CN116001788A

CN116001788A - Car following method, electronic equipment, vehicle and storage medium

Info

Publication number: CN116001788A
Application number: CN202111227301.4A
Authority: CN
Inventors: 成成; 徐成; 张放; 李晓飞; 王肖; 张德兆; 霍舒豪
Original assignee: Dongfeng Motor Group Co Ltd; Beijing Idriverplus Technologies Co Ltd
Current assignee: Dongfeng Motor Group Co Ltd; Beijing Idriverplus Technologies Co Ltd
Priority date: 2021-10-21
Filing date: 2021-10-21
Publication date: 2023-04-25

Abstract

The invention provides a car following method, which comprises the following steps: judging the acceleration and deceleration state of the front vehicle; the acceleration and deceleration states include a uniform speed state, an acceleration state, and a deceleration state; when the acceleration and deceleration state is a uniform speed state, executing conventional vehicle following planning; when the acceleration and deceleration state is the acceleration state, executing conventional vehicle following planning for increasing the acceleration of the vehicle following; and when the acceleration and deceleration state is the deceleration state, executing the follow-up and stop programming, and then executing a re-programming mechanism. According to the vehicle following method provided by the invention, the acceleration and deceleration states of the front vehicle are estimated, and different track planning is carried out on the front vehicle according to the acceleration and deceleration states of the front vehicle, so that the robustness of the planning is improved.

Description

Car following method, electronic equipment, vehicle and storage medium

Technical Field

The invention relates to the technical field of automatic driving, in particular to a car following method, electronic equipment, a vehicle and a storage medium.

Background

The existing car following method is mainly based on the idea of traditional adaptive cruise control (Adaptive Cruise Control, ACC) control. The main principle of ACC control is that the relative position and speed of a target vehicle are obtained from a sensing unit on the vehicle, the current Headway (THW) is calculated, then the expected Headway set in a cruise speed and safety Headway model is compared to determine whether acceleration or deceleration is needed currently, a control module receives acceleration and deceleration information, the driving/braking torque is further determined, and finally the following is realized.

According to the following method based on the ACC control thought, only the instantaneous position and speed of the following front vehicle are considered, and the acceleration and deceleration state of the front vehicle is not considered, so that the problem that the deceleration time is delayed when the front vehicle decelerates at a large deceleration, and the acceleration following cannot be reflected in time when the front vehicle accelerates exists.

Disclosure of Invention

The invention provides a car following method, a car following system and a moving tool, which are used for solving the problems existing in the prior art when a car is to be followed.

To solve the above problems, a first aspect of the present invention provides a vehicle following method based on a front vehicle state estimation, including:

judging the acceleration and deceleration state of the front vehicle; the acceleration and deceleration states comprise a uniform speed state, an acceleration state and a deceleration state;

when the acceleration and deceleration state is a uniform state, executing conventional vehicle following planning;

when the acceleration and deceleration state is an acceleration state, executing conventional vehicle following planning for increasing the acceleration of the vehicle following;

and when the acceleration and deceleration state is a deceleration state, executing a re-programming mechanism after executing the follow-up programming.

In one possible implementation manner, the determining the acceleration and deceleration state of the preceding vehicle specifically includes:

acquiring the collision time and the following distance of the current vehicle; the collision time is the ratio of the distance of the front vehicle to the relative speed; the distance between the front vehicle and the self vehicle is the distance between the self vehicle and the front vehicle; the relative speed is the difference of the front vehicle speed minus the own vehicle speed; the following time distance is the ratio of the distance of the front vehicle to the speed of the own vehicle;

when the collision time is smaller than a preset first time threshold value and the following vehicle time is smaller than a preset first distance judgment threshold value, determining that the acceleration and deceleration state of the front vehicle is a deceleration state;

when the collision time is equal to a preset first time threshold value and the following vehicle time is equal to a preset first distance judgment threshold value, determining that the acceleration and deceleration state of the front vehicle is a uniform speed state;

and when the collision time is greater than a preset first time threshold value and the following vehicle time is greater than a preset first distance judgment threshold value, determining that the acceleration and deceleration state of the front vehicle is an acceleration state.

