CN117261749A

CN117261749A - Brake reminding based on situation detection

Info

Publication number: CN117261749A
Application number: CN202210665279.XA
Authority: CN
Inventors: 杨文龙
Original assignee: Microsoft Technology Licensing LLC
Current assignee: Microsoft Technology Licensing LLC
Priority date: 2022-06-13
Filing date: 2022-06-13
Publication date: 2023-12-22
Also published as: WO2023244371A1

Abstract

The present disclosure presents methods, apparatus, and computer program products for context detection based braking alerting. It is possible to detect whether a preceding vehicle located in front of the current vehicle is braked or is about to be braked. A rear collision probability of the rear vehicle colliding with the current vehicle may be predicted based on a rear context of the current vehicle and assumptions of the current vehicle and rear vehicle brakes located rearward of the current vehicle in response to detecting the front vehicle brake or impending brake. It may be determined whether the rear impact probability is greater than a rear impact threshold. A rear vehicle brake alert may be issued to the rear vehicle in response to determining that the rear collision probability is greater than the rear collision threshold. The present disclosure also proposes a system for context detection based braking alerting. The system may include a processing unit and a rear vehicle brake alert unit.

Description

Brake reminding based on situation detection

Background

Modern motor vehicles are often equipped with brake lights, such as two conventional brake lights at both ends of the tail and a high-end brake light at the upper middle of the tail. These brake signal lights may illuminate when the vehicle is braking or emergency braking, for example when the vehicle's brake pedal is depressed, to alert the vehicle behind it to take braking action as soon as possible, thereby reducing the risk of a collision or rear-end collision accident.

Disclosure of Invention

This summary is provided to introduce a selection of concepts that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Embodiments of the present disclosure propose methods, apparatuses and computer program products for context detection based braking alert. It is possible to detect whether a preceding vehicle located in front of the current vehicle is braked or is about to be braked. A rear collision probability of the rear vehicle colliding with the current vehicle may be predicted based on a rear context of the current vehicle and assumptions of the current vehicle and rear vehicle brakes located rearward of the current vehicle in response to detecting the front vehicle brake or impending brake. It may be determined whether the rear impact probability is greater than a rear impact threshold. A rear vehicle brake alert may be issued to the rear vehicle in response to determining that the rear collision probability is greater than the rear collision threshold.

Embodiments of the present disclosure propose a system for braking alert based on context detection. The system may include a processing unit configured to: detecting whether a front vehicle located in front of a current vehicle is braked or is about to brake, in response to detecting that the front vehicle is braked or is about to brake, predicting a rear collision probability of the rear vehicle colliding with the current vehicle based on a rear situation of the current vehicle and an assumption of the current vehicle and a rear vehicle being located behind the current vehicle, determining whether the rear collision probability is greater than a rear collision threshold, and in response to determining that the rear collision probability is greater than the rear collision threshold, transmitting a rear vehicle brake alert instruction to a rear vehicle brake alert unit; and a rear vehicle brake alert unit configured to: and in response to receiving the rear vehicle braking reminding instruction from the processing unit, sending a rear vehicle braking reminding to the rear vehicle.

It should be noted that one or more of the above aspects include features described in detail below and pointed out with particularity in the claims. The following description and the annexed drawings set forth in detail certain illustrative features of the one or more aspects. These features are indicative, however, of but a few of the various ways in which the principles of various aspects may be employed and the present disclosure is intended to include all such aspects and their equivalents.

Drawings

The disclosed aspects will be described below in conjunction with the drawings, which are provided to illustrate and not limit the disclosed aspects.

FIG. 1 illustrates an exemplary architecture of a system for context-detection based braking alert according to an embodiment of the present disclosure.

FIG. 2 illustrates an exemplary process for context detection based braking alert according to an embodiment of the present disclosure.

FIG. 3 illustrates an exemplary process for calculating an absolute speed of a preceding vehicle according to an embodiment of the present disclosure.

Fig. 4 illustrates an exemplary process for predicting a rear collision probability of a rear vehicle colliding with a current vehicle, according to an embodiment of the present disclosure.

Fig. 5A-5G illustrate examples of context detection based braking alerts according to embodiments of the present disclosure.

FIG. 6 is a flowchart of an exemplary method for context detection based braking alert, according to an embodiment of the present disclosure.

FIG. 7 illustrates an exemplary system for context detection based braking alert in accordance with an embodiment of the present disclosure.

FIG. 8 illustrates an exemplary apparatus for context detection based braking alert in accordance with an embodiment of the present disclosure.

Detailed Description

The present disclosure will now be discussed with reference to several exemplary embodiments. It should be understood that the discussion of these embodiments is merely intended to enable one skilled in the art to better understand and thereby practice the examples of the present disclosure and is not intended to limit the scope of the present disclosure in any way.

Currently, a driver of a rear vehicle can determine whether the current vehicle is braking by observing a brake signal lamp on the current vehicle located in front of the driver during driving. Herein, vehicles that are in the same lane but located in front-rear positions with respect to each other may be referred to by a rear vehicle, a current vehicle, and a front vehicle. The rear vehicle is located behind the current vehicle. The front vehicle is located in front of the current vehicle. If the driver of the rear vehicle determines that the current vehicle is braking, he may accordingly take a braking action in an effort to avoid a rear vehicle collision or to rear-end the current vehicle. Rear-end accidents between a rear vehicle and a current vehicle are generally avoided if a sufficient safe distance between the rear vehicle and the current vehicle can be maintained, road conditions are good, and the driver of the rear vehicle is able to take braking action within a reasonable response time after observing the current vehicle braking. However, in a road section where traffic is heavy and the flow rate of traffic is large, a safe distance between vehicles is sometimes difficult to ensure. In addition, when the road surface becomes slippery due to rain, snow, or the like, the braking distance of the vehicle increases. In addition, the response time of the driver of the rear vehicle to take the braking operation may be increased due to distraction or other reasons. Various factors such as the above factors cause occurrence of a collision or a rear-end collision accident on an actual road.

In general, the current vehicle braking is because a driver of the current vehicle observes that a preceding vehicle is braking and takes a braking operation. While the current vehicle starts braking, i.e., while its brake pedal is depressed, the brake signal light of the current vehicle will normally be on so that the driver of the following vehicle can observe that the current vehicle is braking. If the driver of the rear vehicle can know ahead of time that the current vehicle is to be braked, for example, that the current vehicle is about to be braked before the current vehicle is not braked, the driver of the rear vehicle can take a braking action ahead of time to strive for more response time. There is a solution that makes the driver of the following vehicle aware of the current vehicle to brake early. The solution is that when the current vehicle detects that the brake signal of the preceding vehicle is on, the current vehicle will also turn on its own brake signal, thereby transmitting the brake signal of the preceding vehicle to the following vehicle. However, in many cases, the brake signal of the front vehicle is meaningless for the rear vehicle. If all braking signals of the front vehicle are transmitted to the rear vehicle, interference with the rear vehicle may be caused. For example, when the rear vehicle is farther from the current vehicle, the rear vehicle may not have to immediately take a braking operation even if the current vehicle is braked accordingly due to the front vehicle being braked urgently.

Embodiments of the present disclosure propose a braking alert based on context detection. The front vehicle may determine whether to issue a rear vehicle brake alert to the rear vehicle based on a rear context of the front vehicle when a front vehicle brake or an impending brake is detected. Information related to the rear environment of the current vehicle may be referred to herein as the rear context of the current vehicle. The rear context of the current vehicle may include, for example, a distance between the rear vehicle and the current vehicle, a relative speed of the rear vehicle with respect to the current vehicle, a road surface condition, a weather condition, a vehicle type of the rear vehicle, and the like. The rear vehicle braking alert may alert the rear vehicle to a braking action. Upon detection of a front vehicle brake or impending brake, a rear collision probability of a rear vehicle colliding with the current vehicle may be predicted based on a rear context of the current vehicle and assumptions of the current and rear vehicle brakes. The probability of a rear vehicle colliding with the current vehicle may be referred to herein as a rear collision probability. If the rear collision probability is greater than a predetermined rear collision threshold, i.e., if the rear vehicle is likely to collide or rear-end the current vehicle, a rear vehicle brake alert may be sent to the rear vehicle; and if the rear collision probability is not greater than the predetermined rear collision threshold, i.e., if the rear vehicle may not collide or rear-end the current vehicle, the rear vehicle will not issue a rear vehicle brake alert. That is, the rear vehicle brake alert may be issued to the rear vehicle only when the rear vehicle is likely to collide or rear-end the current vehicle. By the mode, accurate rear vehicle braking reminding can be transmitted to the rear vehicle. In addition, if each vehicle can determine whether to send a rear vehicle braking reminding to the vehicle behind the vehicle based on the rear situation of the vehicle, the accurate rear vehicle braking reminding can be sequentially transmitted backwards, so that the risk of collision or rear-end collision accidents on the road is obviously reduced.

