Proximity detection for automotive vehicles and other systems based on probabilistic computing techniques
A method includes identifying, using at least one processor, a first point associated with an uncertain location of an object in a space and a polynomial curve associated with an uncertain location of a feature in the space. The method also includes determining, using the at least one processor, a probabilistic proximity of the object and the feature. The probabilistic proximity is determined by identifying a second point on the polynomial curve, transforming an uncertainty associated with the polynomial curve into an uncertainty associated with the second point, and identifying the probabilistic proximity of the object and the feature using the first and second points and the uncertainty associated with the second point.
1 . A method comprising:
identifying, using at least one processor, a first point associated with an uncertain location of an object in a space and a polynomial curve associated with an uncertain location of a feature in the space; and
determining, using the at least one processor, a probabilistic proximity of the object and the feature by:
identifying a second point on the polynomial curve, including identifying a location on the polynomial curve where a line between the first point and the location on the polynomial curve is a normal vector of the polynomial curve;
transforming an uncertainty associated with the polynomial curve into an uncertainty associated with the second point; and
identifying the probabilistic proximity of the object and the feature using the first and second points and the uncertainty associated with the second point;
identifying at least one action based on the probabilistic proximity; and
performing the at least one action,
wherein the at least one action is associated with a vehicle, and
wherein the at least one action comprises at least one of:
an adjustment to at least one of a steering of the vehicle, a speed of the vehicle, an acceleration of the vehicle, and a braking of the vehicle; and
an activation of an audible, visible, or haptic warning.
2 . The method of claim 1 , wherein transforming the uncertainty associated with the polynomial curve comprises transforming a covariance matrix of the polynomial curve into a covariance matrix of the second point.
3 . The method of claim 2 , wherein eigenvalues of the covariance matrix of the polynomial curve are used to transform the covariance matrix of the polynomial curve into the covariance matrix of the second point.
4 . The method of claim 1 , wherein identifying the probabilistic proximity comprises determining a statistical distance between the first and second points.
5 . The method of claim 4 , wherein identifying the probabilistic proximity further comprises determining a probability that the first point is on the polynomial curve.
6 . The method of claim 1 , wherein the first point is associated with an object around the vehicle, the object sensed using at least one sensor of the vehicle.
7 . The method of claim 6 , wherein the polynomial curve is associated with an estimated path of the vehicle, an estimated center location of a lane, or an estimated location of a lane-marking line.
8 . An apparatus comprising:
at least one processor configured to:
identify a first point associated with an uncertain location of an object in a space and a polynomial curve associated with an uncertain location of a feature in the space; and
determine a probabilistic proximity of the object and the feature;
wherein, to determine the probabilistic proximity, the at least one processor is configured to:
identify a second point on the polynomial curve by an identification of a location on the polynomial curve where a line between the first point and the location on the polynomial curve is a normal vector of the polynomial curve;
transform an uncertainty associated with the polynomial curve into an uncertainty associated with the second point; and
identify the probabilistic proximity of the object and the feature using the first and second points and the uncertainty associated with the second point;
identify at least one action based on the probabilistic proximity; and
initiate performance of the at least one action,
wherein the at least one action is associated with a vehicle, and
wherein the at least one action comprises at least one of:
an adjustment to at least one of a steering of the vehicle, a speed of the vehicle, an acceleration of the vehicle, and a braking of the vehicle; and
an activation of an audible, visible, or haptic warning.
9 . The apparatus of claim 8 , wherein, to transform the uncertainty associated with the polynomial curve, the at least one processor is configured to transform a covariance matrix of the polynomial curve into a covariance matrix of the second point.
10 . The apparatus of claim 9 , wherein eigenvalues of the covariance matrix of the polynomial curve are used to transform the covariance matrix of the polynomial curve into the covariance matrix of the second point.
11 . The apparatus of claim 8 , wherein, to identify the probabilistic proximity, the at least one processor is configured to determine a statistical distance between the first and second points.
12 . The apparatus of claim 11 , wherein, to identify the probabilistic proximity, the at least one processor is further configured to determine a probability that the first point is on the polynomial curve.
13 . The apparatus of claim 8 , further comprising:
one or more sensors configured to generate sensor measurements,
wherein the first point is associated with an object around the vehicle sensed using at least one of the one or more sensors.
14 . The apparatus of claim 13 , wherein the at least one processor is further configured to generate the polynomial curve as an estimated path of the vehicle, an estimated center location of a lane, or an estimated location of a lane-marking line.
15 . A non-transitory machine-readable medium containing instructions that when executed cause at least one processor to:
identify a first point associated with an uncertain location of an object in a space and a polynomial curve associated with an uncertain location of a feature in the space; and
determine a probabilistic proximity of the object and the feature;
wherein the instructions that when executed cause the at least one processor to determine the probabilistic proximity comprise instructions that when executed cause the at least one processor to:
identify a second point on the polynomial curve by an identification of a location on the polynomial curve where a line between the first point and the location on the polynomial curve is a normal vector of the polynomial curve;
transform an uncertainty associated with the polynomial curve into an uncertainty associated with the second point; and
identify the probabilistic proximity of the object and the feature using the first and second points and the uncertainty associated with the second point;
identify at least one action based on the probabilistic proximity; and
initiate performance of the at least one action,
wherein the at least one action is associated with a vehicle, and
wherein the at least one action comprises at least one of:
an adjustment to at least one of a steering of the vehicle, a speed of the vehicle, an acceleration of the vehicle, and a braking of the vehicle; and
an activation of an audible, visible, or haptic warning.
16 . The non-transitory machine-readable medium of claim 15 , wherein the instructions that when executed cause the at least one processor to transform the uncertainty associated with the polynomial curve comprise instructions that when executed cause the at least one processor to transform a covariance matrix of the polynomial curve into a covariance matrix of the second point.
17 . The non-transitory machine-readable medium of claim 16 , wherein eigenvalues of the covariance matrix of the polynomial curve are used to transform the covariance matrix of the polynomial curve into the covariance matrix of the second point.
18 . The non-transitory machine-readable medium of claim 15 , wherein the instructions that when executed cause the at least one processor to identify the probabilistic proximity comprise instructions that when executed cause the at least one processor to determine a statistical distance between the first and second points.
19 . The non-transitory machine-readable medium of claim 18 , wherein the instructions that when executed cause the at least one processor to identify the probabilistic proximity comprise instructions that when executed cause the at least one processor to determine a probability that the first point is on the polynomial curve.
20 . The non-transitory machine-readable medium of claim 15 , wherein:
the first point is associated with an object around the vehicle that is sensed using at least one sensor of the vehicle; and
the instructions when executed further cause the at least one processor to generate the polynomial curve as an estimated path of the vehicle, an estimated center location of a lane, or an estimated location of a lane-marking line.