Lane path modification framework
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that generates lane path descriptors for use by autonomous vehicles. One of the methods includes receiving data that defines valid lane paths in a scene in an environment. Each valid lane path represents a path through the scene that can be traversed by a vehicle. User interface presentation data can be provided to a user device. The user interface can contain: (i) a first display area that displays a first visual representation of the sensor measurement; and (ii) a second display area that displays a second visual representation of the set of valid lane paths. User input modifying the second visual representation of the set of valid lane paths can be received; and in response to receiving the user input, the set of valid lane paths of the scene in the environment can be modified.
1. A computer-implemented method comprising:
receiving data representing a sensor measurement, generated by one or more sensors, of a scene in an environment;
receiving data defining a set of valid lane paths in the scene in the environment, each valid lane path representing a path through the scene that can be traversed by a vehicle;
receiving data indicating that at least one valid lane path in the scene has become an invalid lane path, each invalid lane path representing a path that contains an obstruction that prevents a vehicle from traversing a path through the scene represented by the invalid lane path;
providing user interface presentation data to a user device that causes the user device to display a user interface, the user interface comprising:
(i) a first display area that displays a first visual representation of the sensor measurement; and
(ii) a second display area that displays a second visual representation of the at least one invalid lane path;
receiving a user input modifying the second visual representation of the at least one invalid lane path such that the modified visual representation avoids the obstruction;
generating, using the user input, a lane path that can be traversed by a vehicle; and
in response to receiving the user input modifying the second visual representation, modifying the set of valid lane paths of the scene in the environment to include the generated lane path.
2. The method of claim 1 wherein each of the lane paths is defined by a lane path descriptor that specifies:
a plurality of nodes comprising a start node and an end node;
the start node represents the beginning of the lane path and the end node represents the end of the lane path; and
one or more directed edges connecting the start node to the end node.
3. The method of claim 2 where the user input removes at least one of the plurality of nodes of the invalid lane path.
4. The method of claim 2 where the user input adds at least one node to the plurality of nodes of the invalid lane path.
5. The method of claim 2 where the user input modifies the location of at least one node of the plurality of nodes of the invalid lane path.
6. The method of claim 1 further comprising:
receiving a user input representing vertices of a polygon enclosing at least a portion of the sensor data; and
in response, associating the enclosed at least a portion with a label that identifies the enclosed portion as a measurement of a roadway obstruction.
7. The method of claim 1 where the first display area displays the first visual representation of the sensor measurement as a top-down representation.
8. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising:
receiving data representing a sensor measurement, generated by one or more sensors, of a scene in an environment;
receiving data defining a set of valid lane paths in the scene in the environment, each valid lane path representing a path through the scene that can be traversed by a vehicle;
receiving data indicating that at least one valid lane path in the scene has become an invalid lane path, each invalid lane path representing a path that contains an obstruction that prevents a vehicle from traversing a path through the scene represented by the invalid lane path;
providing user interface presentation data to a user device that causes the user device to display a user interface, the user interface comprising:
(i) a first display area that displays a first visual representation of the sensor measurement; and
(ii) a second display area that displays a second visual representation of the at least one invalid lane path;
receiving a user input modifying the second visual representation of the at least one invalid lane path such that the modified visual representation avoids the obstruction;
generating, using the user input, a lane path that can be traversed by a vehicle; and
in response to receiving the user input modifying the second visual representation, modifying the set of valid lane paths of the scene in the environment to include the generated lane path.
9. The system of claim 8 wherein each of the lane paths is defined by a lane path descriptor that specifies:
a plurality of nodes comprising a start node and an end node;
the start node represents the beginning of the lane path and the end node represents the end of the lane path; and
one or more directed edges connecting the start node to the end node.
10. The system of claim 9 where the user input removes at least one of the plurality of nodes of the invalid lane path.
11. The system of claim 9 where the user input adds at least one node to the plurality of nodes of the invalid lane path.
12. The system of claim 9 where the user input modifies the location of at least one node of the plurality of nodes of the invalid lane path.
13. The system of claim 8 , the operations further comprising:
receiving a user input representing vertices of a polygon enclosing at least a portion of the sensor data; and
in response, associating the enclosed at least a portion with a label that identifies the enclosed portion as a measurement of a roadway obstruction.
14. The system of claim 8 where the first display area displays the first visual representation of the sensor measurement as a top-down representation.
15. One or more non-transitory computer-readable storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
receiving data representing a sensor measurement, generated by one or more sensors, of a scene in an environment;
receiving data defining a set of valid lane paths in the scene in the environment, each valid lane path representing a path through the scene that can be traversed by a vehicle;
receiving data indicating that at least one valid lane path in the scene has become an invalid lane path, each invalid lane path representing a path that contains an obstruction that prevents a vehicle from traversing a path through the scene represented by the invalid lane path;
providing user interface presentation data to a user device that causes the user device to display a user interface, the user interface comprising:
(i) a first display area that displays a first visual representation of the sensor measurement; and
(ii) a second display area that displays a second visual representation of the at least one invalid lane path;
receiving a user input modifying the second visual representation of the at least one invalid lane path such that the modified visual representation avoids the obstruction;
generating, using the user input, a lane path that can be traversed by a vehicle; and
in response to receiving the user input modifying the second visual representation, modifying the set of valid lane paths of the scene in the environment to include the generated lane path.
16. The one or more non-transitory computer-readable storage media of claim 15 , the operations further comprising:
receiving a user input representing vertices of a polygon enclosing at least a portion of the sensor data; and
in response, associating the enclosed at least a portion with a label that identifies the enclosed portion as a measurement of a roadway obstruction.
17. The one or more non-transitory computer-readable storage media of claim 15 where the first display area displays the first visual representation of the sensor measurement as a top-down representation.
18. The one or more non-transitory computer-readable storage media of claim 7 wherein each of the lane paths is defined by a lane path descriptor that specifies:
a plurality of nodes comprising a start node and an end node;
the start node represents the beginning of the lane path and the end node represents the end of the lane path; and
one or more directed edges connecting the start node to the end node.
19. The one or more non-transitory computer-readable storage media of claim 18 where the user input removes at least one of the plurality of nodes of the invalid lane path.
20. The one or more non-transitory computer-readable storage media of claim 7 where the user input removes at least one of the plurality of nodes of the invalid lane path.