In one aspect, embodiments of the present disclosure propose to detect whether a preceding vehicle is braked or is about to brake in a number of ways. In one embodiment, whether the front vehicle is braked or is about to brake may be detected by detecting whether the front vehicle is issuing a brake lift. For example, it may be detected whether a preceding vehicle emits a visual signal, an infrared signal, an acoustic signal, a wireless signal, or the like for alerting of the current vehicle braking. In another embodiment, whether the preceding vehicle is braked may be detected by detecting whether the magnitude of the drop in the absolute speed of the preceding vehicle exceeds a drop threshold. When it is detected that the magnitude of the drop in the absolute speed of the preceding vehicle exceeds the drop threshold, it may be determined that braking of the preceding vehicle has occurred. In particular, when it is detected that the magnitude of the drop in the absolute speed of the preceding vehicle exceeds the drop threshold in an extremely short time, it may be determined that emergency braking of the preceding vehicle has occurred. Either of the two embodiments described above may be employed to detect whether a preceding vehicle is braked or is about to be braked. In this way, it is possible to timely and accurately detect whether the preceding vehicle is braked or is about to brake, which helps the current vehicle to timely issue an accurate rear-vehicle brake alert to the following vehicle and timely take a braking action.

In another aspect, embodiments of the present disclosure propose to issue a rear vehicle brake alert to a rear vehicle in a number of ways. For example, the rear vehicle brake alert may be issued to the rear vehicle by issuing at least one of a visual signal, an infrared signal, an acoustic signal, and a wireless signal to the rear vehicle to alert the rear vehicle to brake. These signals may be issued by the respective hardware units of the current vehicle. For example, the visual signal may be emitted by a brake signal light of the current vehicle. The brake signal lights may be existing lights on the vehicle that indicate that the brake pedal is depressed, such as conventional brake signal lights at both ends of the tail or high-end brake signal lights located in the middle and upper portion of the tail. According to embodiments of the present disclosure, a brake signal light on a vehicle may also be used to issue a rear vehicle brake alert to a vehicle behind it. Preferably, the visual signal may be emitted by a brake alert light of the current vehicle. The brake alert light may be a light added at the rear of the vehicle specifically configured to alert the vehicle behind the vehicle to the brake of the rear vehicle. The shape of the brake alert light or the nature of the light it emits may be significantly different from the brake signal light so that a rear vehicle can easily detect a rear vehicle brake alert it emits.

In yet another aspect, embodiments of the present disclosure propose to determine whether to send a host vehicle braking instruction inside a current vehicle based on a front context of the current vehicle when front vehicle braking or impending braking is detected. Information related to the forward environment of the current vehicle may be referred to herein as the forward context of the current vehicle. The forward context of the current vehicle may include, for example, a distance between the front vehicle and the current vehicle, a relative speed of the front vehicle with respect to the current vehicle, a road surface condition, a weather condition, a model of the front vehicle, and the like. Upon detection of a front vehicle brake or impending brake, a front collision probability of the current vehicle colliding with the front vehicle may be predicted based on a front context of the current vehicle and assumptions of the front vehicle and the current vehicle brake. The probability of the current vehicle colliding with the preceding vehicle may be referred to herein as a forward collision probability. If the front collision probability is greater than a predetermined front collision threshold, i.e., if the current vehicle is likely to collide or rear-end the front vehicle, the own vehicle brake instruction may be transmitted inside the current vehicle; and if the front collision probability is not greater than the predetermined front collision threshold, i.e., if the current vehicle may not collide or rear-end the front vehicle, the own vehicle brake instruction may not be transmitted inside the current vehicle. Transmitting the own vehicle braking command inside the current vehicle may prompt the driver of the current vehicle or the automatic braking unit to take braking action, thereby avoiding the current vehicle collision or rear-end collision with the preceding vehicle. If the vehicle brake command is not sent inside the current vehicle, the current vehicle may continue to travel forward a distance until the front collision probability is greater than the front collision threshold. If at this time, the rear vehicle is likely to collide with or rear-end the current vehicle, and the rear vehicle can immediately make an emergency brake when receiving the rear brake alert, while the current vehicle still continues to travel for a distance while ensuring that the front vehicle is not rear-ended, the distance between the rear vehicle and the current vehicle may be increased. In this way, the risk of the rear vehicle following the current vehicle can be reduced.

In yet another aspect, embodiments of the present disclosure propose to decide how to send a host vehicle brake command inside the current vehicle based on the type of current vehicle. If the current vehicle is a manual driving vehicle, the vehicle braking reminding unit in the current vehicle can send a vehicle braking instruction to the vehicle braking reminding unit so that the vehicle braking reminding unit sends out a vehicle braking reminding. The present vehicle brake alert may alert the driver of the current vehicle to apply a braking operation, such as an emergency braking operation, as soon as possible. Preferably, the intensity of the own-vehicle brake alert issued by the own-vehicle brake alert unit may be correlated with the front collision probability. If the current vehicle is an autonomous vehicle, a host vehicle braking instruction may be sent at least to an automatic braking unit in the current vehicle to cause the automatic braking unit to perform an automatic braking operation. Preferably, the braking force of the automatic braking operation performed by the automatic braking unit may be correlated with the front collision probability.

FIG. 1 illustrates an exemplary architecture 100 of a system for context-detection-based braking alert according to an embodiment of the present disclosure. The system may be deployed on any vehicle, such as on a manually driven vehicle, an automatically driven vehicle, or the like.

Architecture 100 may include at least one receiving unit 110. The at least one receiving unit 110 may receive at least front information 102 from a front of the current vehicle and rear information 104 from a rear of the current vehicle. The front information 102 may include information of a front vehicle located in front of the current vehicle. The rear information 104 may include information of a rear vehicle located behind the current vehicle. In one embodiment, the at least one receiving unit 110 may include a front camera toward the front of the current vehicle and a rear camera toward the rear of the current vehicle. The front camera may receive front information 102. The rear camera may receive rear information 104. In another embodiment, the at least one receiving unit 110 may include a lidar. The lidar may receive information surrounding the current vehicle, including front information 102 and rear information 104.

The at least one receiving unit 110 may process the front information 102 and the rear information 104 and generate a front input 112 and a rear input 114 suitable for processing by the processing unit 120. When the at least one receiving unit 110 includes a front camera and a rear camera, the front input 112 and the rear input 114 may be an image corresponding to a front environment of the current vehicle and an image corresponding to a rear environment of the current vehicle, respectively. For example, the front input 112 may contain an image of a front vehicle and the rear input 114 may contain an image of a rear vehicle. When the at least one receiving unit 110 includes a lidar, the front input 112 and the rear input 114 may be a point cloud corresponding to a front environment of the current vehicle and a point cloud corresponding to a rear environment of the current vehicle, respectively. For example, the front input 112 may contain a point cloud of a front vehicle and the rear input 114 may contain a point cloud of a rear vehicle.

