Probabilistic driving behavior modeling system for a vehicle
A hybrid probabilistic driving behavior modeling system conditioned on weather for a vehicle includes one or more controllers executing instructions to determine, by a longitudinal driving model stored by the one or more controllers, a probabilistic longitudinal velocity of the vehicle with respect to a current weather condition based on a car-following model, a semantic rule system, and a speed and visibility model. The current weather condition indicates an adverse weather condition impacting driving conditions for the vehicle. The one or more controllers determine, by a probabilistic lateral driving model by the one or more controllers, one or more lane choices for the vehicle with respect to the current weather condition based on a route plan of the vehicle and perception data indicative of an environment surrounding the vehicle and selects a final lane choice from the one or more lane choices.
1 . A hybrid probabilistic driving behavior modeling system for a vehicle conditioned on weather, the hybrid probabilistic driving behavior modeling system comprising:
one or more controllers executing instructions to:
determine, by a longitudinal driving model stored by the one or more controllers, a probabilistic longitudinal velocity of the vehicle with respect to a current weather condition based on a car-following model, a semantic rule system, and a speed and visibility model, wherein the current weather condition indicates an adverse weather condition impacting driving conditions for the vehicle;
determine, by a probabilistic lateral driving model by the one or more controllers, one or more lane choices for the vehicle with respect to the current weather condition based on a route plan of the vehicle and perception data indicative of an environment surrounding the vehicle;
select a final lane choice from the one or more lane choices, wherein the final lane choice includes a maximum probability of being selected at the probabilistic longitudinal velocity when compared to remaining lane choices that are part of the one or more lane choices;
determine a next state of the vehicle based on the final lane choice and the probabilistic longitudinal velocity;
receive a road segment that is part of the route plan, wherein the road segment includes an intersection;
determine the vehicle is able to execute a maneuver at the intersection based on the perception data; and
in response to determining the vehicle is able to execute the maneuver, instruct the vehicle to execute the maneuver by assisting with steering, braking, and accelerating.
2 . The hybrid probabilistic driving behavior modeling system of claim 1 , wherein the probabilistic longitudinal velocity is determined by:
determining, by the car-following model, a velocity of the vehicle by calculating a first maximum velocity and a second maximum velocity; and
selecting a minimum value between the first maximum velocity and the second maximum velocity.
3 . The hybrid probabilistic driving behavior modeling system of claim 2 , wherein the first maximum velocity represents when the vehicle is driven to achieve a target speed and the second maximum velocity represents when the vehicle is driven to preserve a recommended distance from a leading vehicle.
4 . The hybrid probabilistic driving behavior modeling system of claim 2 , wherein the probabilistic longitudinal velocity is determined by:
determining, by the semantic rule system, a constrained velocity that limits the velocity of the vehicle determined by the car-following model based on a plurality of high-level rules.
5 . The hybrid probabilistic driving behavior modeling system of claim 4 , wherein the plurality of high-level rules limit the velocity of the vehicle determined by the car-following model based on one or more driving conditions that are created by a specific adverse weather condition indicated by the current weather condition.
6 . The hybrid probabilistic driving behavior modeling system of claim 5 , wherein the speed and visibility model represents a relationship between the constrained velocity and a visibility distance of a driver of the vehicle for a specific locality, wherein the constrained velocity is negatively correlated with an inverse of the visibility distance.
7 . The hybrid probabilistic driving behavior modeling system of claim 4 , wherein the probabilistic longitudinal velocity is determined by:
determining, by the speed and visibility model, the probabilistic longitudinal velocity of the vehicle with respect to the current weather condition by limiting the constrained velocity based on a visibility distance.
8 . The hybrid probabilistic driving behavior modeling system of claim 1 , wherein the probabilistic lateral driving model classifies a current road segment that is part of a road plan as including either a necessary lane change or a free lane change.
9 . The hybrid probabilistic driving behavior modeling system of claim 8 , wherein the current road segment is classified as including the necessary lane change in response to determining a lane change is necessary at the current road segment to reach the next road segment that is part of the route plan.
10 . The hybrid probabilistic driving behavior modeling system of claim 8 , wherein the current road segment is classified as including a free lane change in response to determining the vehicle is performing one or more of the following: changing lanes to increase a distance between either a leading or trailing vehicle, and to achieve a higher velocity.
11 . The hybrid probabilistic driving behavior modeling system of claim 1 , wherein the one or more controllers store a plurality of joint probability distribution models that indicate a probability that a specific lane choice is selected at a specified longitudinal speed of the vehicle at a specific adverse weather condition.
