Vehicle avoidance method, device, equipment and storage medium

Abstract

The present invention belongs to the field of autonomous driving technology, and discloses a vehicle avoidance method, device, equipment and storage medium. The method comprises: when a first target vehicle is detected, obtaining first motion information of the first target vehicle; screening associated vehicles according to the motion information of the first target vehicle; predicting the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result; and controlling the current vehicle to travel according to the prediction result. Through the above scheme, the potential lane change danger is predicted, and the safety of vehicle travel is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a vehicle avoidance method, device, equipment and storage medium. Background Art

[0002] At present, autonomous vehicles lack effective measures for targets that cut in quickly at close range or targets whose trajectory changes suddenly. Some vehicles use methods such as adding cameras and lidar to detect targets, but it is very difficult to determine whether the target will interfere with the driving of the vehicle in the early stage of an emergency. Often, when the target reaches the dangerous posture set by the system, the impact is unavoidable.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a vehicle avoidance method, device, equipment and storage medium, aiming to solve the technical problem that the existing technology cannot cope with sudden driving situations.

[0005] To achieve the above object, the present invention provides a vehicle avoidance method, the method comprising the following steps:

[0006] When a first target vehicle is detected, first motion information of the first target vehicle is acquired;

[0007] Filtering related vehicles according to the movement information of the first target vehicle;

[0008] Predicting the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result;

[0009] Control the current vehicle driving according to the prediction results.

[0010] Optionally, the screening of associated vehicles according to the movement information of the first target vehicle includes:

[0011] Determine a candidate vehicle based on the motion information of the first target vehicle;

[0012] Obtaining third motion information of the candidate vehicle;

[0013] determining a lane change risk of the candidate vehicle according to the third motion information and the first motion information;

[0014] When the lane change risk is an imminent lane change, the candidate vehicle is determined as an associated vehicle.

[0015] Optionally, determining the lane change risk of the candidate vehicle according to the third motion information and the first motion information includes:

[0016] Determine first speed information and first lane information of a first target vehicle according to the first motion information;

[0017] Determine third speed information and third lane information of the candidate vehicle according to the third motion information;

[0018] The first speed information, the first lane information, the third speed information, and the third lane information determine the collision risk between the first target vehicle and the candidate vehicle;

[0019] When the collision risk is that there is a collision risk, it is determined that the lane change risk of the candidate vehicle is about to change lanes.

[0020] Optionally, performing trajectory prediction on the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result includes:

[0021] Determine first speed information and first lane information of a first target vehicle according to the first motion information;

[0022] Determine second speed information and second lane information of the associated vehicle according to the second motion information;

[0023] predicting a target lane for the associated vehicle based on the first lane information and the second lane information;

[0024] predicting a vehicle speed of the associated vehicle after lane change according to the first speed information and the second speed information;

[0025] The prediction result is determined according to the target lane and the vehicle speed after the lane change.

[0026] Optionally, predicting the vehicle speed of the associated vehicle after lane change according to the first speed information and the second speed information includes:

[0027] Get current road information;

[0028] The vehicle speed of the associated vehicle after the lane change is predicted according to the current road information, the first speed information and the second speed information.

[0029] Optionally, controlling the current vehicle driving according to the prediction result includes:

[0030] Obtain the fourth motion information of the current vehicle;

[0031] Determining a current vehicle collision risk according to the fourth motion information and the prediction result;

[0032] When the current vehicle collision risk is that there is a collision risk, the current vehicle is controlled to avoid the collision according to the prediction result and the fourth motion information.

[0033] Optionally, when the current vehicle collision risk is a collision risk, controlling the current vehicle to avoid the collision according to the prediction result and the fourth motion information includes:

[0034] determining a current required braking speed of the vehicle according to the fourth motion information and the prediction information;

[0035] When the required braking speed is greater than the preset deceleration, detecting adjacent lane information;

[0036] The current vehicle is controlled to avoid according to the adjacent lane information.

[0037] In addition, to achieve the above-mentioned purpose, the present invention further provides a vehicle avoidance device, the vehicle avoidance device comprising:

[0038] A processing module, configured to obtain first motion information of the first target vehicle when the first target vehicle is detected;

[0039] The processing module is further used to filter associated vehicles according to the motion information of the first target vehicle;

[0040] The processing module is further used to predict the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result;

[0041] The control module is used to control the current vehicle driving according to the prediction results.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a vehicle avoidance device, which includes: a memory, a processor, and a vehicle avoidance program stored in the memory and executable on the processor, and the vehicle avoidance program is configured to implement the steps of the vehicle avoidance method described above.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a vehicle avoidance program is stored, and when the vehicle avoidance program is executed by a processor, the steps of the vehicle avoidance method described above are implemented.