The processing unit 120 may be a chipset system that includes an artificial intelligence chip. The processing unit 120 may perform a process for context-detection-based braking alert based on the front input 112 and the rear input 114. For example, the processing unit 120 may detect whether a preceding vehicle is braked or is about to brake. If front vehicle braking or impending braking is detected, the processing unit 120 may predict a rear collision probability of the rear vehicle colliding with the current vehicle based on a rear context of the current vehicle and assumptions of the current vehicle and rear vehicle braking. If the rear collision probability is greater than the rear collision threshold, it is indicated that there will be a greater probability that the rear vehicle will collide with the current vehicle, i.e., the rear vehicle will likely rear-end the current vehicle. In this case, the processing unit 120 may issue a rear vehicle brake alert 132 for alerting the rear vehicle to brake, to alert the rear vehicle to brake as soon as possible. For example, the processing unit 120 may generate and send the rear vehicle brake alert instructions 122 to the rear vehicle brake alert unit 130. The rear vehicle brake alert unit 130 may receive the rear vehicle brake alert instruction 122 and issue a rear vehicle brake alert 132 to the rear vehicle. The rear vehicle brake alert unit 130 may be a hardware unit capable of emitting at least one of a visual signal, an infrared signal, an acoustic signal, and a wireless signal. Accordingly, the rear vehicle brake alert 132 may include, for example, a visual signal, an infrared signal, an acoustic signal, a wireless signal, etc. for alerting of rear vehicle braking. As an example, the rear vehicle brake alert unit 130 may be a brake signal light of the current vehicle. The brake signal lights may be existing lights on the vehicle that indicate that the brake pedal is depressed, such as conventional brake signal lights at both ends of the tail or high-end brake signal lights located in the middle and upper portion of the tail. According to embodiments of the present disclosure, a brake signal on the vehicle may also be used to issue a rear vehicle brake alert 132 to the vehicle behind it. Preferably, the rear vehicle brake alert unit 130 may be an alert light of the brake of the current vehicle. The brake alert light may be a light added at the rear of the vehicle specifically configured to alert the vehicle behind the vehicle to the brake of the rear vehicle. The shape of the brake alert light or the nature of the light it emits may be significantly different from the brake signal light so that a rear vehicle can easily detect the rear vehicle brake alert 132 it emits.

In addition, if front vehicle braking or impending braking is detected, the processing unit 120 may predict a front collision probability of the current vehicle colliding with the front vehicle based on a front context of the current vehicle and assumptions of the front vehicle and the current vehicle braking. If the front collision probability is greater than the front collision threshold, it is indicated that there will be a greater probability that the current vehicle will collide with the front vehicle, i.e., the current vehicle will likely rear-end the front vehicle. In this case, the processing unit 120 may send the own vehicle brake instruction 124 inside the current vehicle.

If the current vehicle is a manually driven vehicle, the processing unit 120 may send the own vehicle braking instruction 124 to the own vehicle braking alert unit 140 in the current vehicle, so that the own vehicle braking alert unit 140 issues an own vehicle braking alert 142. The present vehicle brake alert unit 140 may be a hardware unit capable of emitting at least one of a visual signal, an acoustic signal, and a tactile signal. Accordingly, the present vehicle brake alert 142 may include, for example, a visual signal, an acoustic signal, a tactile signal, and the like. The present vehicle brake alert 142 may alert the driver of the current vehicle to apply the braking operation as soon as possible. Preferably, the intensity of the own vehicle brake alert 142 issued by the own vehicle brake alert unit 140 may be correlated with the front collision probability. The greater the frontal collision probability, the greater the intensity of the own vehicle braking alert 142 may be to encourage the driver to perform the braking operation with greater braking effort. For example, when the own-vehicle braking alert 142 is an acoustic signal, the acoustic signal may be jerky if the frontal collision probability is a greater value than the frontal collision threshold; and if the frontal collision probability is a small value greater than the frontal collision threshold, the acoustic signal may be flat.

If the current vehicle is an autonomous vehicle, the processing unit 120 may send at least the own vehicle braking instruction 124 to the automatic braking unit 150 in the current vehicle to cause the automatic braking unit 150 to perform an automatic braking operation 152. Preferably, the braking effort of the automatic braking operation 152 implemented by the automatic braking unit 150 may be associated with a frontal collision probability. The greater the frontal collision probability, the greater the braking effort of the autobrake operation 152 may be to enable the current vehicle to stop as quickly as possible. Alternatively, if the current vehicle is an autonomous vehicle, the processing unit 120 may also send the own vehicle braking instruction 124 to the own vehicle braking alert unit 140 in the current vehicle so that the driver in the current vehicle may also know that the current vehicle is about to be automatically braked and take over the vehicle and take appropriate action if necessary. That is, if the current vehicle is an autonomous vehicle, the architecture 100 may include only the automatic braking unit 150 or both the own vehicle braking alert unit 140 and the automatic braking unit 150.

An exemplary process performed by the processing unit 120 for context detection based braking alert will be described later in connection with fig. 2.

At least some of the above-described units in architecture 100 may be obtained by retrofitting existing components on the vehicle. For example, modern vehicles are typically equipped with front and rear cameras. These two cameras may be used as the receiving unit 110 in the architecture 100. In addition, modern vehicles are typically equipped with chipset systems such as those used for automatic parking assistance systems (Automatic Parking Assist System, APAS), forward looking systems (Front Looking System, FLS), car entertainment systems, and the like. Such a chipset system may be modified in accordance with embodiments of the present disclosure to function as a processing unit 120 in architecture 100. Therefore, the vehicle can realize the situation detection-based braking reminding at a lower cost without greatly changing the hardware structure of the vehicle.

It should be appreciated that the architecture 100 shown in FIG. 1 is merely one example of an architecture for a system for context-detection based braking alert. The system for context-detection based braking alert may have any other architecture and may include more or fewer elements, depending on the actual application requirements. In addition, the various units in architecture 100 may have any other implementation. For example, the receiving unit 110 may include a sensor, such as a millimeter wave radar, in addition to a camera, a laser radar, and the like.

FIG. 2 illustrates an exemplary process 200 for context-detection-based braking alert, according to an embodiment of the present disclosure. Process 200 may be performed, for example, by processing unit 120 in fig. 1.

At 202, a front input may be obtained. The front input may be received, for example, from a receiving unit. In the case where the receiving unit is a camera, the front input may be an image corresponding to the environment in front of the current vehicle. The image may include an image of a vehicle ahead in front of the current vehicle. In the case where the receiving unit is a lidar, the front input may be a point cloud corresponding to the environment in front of the current vehicle. The point cloud may comprise a point cloud of a preceding vehicle.

At 204, it may be detected whether the front vehicle is braked or is about to brake based on the front input.

In one embodiment, whether the front vehicle is braked or is about to brake may be detected by detecting whether the front vehicle is issuing a brake lift. For example, it may be detected whether a preceding vehicle emits a visual signal, an infrared signal, an acoustic signal, a wireless signal, or the like for alerting of the current vehicle braking. The visual signal, infrared signal, acoustic signal, wireless signal, etc. may be emitted by the corresponding hardware unit of the preceding vehicle. As an example, the visual signal may be emitted by a brake signal light or a brake alert light of the preceding vehicle. The brake signal lights may be existing lights on the vehicle that indicate that the brake pedal is depressed, such as conventional brake signal lights at both ends of the tail or high-end brake signal lights located in the middle and upper portion of the tail. According to embodiments of the present disclosure, a brake signal light on a vehicle may also be used to issue a brake alert to a vehicle behind it. The brake alert light may be a light added at the rear of the vehicle specifically configured to alert the vehicle behind it. For example, a front vehicle may immediately make an emergency braking when it observes an emergency situation in front of it, and at the same time, the vehicle behind it is alerted to take a braking action by a brake alert light. The method can be used for detecting whether the front vehicle sends out the braking reminding or not according to the form of the braking reminding sent out by the front vehicle and the form of the receiving unit of the current vehicle. For example, when the brake alert is a visual signal emitted through a brake signal light or a brake alert light, and the receiving unit of the preceding vehicle is a camera, it is possible to determine whether the brake signal light or the brake alert light is on by performing image detection on an image provided by the camera, thereby detecting whether the preceding vehicle emits a brake alert.

In another embodiment, whether the preceding vehicle is braked may be detected by detecting whether the magnitude of the drop in the absolute speed of the preceding vehicle exceeds a drop threshold. When it is detected that the magnitude of the drop in the absolute speed of the preceding vehicle exceeds the drop threshold, it may be determined that braking of the preceding vehicle has occurred. In particular, when it is detected that the magnitude of the drop in the absolute speed of the preceding vehicle exceeds the drop threshold in an extremely short time, it may be determined that emergency braking of the preceding vehicle has occurred. FIG. 3 illustrates an exemplary process 300 for calculating an absolute speed of a preceding vehicle in accordance with an embodiment of the present disclosure. At 302, a change in distance between a preceding vehicle and a current vehicle over a predetermined time may be estimated. The distance between the preceding vehicle and the current vehicle may be estimated by known inter-vehicle ranging techniques. At 304, a relative speed of the preceding vehicle with respect to the current vehicle may be calculated based on the change and the predetermined time. At 306, an absolute speed of the front vehicle may be calculated based on the relative speed of the front vehicle with respect to the current vehicle and the absolute speed of the current vehicle.

