been detected by the autonomous vehicle with incorrect object classification data.
14. The computing system of claim 12 , wherein the common classification update to be applied to the group of objects comprises:
an indication that the group of objects are static and the autonomous vehicle should pass on the left of the group of objects;
an indication that the group of objects are static and the autonomous vehicle should pass on the right of the group of objects; or
an indication that the group of objects are not static objects.
15. The computing system of claim 12 , wherein the group of objects comprises one or more of:
construction objects in a construction zone of a roadway;
foreign object debris in the roadway;
parked emergency vehicles in the roadway; or
an unknown class object in close proximity to the autonomous vehicle.
16. The computing system of claim 12 , wherein an original classification of each object included in the group of objects is stored along with the common classification update for each object included in the group of objects.
17. The computing system of claim 12 ,
wherein determining the group of objects of the plurality of objects, the group of objects including the problem object and one or more other objects in proximity to the problem object comprises receiving a selection of the problem object and one or more of the other objects in proximity to the problem object from a display of the plurality of objects; and
wherein determining the common classification update to be applied to the group of objects comprises receiving an indication of the common classification update to be applied to the group of objects.
18. The computing system of claim 12 , wherein the operations further comprise:
providing the plurality of objects to a model that is configured to determine the group of objects inclusive of the problem object from the plurality of objects and to determine the common classification update for the group of objects.
19. One or more tangible, non-transitory computer-readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations comprising:
obtaining, from an autonomous vehicle, data describing a plurality of objects within a surrounding environment of the autonomous vehicle, the data indicating that at least one of the plurality of objects is a problem object encountered by the autonomous vehicle while navigating a planned route;
determining a group of objects of the plurality of objects, the group of objects including the problem object and one or more other objects in proximity to the problem object;
determining a common classification update to be applied to the group of objects;
applying the common classification update to the group of objects; and
providing data indicative of the common classification update for the group of objects to the autonomous vehicle for use in motion planning.
20. The one or more tangible, non-transitory computer-readable media of claim 19 , wherein the common classification update to be applied to the group of objects comprises:
an indication that the group of objects are static and the autonomous vehicle should pass on the left of the group of objects;
an indication that the group of objects are static and the autonomous vehicle should pass on the right of the group of objects; or
an indication that the group of objects are not static objects.