Granted Patent B2

US 12,630,182 · App. 18/090,743 · Granted May 19, 2026

Inventors: Qiyu Liu (Beijing, CN); Zhongpu Xia (Beijing, CN)

Assignee: Apollo Intelligent Driving Technology (Beijing) Co., Ltd.

B60W60/0011B60W30/09B60W30/0956B60W30/18159B60W2552/53B60W2554/4041B60W2554/4044B60W2554/80

Abstract

Claims (80)

1 . A method for automatic driving at an intersection, comprising:

determining a first initial convergence location information between an obstacle and a vehicle, a current location information of the obstacle, and an orientation information of the obstacle;

determining a target convergence location information between the obstacle and the vehicle according to the first initial convergence location information, the current location information of the obstacle and the orientation information of the obstacle;

determining a target travelling plan from a plurality of candidate travelling plans for the vehicle according to the target convergence location information and a current travelling parameter of the obstacle; and

controlling the automatic driving of the vehicle according to the target travelling plan,

wherein the determining a target travelling plan from a plurality of candidate travelling plans for the vehicle according to the target convergence location information and a current travelling parameter of the obstacle comprises:

determining, for each candidate travelling plan of the plurality of candidate travelling plans, an expected travelling parameter required for the obstacle to avoid a collision with the vehicle as an expected travelling parameter corresponding to the candidate travelling plan, according to the target convergence location information;

in response to a determination that the current travelling parameter of the obstacle and the expected travelling parameter do not meet a predetermined condition, removing, from the plurality of candidate travelling plans, a candidate travelling plan corresponding to the expected travelling parameter, so as to obtain a plurality of remaining candidate travelling plans; and

determining the target travelling plan from the plurality of remaining candidate travelling plans,

wherein the determining an expected travelling parameter required for the obstacle to avoid a collision with the vehicle according to the target convergence location information comprises:

determining an expected acceleration of the obstacle according to a time length required for the vehicle to travel to the target convergence location information, a current speed of the obstacle, and a traveling distance information required for the obstacle to travel to the target convergence location information, and

wherein the predetermined condition comprises:

meeting a first predetermined expression in response to a determination that the obstacle avoids the vehicle; or

meeting a second predetermined expression in response to a determination that the obstacle does not avoid the vehicle,

wherein the first predetermined expression is: thw obs_t1 −thw adc_t1 <thw obs_t2 −thw adc_t2 , the second predetermined expression is: thw obs_t1 −thw adc_t1 >thw obs_t2 −thw adc_t2 , thw obs_t1 represents a ratio of a travelling distance to a travelling speed of the obstacle from a first time instant to the target convergence location, thw adc_t1 represents a ratio of a travelling distance to a travelling speed of the vehicle from the first time instant to the target convergence location, thw obs_t2 represents a ratio of a travelling distance to a travelling speed of the obstacle from a second time instant to the target convergence location, thw adc_t2 represents a ratio of a travelling distance to a travelling speed of the vehicle from the second time instant to the target convergence location, and the first time instant is before the second time instant.

2 . The method according to claim 1 , wherein the determining a target convergence location information between the obstacle and the vehicle according to the first initial convergence location information, the current location information of the obstacle and the orientation information of the obstacle comprises:

determining a second initial convergence location information according to the current location information of the obstacle, a current orientation information of the obstacle and an angular speed of the obstacle; and

determining the target convergence location information according to the first initial convergence location information and the second initial convergence location information.

3 . The method according to claim 2 , wherein the determining the target convergence location information according to the first initial convergence location information and the second initial convergence location information comprises:

determining a probability distribution according to the first initial convergence location information and the second initial convergence location information, wherein the probability distribution indicates a correspondence between a candidate convergence location information and a probability; and

determining the target convergence location information according to a mean value of the probability distribution.

4 . The method according to claim 3 , wherein the determining the target convergence location information according to a mean value of the probability distribution comprises:

determining an intersection point of lanes according to an information of a lane where the obstacle is located and an information of a lane where the vehicle is located;

determining at least one candidate convergence location information in response to a determination that a distance between a candidate convergence location information corresponding to the mean value of the probability distribution and the intersection point of the lanes is greater than or equal to a distance threshold, wherein a distance between the at least one candidate convergence location information and the intersection point of the lanes is less than or equal to the distance threshold; and

determining the target convergence location information from the at least one candidate convergence location information according to the probability distribution.