Either of the two embodiments described above may be employed to detect whether a preceding vehicle is braked or is about to be braked. In this way, it is possible to timely and accurately detect whether the preceding vehicle is braked or is about to brake, which helps the current vehicle to timely issue an accurate rear-vehicle brake alert to the following vehicle and timely take a braking action.

If front vehicle braking or impending braking is not detected at 204, process 200 may return to 202, i.e., continue to obtain front input.

If a front vehicle brake or impending brake is detected at 204, process 200 may proceed synchronously to 206 and 216.

At 206, a rear input may be obtained. The rear input may be received, for example, from a receiving unit. In the case where the receiving unit is a camera, the rear input may be an image corresponding to the rear environment of the current vehicle. The image may include an image of a rear vehicle located behind the current vehicle. In the case where the receiving unit is a lidar, the rear input may be a point cloud corresponding to the rear environment of the current vehicle. The point cloud may comprise a point cloud of a rear vehicle.

At 208, a rear context of the current vehicle may be obtained by analyzing the rear input. The rear context may include, for example, a distance between the rear vehicle and the current vehicle, a relative speed of the rear vehicle with respect to the current vehicle, road conditions, weather conditions, a model of the rear vehicle, and the like. The rear context may be obtained in a known manner. For example, the distance between the rear vehicle and the current vehicle may be obtained by known inter-vehicle ranging techniques. For the relative speed of the rear vehicle with respect to the current vehicle, a change in the distance between the rear vehicle and the current vehicle may be estimated first, and then based on the change and the predetermined time, the relative speed of the rear vehicle with respect to the current vehicle may be calculated. For road surface conditions, weather conditions, vehicle types of rear vehicles, etc., it can be obtained by known image classification techniques.

At 210, a rear collision probability of the rear vehicle colliding with the current vehicle may be predicted based on a rear context of the current vehicle and assumptions of the current vehicle and rear vehicle brakes. The rear collision probability may be a number normalized to be in the range of 0, 1. The greater the rear collision probability, the greater the probability that the rear vehicle will collide with the current vehicle, i.e., the more likely the rear vehicle will rear-end the current vehicle. An exemplary procedure for predicting the rear collision probability will be described later with reference to fig. 4.

At 212, it may be determined whether the rear impact probability is greater than a rear impact threshold.

If, at 212, it is determined that the rear impact probability is greater than the rear impact threshold, process 200 may proceed to 214. At 214, a rear vehicle brake alert may be issued to the rear vehicle. For example, a rear vehicle brake alert instruction may be sent to a rear vehicle brake alert unit in the current vehicle, so that the rear vehicle brake alert unit sends out a rear vehicle brake alert. The rear vehicle brake alert may include, for example, a visual signal, an infrared signal, an acoustic signal, a wireless signal, etc. for alerting the rear vehicle to brake. The visual signal, infrared signal, acoustic signal, wireless signal, etc. may be emitted by the corresponding hardware unit of the current vehicle. As an example, the rear vehicle brake alert unit may be a brake signal light of the current vehicle. The brake signal lights may be existing lights on the vehicle that indicate that the brake pedal is depressed, such as conventional brake signal lights at both ends of the tail or high-end brake signal lights located in the middle and upper portion of the tail. According to embodiments of the present disclosure, a brake signal light on a vehicle may also be used to issue a rear vehicle brake alert to a vehicle behind it. Preferably, the rear vehicle brake alert unit may be an alert light of a brake of a current vehicle. The brake alert light may be a light added at the rear of the vehicle specifically configured to alert the vehicle behind the vehicle to the brake of the rear vehicle. The shape of the brake alert light or the nature of the light it emits may be significantly different from the brake signal light so that a rear vehicle can easily detect a rear vehicle brake alert it emits.

If it is determined at 212 that the rear impact probability is less than or equal to the rear impact threshold, the process 200 may return to 206, where the rear input may continue to be obtained. In this case, the current vehicle may not issue a rear-vehicle brake alert to the rear vehicle to avoid interfering with the rear vehicle.

As can be seen from steps 212 to 214, if the rear collision probability is greater than a predetermined rear collision threshold, i.e., if the rear vehicle is likely to collide or rear-end the current vehicle, a rear vehicle brake alert may be issued to the rear vehicle; and if the rear collision probability is not greater than the predetermined rear collision threshold, i.e., if the rear vehicle may not collide or rear-end the current vehicle, a rear vehicle brake alert is not issued to the rear vehicle. That is, the rear vehicle brake alert may be issued to the rear vehicle only when the rear vehicle is likely to collide or rear-end the current vehicle. By the mode, accurate rear vehicle braking reminding can be transmitted to the rear vehicle. In addition, if each vehicle can determine whether to send a rear vehicle braking reminding to the vehicle behind the vehicle based on the rear situation of the vehicle, the accurate rear vehicle braking reminding can be sequentially transmitted backwards, so that the risk of collision or rear-end collision accidents on the road is obviously reduced.

If front vehicle braking or impending braking is detected at 204, process 200 may also proceed to 216. At 216, a front context of the current vehicle is obtained by analyzing the front inputs. The forward context of the current vehicle may include, for example, a distance between the front vehicle and the current vehicle, a relative speed of the front vehicle with respect to the current vehicle, a road surface condition, a weather condition, a model of the front vehicle, and the like. The front context may be obtained in a known manner. For example, the distance between the preceding vehicle and the current vehicle may be obtained by known inter-vehicle ranging techniques. For the relative speed of the preceding vehicle with respect to the current vehicle, a change in the distance between the preceding vehicle and the current vehicle may be estimated first, and then based on the change and the predetermined time, the relative speed of the preceding vehicle with respect to the current vehicle may be calculated. For road surface conditions, weather conditions, vehicle types of preceding vehicles, etc., it can be obtained by known image classification techniques.

At 218, a forward collision probability of the current vehicle colliding with the forward vehicle may be predicted based on the forward context of the current vehicle and assumptions of the forward vehicle and the current vehicle brakes. The frontal collision probability may be a number normalized to be in the range of 0, 1. The greater the probability of a frontal collision, the greater the probability that the current vehicle will collide with the front vehicle, i.e., the more likely the current vehicle will rear-end the front vehicle. The front collision probability may be predicted in a similar manner to that of the rear collision probability.

At 220, it may be determined whether the frontal collision probability is greater than a frontal collision threshold.

If it is determined at 220 that the frontal collision probability is greater than the frontal collision threshold, then a host vehicle brake command may be sent inside the current vehicle. It may be decided how to transmit the own vehicle brake instruction inside the current vehicle according to the type of the current vehicle. The types of vehicles currently may include, for example, manually driven vehicles, automatically driven vehicles, and the like.

Process 200 may proceed to 222. At 222, it may be determined whether the current vehicle is a manually driven vehicle.

If it is determined at 222 that the current vehicle is a manually driven vehicle, process 200 may proceed to 224. At 224, a host vehicle braking alert may be sent to a host vehicle braking alert unit in the current vehicle to cause the host vehicle braking alert unit to issue a host vehicle braking alert. The present vehicle brake alert may alert the driver of the current vehicle to apply a braking operation, such as an emergency braking operation, as soon as possible. The vehicle brake alert may include, for example, a visual signal, an acoustic signal, a tactile signal, and the like. Preferably, the intensity of the own-vehicle brake alert issued by the own-vehicle brake alert unit may be correlated with the front collision probability. The greater the frontal collision probability, the greater the intensity of the own-vehicle braking alert may be to encourage the driver to perform the braking operation with greater braking effort. For example, when the own-vehicle braking alert is an acoustic signal, the acoustic signal may be jerky if the frontal collision probability is a greater value than the frontal collision threshold; and if the frontal collision probability is a small value greater than the frontal collision threshold, the acoustic signal may be flat.