[0044] When the first target vehicle is detected, the present invention obtains the first motion information of the first target vehicle; selects the associated vehicle according to the motion information of the first target vehicle; predicts the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result; and controls the driving of the current vehicle according to the prediction result. Through the above scheme, the potential lane change danger is predicted and the safety of vehicle driving is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1It is a structural diagram of a vehicle avoidance device in a hardware operating environment involved in an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of a flow chart of a first embodiment of a vehicle avoidance method of the present invention;

[0047] Figure 3 A schematic diagram of a vehicle according to an embodiment of a vehicle avoidance method of the present invention;

[0048] Figure 4 A schematic diagram of a vehicle according to an embodiment of a vehicle avoidance method of the present invention;

[0049] Figure 5 A schematic diagram of a flow chart of a second embodiment of a vehicle avoidance method of the present invention;

[0050] Figure 6 This is a structural block diagram of the first embodiment of the vehicle avoidance device of the present invention.

[0051] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0053] Reference Figure 1 , Figure 1 A schematic diagram of the structure of a vehicle avoidance device in a hardware operating environment according to an embodiment of the present invention.

[0054] like Figure 1 As shown, the vehicle avoidance device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0055] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the vehicle avoidance device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0056] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a vehicle avoidance program.

[0057] exist Figure 1 In the vehicle avoidance device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the vehicle avoidance device of the present invention can be set in the vehicle avoidance device, and the vehicle avoidance device calls the vehicle avoidance program stored in the memory 1005 through the processor 1001, and executes the vehicle avoidance method provided by the embodiment of the present invention.

[0058] The embodiment of the present invention provides a vehicle avoidance method, referring to Figure 2 , Figure 2 The figure is a flow chart of a first embodiment of a vehicle avoidance method according to the present invention.

[0059] In this embodiment, the vehicle avoidance method includes the following steps:

[0060] Step S10: when a first target vehicle is detected, first motion information of the first target vehicle is acquired.

[0061] It should be noted that the executor of this embodiment is a vehicle control system, which may be a vehicle motion control unit or a combination of other units having the same or similar functions as the motion control unit, and this embodiment does not limit this.

[0062] It should be noted that in the process of vehicle driving avoidance control applied in this embodiment, there is a lack of effective measures for targets that quickly cut in at close range and targets whose motion trajectories suddenly change in the autonomous driving vehicle. Some vehicles use methods such as adding cameras and laser radars to detect targets, but it is very difficult to determine whether the target will interfere with the driving of the vehicle in the early stage of an emergency. Often, when the target reaches the dangerous posture set by the system, the impact is already unavoidable. Therefore, there are great safety hazards in performing avoidance operations based on actual vehicle actions. Based on the above content, this embodiment proposes a method for evaluating the driving style of the target and predicting its next trajectory according to the speed and position comparison relationship between the target and the target, and judging the impact on the trajectory of the targets around the vehicle according to its motion trajectory, thereby affecting the driving of the vehicle. According to the relationship between the predicted trajectory of the target and the position of the vehicle, advance acceleration, steering, deceleration and other operations are performed to avoid damage to the vehicle or a bad experience for the driver due to temporary lane changes, acceleration, deceleration, etc.

[0063] It can be understood that the first target vehicle is the vehicle detected as the target. Multiple vehicles may be detected during driving. The detected vehicles are traversed and the traversed vehicles are taken as the first target vehicles. Each vehicle is analyzed one by one, and the analysis object is the first target vehicle.

[0064] Among them, the first motion information of the first target vehicle is the speed, acceleration, steering, signal light, lane and other information of the first target vehicle, which is used to experience the motion state and position information of the first target vehicle.

[0065] Step S20: Filter related vehicles according to the movement information of the first target vehicle.