12 . The hybrid probabilistic driving behavior modeling system of claim 11 , wherein the joint probability distribution models are determined by defining a set of random variables and set of weather conditions, wherein a first random variable represents longitudinal behavior and second random variable represents lateral behavior.
13 . The hybrid probabilistic driving behavior modeling system of claim 1 , wherein the adverse weather condition is one of the following: rain, fog, snow, and reduced illumination.
14 . A method of determining a next state of a vehicle by a hybrid probabilistic driving behavior modeling system for a vehicle, the method comprising:
determining, by a longitudinal driving model stored by one or more controllers, a probabilistic longitudinal velocity of the vehicle with respect to a current weather condition based on a car-following model, a semantic rule system, and a speed and visibility model, wherein the current weather condition indicates an adverse weather condition impacting driving conditions for the vehicle;
determining, by a probabilistic lateral driving model stored by the one or more controllers, one or more lane choices for the vehicle with respect to the current weather condition based on a route plan of the vehicle and perception data indicative of an environment surrounding the vehicle;
selecting, by the one or more controllers, a final lane choice from the one or more lane choices, wherein the final lane choice includes a maximum probability of being selected at the probabilistic longitudinal velocity when compared to remaining lane choices that are part of the one or more lane choices;
determining a next state of the vehicle based on the final lane choice and the probabilistic longitudinal velocity;
receiving a road segment that is part of the route plan, wherein the road segment includes an intersection;
determining the vehicle is able to execute a maneuver at the intersection based on the perception data; and
in response to determining the vehicle is able to execute the maneuver, instructing the vehicle to execute the maneuver by assisting with steering, braking, and accelerating.
15 . The method of claim 14 , wherein the method comprises:
determining, by the car-following model, a velocity of the vehicle by calculating a first maximum velocity and a second maximum velocity; and
selecting a minimum value between the first maximum velocity and the second maximum velocity.
16 . The method of claim 15 , wherein the method comprises:
determining, by the semantic rule system, a constrained velocity that limits the velocity of the vehicle determined by the car-following model based on a plurality of high-level rules.
17 . The method of claim 16 , wherein the method comprises:
determining, by the speed and visibility model, the probabilistic longitudinal velocity of the vehicle with respect to the current weather condition by limiting the constrained velocity based on a visibility distance.
18 . The method of claim 14 , wherein the method comprises:
classifying a current road segment that is part of a road plan as including either a necessary lane change or a free lane change.
19 . A hybrid probabilistic driving behavior modeling system for a vehicle, the hybrid probabilistic driving behavior modeling system comprising:
one or more controllers executing instructions to:
determine, by a longitudinal driving model stored by the one or more controllers, a probabilistic longitudinal velocity of the vehicle with respect to a current weather condition based on a car-following model, a semantic rule system, and a speed and visibility model, wherein the current weather condition indicates an adverse weather condition impacting driving conditions for the vehicle, and wherein the probabilistic longitudinal velocity is determined by:
determining, by the car-following model, a velocity of the vehicle by calculating a first maximum velocity and a second maximum velocity;
selecting a minimum value between the first maximum velocity and the second maximum velocity;
determining, by the semantic rule system, a constrained velocity that limits the velocity of the vehicle determined by the car-following model based on a plurality of high-level rules, wherein the plurality of high-level rules limit the velocity of the vehicle determined by the car-following model based on one or more driving conditions that are created by a specific adverse weather condition indicated by the current weather condition; and
determining, by the speed and visibility model of the one or more controllers, the probabilistic longitudinal velocity of the vehicle with respect to the current weather condition by limiting the constrained velocity based on a visibility distance;
determine, by a probabilistic lateral driving model stored by the one or more controllers, one or more lane choices for the vehicle with respect to the current weather condition based on a route plan of the vehicle and perception data indicative of an environment surrounding the vehicle;
select a final lane choice from the one or more lane choices, wherein the final lane choice includes a maximum probability of being selected at the probabilistic longitudinal velocity when compared to remaining lane choices that are part of the one or more lane choices;
determine a next state of the vehicle based on the final lane choice and the probabilistic longitudinal velocity;
receive a road segment that is part of the route plan, wherein the road segment includes an intersection;
determine the vehicle is able to execute a maneuver at the intersection based on the perception data; and
in response to determining the vehicle is able to execute the maneuver, instruct the vehicle to execute the maneuver by assisting with steering, braking, and accelerating.
20 . The hybrid probabilistic driving behavior modeling system of claim 19 , wherein the probabilistic lateral driving model classifies a current road segment that is part of a road plan as including either a necessary lane change or a free lane change.