If it is determined at 222 that the current vehicle is not a manually driven vehicle, the current vehicle may be an automatically driven vehicle. In this case, process 200 may proceed to 226. At 226, the present vehicle braking command may be sent at least to an automatic braking unit in the current vehicle to cause the automatic braking unit to perform an automatic braking operation. Preferably, the braking force of the automatic braking operation performed by the automatic braking unit may be correlated with the front collision probability. The greater the frontal collision probability, the greater the braking force of the automatic braking operation may be, so that the current vehicle can be stopped as soon as possible. Alternatively, if the current vehicle is an autonomous vehicle, a host vehicle braking instruction may also be sent to a host vehicle braking alert unit in the current vehicle, so that the driver in the current vehicle may also know that the current vehicle is about to be automatically braked and take over the vehicle and take appropriate action if necessary.

If it is determined at 220 that the frontal collision probability is less than or equal to the frontal collision threshold, the process 200 may return to 202, i.e., continue to obtain the frontal input. In this case, the current vehicle may continue to travel forward for a distance until the front collision probability is greater than the front collision threshold, and a own vehicle braking instruction may not be transmitted inside the current vehicle so that the automatic driving unit or the driver of the current vehicle takes a braking operation. If at this time, the rear vehicle is likely to collide with or rear-end the current vehicle, and the rear vehicle can immediately make an emergency brake when receiving the rear brake alert, while the current vehicle still continues to travel for a distance while ensuring that the front vehicle is not rear-ended, the distance between the rear vehicle and the current vehicle may be increased. In this way, the risk of the rear vehicle following the current vehicle can be reduced.

It should be appreciated that the process for context-detection based braking alert described above in connection with fig. 2 is merely exemplary. The steps in the process for context-detection based braking alert may be replaced or modified in any manner depending on the actual application requirements, and the process may include more or fewer steps. Further, the particular order or hierarchy of steps in process 200 is merely exemplary, and the process for context-detection based brake alert may be performed in an order different from that described.

Fig. 4 illustrates an exemplary process 400 for predicting a rear collision probability of a rear vehicle colliding with a current vehicle, in accordance with an embodiment of the present disclosure. Process 400 may correspond to step 210 in fig. 2.

At 402, a time of collision of the rear vehicle with the current vehicle may be estimated based on a rear context of the current vehicle and assumptions of the current vehicle and rear vehicle brakes. The rear context may include, for example, a distance between the rear vehicle and the current vehicle, a relative speed of the rear vehicle with respect to the current vehicle, road conditions, weather conditions, a model of the rear vehicle, and the like.

Assume that the time at which the rear vehicle and the current vehicle start braking is an initial time 0, and the time at which the rear vehicle collides with the current vehicle is t _b . That is, the time of collision of the rear vehicle with the current vehicle may be marked as t _b . From the initial time 0 to time t _b During which the following vehicle travels a distance S _b (t _b ) Distance S to the current vehicle _c (t _b ) There may be the following relationship:

S _b (t _b )＝S _c (t _b )+L _b -(V _b -V _c )*t _d (1)

wherein L is _b Is the initial distance between the rear vehicle and the current vehicle, V _b Is the initial speed of the rear vehicle, V _c Is the initial speed of the current vehicle, and t _d Is the brake response time of the rear vehicle and the current vehicle. Here, for simplicity, it is assumed that the following vehicle and the current vehicle have the same brake response time. Brake response time t _d May be an empirical value, for example 0.4 seconds or 0.5 seconds.

The time t from the initial time 0 can be calculated, for example, by the following formula _b During which the following vehicle travels a distance S _b (t _b )：

Wherein a is _b Is the braking acceleration of the rear vehicle.

Braking acceleration a of a rear vehicle _b Is composed of braking force f _b And (3) generating. The braking force f can be expressed, for example, by the following formula _b ：

f _b ＝μ _b *G _b ＝μ _b *m _b *g (3)

Wherein mu _b Is the braking force coefficient of the rear vehicle, m _b Is the mass of the rear vehicle and g is the gravitational acceleration. Braking force coefficient mu _b May be related to road conditions, weather conditions, vehicle type of the vehicle behind, etc. Weather conditions can affect road conditions, such as the level of road wetting. The road surface condition affects the friction between the vehicle and the road surface, thereby affecting the braking force coefficient mu _b . The type of the vehicle is related to the maximum allowable braking force of the vehicle, thereby influencing the braking force coefficient mu _b . For example, the maximum allowable braking force of a heavy truck may be less than the maximum allowable braking force of a light car, which would result in the braking distance of a heavy truck being greater than the braking distance of a light car under comparable conditions.

Based on equation (3), it can be obtained that:

combining equation (2) and equation (4), one can obtain:

can similarly calculate from the initial time 0 to the time t _b During which the current vehicle travels a distance S _c (t _b ) The following are provided:

combining equation (1), equation (5) and equation (6), one can get:

equation (7) relates to t _b Is a unitary quadratic equation of (a). The equation may be solved by known unitary quadratic equation solving methods. For example, equation (7) may have two solutions:

the two solutions may be positive and negative solutions, respectively. The positive solution of the two solutions can be taken as the time t of collision of the rear vehicle with the current vehicle _b 。

From equation (8), it can be seen that the brake response time t _d Constant time t of collision of the rear vehicle with the current vehicle _b Can be compared with the relative speed (V _b -V _c ) Braking force coefficient mu of a rear vehicle _b Braking force coefficient mu with current vehicle _c Difference (mu) _b -μ _c ) And an initial distance L between the rear vehicle and the current vehicle _b Related to the following.

Alternatively, μmay be assumed for optimization of computational cost or increase of operating speed _b ＝μ _c . In this case, equation (7) can be reduced to:

V _b *t _b ＝V _c *t _b +L _b -(V _b -V _c )*t _d (9)

thus, it is possible to solve:

from equation (10), it can be seen that the brake response time t _d Constant time t of collision of the rear vehicle with the current vehicle _b Can be compared with the relative speed (V _b -V _c ) And an initial distance L between the rear vehicle and the current vehicle _b Related to the following.

At time t when collision of the rear vehicle with the current vehicle is estimated _b Thereafter, the estimated time t may be based on _b To calculate the rear collision probability. Preferably, the rear collision probability may be normalized to [0,1 ]]Values within the range. In one embodiment, the normalized time may be obtained first, and then the normalized rear-end collision probability may be obtained based on the normalized time. For example, at 404, the estimated time t may be determined by _b Performing a normalization operation to obtain a normalized time t' _b . Normalized time t' _b May be [0,1 ] ]Values within the range. Various known normalization methods may be employed for the estimated time t _b A normalization operation is performed. As an example, the normalization method may be a maximum minimum normalization (Min-Max Normalization) method. Accordingly, the normalized time t 'can be calculated, for example, by the following formula' _b ：

Wherein t is _min Is time t _b And t is the minimum value of _max Is time t _b Is a maximum value of (a). Theoretically, time t _b And may be any number from 0 to plus infinity. Namely t _min May be 0. Can be t _max Is set to a predetermined value, for example 30 seconds. This means that if the rear vehicle does not collide with the current vehicle within 30 seconds, it can be considered that the rear vehicle will not collide with the current vehicle.

At t _min With 0, equation (11) can be further evolved to:

after a normalized time t 'is obtained' _b Thereafter, at 406, a normalized time t 'may be based' _b Calculating a rear collision probability P of a rear vehicle colliding with a current vehicle _b . The rear collision probability P may be calculated, for example, by the following formula _b ：

t′ _b Is normalized to [0,1 ]]Values within the range. Correspondingly, P _b Is also normalized to [0,1 ]]Values within the range. At t _max Under constant conditions, t _b The smaller the value of P _b The closer to 1, i.e., the greater the rear collision probability; and t is _b The greater the value of P _b The closer to 0, i.e., the smaller the rear collision probability will be.

