Proactive risk mitigation with generalized virtual vehicles
Proactively mitigating risk to a vehicle traversing a vehicle transportation network includes identifying a location for a virtual vehicle. The virtual vehicle is added to a world object model maintained with respect to the vehicle. A trajectory is predicted for the virtual vehicle. The vehicle is autonomously controlled according to an adjusted trajectory that is based on the trajectory for the virtual vehicle. The adjusted trajectory includes at least one of a lateral constraint or a speed constraint. The location for the virtual vehicle is identified based on a lane in map data, a trajectory of a vehicle, and a perceptible area by sensors of the vehicle. The virtual vehicle is a hypothetical vehicle that is not observed by sensors of the vehicle.
1 . A method, comprising:
identifying a location for a virtual vehicle,
wherein the location is identified based on a lane in map data, a trajectory of a vehicle, and a perceptible area by sensors of the vehicle,
wherein the virtual vehicle is a hypothetical vehicle that is not observed by sensors of the vehicle, and
wherein identifying the location for the virtual vehicle comprises:
searching backwards, starting at a location along the lane corresponding to a current location of the vehicle, along a predicted trajectory of the virtual vehicle until a location outside the perceptible area of the sensors is identified;
setting a location of the virtual vehicle, as a determined trajectory, along the predicted trajectory that is not visible to the sensors; and
adjusting the location of the virtual vehicle to an adjusted location, that is along the determined trajectory, at a time of instantiating the virtual vehicle to account for a processing delay associated with the sensors of the vehicle so that the virtual vehicle is within the perceptible area,
wherein the processing delay comprises perception delays, tracking delays, and prediction delays in converting sensor data into classified objects, and
wherein the adjusted location is positioned further along a predicted path of the virtual vehicle in accordance with the processing delay;
including the virtual vehicle at the adjusted location to a world object model maintained with respect to the vehicle;
predicting a trajectory for the virtual vehicle; and
autonomously controlling the vehicle according to an adjusted trajectory that is based on the determined trajectory for the virtual vehicle, wherein the adjusted trajectory includes at least one of a lateral constraint or a speed constraint.
2 . The method of claim 1 , wherein the lane is a same lane on which the vehicle is traveling, the virtual vehicle is a leading virtual vehicle that would be ahead of the vehicle on the trajectory of the vehicle, and wherein the searching backwards comprises searching along the trajectory of the vehicle until a location outside the perceptible area is identified.
3 . The method of claim 2 , wherein the leading virtual vehicle is instantiated as a static virtual vehicle.
4 . The method of claim 1 , wherein the lane is an oncoming lane, the virtual vehicle is an oncoming virtual vehicle, and wherein the predicted trajectory is a trajectory that would bring the oncoming virtual vehicle toward the vehicle within lane geometry obtained from the map data.
5 . The method of claim 4 , wherein after identifying the location outside the perceptible area, the oncoming virtual vehicle is located at an adjusted location that accounts for predicted movement of the oncoming virtual vehicle during the processing delay.
6 . The method of claim 5 , wherein the processing delay comprises delays specific to sensor fusion algorithms used to integrate data from multiple sensor types.
7 . The method of claim 1 , wherein the lane is a crossing lane, the virtual vehicle is a crossing virtual vehicle, and wherein the predicted trajectory would cause the crossing virtual vehicle to intersect the trajectory of the vehicle.
8 . The method of claim 7 , wherein after identifying the location outside the perceptible area, the crossing virtual vehicle is located at an adjusted location that accounts for predicted movement of the crossing virtual vehicle during the processing delay.
9 . A vehicle, comprising:
one or more memories; and
one or more processors, the one or more processors configured to execute instructions stored in the one or more memories to:
identify a location for a virtual vehicle,
wherein the location is identified based on a lane in map data, a trajectory of a vehicle, and a perceptible area by sensors of the vehicle,
wherein the virtual vehicle is a hypothetical vehicle that is not observed by sensors of the vehicle,
and wherein, to identify the location for the virtual vehicle, the one or more processors configured to execute instructions stored in the one or more memories to:
search backwards, starting at a location along the lane corresponding to a current location of the vehicle, along a predicted trajectory of the virtual vehicle until a location outside the perceptible area of the sensors is identified;
set a location of the virtual vehicle, as a determined trajectory, along the predicted trajectory that is not visible to the sensors; and
adjust the location of the virtual vehicle to an adjusted location, that is along the determined trajectory, at a time of instantiating the virtual vehicle to account for a processing delay associated with the sensors of the vehicle so that the virtual vehicle is within the perceptible area,
wherein the processing delay comprises perception delays, tracking delays, and prediction delays in converting sensor data into classified objects, and
wherein the adjusted location is positioned further along a predicted path of the virtual vehicle in accordance with the processing delay;
include the virtual vehicle at the adjusted location to a world object model maintained with respect to the vehicle;
predict a trajectory for the virtual vehicle; and
autonomously control the vehicle according to an adjusted trajectory that is based on the determined trajectory for the virtual vehicle, wherein the adjusted trajectory includes at least one of a lateral constraint or a speed constraint.
