Dynamically adjustable reference line sampling point density for autonomous vehicles
According to some embodiments, a system receives a first set of reference points based on a map and a route information, the first plurality of reference points representing a reference line in which the ADV is to follow. The system selects a second set of reference points along the reference line, including iteratively performing, selecting a current reference point from the first set of reference points, determining a sampling distance along the first set of reference points based on the currently selected reference point using a nonlinear algorithm, and selecting a next reference point based on the determined sampling distance such that a density of the second set of reference points closer to the ADV is higher than a density of the selected reference points farther away from the ADV. The system plans a trajectory for the ADV using the second set of reference points to control the ADV.
1. A computer-implemented method to generate a driving trajectory with progressive sampling distance for an autonomous driving vehicle (ADV), the method comprising:
receiving a first set of reference points based on a map and a route information, the first set of reference points representing a reference line in which the ADV is to follow;
selecting a second set of reference points along the reference line corresponding to the first set of reference points, including iteratively performing, selecting a current reference point from the first set of reference points;
determining a sampling distance along the first set of reference points based on the currently selected reference point using a nonlinear algorithm; and
selecting a next reference point along the first set of reference points based on the determined sampling distance such that a density of the selected reference points closer to the ADV is higher than a density of the selected reference points farther away from the ADV; and
planning a trajectory for the ADV using the second set of reference points to control the ADV.
2. The computer-implemented method of claim 1 , wherein determining a sampling distance further comprises:
determining a minimum sampling distance; and
determining a maximum sampling distance, wherein the sampling distance is determined based on the minimum sampling distance and the maximum sampling distance.
3. The computer-implemented method of claim 2 , wherein the sampling distance is determined further in view of a length of the reference line.
4. The computer-implemented method of claim 1 , wherein the second set of reference points includes points that are separated by a distance approximately equal to the minimum sampling distances near the ADV and a distance approximately equal to the maximum sampling distances away from the ADV.
5. The computer-implemented method of claim 1 , wherein the second set of reference points has a density that gradually decreases away from the ADV.
6. The computer-implemented method of claim 1 , wherein the nonlinear algorithm is an inverse of an exponential function.
7. The computer-implemented method of claim 1 , wherein the nonlinear algorithm is
f
(
s
)
=
A
1
+
e
Bs
+
C
,
wherein s is a distance away from the ADV, A is a maximum sampling distance, C is a logarithmic of A divided by a minimum sampling distance minus one, and B is a logarithmic of A/((A−σ)−1), minus C, divided by a length of the reference line, wherein σ is a fractional number.
8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
receiving a first set of reference points based on a map and a route information, the first set of reference points representing a reference line in which the ADV is to follow;
selecting a second set of reference points along the reference line corresponding to the first set of reference points, including iteratively performing, selecting a current reference point from the first set of reference points;
determining a sampling distance along the first set of reference points based on the currently selected reference point using a nonlinear algorithm; and
selecting a next reference point along the first set of reference points based on the determined sampling distance such that a density of the selected reference points closer to the ADV is higher than a density of the selected reference points farther away from the ADV; and
planning a trajectory for the ADV using the second set of reference points to control the ADV.
9. The non-transitory machine-readable medium of claim 8 , wherein determining a sampling distance further comprises:
determining a minimum sampling distance; and
determining a maximum sampling distance, wherein the sampling distance is determined based on the minimum sampling distance and the maximum sampling distance.
10. The non-transitory machine-readable medium of claim 9 , wherein the sampling distance is determined further in view of a length of the reference line.
11. The non-transitory machine-readable medium of claim 8 , wherein the second set of reference points includes points that are separated by a distance approximately equal to the minimum sampling distances near the ADV and a distance approximately equal to the maximum sampling distances away from the ADV.
12. The non-transitory machine-readable medium of claim 8 , wherein the second set of reference points has a density that gradually decreases away from the ADV.
13. The non-transitory machine-readable medium of claim 8 , wherein the nonlinear algorithm is an inverse of an exponential function.
14. The non-transitory machine-readable medium of claim 8 , wherein the nonlinear algorithm is
f
(
s
)
=
A
1
+
e
Bs
+
C
,
wherein s is a distance away from the ADV, A is a maximum sampling distance, C is a logarithmic of A divided by a minimum sampling distance minus one, and B is a logarithmic of A/((A−σ)−1), minus C, divided by a length of the reference line, wherein σ is a fractional number.
15. A data processing system, comprising:
one or more processors; and
a memory coupled to the one or more processors to store instructions, which when executed by the one or more processors, cause the processor to perform operations, the operations including
receiving a first set of reference points based on a map and a route information, the first set of reference points representing a reference line in which the ADV is to follow;
selecting a second set of reference points along the reference line corresponding to the first set of reference points, including iteratively performing, selecting a current reference point from the first set of reference points;
determining a sampling distance along the first set of reference points based on the currently selected reference point using a nonlinear algorithm; and
selecting a next reference point along the first set of reference points based on the determined sampling distance such that a density of the selected reference points closer to the ADV is higher than a density of the selected reference points farther away from the ADV; and
planning a trajectory for the ADV using the second set of reference points to control the ADV.
16. The system of claim 15 , wherein determining a sampling distance further comprises:
determining a minimum sampling distance; and
determining a maximum sampling distance, wherein the sampling distance is determined based on the minimum sampling distance and the maximum sampling distance.
17. The system of claim 16 , wherein the sampling distance is determined further in view of a length of the reference line.
18. The system of claim 15 , wherein the second set of reference points includes points that are separated by a distance approximately equal to the minimum sampling distances near the ADV and a distance approximately equal to the maximum sampling distances away from the ADV.
19. The system of claim 15 , wherein the second set of reference points has a density that gradually decreases away from the ADV.
20. The system of claim 15 , wherein the nonlinear algorithm is an inverse of an exponential function.
21. The system of claim 15 , wherein the nonlinear algorithm is
f
(
s
)
=
A
1
+
e
Bs
+
C
,
wherein s is a distance away from the ADV, A is a maximum sampling distance, C is a logarithmic of A divided by a minimum sampling distance minus one, and B is a logarithmic of A/((A−σ)−1), minus C, divided by a length of the reference line, wherein σ is a fractional number.