In one possible implementation manner, when the acceleration and deceleration state is a uniform speed state, performing conventional vehicle following planning specifically includes:

determining a first function according to the difference between the distance of the front vehicle and the first distance judgment threshold value;

determining a second function based on the relative velocity; the relative speed is the front vehicle speed minus the self-vehicle speed;

determining a desired acceleration of the vehicle according to the first function and the second function;

and carrying out conventional vehicle following planning according to the expected acceleration and the current vehicle speed to obtain a conventional vehicle following planning track.

In one possible implementation manner, when the acceleration state is an acceleration state, performing a conventional vehicle following plan for increasing the acceleration of the following vehicle specifically includes:

performing increasing processing on the expected acceleration to obtain the increased expected acceleration;

and continuing to conduct conventional vehicle following planning according to the expected acceleration and the current vehicle speed after the increase processing, so as to obtain a conventional vehicle following planning track.

In one possible implementation manner, when the acceleration and deceleration state is a deceleration state, executing the heel-and-toe plan specifically includes:

obtaining a sliding distance when the front vehicle is parked according to the speed of the front vehicle and the preset deceleration of the front vehicle;

calculating the following and stopping distance of the own vehicle according to the sliding distance, the safety distance and the front vehicle distance;

determining a starting point and a starting point speed of a follow-up and stop plan according to the current speed of the vehicle and the expected acceleration of the vehicle;

determining target deceleration of the own vehicle according to the following stopping distance of the own vehicle, the starting point and the starting point speed;

and performing heel-and-stop planning according to the target deceleration and the starting point to obtain a heel-and-stop planning track of the heel-and-stop planning.

In one possible implementation manner, the performing a re-planning mechanism specifically includes:

judging whether the difference value between the current heel-and-toe distance and the heel-and-toe distance at any moment before is larger than a preset difference value threshold value or not;

when the absolute value of the difference value between the current heel-and-toe distance and the heel-and-toe distance at any time before is smaller than a preset difference value threshold, the current heel-and-toe planning track is maintained;

and when the absolute value of the difference value between the current heel-and-toe distance and the heel-and-toe distance at any moment before is larger than a preset difference value threshold value, re-executing the heel-and-toe planning.

In one possible implementation manner, before performing the heel-and-toe planning, the method further includes:

when the collision time is smaller than a preset second time threshold and the following distance is smaller than a safety distance threshold, executing a following stop planning;

when the collision time is not less than a preset second time threshold and is greater than a preset third time threshold, and the following time is not less than a safety distance threshold and is greater than a preset second distance judgment threshold, entering a deceleration rapid countdown;

when the collision time is not smaller than a preset third time threshold and larger than a preset fourth time threshold, and the following time is not smaller than a preset second distance judgment threshold and larger than a preset third distance judgment threshold, entering a deceleration slow-down count-down;

and when the collision time is not smaller than a preset fourth time threshold and the following time interval is not smaller than a preset third distance judgment threshold, the vehicle is not decelerated.

A second aspect of the present invention provides a vehicle following apparatus based on a preceding vehicle state estimation, the apparatus comprising:

the judging module is used for judging the acceleration and deceleration state of the front vehicle; the acceleration and deceleration states comprise a uniform speed state, an acceleration state and a deceleration state;

the conventional car following planning module is used for executing conventional car following planning when the acceleration and deceleration state is a uniform state;

the conventional vehicle following planning module is used for executing conventional vehicle following planning for increasing the acceleration of the vehicle following when the acceleration and deceleration state is an acceleration state;

the heel-and-stop planning module is used for executing heel-and-stop planning when the acceleration and deceleration state is a deceleration state;

and the re-planning module is used for executing a re-planning mechanism after the heel-and-toe planning module executes the heel-and-toe planning.

A third aspect of the present invention provides a computer server comprising: memory, processor, and transceiver;

the processor is coupled with the memory, reads and executes the instructions in the memory to realize the following method based on the front car state estimation according to the first aspect;

the transceiver is coupled to the processor and is controlled by the processor to transmit and receive messages.