[0066] It should be noted that related vehicles refer to vehicles whose motion states affect each other, such as Figure 3 As shown, assuming that the vehicle of target 1 approaches the vehicle of target 2 at a faster speed, the vehicle of target 1 may change lanes in order to overtake. Assuming that target 2 is the first target vehicle, the driving of target 1 will be affected by the first target vehicle at this time, and target 1 can be determined as an associated vehicle of the first target vehicle.

[0067] In some embodiments, a candidate vehicle is determined based on the motion information of the first target vehicle; third motion information of the candidate vehicle is obtained; a lane change risk of the candidate vehicle is determined based on the third motion information and the first motion information; and when the lane change risk is an imminent lane change, the candidate vehicle is determined as an associated vehicle.

[0068] It should be noted that the candidate vehicle is determined based on the motion information of the first target vehicle. The candidate vehicles may be all vehicles in the same lane or all vehicles whose distance is less than a certain threshold. By taking the possibly associated vehicles as candidate vehicles, the operation cost of the vehicle can be reduced. Among them, the third motion information is the motion information of the candidate vehicle. The lane change risk of the candidate vehicle is determined based on the third motion information and the first motion information. The lane change risk assessment process can be, for example: first, assess the speed difference between the two vehicles. If one vehicle is approaching the other vehicle quickly, the lane change risk may increase. Secondly, pay attention to the lateral distance between the two vehicles. If a vehicle is trying to cross from an adjacent lane to another lane, the lateral position relationship will affect the lane change risk. Alternatively, observe whether the vehicle has turned on the turn signal, which may indicate that the driver intends to change lanes. Pay attention to the direction of the vehicle's front. Sometimes the driver's target lane change direction can be judged by the bias of the front of the vehicle. Finally, if the rear vehicle is too close to the vehicle, the collision risk during lane change may increase. In summary, in the above-mentioned assessment of a high lane change risk, that is, when the lane change risk is an imminent lane change, the candidate vehicle is determined as an associated vehicle.

[0069] In some embodiments, the first speed information and the first lane information of the first target vehicle are determined based on the first motion information; the third speed information and the third lane information of the candidate vehicle are determined based on the third motion information; the first speed information, the first lane information, the third speed information and the third lane information determine the collision risk between the first target vehicle and the candidate vehicle; when the collision risk is that there is a collision risk, the lane change risk of the candidate vehicle is determined to be an imminent lane change.

[0070] Step S30: predicting the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result.

[0071] It should be noted that, according to the first motion information and the second motion information of the associated vehicle, the trajectory prediction of the associated vehicle can be performed using an appropriate motion model to describe the motion characteristics of the vehicle. Common motion models include a uniform speed model, an acceleration model, and the like.

[0072] This embodiment proposes the following preferred method to perform trajectory prediction, for example: Figure 3 as well as Figure 4As shown, the possibility of target trajectory change is judged; according to the position relationship between the target and the vehicle, the target vehicle is divided into the rear target and the front target. 1.1 If target 1 is the front target, the front target 2 in the lane where target 1 is located is judged, and the speed of target 2 is compared with the speed of the parallel vehicle of target 2. If the speed v2 of target 2 is lower than the speed v3 of the parallel vehicle, then the greater the speed difference within a certain range, the greater the possibility p1 of lane change of target 1. And judge the distance s1 between the front and rear vehicles in the adjacent lane of target 1. The greater the ratio of the distance to the speed v1 of target 1 within a certain range, the greater the possibility of lane change. p1=k1*(v3–v2)+k2*s1 / v1 (k1 and k2 are coefficients) When the speed difference exceeds the range, it is calculated according to the maximum difference. When the distance s1 is lower than a certain value, there is no possibility of lane change; when it is greater than a certain value, it is calculated according to the maximum value in the range. At the same time, the lateral position relationship between target 1 and target 2 is considered. Within a certain range, the greater the lateral position difference s2 between target 1 and target 2, and the greater the lateral position change vy1 of target 1, the greater the possibility of lane change. p1=p1+k3*s2*vy1(k3 is a coefficient) According to p1, set the line distance s3 of target 1, s3=k4*p1(k4 is a coefficient) When the lateral distance between target 1 and the lane line is less than s3, it is judged that target 1 is about to change lanes. The direction in which the distance value satisfies is the lane change direction. 1.2 If target 1 is a rear target, calculate the possible time t1 of target 1 changing lanes according to its speed v1, acceleration a1, and the distance s4, speed v4, and acceleration a4 of the front target in its lane. Calculate t1 according to the formula s4-s5=(v1-v4)*t1+1 / 2*(a1-a4)*t12, s5 is the distance from target 2 when changing lanes calibrated in combination with the speed of target 1. Compare the front and rear position relationship between target 1 and the vehicle at time t1. The current vehicle speed v5, acceleration a5, and longitudinal distance s6 between target 1 and the vehicle. Then compare the relationship between v1*t1+1 / 2*a1*t12 and s6+v5*t1+1 / 2*a5*t12. If the former is larger, proceed to the next step. If the latter is larger, it is judged that target 1 has no risk and no subsequent calculation is performed.

