Systems and methods for operating an autonomous vehicle
An autonomous vehicle (AV) includes features that allows the AV to perform safe driving operations. An example method includes detecting that a motorcycle is operating on a roadway on which the autonomous vehicle is located. The method further includes classifying a behavior state of the motorcycle based on a location of the motorcycle relative to a split zone that extends between and into two adjacent lanes of the roadway. The behavior state indicates whether the motorcycle is lane splitting. The method further includes determining, based on the behavior state of the motorcycle, a lane permission parameter that controls whether a given trajectory for the autonomous vehicle can extend into one of the two adjacent lanes. The method further includes causing the autonomous vehicle to operate in accordance with a trajectory that satisfies the lane permission parameter based on transmitting instructions related to the trajectory to subsystems of the autonomous vehicle.
1. A method of operating an autonomous vehicle, comprising:
detecting, by a controller disposed on the autonomous vehicle, that a motorcycle is operating on a roadway on which the autonomous vehicle is located;
classifying, by the controller, a behavior state of the motorcycle based on a location of the motorcycle relative to a split zone that extends between and into two adjacent lanes of the roadway, wherein the behavior state indicates whether the motorcycle is lane splitting;
determining, by the controller based on the behavior state of the motorcycle, a lane permission parameter for the autonomous vehicle that controls whether a given trajectory determined for the autonomous vehicle is permitted to extend into one of the two adjacent lanes; and
causing, by the controller, the autonomous vehicle to operate in accordance with a trajectory that satisfies the lane permission parameter based on transmitting instructions related to the trajectory to one or more subsystems of the autonomous vehicle,
wherein the lane permission parameter is determined further based on whether a jurisdiction in which the autonomous vehicle is located permits lane splitting of motorcycles.
2. The method of claim 1 , wherein the given trajectory is determined by a navigation module that is logically downstream of the controller.
3. The method of claim 1 , wherein the trajectory is configured, based on the behavior state indicating that the motorcycle is lane splitting, to bias the autonomous vehicle within a current lane of the autonomous vehicle away from the location of the motorcycle.
4. The method of claim 1 , wherein the split zone extends into each of the two adjacent lanes by a given distance that leaves a width of the autonomous vehicle in each adjacent lane.
5. The method of claim 1 , wherein causing the autonomous vehicle to operate in accordance with the lane permission parameter includes causing the autonomous vehicle to move from a current lane to a different lane before the autonomous vehicle is within a pre-determined distance from the motorcycle.
6. The method of claim 1 , wherein the lane permission parameter permits the given trajectory into one of the two adjacent lanes in response to the jurisdiction within which the autonomous vehicle is located permitting lane splitting of motorcycles.
7. The method of claim 1 , further comprising:
in response to (i) the behavior state indicating that the motorcycle is lane splitting and (ii) the jurisdiction within which the autonomous vehicle is located not permitting lane splitting of motorcycles, automatically indicating an alert to an operator associated with the autonomous vehicle that includes the behavior state of the motorcycle.
8. The method of claim 1 , further comprising:
classifying the motorcycle as a two-wheel motorcycle or a three-wheel motorcycle, wherein the lane permission parameter is further determined based on the classifying.
9. The method of claim 1 , wherein the lane permission parameter does not permit the given trajectory to extend into one of the two adjacent lanes based on the motorcycle being a three-wheel motorcycle.
10. The method of claim 1 , wherein detecting that the motorcycle is operating on the roadway includes:
obtaining a point cloud that captures the motorcycle from one or more light detection and ranging (LiDAR) sensing devices located on the autonomous vehicle,
filtering a subset of the point cloud that is attributed to a micro-Doppler effect of wheels of the motorcycle, and
determining a bounding box and the location of the motorcycle using the filtered point cloud.
11. A system for operating an autonomous vehicle, comprising a computer that includes a processor configured to execute instructions to cause the system to:
detect that a motorcycle is operating on a roadway on which the autonomous vehicle is located;
classify a behavior state of the motorcycle based on a location of the motorcycle relative to a split zone that extends between and into two adjacent lanes of the roadway, wherein the behavior state indicates whether the motorcycle is lane splitting;
determine, based on the behavior state of the motorcycle, a lane permission parameter for the autonomous vehicle that controls whether a given trajectory determined for the autonomous vehicle is permitted to extend into one of the two adjacent lanes; and
cause the autonomous vehicle to operate in accordance with a trajectory that satisfies the lane permission parameter based on transmitting instructions related to the trajectory to one or more subsystems of the autonomous vehicle,
wherein the lane permission parameter is further determined based on whether a jurisdiction within which the autonomous vehicle is located permits lane splitting of motorcycles.
12. The system of claim 11 , wherein the split zone extends into each of the two adjacent lanes by a given distance that is less than half of a width of each adjacent lane.
13. The system of claim 11 , wherein detecting that the motorcycle is operating on the roadway includes:
identifying the motorcycle in image data captured by one or more cameras located on the autonomous vehicle,
tracking the motorcycle in one or more subsequent sets of image data captured by the one or more cameras, and
dynamically updating the location of the motorcycle based on the tracking.
14. The system of claim 11 , wherein detecting that the motorcycle is operating on the roadway includes classifying a detected vehicle as a motorcycle due to the detected vehicle having three or fewer wheels.
15. A non-transitory computer readable program storage medium having code stored thereon, the code, when executed by a processor, causing the processor to:
detect, that a motorcycle is operating on a roadway on which an autonomous vehicle is located;
classify a behavior state of the motorcycle based on a location of the motorcycle relative to a split zone that extends between and into two adjacent lanes of the roadway, wherein the behavior state indicates whether the motorcycle is lane splitting;
determine, based on the behavior state of the motorcycle, a lane permission parameter for the autonomous vehicle that controls whether a given trajectory determined for the autonomous vehicle is permitted to extend into one of the two adjacent lanes; and
cause the autonomous vehicle to operate in accordance with a trajectory that satisfies the lane permission parameter based on transmitting instructions related to the trajectory to one or more subsystems of the autonomous vehicle,
wherein the lane permission parameter is further determined based on whether a jurisdiction within which the autonomous vehicle is located permits lane splitting of motorcycles.
16. The non-transitory computer readable program storage medium of claim 15 , wherein the split zone extends into each of the two adjacent lanes by a given distance that corresponds to respective widths of the two adjacent lanes and a curvature of the two adjacent lanes.
17. The non-transitory computer readable program storage medium of claim 15 , wherein detecting that the motorcycle is operating on the roadway includes:
identifying the motorcycle in radar data obtained from one or more radar devices located on the autonomous vehicle, and
determining the location of the motorcycle from the radar data.
18. The non-transitory computer readable program storage medium of claim 15 , wherein the lane permission parameter does not permit the given trajectory into one of the two adjacent lanes in response to the jurisdiction within which the autonomous vehicle is located not permitting lane splitting of motorcycles.
19. The system of claim 11 , wherein the lane permission parameter permits the given trajectory into one of the two adjacent lanes in response to the jurisdiction within which the autonomous vehicle is located permitting lane splitting of motorcycles.
20. The non-transitory computer readable program storage medium of claim 15 , wherein the lane permission parameter permits the given trajectory into one of the two adjacent lanes in response to the jurisdiction within which the autonomous vehicle is located permitting lane splitting of motorcycles.