A fourth aspect of the invention provides a system on a chip comprising a processor coupled to a memory, the memory storing program instructions which, when executed by the processor, implement a method of following a vehicle based on a prior vehicle condition estimation as described in the first aspect.

A fourth aspect of the invention provides a computer system comprising a memory, and one or more processors communicatively coupled to the memory;

the memory stores instructions executable by the one or more processors to cause the one or more processors to implement the method of following a vehicle based on a prior vehicle state estimate as described in the first aspect.

A fifth aspect of the present invention provides a mobile tool comprising the computer server of the third aspect.

By applying the vehicle following method based on the front vehicle state estimation, the acceleration and deceleration state of the front vehicle is estimated, different track planning is carried out on the front vehicle according to the acceleration and deceleration state of the front vehicle, and the robustness of the planning is improved. Furthermore, when the state of the front vehicle is estimated, the statistical average value of the deceleration with three levels of emergency, non-emergency and general can be used as the front vehicle deceleration when the observation time period is not long enough, so that the following and stopping planning of the vehicle can be conveniently carried out. Furthermore, whether the own vehicle decelerates or not is judged in a counting mode, so that frequent triggering of switching between the following stop planning and the conventional following vehicle planning caused by sensing input fluctuation is avoided, and the robustness of planning is improved. Furthermore, the re-planning mechanism solves the problem of incorrect planning caused by overshoot of longitudinal control during follow-up planning, and reduces the safety risk caused by long-time non-re-planning.

Drawings

Fig. 1 is a schematic flow chart of a following method based on a front vehicle state estimation according to an embodiment of the invention;

FIG. 2 is a flowchart showing step 110 of FIG. 1;

FIG. 3 is a schematic diagram showing the judgment of the acceleration/deceleration state of the front vehicle;

FIG. 4 is a flowchart showing step 120 of FIG. 1;

FIG. 5 is a flowchart showing step 130 of FIG. 1;

FIG. 6 is a schematic diagram of conditions for entering deceleration of a host vehicle;

FIG. 7 is a flowchart for determining whether a host vehicle is performing a following stop plan;

FIG. 8 is a diagram of an obstacle distance curve fit;

FIG. 9 is a flowchart showing step 140 of FIG. 1;

FIG. 10 is a schematic diagram of a heel-and-toe plan;

FIG. 11 is a flowchart showing the re-planning mechanism of FIG. 1;

FIG. 12 is a detailed schematic of FIG. 11;

fig. 13 is a schematic diagram of a following device based on a front vehicle state estimation according to a second embodiment of the present invention;

fig. 14 is a schematic diagram of a second embodiment of a vehicle following device based on a front vehicle state estimation.

Detailed Description

The present application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.

It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Example 1

Fig. 1 is a schematic flow chart of a following method based on a front vehicle state estimation according to an embodiment of the present invention, where an execution body of the present application is a terminal, a server or a processor with a computing function. The application describes an example of applying the method to an unmanned vehicle running on an unstructured road, and when the method is applied to an unmanned vehicle, the execution subject of the method is an autonomous vehicle control unit (Automated Vehicle Control Unit, AVCU), i.e. the central processor of the unmanned vehicle corresponds to the "brain" of the unmanned vehicle. The method comprises the following steps:

step 110, judging the acceleration and deceleration state of the front vehicle.

The acceleration and deceleration states comprise a uniform speed state, an acceleration state and a deceleration state.

As shown in fig. 2, step 110 includes the steps of:

step 1101, obtaining the collision time and the following distance of the current vehicle; the collision time is the ratio of the distance of the front vehicle to the relative speed; the distance between the front vehicle and the self vehicle is the distance between the self vehicle and the front vehicle; the relative speed is the difference of the front vehicle speed minus the own vehicle speed; the following time distance is the ratio of the distance of the front vehicle to the speed of the own vehicle;

specifically, when the vehicle is driven, the change of the distance between the front vehicles is generally used as a judging standard of whether the front vehicles are accelerating or decelerating, so as to make corresponding actions of stepping on/loosening the throttle.