[0073] Furthermore, determine whether the trajectory change of target 1 affects other targets. If target 1 is the front target, set the time tc to complete the lane change as the evaluation time tp1; if target 1 is the rear target, set tc+t1 as the evaluation time tp1. Set a threshold tf as the system's predicted capacity limit. When tp1>tf, the system does not take action; when tp1≤tf, all targets except target 1 calculate the speed and position after tp1 time according to the current speed, acceleration, position, etc., and the acceleration remains unchanged. 2.1 Determine the speed of target 1 after changing lanes based on target 3 in front of the lane where target 1 is located after changing lanes; 2.1.1 If there is no target within a certain distance l1 ahead of the lane where target 1 is located after changing lanes, and it is not in the rightmost lane or there is no ramp within a distance l2 ahead, then it is determined that target 1 will not slow down, and the current speed v1 of target 1 is set to the speed vc1 after changing lanes; 2.1.2 If there is a target 3 in front of the lane where target 1 is located after changing lanes, its speed is vc2, and the distance between it and target 3 after changing lanes is sc1, then determine whether target 1 will slow down based on the threshold tc1: if tc1≤sc1 / (v1–vc1 ), it is determined that target 1 will not decelerate after changing lanes, and v1 is set to vc1; if tc1>sc1 / (v1–vc1), it is determined that target 1 will decelerate after changing lanes, and vc2 is set to vc1; 2.2 According to the distance sc2, speed vc3, and threshold tc2 of target 4 behind target 1 in the lane where target 1 is located after changing lanes, it is determined whether the driving of the rear target will be affected: if tc2≤sc2 / (vc3–vc1), it is determined that target 4 will not be affected by target 1; if tc2>sc2 / (vc3–vc1), it is determined that target 4 will be affected by target 1 and decelerate or change lanes.

[0074] Finally, the possibility of lane change is determined through the above process, and then the direction of the vehicle's lane change is determined based on the road information. Combined with the above-mentioned driving speed and acceleration, it is possible to predict whether the trajectory will change.

[0075] In some embodiments, first speed information and first lane information of a first target vehicle are determined based on the first motion information; second speed information and second lane information of an associated vehicle are determined based on the second motion information; a target lane of the associated vehicle is predicted based on the first lane information and the second lane information; a speed of the associated vehicle after lane change is predicted based on the first speed information and the second speed information; and a prediction result is determined based on the target lane and the speed after lane change.

[0076] It can be understood that speed information is the change of the speed and acceleration of the vehicle in the lane direction, and lane information is the lane in which the vehicle is located. This embodiment proposes a quick prediction method, that is, when two vehicles are in the same lane and the speed difference is large, the rear vehicle has a risk of changing lanes, and the direction of lane change is to change lanes in the direction where there is space for lane change. Generally speaking, the speed of the vehicle after changing lanes will be faster than the speed before changing lanes.

[0077] In some embodiments, current road information is obtained; and the speed of the associated vehicle after lane change is predicted based on the current road information, the first speed information, and the second speed information.

[0078] It should be noted that if the speed after changing lanes is to be accurately predicted, the current road information needs to be considered. This is because, assuming that there is a fork in the road or a road entrance or exit ahead, the vehicle ahead may only change lanes without overtaking. Therefore, the speed after changing lanes may be different from the vehicle speed after changing lanes. Figure 3 The speed of target 2 vehicle is always the same, causing the two vehicles to run parallel. Therefore, it is necessary to make a reasonable prediction of the speed of the associated vehicle after changing lanes based on the current road information. When there is a fork in the road or a road exit ahead in the current road information, it is predicted that the speed after changing lanes will remain at the preset speed.

[0079] Step S40: Control the current vehicle driving according to the prediction result.

