Systems and methods for estimating lane geometry
Systems and methods for estimating lane geometry are disclosed herein. One embodiment receives sensor data from one or more sensors; detects a road agent based on the sensor data; detects, based on the sensor data, that the road agent has performed a lane shift from a first lane of a roadway to a second lane of the roadway; and estimates a boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift.
1. A system for estimating lane geometry, the system comprising:
one or more sensors;
one or more processors; and
a memory communicably coupled to the one or more processors and storing:
a detection module including instructions that when executed by the one or more processors cause the one or more processors to:
receive sensor data from the one or more sensors;
detect a road agent based on the sensor data; and
detect, based on the sensor data, that the road agent has performed a lane shift from a first lane of a roadway to a second lane of the roadway; and
an estimation module including instructions that when executed by the one or more processors cause the one or more processors to estimate a boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift.
2. The system of claim 1 , wherein the instructions in the detection module to detect, based on the sensor data, that the road agent has performed the lane shift from the first lane of the roadway to the second lane of the roadway include instructions to track a trajectory of the road agent in relation to an estimated midline of the first lane of the roadway.
3. The system of claim 1 , wherein the instructions in the estimation module to estimate the boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift include instructions to estimate that the boundary line lies halfway between a first lateral position occupied by the road agent in the first lane of the roadway prior to the lane shift and a second lateral position occupied by the road agent in the second lane of the roadway upon completion of the lane shift.
4. The system of claim 1 , wherein the instructions in the estimation module to estimate the boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift include instructions to estimate that the boundary line passes through a point of inflection of a trajectory traversed by the road agent during the lane shift.
5. The system of claim 1 , wherein the estimation module includes further instructions that when executed by the one or more processors cause the one or more processors to compare the estimated boundary line with a prior estimated boundary line generated, at least in part, through detection of a different lane shift by a different road agent.
6. The system of claim 1 , wherein the one or more sensors include at least one of an image sensor, a radar sensor, and a Light Detection and Ranging (LIDAR) sensor.
7. The system of claim 1 , wherein the road agent is one of a vehicle, a motorcycle, a scooter, and a bicycle.
8. A non-transitory computer-readable medium for estimating lane geometry and storing instructions that when executed by one or more processors cause the one or more processors to:
receive sensor data from one or more sensors;
detect a road agent based on the sensor data;
detect, based on the sensor data, that the road agent has performed a lane shift from a first lane of a roadway to a second lane of the roadway; and
estimate a boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift.
9. The non-transitory computer-readable medium of claim 8 , wherein the instructions to detect, based on the sensor data, that the road agent has performed the lane shift from the first lane of the roadway to the second lane of the roadway include instructions to track a trajectory of the road agent in relation to an estimated midline of the first lane of the roadway.
10. The non-transitory computer-readable medium of claim 8 , wherein the instructions to estimate the boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift include instructions to estimate that the boundary line lies halfway between a first lateral position occupied by the road agent in the first lane of the roadway prior to the lane shift and a second lateral position occupied by the road agent in the second lane of the roadway upon completion of the lane shift.
11. The non-transitory computer-readable medium of claim 8 , wherein the instructions to estimate the boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift include instructions to estimate that the boundary line passes through a point of inflection of a trajectory traversed by the road agent during the lane shift.
12. The non-transitory computer-readable medium of claim 8 , further comprising instructions to compare the estimated boundary line with a prior estimated boundary line generated, at least in part, through detection of a different lane shift by a different road agent.
13. The non-transitory computer-readable medium of claim 8 , wherein the one or more sensors include at least one of an image sensor, a radar sensor, and a Light Detection and Ranging (LIDAR) sensor.
14. A method of estimating lane geometry, the method comprising:
receiving sensor data from one or more sensors;
detecting a road agent based on the sensor data;
detecting, based on the sensor data, that the road agent has performed a lane shift from a first lane of a roadway to a second lane of the roadway; and
estimating a boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift.
15. The method of claim 14 , wherein the detecting, based on the sensor data, that the road agent has performed the lane shift from the first lane of the roadway to the second lane of the roadway includes tracking a trajectory of the road agent in relation to an estimated midline of the first lane of the roadway.
16. The method of claim 14 , wherein the estimating the boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift includes estimating that the boundary line lies halfway between a first lateral position occupied by the road agent in the first lane of the roadway prior to the lane shift and a second lateral position occupied by the road agent in the second lane of the roadway upon completion of the lane shift.
17. The method of claim 14 , wherein the estimating the boundary line between the first lane of the roadway and the second lane of the roadway based, at least in part, on the detected lane shift includes estimating that the boundary line passes through a point of inflection of a trajectory traversed by the road agent during the lane shift.
18. The method of claim 14 , further comprising comparing the estimated boundary line with a prior estimated boundary line generated, at least in part, through detection of a different lane shift by a different road agent.
19. The method of claim 14 , wherein the one or more sensors include at least one of an image sensor, a radar sensor, and a Light Detection and Ranging (LIDAR) sensor.
20. The method of claim 14 , wherein the road agent is one of a vehicle, a motorcycle, a scooter, and a bicycle.