Wherein, the collision Time (Time to Collision, TTC) and the following Time (THW) of the current vehicle can be used as the judging standard of the acceleration and deceleration states of the front vehicle. TTC is defined herein as the distance to front vehicle/relative speed, THW is defined as the distance to front vehicle/speed of the vehicle, i.e.:

wherein t is _ttc For the collision time, t _thw For following the vehicle, d _obs For the distance between the front vehicles, i.e. the distance between the own vehicle and the front vehicle, the calculation can be performed according to the position of the own vehicle and the position of the front vehicle, v _obs The speed v is the speed of the vehicle.

Step 1102, determining that the acceleration/deceleration state of the preceding vehicle is a deceleration state when the collision time is smaller than a preset first time threshold and the following vehicle distance is smaller than a preset first distance judgment threshold;

obtaining a preset first distance judgment threshold value from an ideal following distance model assuming a constant speed of a front vehicle:

wherein,,

a is a preset first distance judgment threshold value, a ^* For the magnitude of deceleration required when the set own vehicle is decelerating to the speed of the preceding vehicle, +.>

For the set following time interval +.>

Is a set safe distance;

Is a preset first time threshold.

Referring to fig. 3, when the front vehicle following state is in the dark area, that is, the collision time is less than the preset first time threshold, and the vehicle following distance is less than the preset first distance judgment threshold, it is indicated that the front vehicle is in a deceleration state.

Step 1103, when the collision time is equal to a preset first time threshold and the following vehicle distance is equal to a preset first distance judgment threshold, determining that the acceleration and deceleration state of the preceding vehicle is a uniform speed state;

with continued reference to fig. 3, when the collision time is equal to a preset first time threshold and the following distance is equal to a preset first distance judgment threshold, it is determined that the acceleration and deceleration state of the preceding vehicle is a uniform speed state.

Step 1104, when the collision time is greater than a preset first time threshold and the following distance is greater than a preset first distance judgment threshold, determining that the acceleration and deceleration state of the preceding vehicle is an acceleration state.

With continued reference to fig. 3, when the collision time is greater than a preset first time threshold and the following distance is greater than a preset first distance judgment threshold, determining that the acceleration/deceleration state of the preceding vehicle is an acceleration state.

Step 120, when the acceleration and deceleration state is a uniform speed state, executing conventional following planning;

referring to fig. 4, by way of example and not limitation, step 120 may include the steps of:

step 1201, determining a first function according to the difference between the distance of the front vehicle and the first distance judgment threshold;

specifically, the distance and relative speed of the front vehicle are two important indicators of the following vehicle, which determine the desired acceleration of the vehicle while following the vehicle. And the conventional vehicle following planning plans out a track in the current state according to the expected acceleration and the current actual vehicle speed, and outputs the track to the control module.

The calculation of the desired acceleration may include two parts, the first part being a first part where a first function is calculated with respect to the preceding vehicle distance and a first distance determination threshold, see the following formula:

wherein a is the expected acceleration,

determining a threshold value for a first distance d _obs Is the distance of the front vehicle.

Some empirical values can be determined by means of a large number of real vehicle tests, and then the final functional form is determined by approximating the real vehicle test data by means of a functional fit. For example, g may be the first evaluation function, and may be any one of an arctangent function, an exponential function, and a coefficient adjustment function.

Step 1202, determining a second function according to the relative speed; the relative speed is the front vehicle speed minus the self-vehicle speed;

with continued reference to the second portion of the above formula, f may be a second function, which may be a polynomial function, the specific order is not limited.

Step 1203, determining the expected acceleration of the bicycle according to the first function and the second function;

wherein, the expected acceleration of the bicycle can be further determined according to the determined first function and the determined second function.

And step 1204, performing conventional vehicle following planning according to the expected acceleration and the current vehicle speed to obtain a conventional vehicle following planning track.