5 . The method according to claim 1 , wherein the determining the target travelling plan from the plurality of remaining candidate travelling plans comprises:

determining, for each candidate travelling plan of the plurality of remaining candidate travelling plans, an evaluation value according to the expected travelling parameter of the obstacle corresponding to the candidate travelling plan, so as to obtain a plurality of evaluation values for the plurality of remaining candidate travelling plans; and

determining the target travelling plan from the plurality of remaining candidate travelling plans according to the plurality of evaluation values.

6 . The method according to claim 1 , wherein the predetermined condition further comprises that:

a maximum value of the expected acceleration of the obstacle is less than or equal to a difference between a current acceleration of the obstacle and an acceleration threshold, in response to a determination that the obstacle avoids the vehicle; or

a minimum value of the expected acceleration of the obstacle is greater than or equal to a sum of the current acceleration of the obstacle and the acceleration threshold, in response to a determination that the obstacle does not avoid the vehicle.

7 . An electronic device, comprising:

at least one processor; and

a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, are configured to cause the at least one processor to at least:

determine a first initial convergence location information between an obstacle and a vehicle, a current location information of the obstacle, and an orientation information of the obstacle;

determine a target convergence location information between the obstacle and the vehicle according to the first initial convergence location information, the current location information of the obstacle and the orientation information of the obstacle;

determine a target travelling plan from a plurality of candidate travelling plans for the vehicle according to the target convergence location information and a current travelling parameter of the obstacle; and

control the automatic driving of the vehicle according to the target travelling plan,

wherein the instructions are further configured to cause the at least one processor to at least:

determine, for each candidate travelling plan of the plurality of candidate travelling plans, an expected travelling parameter required for the obstacle to avoid a collision with the vehicle as an expected travelling parameter corresponding to the candidate travelling plan, according to the target convergence location information;

in response to a determination that the current travelling parameter of the obstacle and the expected travelling parameter do not meet a predetermined condition, remove, from the plurality of candidate travelling plans, a candidate travelling plan corresponding to the expected travelling parameter, so as to obtain a plurality of remaining candidate travelling plans; and

determine the target travelling plan from the plurality of remaining candidate travelling plans,

wherein the instructions are further configured to cause the at least one processor to at least:

determine an expected acceleration of the obstacle according to a time length required for the vehicle to travel to the target convergence location information, a current speed of the obstacle, and a traveling distance information required for the obstacle to travel to the target convergence location information, and

wherein the predetermined condition comprises:

meeting a first predetermined expression in response to a determination that the obstacle avoids the vehicle; or

meeting a second predetermined expression in response to a determination that the obstacle does not avoid the vehicle,

wherein the first predetermined expression is: thw obs_t1 −thw adc_t1 <thw obs_t2 −thw adc_t2 , the second predetermined expression is: thw obs_t1 −thw adc_t1 >thw obs_t2 −thw adc_t2 , thw obs_t1 represents a ratio of a travelling distance to a travelling speed of the obstacle from a first time instant to the target convergence location, thw adc_t1 represents a ratio of a travelling distance to a travelling speed of the vehicle from the first time instant to the target convergence location, thw obs_t2 represents a ratio of a travelling distance to a travelling speed of the obstacle from a second time instant to the target convergence location, thw adc_t2 represents a ratio of a travelling distance to a travelling speed of the vehicle from the second time instant to the target convergence location, and the first time instant is before the second time instant.

8 . The electronic device according to claim 7 , wherein the instructions are further configured to cause the at least one processor to at least:

determine a second initial convergence location information according to the current location information of the obstacle, a current orientation information of the obstacle and an angular speed of the obstacle; and

determine the target convergence location information according to the first initial convergence location information and the second initial convergence location information.

9 . The electronic device according to claim 8 , wherein the instructions are further configured to cause the at least one processor to at least:

determine a probability distribution according to the first initial convergence location information and the second initial convergence location information, wherein the probability distribution indicates a correspondence between a candidate convergence location information and a probability; and

determine the target convergence location information according to a mean value of the probability distribution.