[0080] It should be noted that after detecting that the prediction results show that an associated vehicle may invade the current lane, the current vehicle can be controlled to slow down and give way in advance to avoid the lane invasion risk of the associated vehicle in advance and avoid safety hazards.

[0081] When the first target vehicle is detected, the embodiment obtains the first motion information of the first target vehicle; selects the associated vehicle according to the motion information of the first target vehicle; predicts the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result; and controls the driving of the current vehicle according to the prediction result. Through the above scheme, the potential lane change danger is predicted and the safety of vehicle driving is improved.

[0082] refer to Figure 5 , Figure 5 It is a flow chart of a second embodiment of a vehicle avoidance method of the present invention.

[0083] Based on the first embodiment, the vehicle avoidance method of this embodiment further includes, in step S40:

[0084] Step S41: Obtain the fourth motion information of the current vehicle.

[0085] It can be understood that the fourth motion information of the current vehicle is the motion information of the vehicle where the execution subject is located.

[0086] Step S42: Determine the current vehicle collision risk according to the fourth motion information and the prediction result.

[0087] It should be noted that if Figure 4 The fourth motion information of the current vehicle and the driving prediction results of the associated vehicles are shown to detect whether there is a collision risk. The specific calculation process can be, for example: determine whether the own vehicle is affected 3.1 If target 4 is the own vehicle, and it is determined to be affected according to step 2.2, then according to the speed vc3 of the own vehicle at tp1, the acceleration a5, the speed of the front vehicle vc1, the distance from the front vehicle sc2, and the safe vehicle distance sc3 at the speed vc1, the required acceleration ac is: ac = (vc32-vc12) / (sc2-sc3) / 2 (ac should be a negative value) 3.2 If target 4 is not the own vehicle, then if target 4 is behind the own vehicle at tp1, the system will not process it; if target 4 is in front of the own vehicle but in an alternate lane, it will not be processed either. 3.2.1 If target 4 is in front of the lane where the ego vehicle is located, the speed of target 4 is set to vc1, and the distance between the ego vehicle and target 4 is sc4. According to step 3.1, the required acceleration ac can be calculated; 3.2.2 If target 4 is in front of the adjacent lane of the ego vehicle, it is judged that target 4 will change lanes in front of the ego vehicle when the following conditions are met: the state of target 4 and target 1 at time tp1, the acceleration calculated according to step 3.1 exceeds the threshold as1; at time tp1, there is space for lane change in front of the ego vehicle; if the above two conditions are met, the required acceleration ac of the ego vehicle is calculated according to step 3.2.1. After the required acceleration of the ego vehicle is calculated, it means that there is a collision risk between the current vehicle and the associated vehicle.

[0088] Step S43: When the current vehicle collision risk is a collision risk, the current vehicle is controlled to avoid the collision according to the prediction result and the fourth motion information.

[0089] It should be noted that when the current vehicle collision risk is a collision risk, the current vehicle is controlled to avoid the collision according to the prediction result and the fourth motion information. The specific avoidance process may generally be to slow down and give way, for example: Figure 4As shown in the figure, the driving state of the vehicle is adjusted according to the state change. 4.1 Calculate the acceleration change am=Ⅰac–a5Ⅰ when the vehicle decelerates according to the above steps, and compare it with the set threshold as2. If it is less than as2, no processing is done, and the deceleration is performed normally at the time tp1; 4.2 If am≥as2, deceleration is calculated according to the current time, deceleration am1, am1=(v52–vc12) / (sc2–sc3+v5*tp1+1 / 2*a5*tp12) / 2 (am1 is a negative value) Calculate the acceleration change am2=Ⅰam1–a5Ⅰ, and compare it with as2. If it is less than as2, it is immediately That is, decelerate according to the deceleration of am1; 4.3 If am2 ≥ as2, calculate the acceleration overtaking: If target 4 is the vehicle, the required acceleration change am3 = Ⅰ2*(s4-s5-s6–v5*t1) / t12-a5Ⅰ; If target 4 is the target in front of the vehicle, am3 is set to a larger value that is impossible to implement, such as 10m / s2; If target 4 is the target in the adjacent lane in front of the vehicle, then am3 = 2*sc4 / tp12; 4.4 Compare am2, am3 and threshold as3; 4.4.1 If the smaller value of am2 and am3 is greater than as3, consider changing lanes. It must meet the following conditions: There is space for lane change in the adjacent lane; The adjacent lane is not the lane where target 4 is located. If the conditions are not met, perform the operation according to the acceleration / deceleration corresponding to the smaller value; 4.4.2 If the smaller value of am2 and am3 is smaller than as3, perform the operation according to the acceleration / deceleration corresponding to the smaller value.