It will be appreciated that the calculation of the desired acceleration may be implemented here as well by means of dynamic planning based on displacement-time images (ST), which is not limited in this application.

Step 130, executing a conventional following plan for increasing the following acceleration when the acceleration and deceleration state is an acceleration state;

specifically, referring to fig. 5, step 130 specifically includes the steps of:

step 1301, performing an increase process on the expected acceleration to obtain an increased expected acceleration;

specifically, when the front vehicle is judged to be accelerating, the acceleration of the current vehicle following is increased, and the conventional vehicle following planning is continuously executed. The present application is not limited to this, and the experience value may be set according to actual experience.

And 1302, continuing to perform conventional vehicle following planning according to the increased expected acceleration and the current vehicle speed to obtain a conventional vehicle following planning track.

And 140, executing a re-programming mechanism after executing the heel-and-toe-off programming when the acceleration and deceleration state is the deceleration state.

Specifically, when the preceding vehicle is judged to be in a deceleration state, the own vehicle executes a following stop planning. When performing a follow-up planning, it is often desirable that the deceleration of the planned trajectory fluctuates less, and therefore, adjustments may be made by a re-planning mechanism to ensure that the deceleration of the planned follow-up planned trajectory fluctuates less.

When the front vehicle is judged to be decelerated, the own vehicle also needs to be decelerated, but in order to avoid fluctuation of the perception data, frequent change of the acceleration and deceleration state of the front vehicle is judged, and whether the own vehicle needs to be decelerated or not can be determined by a similar counting method. Each value in the count is an empirical value obtained by multiple experiments, and the condition of entering the deceleration can be intuitively seen from fig. 6, the closer the current state is to the dark area, the faster the own vehicle will enter the deceleration logic, and the easier the following planning is switched to the following stopping planning.

Specifically, in connection with fig. 6 and 7, it may be determined whether the own vehicle performs the following stop planning by the following steps.

Step 150, executing a heel-and-toe plan when the collision time is smaller than a preset second time threshold and the heel-and-toe distance is smaller than a safety distance threshold;

wherein the second time threshold is t _min A safe distance threshold value of d _safe . Second time threshold t _min And a safety distance threshold d _safe Are empirical values obtained from multiple experiments.

Step 160, entering a deceleration rapid countdown when the collision time is not less than a preset second time threshold and is greater than a preset third time threshold, and the following time distance is not less than a safety distance threshold and is greater than a preset second distance judgment threshold;

wherein the third time threshold is

The second distance judgment threshold is->

Third time threshold->

And a second distance judgment threshold->

Are empirical values obtained from multiple experiments.

Step 170, when the collision time is not less than a preset third time threshold and is greater than a preset fourth time threshold, and the following time is not less than a preset second distance judgment threshold and is greater than a preset third distance judgment threshold, entering a deceleration slow countdown;

wherein the fourth time threshold is

The third distance judgment threshold is->

Fourth time threshold->

And a third distance judgment threshold value of +.>

Are empirical values obtained from multiple experiments.

Step 180, when the collision time is not less than a preset fourth time threshold and the following time is not less than a preset third distance judgment threshold, the own vehicle is not decelerated.

After determining that the own vehicle is decelerating immediately, a description is given of how to perform a following stop planning.

When the front vehicle is in a deceleration state, the self vehicle also needs to be decelerated, and is limited by constraints of sensor characteristics, algorithm performance and timeliness, the perception fusion can only provide relatively accurate obstacle position and speed information, but acceleration estimation on the obstacle is often inaccurate. Since the acceleration is the derivative of the velocity, the fluctuation of the velocity can increase the fluctuation of the calculated acceleration information, and one method for solving the acceleration of the obstacle without adopting a differential mode is to perform least square fitting on the accumulated distance travelled by the obstacle, wherein the coefficient of the quadratic term is the acceleration of the obstacle. However, the curve fitting mode can be used for fitting a better result only when the observation time is long enough and the accumulated distance data are large enough, and the obtained acceleration is accurate enough. As shown in fig. 8.