It should be appreciated that the process for predicting the rear collision probability described above in connection with fig. 4 is merely exemplary. The steps in the process for predicting the rear collision probability may be replaced or modified in any manner according to actual application requirements, and the process may include more or fewer steps. For example, except that a maximum-minimum normalization method is employed for the estimated time t _b In addition to performing normalization operations, any other normalization method may be used to normalize the estimated time t _b A normalization operation is performed. In addition, after a normalized time t 'is obtained' _b Thereafter, except for calculating the rear collision probability P by the formula (13) _b Other ways of calculating the rear collision probability P are also possible _b 。

The forward collision probability P of the current vehicle colliding with the preceding vehicle may be predicted by a process similar to process 400 _f . For example, the time t of the current vehicle to front vehicle collision may be estimated based on the front context of the current vehicle and assumptions of the current vehicle and front vehicle braking _f . Subsequently, the estimated time t can be calculated by _f Performing a normalization operation to obtain a normalized time t' _f . Then, the time t 'based on the normalization can be' _f Calculating a front collision probability P of a collision between a current vehicle and a preceding vehicle _f 。

Fig. 5A-5G illustrate examples 500 a-500G of context detection based braking alerts according to embodiments of the present disclosure.

In example 500a in fig. 5A, weather conditions and road conditions are normal. The front vehicle 504a located in front of the current vehicle 502a is being braked urgently. The distance between the front vehicle 504a and the current vehicle 502a is far. The rear vehicle 506a located behind the current vehicle 502a is a truck and is closer to the current vehicle 502 a. The rear collision probability of the rear vehicle 506a colliding with the current vehicle 502a predicted by the process 200 in fig. 2 may be greater than the rear collision threshold. In this case, the current vehicle 502a may issue a rear-vehicle braking alert to the rear vehicle 506a to alert the rear vehicle 506a that it is to be braked immediately. For example, the current vehicle 502a may have its brake signal light or brake alert light immediately on. Meanwhile, the front collision probability of the current vehicle 502a colliding with the front vehicle 504a predicted by the process 200 in fig. 2 may be smaller than the front collision threshold. In this case, the current vehicle 502a may not take braking action. In this case, the current vehicle 502a may continue to travel forward a distance until the front collision probability is greater than the front collision threshold. If the rear vehicle 506a is able to immediately emergency brake upon detection of a rear-end vehicle brake alert issued by the current vehicle 502a, while the current vehicle 502a continues to travel a distance while ensuring that the front vehicle 504a is not knocked back, the distance between the rear vehicle 506a and the current vehicle 502a may be increased. In this way, the risk of rear-end collision of the rear vehicle 506a with the current vehicle 502a may be reduced.

In example 500B in fig. 5B, the weather conditions and the road surface conditions are normal. The front vehicle 504b located in front of the current vehicle 502b is being braked urgently. The distance between the front vehicle 504b and the current vehicle 502b is moderate. The rear vehicle 506b located rearward of the current vehicle 502b is moderately distant from the current vehicle 502 b. The rear collision probability of the rear vehicle 506b colliding with the current vehicle 502b predicted by the process 200 in fig. 2 may be less than the rear collision threshold. In this case, the current vehicle 502b may not issue a rear vehicle brake alert to the rear vehicle 506b to avoid interfering with the rear vehicle 506b. Meanwhile, the front collision probability of the current vehicle 502b colliding with the front vehicle 504b predicted by the process 200 in fig. 2 may be smaller than the front collision threshold. In this case, the current vehicle 502b may not take braking action. In this case, the current vehicle 502b may continue to travel forward a distance until the front collision probability is greater than the front collision threshold.

In example 500C in fig. 5C, the road surface is raining at that time, and thus slippery. The front vehicle 504c located in front of the current vehicle 502c is being braked urgently. The distance between the front vehicle 504c and the current vehicle 502c is far. The distance between the rear vehicle 506c located rearward of the current vehicle 502c and the current vehicle 502c is closer. The rear collision probability of the rear vehicle 506c colliding with the current vehicle 502c predicted by the process 200 in fig. 2 may be greater than the rear collision threshold. In this case, the current vehicle 502c may issue a rear vehicle brake alert to the rear vehicle 506 c. For example, the current vehicle 502c may have its brake light or brake alert light turned on immediately to alert the rear vehicle 506c to be braked immediately. Meanwhile, the front collision probability of the current vehicle 502c colliding with the front vehicle 504c predicted by the process 200 in fig. 2 may be smaller than the front collision threshold. In this case, the current vehicle 502c may not take braking action. In this case, the current vehicle 502c may continue to travel forward a distance until the front collision probability is greater than the front collision threshold. If the rear vehicle 506c is able to immediately emergency brake upon detection of a rear-end vehicle brake alert issued by the current vehicle 502c, while the current vehicle 502c continues to travel a distance while ensuring that the front vehicle 504c is not rear-ended, the distance between the rear vehicle 506c and the current vehicle 502c may be increased. In this way, the risk of rear-end vehicle 506c to rear-end current vehicle 502c may be reduced.

In example 500D in fig. 5D, the weather conditions and the road surface conditions are normal. The front vehicle 504d located in front of the current vehicle 502d is being braked urgently. The distance between the front vehicle 504d and the current vehicle 502d is relatively close. A rear vehicle 506d located rearward of the current vehicle 502d is farther from the current vehicle 502 d. The rear collision probability of the rear vehicle 506d colliding with the current vehicle 502d predicted by the process 200 in fig. 2 may be less than the rear collision threshold. In this case, the current vehicle 502d may not issue a rear vehicle brake alert to the rear vehicle 506d to avoid interfering with the rear vehicle 506d. Meanwhile, the front collision probability of the current vehicle 502d colliding with the front vehicle 504d predicted by the process 200 in fig. 2 may be greater than the front collision threshold. In this case, the current vehicle 502d may immediately take an emergency braking operation to avoid a collision with the preceding vehicle 504 d.

In example 500E in fig. 5E, weather conditions and road conditions are normal. A front vehicle 504e located in front of the current vehicle 502e is braking but not emergency braking. The distance between the front vehicle 502e and the front vehicle 504e is moderate. The rear vehicle 506e located behind the current vehicle 502e is a truck and is moderately distant from the current vehicle 502 e. The rear collision probability of the rear vehicle 506e colliding with the current vehicle 502e predicted by the process 200 in fig. 2 may be less than the rear collision threshold. In this case, the current vehicle 502e may not issue a rear-vehicle brake alert to the rear vehicle 506e to avoid interfering with the rear vehicle 506e. Meanwhile, the front collision probability of the current vehicle 502e colliding with the front vehicle 504e predicted by the process 200 in fig. 2 may be smaller than the front collision threshold. In this case, the current vehicle 502e may not take braking action. In this case, the current vehicle 502e may continue to travel forward a distance until the front collision probability is greater than the front collision threshold.

In example 500F in fig. 5F, the weather conditions and the road surface conditions are normal. The front vehicle 504f, which is located in front of the current vehicle 502f, has not been braked, but its brake alert light is on. The distance between the front vehicle 504f and the current vehicle 502f is moderate. The rear vehicle 506f located behind the current vehicle 502f is a truck and is closer to the current vehicle 502 f. The rear collision probability of the rear vehicle 506f colliding with the current vehicle 502f predicted by the process 200 in fig. 2 may be greater than the rear collision threshold. In this case, the current vehicle 502f may issue a rear vehicle brake alert to the rear vehicle 506 f. For example, the current vehicle 502f may have its brake light or brake alert light turned on immediately to alert the rear vehicle 506f to be braked immediately. Meanwhile, the front collision probability of the current vehicle 502f colliding with the front vehicle 504f predicted by the process 200 in fig. 2 may be smaller than the front collision threshold. In this case, the current vehicle 502f may not take braking action. In this case, the current vehicle 502f may continue to travel forward a distance until the front collision probability is greater than the front collision threshold. If the rear vehicle 506f is able to immediately emergency brake upon detection of a rear vehicle braking alert from the current vehicle 502f, while the current vehicle 502f continues to travel a distance while ensuring that the front vehicle 504f is not knocked back, the distance between the rear vehicle 506f and the current vehicle 502f may be increased. In this way, the risk of the rear vehicle 506f following the current vehicle 502f may be reduced.