[0090] In some embodiments, the required braking speed of the current vehicle is determined based on the fourth motion information and the prediction information; when the required braking speed is greater than a preset deceleration, adjacent lane information is detected; and the current vehicle is controlled to avoid according to the adjacent lane information.

[0091] It is understandable that in addition to slowing down, you can also choose to change lanes to avoid more directly. Therefore, when the required braking speed is high, you can choose to change lanes to avoid. For example: in the above 4.4.1, if the smaller value of am2 and am3 is greater than as3, consider changing lanes, which can be completed when there is space for changing lanes in the adjacent lane.

[0092] This embodiment obtains the fourth motion information of the current vehicle; determines the collision risk of the current vehicle according to the fourth motion information and the prediction result; when the collision risk of the current vehicle is a collision risk, controls the current vehicle to avoid the collision according to the prediction result and the fourth motion information. Through the above scheme, an effective avoidance strategy is implemented when there is a collision risk, thereby improving the safety of the vehicle.

[0093] In addition, an embodiment of the present invention further proposes a storage medium, on which a vehicle avoidance program is stored. When the vehicle avoidance program is executed by a processor, the steps of the vehicle avoidance method described above are implemented.

[0094] Reference Figure 6 , Figure 6 This is a structural block diagram of the first embodiment of the vehicle avoidance device of the present invention.

[0095] like Figure 6 As shown, the vehicle avoidance device proposed in the embodiment of the present invention includes:

[0096] The processing module 10 is used to obtain first motion information of the first target vehicle when the first target vehicle is detected;

[0097] The processing module 10 is further used to filter associated vehicles according to the movement information of the first target vehicle;

[0098] The processing module 10 is further used to predict the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result;

[0099] The control module 20 is used to control the current vehicle driving according to the prediction result.

[0100] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0101] When the processing module 10 of this embodiment detects the first target vehicle, it obtains the first motion information of the first target vehicle; the processing module 10 selects the associated vehicle according to the motion information of the first target vehicle; the processing module 10 predicts the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain the prediction result; the control module 20 controls the current vehicle to drive according to the prediction result. Through the above scheme, the potential lane change danger is predicted and the safety of vehicle driving is improved.

[0102] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0103] In addition, for technical details not fully described in this embodiment, reference can be made to the vehicle avoidance method provided in any embodiment of the present invention, and will not be repeated here.

[0104] In some embodiments, the processing module 10 is further used to determine a candidate vehicle according to the motion information of the first target vehicle;

[0105] Obtaining third motion information of the candidate vehicle;

[0106] determining a lane change risk of the candidate vehicle according to the third motion information and the first motion information;

[0107] When the lane change risk is an imminent lane change, the candidate vehicle is determined as an associated vehicle.

[0108] In some embodiments, the processing module 10 is further used to determine first speed information and first lane information of the first target vehicle according to the first motion information;

[0109] Determine third speed information and third lane information of the candidate vehicle according to the third motion information;

[0110] The first speed information, the first lane information, the third speed information, and the third lane information determine the collision risk between the first target vehicle and the candidate vehicle;

[0111] When the collision risk is that there is a collision risk, it is determined that the lane change risk of the candidate vehicle is about to change lanes.

[0112] In some embodiments, the processing module 10 is further used to determine first speed information and first lane information of the first target vehicle according to the first motion information;

[0113] Determine second speed information and second lane information of the associated vehicle according to the second motion information;

[0114] predicting a target lane for the associated vehicle based on the first lane information and the second lane information;

[0115] predicting a vehicle speed of the associated vehicle after lane change according to the first speed information and the second speed information;

[0116] The prediction result is determined according to the target lane and the vehicle speed after the lane change.

[0117] In some embodiments, the processing module 10 is further used to obtain current road information;

[0118] The vehicle speed of the associated vehicle after the lane change is predicted according to the current road information, the first speed information and the second speed information.