When the distance between the front vehicle and the vehicle is rapidly approaching due to the deceleration of the front vehicle during the following process, the deceleration of the front vehicle can be set as the statistical average value a of the deceleration of the general vehicle during the deceleration _obs The method is used for following stop planning at the back, solves the problem of inaccurate acceleration calculation caused by insufficient observation time, and ensures that the own vehicle can quickly make a deceleration action following the front vehicle so as to ensure safety.

Further, as shown in fig. 9, when the acceleration/deceleration state is the deceleration state in the step 140, performing the heel-and-toe planning specifically includes:

step 1401, obtaining a sliding distance when the front vehicle is parked according to the front vehicle speed and the preset front vehicle deceleration;

specifically, it is assumed that the preceding vehicle follows a statistical average a of deceleration _obs And decelerating until the sliding distance during parking is as follows:

wherein s is _obs V is the sliding distance _obs A is the speed of the front vehicle _obs The preset front vehicle deceleration is the statistical average value of the deceleration.

Step 1402, calculating the following stopping distance of the own vehicle according to the sliding distance, the safety distance and the front vehicle distance;

in particular, the safety distance behind the front car is needed by the own car

The vehicle must stop at the outside, and the planned track can drive the vehicle at the farthest _stop Parking after a distance that satisfies the following constraints:

wherein s is _stop Is the following and stopping distance of the bicycle, d _obs For the distance of the front car,

is a set safe distance.

Step 1403, determining a starting point and a starting point speed of the following-stop plan according to the current speed of the vehicle and the expected acceleration of the vehicle;

specifically, considering the response time dt of the control module and the bottom layer, calculating the point after the dt time according to the speed and the acceleration of the current vehicle as a planning starting point at the current moment T _match The planning result of the previous frame is maintained within the following dt time, as shown in fig. 10.

Planning s that the starting point should be in front of the current position of the vehicle _start At the position, its corresponding speed is v _start The method comprises the following steps:

υ _start ＝υ+a·dt

wherein sstart is the distance between the current position of the vehicle and the starting point of the stop plan, v is the current vehicle speed, a is the current vehicle acceleration, v _start Is the onset speed.

Step 1404, determining a target deceleration of the own vehicle according to the following distance of the own vehicle, the starting point and the starting point speed;

specifically, the deceleration distance zone of the own vehicle is (s _stop -s _start ) The planned target deceleration is:

wherein alpha is _target Is the target deceleration of the own vehicle.

And step 1405, performing a heel-and-toe planning according to the target deceleration and the starting point to obtain a heel-and-toe planning track of the heel-and-toe planning.

Specifically, according to the target deceleration and the planned starting point, a final following-stop planning track can be determined, and the following-stop planning speed at any time t in the following-stop planning time is as follows:

wherein v is _t，last The speed corresponding to time t in the track planned for the previous frame. Therefore, the following stop planning speed of the own vehicle during the following stop can be planned and obtained.

Further, as shown in fig. 11, the re-planning mechanism in the execution step 140 specifically includes:

step 1406, judging whether the difference between the current stopping distance and the stopping distance at any previous moment is greater than a preset difference threshold;

as shown in FIG. 12, the current stopping and following distance may be s _stop1 The following stopping distance at any moment is s _stop2 The preset difference value threshold is as follows

Step 1407, when the difference between the current heel-and-toe distance and the heel-and-toe distance at any time before is smaller than a preset difference threshold, maintaining the current heel-and-toe planning track;

in step 1408, when the difference between the current heel-and-toe distance and the previous heel-and-toe distance is greater than the preset difference threshold, the heel-and-toe planning is re-executed.

Therefore, through a re-planning mechanism, the incorrect planning caused by the overshoot of the longitudinal control during the follow-up planning is solved, and the safety risk caused by long-time non-re-planning is also solved.

Example two

Fig. 13 is a schematic structural diagram of a following device based on a front vehicle state estimation according to a second embodiment of the present invention, where, as shown in fig. 13, the device includes: the system comprises a judging module 210, a conventional following planning module 220, a conventional following planning module 230 for increasing the following speed, a following stop planning module 240 and a re-planning module 250.