In example 500G in fig. 5G, the weather conditions and the road surface conditions are normal. The front vehicle 504g, which is located in front of the current vehicle 502g, has not been braked, but its brake alert light is on. The distance between the front vehicle 504g and the current vehicle 502g is relatively close. A rear vehicle 506g located rearward of the current vehicle 502g is farther from the current vehicle 502 g. The rear collision probability of the rear vehicle 506g colliding with the current vehicle 502g predicted by the process 200 in fig. 2 may be less than the rear collision threshold. In this case, the current vehicle 502g may not issue a rear vehicle brake alert to the rear vehicle 506g to avoid interfering with the rear vehicle 506g. Meanwhile, the front collision probability of the current vehicle 502g colliding with the front vehicle 504g predicted by the process 200 in fig. 2 may be greater than the front collision threshold. In this case, the current vehicle 502g may take an emergency braking operation to avoid a collision with the preceding vehicle 504 g.

The foregoing describes a context detection based brake alert according to an embodiment of the present disclosure. The front vehicle may issue a rear vehicle brake alert to the rear vehicle upon detecting a front vehicle brake or impending brake. The current vehicle may be in the same lane as the front and rear vehicles. Alternatively, the present vehicle may also detect whether the side front vehicle in the adjacent lane is braked or is about to brake, and issue a brake alert to the side rear vehicle in the adjacent lane when the side front vehicle in the adjacent lane is detected to be braked or is about to brake. The braking alert to the side rear vehicle may be different from the braking alert to the rear vehicle, e.g., a different light may be illuminated, a different coded wireless signal sent, etc.

FIG. 6 is a flowchart of an exemplary method 600 for context-detection-based braking alert, according to an embodiment of the present disclosure.

At 610, it may be detected whether a front vehicle located in front of the current vehicle is braked or is about to brake.

At 620, a rear collision probability of the rear vehicle colliding with the current vehicle may be predicted based on a rear context of the current vehicle and assumptions of the current vehicle and rear vehicle brakes located rearward of the current vehicle in response to detecting the front vehicle braking or impending braking.

At 630, it may be determined whether the rear impact probability is greater than a rear impact threshold.

At 640, a rear vehicle brake alert may be issued to the rear vehicle in response to determining that the rear collision probability is greater than the rear collision threshold.

In one embodiment, the detecting whether the preceding vehicle is braked or is about to brake may include: detecting whether the front vehicle sends out a braking reminding; and/or detecting whether a magnitude of a drop in absolute speed of the preceding vehicle exceeds a drop threshold.

The detecting whether the front vehicle issues a braking alert may include: detecting whether the front vehicle emits at least one of a visual signal, an infrared signal, an acoustic signal, and a wireless signal for alerting of the current vehicle braking.

The visual signal may be emitted by a brake signal light or a brake alert light of the preceding vehicle.

The absolute speed of the preceding vehicle may be calculated by: estimating a change in a distance between the preceding vehicle and the current vehicle over a predetermined time; calculating a relative speed of the preceding vehicle with respect to the current vehicle based on the change and the predetermined time; and calculating an absolute speed of the preceding vehicle based on the relative speed and an absolute speed of the current vehicle.

In one embodiment, the predicting the rear collision probability may include: estimating a time of collision of the rear vehicle with the current vehicle based on the rear context and assumptions of the current vehicle and the rear vehicle brakes; obtaining a normalized time by performing a normalization operation on the estimated time; and calculating the rear collision probability based on the normalized time.

In one embodiment, the rear context may include: a relative speed of the rear vehicle with respect to the current vehicle and a distance between the rear vehicle and the current vehicle.

In one embodiment, the issuing the rear vehicle brake alert may include: at least one of a visual signal, an infrared signal, an acoustic signal, and a wireless signal for alerting the rear vehicle to brake is sent to the rear vehicle.

The visual signal may be emitted by a brake signal light or a brake alert light of the current vehicle.

In one embodiment, the method 600 may further comprise: in response to detecting the front vehicle braking or impending braking, predicting a front collision probability of the current vehicle colliding with the front vehicle based on a front context of the current vehicle and assumptions of the front vehicle and the current vehicle braking; determining whether the frontal collision probability is greater than a frontal collision threshold; and in response to determining that the front collision probability is greater than the front collision threshold, transmitting a host vehicle brake command inside the current vehicle.

The front context may include: a relative speed of the front vehicle with respect to the current vehicle and a distance between the front vehicle and the current vehicle.

The current vehicle may be a manually driven vehicle. The sending the vehicle brake command may include: and sending the vehicle braking instruction to a vehicle braking reminding unit in the current vehicle so that the vehicle braking reminding unit sends out a vehicle braking reminding.

The vehicle brake alert may include at least one of a visual signal, an acoustic signal, and a tactile signal.

The intensity of the vehicle braking alert may be correlated with the frontal collision probability.

The current vehicle may be an autonomous vehicle. The sending the vehicle brake command may include: and sending the vehicle braking instruction to at least an automatic braking unit in the current vehicle so that the automatic braking unit performs automatic braking operation.

The braking effort of the automatic braking operation may be associated with the frontal collision probability.

The rear context may further include at least one of a road surface condition, a weather condition, a model of the rear vehicle. The front context may further include at least one of a road surface condition, a weather condition, a model of the front vehicle.

It should be appreciated that method 600 may also include any steps/processes for context-based detection of braking alerts according to embodiments of the present disclosure as described above.

FIG. 7 illustrates an exemplary system 700 for context-detection-based braking alert in accordance with an embodiment of the present disclosure.

The system 700 may include: a processing unit 710 configured to: detecting whether a front vehicle located in front of a current vehicle is braked or is about to brake, in response to detecting that the front vehicle is braked or is about to brake, predicting a rear collision probability of the rear vehicle colliding with the current vehicle based on a rear situation of the current vehicle and an assumption of the current vehicle and a rear vehicle being located behind the current vehicle, determining whether the rear collision probability is greater than a rear collision threshold, and in response to determining that the rear collision probability is greater than the rear collision threshold, transmitting a rear vehicle brake alert instruction to a rear vehicle brake alert unit; and a rear vehicle brake alert unit 720 configured to: and in response to receiving the rear vehicle braking reminding instruction from the processing unit, sending a rear vehicle braking reminding to the rear vehicle.

The processing unit 710 may also be configured to: in response to detecting the front vehicle braking or impending braking, predicting a front collision probability of the current vehicle colliding with the front vehicle based on a front context of the current vehicle and assumptions of the front vehicle and the current vehicle braking, determining whether the front collision probability is greater than a front collision threshold, and in response to determining that the front collision probability is greater than the front collision threshold, transmitting a host vehicle braking instruction inside the current vehicle. The system 700 may further include: a host vehicle brake alert unit 730 configured to issue a host vehicle brake alert in response to receiving the host vehicle brake instruction from the processing unit; and/or an automatic braking unit 740 configured to perform an automatic braking operation in response to receiving the own vehicle braking instruction from the processing unit.

It should be appreciated that system 700 may also include performing braking alert for context-based detection in accordance with embodiments of the present disclosure as described above

FIG. 8 illustrates an exemplary apparatus 800 for context detection based braking alert according to an embodiment of the present disclosure.

The apparatus 800 may include: at least one processor 810; and a memory 820 storing computer-executable instructions. The computer-executable instructions, when executed, may cause the at least one processor 810 to: the method includes detecting whether a front vehicle located in front of a current vehicle is braked or is about to brake, responsive to detecting that the front vehicle is braked or is about to brake, predicting a rear collision probability of the rear vehicle colliding with the current vehicle based on a rear context of the current vehicle and an assumption of the current vehicle and a rear vehicle brake located behind the current vehicle, determining whether the rear collision probability is greater than a rear collision threshold, and responsive to determining that the rear collision probability is greater than the rear collision threshold, issuing a rear vehicle brake alert to the rear vehicle.

It should be appreciated that the processor 810 may also perform any other steps/processes of a method for context-detection based braking alert according to embodiments of the present disclosure as described above.

Embodiments of the present disclosure propose a computer program product for context detection based braking alert, comprising a computer program for execution by at least one processor for: detecting whether a front vehicle located in front of a current vehicle is braked or is about to brake; in response to detecting the front vehicle braking or impending braking, predicting a rear collision probability of the rear vehicle colliding with the current vehicle based on a rear context of the current vehicle and assumptions of the current vehicle and rear vehicle braking located rearward of the current vehicle; determining whether the rear impact probability is greater than a rear impact threshold; and in response to determining that the rear collision probability is greater than the rear collision threshold, issuing a rear vehicle brake alert to the rear vehicle. Furthermore, the computer program may also be executed to implement any other steps/processes of a method for context-detection based braking alert according to embodiments of the present disclosure as described above.