10 . The electronic device according to claim 9 , wherein the instructions are further configured to cause the at least one processor to at least:

determine an intersection point of lanes according to an information of a lane where the obstacle is located and an information of a lane where the vehicle is located;

determine at least one candidate convergence location information in response to a determination that a distance between a candidate convergence location information corresponding to the mean value of the probability distribution and the intersection point of the lanes is greater than or equal to a distance threshold, wherein a distance between the at least one candidate convergence location information and the intersection point of the lanes is less than or equal to the distance threshold; and

determine the target convergence location information from the at least one candidate convergence location information according to the probability distribution.

11 . The electronic device according to claim 7 , wherein the instructions are further configured to cause the at least one processor to at least:

determine, for each candidate travelling plan of the plurality of remaining candidate travelling plans, an evaluation value according to the expected travelling parameter of the obstacle corresponding to the candidate travelling plan, so as to obtain a plurality of evaluation values for the plurality of remaining candidate travelling plans; and

determine the target travelling plan from the plurality of remaining candidate travelling plans according to the plurality of evaluation values.

12 . The electronic device according to claim 7 , wherein the predetermined condition further comprises that:

a maximum value of the expected acceleration of the obstacle is less than or equal to a difference between a current acceleration of the obstacle and an acceleration threshold, in response to a determination that the obstacle avoids the vehicle; or

a minimum value of the expected acceleration of the obstacle is greater than or equal to a sum of the current acceleration of the obstacle and the acceleration threshold, in response to a determination that the obstacle does not avoid the vehicle.

13 . An automatic driving vehicle, comprising the electronic device according to claim 7 .

14 . A non-transitory computer-readable storage medium having computer instructions therein, wherein the computer instructions are configured to cause a computer system to at least:

determine a first initial convergence location information between an obstacle and a vehicle, a current location information of the obstacle, and an orientation information of the obstacle;

determine a target convergence location information between the obstacle and the vehicle according to the first initial convergence location information, the current location information of the obstacle and the orientation information of the obstacle;

determine a target travelling plan from a plurality of candidate travelling plans for the vehicle according to the target convergence location information and a current travelling parameter of the obstacle; and

control the automatic driving of the vehicle according to the target travelling plan,

wherein the computer instructions are further configured to cause the computer system to at least:

determine, for each candidate travelling plan of the plurality of candidate travelling plans, an expected travelling parameter required for the obstacle to avoid a collision with the vehicle as an expected travelling parameter corresponding to the candidate travelling plan, according to the target convergence location information;

in response to a determination that the current travelling parameter of the obstacle and the expected travelling parameter do not meet a predetermined condition, remove, from the plurality of candidate travelling plans, a candidate travelling plan corresponding to the expected travelling parameter, so as to obtain a plurality of remaining candidate travelling plans; and

determine the target travelling plan from the plurality of remaining candidate travelling plans,

wherein the computer instructions are further configured to cause the computer system to at least:

determine an expected acceleration of the obstacle according to a time length required for the vehicle to travel to the target convergence location information, a current speed of the obstacle, and a traveling distance information required for the obstacle to travel to the target convergence location information, and

wherein the predetermined condition comprises:

meeting a first predetermined expression in response to a determination that the obstacle avoids the vehicle; or

meeting a second predetermined expression in response to a determination that the obstacle does not avoid the vehicle,

wherein the first predetermined expression is: thw obs_t1 −thw adc_t1 <thw obs_t2 −thw adc_t2 , the second predetermined expression is: thw obs_t1 −thw adc_t1 >thw obs_t2 −thw adc_t2 , thw obs_t1 represents a ratio of a travelling distance to a travelling speed of the obstacle from a first time instant to the target convergence location, thw adc_t1 represents a ratio of a travelling distance to a travelling speed of the vehicle from the first time instant to the target convergence location, thw obs_t2 represents a ratio of a travelling distance to a travelling speed of the obstacle from a second time instant to the target convergence location, thw adc_t2 represents a ratio of a travelling distance to a travelling speed of the vehicle from the second time instant to the target convergence location, and the first time instant is before the second time instant.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (23)