The judging module 210 is configured to judge an acceleration/deceleration state of a preceding vehicle; the acceleration and deceleration states comprise a uniform speed state, an acceleration state and a deceleration state;

the conventional following planning module 220 is configured to execute conventional following planning when the acceleration and deceleration state is a uniform state;

the conventional following schedule module 230 for increasing the following speed is configured to perform conventional following schedule for increasing the acceleration of the following vehicle when the acceleration/deceleration state is an acceleration state;

the heel-and-toe planning module 240 is configured to execute heel-and-toe planning when the acceleration and deceleration state is a deceleration state;

the re-planning module 250 is configured to execute a re-planning mechanism after the heel-and-toe planning module executes the heel-and-toe planning.

Further, the judging module 210 specifically performs: acquiring the collision time and the following distance of the current vehicle; the collision time is the ratio of the distance of the front vehicle to the relative speed; the distance between the front vehicle and the self vehicle is the distance between the self vehicle and the front vehicle; the relative speed is the difference of the front vehicle speed minus the own vehicle speed; the following time distance is the ratio of the distance of the front vehicle to the speed of the own vehicle; when the collision time is smaller than a preset first time threshold value and the following vehicle time is smaller than a preset first distance judgment threshold value, determining that the acceleration and deceleration state of the front vehicle is a deceleration state; when the collision time is equal to a preset first time threshold value and the following vehicle time is equal to a preset first distance judgment threshold value, determining that the acceleration and deceleration state of the front vehicle is a uniform speed state; and when the collision time is greater than a preset first time threshold value and the following vehicle time is greater than a preset first distance judgment threshold value, determining that the acceleration and deceleration state of the front vehicle is an acceleration state.

The conventional following plan module 220 specifically performs: determining a first function according to the difference between the distance of the front vehicle and the first distance judgment threshold value; determining a second function based on the relative velocity; the relative speed is the front vehicle speed minus the self-vehicle speed; determining a desired acceleration of the vehicle according to the first function and the second function; and carrying out conventional vehicle following planning according to the expected acceleration and the current vehicle speed to obtain a conventional vehicle following planning track.

The conventional following schedule module 230 for increasing the following speed specifically performs: performing increasing processing on the expected acceleration to obtain the increased expected acceleration; and continuing to conduct conventional vehicle following planning according to the expected acceleration and the current vehicle speed after the increase processing, so as to obtain a conventional vehicle following planning track.

The keep-alive planning module 240 specifically performs: obtaining a sliding distance when the front vehicle is parked according to the speed of the front vehicle and the preset deceleration of the front vehicle; calculating the following and stopping distance of the own vehicle according to the sliding distance, the safety distance and the front vehicle distance; determining a starting point and a starting point speed of a follow-up and stop plan according to the current speed of the vehicle and the expected acceleration of the vehicle; determining target deceleration of the own vehicle according to the following stopping distance of the own vehicle, the starting point and the starting point speed; and performing heel-and-stop planning according to the target deceleration and the starting point to obtain a heel-and-stop planning track of the heel-and-stop planning.

The re-planning module 250 specifically performs: judging whether the difference value between the current heel-and-toe distance and the heel-and-toe distance at any moment before is larger than a preset difference value threshold value or not; when the absolute value of the difference value between the current heel-and-toe distance and the heel-and-toe distance at any time before is smaller than a preset difference value threshold, the current heel-and-toe planning track is maintained; and when the absolute value of the difference value between the current heel-and-toe distance and the heel-and-toe distance at any moment before is larger than a preset difference value threshold value, re-executing the heel-and-toe planning.