[0119] In some embodiments, the control module 20 is further used to obtain fourth motion information of the current vehicle;

[0120] Determining a current vehicle collision risk according to the fourth motion information and the prediction result;

[0121] When the current vehicle collision risk is that there is a collision risk, the current vehicle is controlled to avoid the collision according to the prediction result and the fourth motion information.

[0122] In some embodiments, the control module 20 is further used to determine the required braking speed of the current vehicle according to the fourth motion information and the prediction information;

[0123] When the required braking speed is greater than the preset deceleration, detecting adjacent lane information;

[0124] The current vehicle is controlled to avoid according to the adjacent lane information.

[0125] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0126] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0127] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0128] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A vehicle avoidance method, characterized in that: The vehicle avoidance method comprises: When a first target vehicle is detected, first motion information of the first target vehicle is acquired; Filtering related vehicles according to the movement information of the first target vehicle; Predicting the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result; Control the current vehicle driving according to the prediction results; The step of screening the associated vehicles according to the movement information of the first target vehicle includes: Determine a candidate vehicle based on the motion information of the first target vehicle; Obtaining third motion information of the candidate vehicle; determining a lane change risk of the candidate vehicle according to the third motion information and the first motion information; When the lane change risk is an imminent lane change, the candidate vehicle is determined as an associated vehicle.

2. The method according to claim 1, characterized in that The determining the lane change risk of the candidate vehicle according to the third motion information and the first motion information includes: Determine first speed information and first lane information of a first target vehicle according to the first motion information; Determine third speed information and third lane information of the candidate vehicle according to the third motion information; The first speed information, the first lane information, the third speed information, and the third lane information determine the collision risk between the first target vehicle and the candidate vehicle; When the collision risk is that there is a collision risk, it is determined that the lane change risk of the candidate vehicle is about to change lanes.

3. The method according to claim 1, characterized in that The step of performing trajectory prediction on the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result includes: Determine first speed information and first lane information of a first target vehicle according to the first motion information; Determine second speed information and second lane information of the associated vehicle according to the second motion information; predicting a target lane for the associated vehicle based on the first lane information and the second lane information; predicting a vehicle speed of the associated vehicle after lane change according to the first speed information and the second speed information; The prediction result is determined according to the target lane and the vehicle speed after the lane change.

4. The method according to claim 3, characterized in that The predicting the vehicle speed of the associated vehicle after lane change according to the first speed information and the second speed information includes: Get current road information; The vehicle speed of the associated vehicle after the lane change is predicted according to the current road information, the first speed information and the second speed information.

5. The method according to claim 1, characterized in that The controlling the current vehicle driving according to the prediction result includes: Obtain the fourth motion information of the current vehicle; Determining a current vehicle collision risk according to the fourth motion information and the prediction result; When the current vehicle collision risk is that there is a collision risk, the current vehicle is controlled to avoid the collision according to the prediction result and the fourth motion information.

6. The method according to claim 5, characterized in that When the current vehicle collision risk is a collision risk, controlling the current vehicle to avoid the collision according to the prediction result and the fourth motion information includes: determining a current required braking speed of the vehicle according to the fourth motion information and the prediction information; When the required braking speed is greater than the preset deceleration, detecting adjacent lane information; The current vehicle is controlled to avoid according to the adjacent lane information.

7. A vehicle avoidance device, characterized in that: The vehicle avoidance device comprises: A processing module, configured to obtain first motion information of the first target vehicle when the first target vehicle is detected; The processing module is further used to filter associated vehicles according to the motion information of the first target vehicle; The processing module is further used to predict the trajectory of the associated vehicle according to the first motion information and the second motion information of the associated vehicle to obtain a prediction result; A control module, used for controlling the current vehicle driving according to the prediction result; The step of screening the associated vehicles according to the movement information of the first target vehicle includes: Determine a candidate vehicle based on the motion information of the first target vehicle; Obtaining third motion information of the candidate vehicle; determining a lane change risk of the candidate vehicle according to the third motion information and the first motion information; When the lane change risk is an imminent lane change, the candidate vehicle is determined as an associated vehicle.

8. A vehicle avoidance device, characterized in that: The device comprises: a memory, a processor, and a vehicle avoidance program stored in the memory and executable on the processor, wherein the vehicle avoidance program is configured to implement the steps of the vehicle avoidance method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a vehicle avoidance program, which, when executed by a processor, implements the steps of the vehicle avoidance method according to any one of claims 1 to 6.

Images