Determining drivability of objects for autonomous vehicles
Aspects of the disclosure relate to maneuvering a vehicle. As an example, sensor information identifying a set of objects as well as a set of characteristics for each object of the set of objects is received from a perception system of a vehicle. The set of objects is filtered to remove objects corresponding to vehicles, bicycles, and pedestrians. An object within an expected future path of the vehicle is selected from the filtered set of objects. The object is classified as drivable or not drivable based on the set of characteristics. Drivable indicates that the vehicle can drive over the object without causing damage to the vehicle. The vehicle is maneuvered based on the classification such that when the object is classified as drivable, maneuvering the vehicle includes driving the vehicle over the object by not altering the expected future path of the vehicle.
1. A method of maneuvering a vehicle, the method comprising:
receiving, by one or more processors from a perception system of the vehicle, sensor information identifying a set of objects as well as a set of characteristics for each object of the set of objects;
filtering, by the one or more processors, the set of objects to remove objects corresponding to vehicles, bicycles, and pedestrians;
selecting, by the one or more processors, from the filtered set of objects, an object within an expected future path of the vehicle;
classifying, by the one or more processors, the object as drivable or not drivable based on the set of characteristics for the object, wherein drivable indicates that the vehicle can drive over the object without causing damage to the vehicle; and
maneuvering, by the one or more processors, the vehicle based on the classification such that when the object is classified as drivable, maneuvering the vehicle includes driving the vehicle over the object by not altering the expected future path of the vehicle.
2. The method of claim 1 , wherein the set of characteristics includes a location of the object, and the method further comprises prior to classifying, determining that the object was not included in pre-stored map information describing a driving environment of the vehicle at the location.
3. The method of claim 1 , wherein the receiving of the sensor information occurs when the vehicle is approaching the object such that the classification and maneuvering are performed in real time.
4. The method of claim 1 , wherein when the classification is not drivable, maneuvering the vehicle includes altering the expected future path of the vehicle to avoid driving over the object.
5. The method of claim 1 , further comprising, when an object is classified as not drivable, further classifying the object as not drivable but likely to move out of expected future path of the vehicle.
6. The method of claim 5 , wherein when the object is classified as not drivable but likely to move out of the expected future path of the vehicle, maneuvering the vehicle includes slowing the vehicle down as the vehicle approaches the object.
7. The method of claim 1 , wherein the filtering further includes filtering the set of objects to remove objects not within a lane in which the vehicle is currently traveling.
8. The method of claim 1 , wherein the filtering further includes filtering the set of objects to remove objects having a height that meets a predetermined height threshold.
9. The method of claim 1 , wherein the filtering further includes filtering the set of objects to remove objects having a predetermined shape.
10. The method of claim 1 , wherein classifying, by the one or more processors, the object as drivable further includes:
classifying the object as drivable if straddled between two wheels of the vehicle, and
wherein when the object is classified as drivable if straddled between two wheels of the vehicle, maneuvering the vehicle based on the classification includes maneuvering the vehicle in order to straddle the object between the two wheels of the vehicle.
11. A system for maneuvering a vehicle, the system comprising one or more processors configured to:
receive, from a perception system of the vehicle, sensor information identifying a set of objects as well as a set of characteristics for each object of the set of objects;
filter the set of objects to remove objects corresponding to vehicles, bicycles, and pedestrians;
select from the filtered set of objects, an object within an expected future path of the vehicle;
classify the object as drivable or not drivable based on the set of characteristics for the object, wherein drivable indicates that the vehicle can drive over the object without causing damage to the vehicle; and
maneuver the vehicle based on the classification such that when the object is classified as drivable, maneuvering the vehicle includes driving the vehicle over the object by not altering the expected future path of the vehicle.
12. The system of claim 11 , further comprising the vehicle.
13. The system of claim 11 , wherein the set of characteristics includes a location of the object, and the one or more processors are further configured to, prior to classifying, determining that the object was not included in pre-stored map information describing a driving environment of the vehicle at the location.
14. The system of claim 11 , wherein the one or more processors are further configured such that when the receiving of the sensor information occurs when the vehicle is approaching the object, the classification and maneuvering are performed in real time.
15. The system of claim 11 , wherein when the classification is not drivable, the one or more processors are further configured to maneuver the vehicle by altering the expected future path of the vehicle to avoid driving over the object.
16. The system of claim 11 , when an object is classified as not drivable, the one or more processors are further configured to further classify the object as not drivable but likely to move out of the expected future path of the vehicle.
17. The system of claim 11 , wherein the one or more processors are further configured to filter the set of objects by also removing objects not within a lane in which the vehicle is currently traveling.
18. The system of claim 11 , wherein the one or more processors are further configured to filter the set of objects by also removing objects having a height that meets a predetermined height threshold.
19. The system of claim 11 , wherein the one or more processors are further configured to filter the set of objects by also removing objects having a predetermined shape.
20. A non-transitory computer readable storage medium on which instructions are stored, the instructions, when executed by one or more processors cause the one or more processors to perform a method for maneuvering a vehicle, the method comprising:
receiving, from a perception system of the vehicle, sensor information identifying a set of objects as well as a set of characteristics for each object of the set of objects;
filtering the set of objects to remove objects corresponding to vehicles, bicycles, and pedestrians;
selecting from the filtered set of objects, an object within an expected future path of the vehicle;
classifying the object as drivable or not drivable based on the set of characteristics for the object, wherein drivable indicates that the vehicle can drive over the object without causing damage to the vehicle; and
maneuvering the vehicle based on the classification such that when the object is classified as drivable, maneuvering the vehicle includes driving the vehicle over the object by not altering the expected future path of the vehicle.