In an alternative implementation, before the following stop planning module 240, a vehicle deceleration judging module 260 is further included, referring to fig. 14, where the vehicle deceleration judging module 260 specifically performs: when the collision time is smaller than a preset second time threshold and the following distance is smaller than a safety distance threshold, executing a following stop planning; when the collision time is not less than a preset second time threshold and is greater than a preset third time threshold, and the following time is not less than a safety distance threshold and is greater than a preset second distance judgment threshold, entering a deceleration rapid countdown; when the collision time is not smaller than a preset third time threshold and larger than a preset fourth time threshold, and the following time is not smaller than a preset second distance judgment threshold and larger than a preset third distance judgment threshold, entering a deceleration slow-down count-down; and when the collision time is not smaller than a preset fourth time threshold and the following time interval is not smaller than a preset third distance judgment threshold, the vehicle is not decelerated.

Example III

The third embodiment of the invention provides a chip system, which comprises a processor, wherein the processor is coupled with a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, any one of the following methods based on the front vehicle state estimation provided in the first embodiment is realized.

Example IV

A fourth embodiment of the present invention provides a computer server, including: memory, processor, and transceiver;

the processor is coupled to the memory, reads and executes the instructions in the memory, so as to implement any one of the following methods based on the estimation of the state of the front vehicle provided in the first embodiment;

the transceiver is coupled to the processor, and the processor controls the transceiver to transmit and receive messages.

Example five

A fifth embodiment of the present invention provides a computer readable storage medium including a program or instructions, which when executed on a computer, implement any one of the following methods based on a preceding vehicle state estimation provided in the first embodiment.

Example six

A sixth embodiment provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform any one of the following methods based on a preceding vehicle state estimation as provided in the first embodiment.

Example seven

The seventh embodiment of the invention provides a mobile tool, which comprises the computer server.

The moving means may be any means that can be moved, such as vehicles (e.g., dust trucks, sweeper, floor wash, logistics trolley, passenger car, sanitation car, buses, vans, trucks, loaders, trailers, dump trucks, cranes, excavators, shovels, road trains, road sweeper, sprinkler, garbage truck, engineering truck, rescue car, AGVs (Automated Guided Vehicle, automated guided vehicles), etc.), motorcycles, bicycles, tricycles, carts, robots, road sweeper, balance cars, etc., the type of moving means is not strictly limited herein and is not exhaustive.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of function in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The foregoing detailed description of the invention has been presented for purposes of illustration and description, and it should be understood that the invention is not limited to the particular embodiments disclosed, but is intended to cover all modifications, equivalents, alternatives, and improvements within the spirit and principles of the invention.

Claims

1. A method for following a vehicle based on a front vehicle state estimation, the method comprising:

2. The method according to claim 1, wherein the determining the acceleration/deceleration state of the preceding vehicle specifically includes:

3. The method according to claim 1, wherein when the acceleration and deceleration state is a constant velocity state, performing a conventional follow-up plan specifically includes:

4. A method according to claim 3, wherein said performing a conventional follow-up plan that increases the acceleration of the following vehicle when said acceleration and deceleration state is an acceleration state comprises:

5. The method according to claim 2, wherein when the acceleration and deceleration state is a deceleration state, performing a heel-and-toe plan specifically includes:

6. The method according to claim 5, wherein the performing a re-planning mechanism specifically comprises:

7. The method of claim 5, wherein prior to performing a heel-and-toe plan further comprises:

8. A vehicle following apparatus based on a front vehicle state estimation, the apparatus comprising:

9. A computer server, comprising: memory, processor, and transceiver;

the processor is coupled to the memory, and reads and executes the instructions in the memory to implement the method for following a vehicle based on a prior vehicle state estimation as claimed in any one of claims 1 to 7;

10. A system on a chip comprising a processor coupled to a memory, the memory storing program instructions that when executed by the processor implement the method of tracking based on a prior vehicle condition estimation of any one of claims 1-7.

11. A computer system comprising a memory, and one or more processors communicatively coupled to the memory;

stored in the memory are instructions executable by the one or more processors to cause the one or more processors to implement the method of tracking based on a prior vehicle state estimate as recited in any one of claims 1-7.

12. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program for executing the following method based on the preceding vehicle state estimation according to any one of claims 1-7 by a processor.

13. A mobile tool comprising the computer server of claim 9.