10 . The vehicle of claim 9 , wherein the lane is a same lane on which the vehicle is traveling, the virtual vehicle is a leading virtual vehicle that would be ahead of the vehicle on the trajectory of the vehicle, and wherein, to search backwards, the one or more processors configured to execute instructions stored in the one or more memories to search along the trajectory of the vehicle until a location outside the perceptible area is identified.
11 . The vehicle of claim 10 , wherein the leading virtual vehicle is instantiated as a static virtual vehicle.
12 . The vehicle of claim 9 , wherein the lane is an oncoming lane, the virtual vehicle is an oncoming virtual vehicle, and wherein the predicted trajectory is a trajectory that would bring the oncoming virtual vehicle toward the vehicle within lane geometry obtained from the map data.
13 . The vehicle of claim 12 , wherein after identifying the location outside the perceptible area, the oncoming virtual vehicle is located at an adjusted location that accounts for predicted movement of the oncoming virtual vehicle, via the determined trajectory, during the processing delay.
14 . The vehicle of claim 13 , wherein the processing delay comprises delays specific to sensor fusion algorithms used to integrate data from multiple sensor types.
15 . The vehicle of claim 9 , wherein the lane is a crossing lane, the virtual vehicle is a crossing virtual vehicle, and wherein the predicted trajectory would cause the crossing virtual vehicle to intersect the trajectory of the vehicle.
16 . The vehicle of claim 15 , wherein after identifying the location outside the perceptible area, the crossing virtual vehicle is located at an adjusted location that accounts for predicted movement of the crossing virtual vehicle during the processing delay.
17 . One or more non-transitory computer-readable media including instructions that, when executed by one or more processors, perform operations comprising:
identifying a location for a virtual vehicle,
wherein the location is identified based on a lane in map data, a trajectory of a vehicle, and a perceptible area by sensors of the vehicle,
wherein the virtual vehicle is a hypothetical vehicle that is not observed by sensors of the vehicle, and
wherein identifying the location for the virtual vehicle comprises:
searching backwards, starting at a location along the lane corresponding to a current location of the vehicle, along a predicted trajectory of the virtual vehicle until a location outside the perceptible area of the sensors is identified;
setting a location of the virtual vehicle, as a determined trajectory, along the predicted trajectory that is not visible to the sensors; and
adjusting the location of the virtual vehicle to an adjusted location, that is along the determined trajectory, at a time of instantiating the virtual vehicle to account for a processing delay associated with the sensors of the vehicle so that the virtual vehicle is within the perceptible area,
wherein the processing delay comprises perception delays, tracking delays, and prediction delays in converting sensor data into classified objects, and
wherein the adjusted location is positioned further along a predicted path of the virtual vehicle in accordance with the processing delay;
including the virtual vehicle at the adjusted location to a world object model maintained with respect to the vehicle;
predicting a trajectory for the virtual vehicle; and
autonomously controlling the vehicle according to an adjusted trajectory that is based on the determined trajectory for the virtual vehicle, wherein the adjusted trajectory includes at least one of a lateral constraint or a speed constraint.
18 . The one or more non-transitory computer-readable media of claim 17 , wherein the lane is a same lane on which the vehicle is traveling, the virtual vehicle is a leading virtual vehicle that would be ahead of the vehicle on the trajectory of the vehicle, and wherein the searching backwards comprises searching along the trajectory of the vehicle until a location outside the perceptible area is identified.
19 . The one or more non-transitory computer-readable media of claim 18 , wherein the leading virtual vehicle is instantiated as a static virtual vehicle.
20 . The one or more non-transitory computer-readable media of claim 17 , wherein the lane is an oncoming lane, the virtual vehicle is an oncoming virtual vehicle, and wherein the predicted trajectory is a trajectory that would bring the oncoming virtual vehicle toward the vehicle within lane geometry obtained from the map data.