Embodiments of the present disclosure may be embodied in a non-transitory computer readable medium. The non-transitory computer-readable medium may include instructions that, when executed, cause one or more processors to perform any operations of a method for context-detection-based braking alert according to embodiments of the present disclosure as described above.

It should be understood that all operations in the methods described above are merely exemplary, and the present disclosure is not limited to any operations in the methods or the order of such operations, but rather should cover all other equivalent variations under the same or similar concepts. In addition, the articles "a" and "an" as used in this specification and the appended claims should generally be construed to mean "one" or "one or more" unless specified otherwise or clear from context to be directed to a singular form.

It should also be understood that all of the modules in the apparatus described above may be implemented in various ways. These modules may be implemented as hardware, software, or a combination thereof. Furthermore, any of these modules may be functionally further divided into sub-modules or combined together.

The processor has been described in connection with various apparatuses and methods. These processors may be implemented using electronic hardware, computer software, or any combination thereof. Whether such processors are implemented as hardware or software will depend upon the particular application and the overall design constraints imposed on the system. As an example, a processor, any portion of a processor, or any combination of processors presented in this disclosure may be implemented with a microprocessor, microcontroller, digital Signal Processor (DSP), field Programmable Gate Array (FPGA), programmable Logic Device (PLD), state machine, gated logic unit, discrete hardware circuits, and other suitable processing components configured to perform the various functions described in this disclosure. The functions of a processor, any portion of a processor, or any combination of processors presented in this disclosure may be implemented using software that is executed by a microprocessor, microcontroller, DSP, or other suitable platform.

Software should be construed broadly to mean instructions, instruction sets, code segments, program code, programs, subroutines, software modules, applications, software packages, routines, subroutines, objects, threads of execution, procedures, functions, and the like. The software may reside in a computer readable medium. Computer-readable media may include, for example, memory, which may be, for example, a magnetic storage device (e.g., hard disk, floppy disk, magnetic strips), optical disk, smart card, flash memory device, random Access Memory (RAM), read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), registers, or removable disk. Although the memory is shown separate from the processor in various aspects presented in this disclosure, the memory may also be located internal to the processor, such as a cache or register.

The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Accordingly, the claims are not intended to be limited to the aspects shown herein. All structural and functional equivalents to the elements of the various aspects described in the disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein and are intended to be encompassed by the claims.

Claims

1. A method for context detection based braking alert, comprising:

detecting whether a front vehicle located in front of a current vehicle is braked or is about to brake;

in response to detecting the front vehicle braking or impending braking, predicting a rear collision probability of the rear vehicle colliding with the current vehicle based on a rear context of the current vehicle and assumptions of the current vehicle and rear vehicle braking located rearward of the current vehicle;

determining whether the rear impact probability is greater than a rear impact threshold; and

in response to determining that the rear collision probability is greater than the rear collision threshold, a rear vehicle brake alert is issued to the rear vehicle.

2. The method of claim 1, wherein the detecting whether the preceding vehicle is braked or is about to brake comprises:

detecting whether the front vehicle sends out a braking reminding; and/or

It is detected whether a decrease amplitude of the absolute speed of the preceding vehicle exceeds a decrease threshold.

3. The method of claim 2, wherein the detecting whether the front vehicle issues a braking alert comprises:

detecting whether the front vehicle emits at least one of a visual signal, an infrared signal, an acoustic signal, and a wireless signal for alerting of the current vehicle braking.

4. A method according to claim 3, wherein the visual signal is emitted by a brake signal light or a brake alert light of the preceding vehicle.

5. The method of claim 2, wherein the absolute speed of the front vehicle is calculated by:

estimating a change in a distance between the preceding vehicle and the current vehicle over a predetermined time;

calculating a relative speed of the preceding vehicle with respect to the current vehicle based on the change and the predetermined time; and

an absolute speed of the preceding vehicle is calculated based on the relative speed and an absolute speed of the current vehicle.

6. The method of claim 1, wherein the predicting a rear collision probability comprises:

estimating a time of collision of the rear vehicle with the current vehicle based on the rear context and assumptions of the current vehicle and the rear vehicle brakes;

obtaining a normalized time by performing a normalization operation on the estimated time; and

based on the normalized time, the rear collision probability is calculated.

7. The method of claim 1, wherein the rear context comprises: a relative speed of the rear vehicle with respect to the current vehicle and a distance between the rear vehicle and the current vehicle.

8. The method of claim 1, wherein the issuing a rear vehicle brake alert comprises:

at least one of a visual signal, an infrared signal, an acoustic signal, and a wireless signal for alerting the rear vehicle to brake is sent to the rear vehicle.

9. The method of claim 8, wherein the visual signal is to be emitted by a brake signal light or a brake alert light of the current vehicle.

10. The method of claim 1, further comprising:

in response to detecting the front vehicle braking or impending braking, predicting a front collision probability of the current vehicle colliding with the front vehicle based on a front context of the current vehicle and assumptions of the front vehicle and the current vehicle braking;

Determining whether the frontal collision probability is greater than a frontal collision threshold; and

in response to determining that the frontal collision probability is greater than the frontal collision threshold, a host vehicle brake command is sent inside the current vehicle.

11. The method of claim 10, wherein the front context comprises: a relative speed of the front vehicle with respect to the current vehicle and a distance between the front vehicle and the current vehicle.

12. The method of claim 10, wherein the current vehicle is a manually driven vehicle, and the transmitting the host vehicle brake instruction comprises:

and sending the vehicle braking instruction to a vehicle braking reminding unit in the current vehicle so that the vehicle braking reminding unit sends out a vehicle braking reminding.

13. The method of claim 12, wherein the host vehicle brake alert comprises at least one of a visual signal, an acoustic signal, and a tactile signal.

14. The method of claim 12, wherein the intensity of the host vehicle brake alert is associated with the frontal collision probability.

15. The method of claim 10, wherein the current vehicle is an autonomous vehicle, and the transmitting the host vehicle brake instruction comprises:

And sending the vehicle braking instruction to at least an automatic braking unit in the current vehicle so that the automatic braking unit performs automatic braking operation.

16. The method of claim 15, wherein a braking effort of the automatic braking operation is associated with the frontal collision probability.

17. The method according to claim 7 or 11, wherein:

the rear situation further comprises at least one of road surface condition, weather condition, vehicle type of the rear vehicle, or

The front context further includes at least one of a road surface condition, a weather condition, a model of the front vehicle.

18. A system for context detection based braking alert, comprising:

a processing unit configured to:

detecting whether a preceding vehicle located in front of the current vehicle is braked or is about to brake,

in response to detecting the front vehicle braking or impending braking, predicting a rear collision probability of the rear vehicle with the current vehicle based on a rear context of the current vehicle and assumptions of the current vehicle and rear vehicle braking located rearward of the current vehicle,

determining whether the rear impact probability is greater than a rear impact threshold, and

Responsive to determining that the rear collision probability is greater than the rear collision threshold, sending a rear vehicle brake alert instruction to a rear vehicle brake alert unit; and

a rear vehicle brake alert unit configured to:

and in response to receiving the rear vehicle braking reminding instruction from the processing unit, sending a rear vehicle braking reminding to the rear vehicle.

19. The system of claim 18, wherein,

the processing unit is further configured to:

in response to detecting the front vehicle braking or impending braking, predicting a front collision probability of the current vehicle colliding with the front vehicle based on a front context of the current vehicle and assumptions of the front vehicle and the current vehicle braking,

determining whether the frontal collision probability is greater than a frontal collision threshold, and

in response to determining that the frontal collision probability is greater than the frontal collision threshold, transmitting a host vehicle brake command inside the current vehicle, and

the system further comprises:

a host vehicle brake alert unit configured to issue a host vehicle brake alert in response to receiving the host vehicle brake instruction from the processing unit; and/or

An automatic braking unit configured to perform an automatic braking operation in response to receiving the own vehicle braking instruction from the processing unit.

20. A computer program product for context detection based braking alert, comprising a computer program for execution by at least one processor for: