CN116161020A - Auxiliary driving control method, equipment and medium - Google Patents
Auxiliary driving control method, equipment and medium Download PDFInfo
- Publication number
- CN116161020A CN116161020A CN202111403780.0A CN202111403780A CN116161020A CN 116161020 A CN116161020 A CN 116161020A CN 202111403780 A CN202111403780 A CN 202111403780A CN 116161020 A CN116161020 A CN 116161020A
- Authority
- CN
- China
- Prior art keywords
- target
- previous
- attribute
- risk level
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000013486 operation strategy Methods 0.000 claims description 11
- 230000007613 environmental effect Effects 0.000 claims description 8
- 230000033001 locomotion Effects 0.000 claims description 6
- 230000000977 initiatory effect Effects 0.000 claims description 2
- 229910000831 Steel Inorganic materials 0.000 claims 2
- 239000010959 steel Substances 0.000 claims 2
- 238000011156 evaluation Methods 0.000 description 10
- 101000772194 Homo sapiens Transthyretin Proteins 0.000 description 5
- 102100029290 Transthyretin Human genes 0.000 description 5
- 230000010485 coping Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/408—Radar; Laser, e.g. lidar
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/50—Barriers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/20—Static objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4041—Position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/801—Lateral distance
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/802—Longitudinal distance
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a control device and method, the device comprising an input interface for receiving a detection signal for a current target from an environment-aware sensor, wherein the detection signal comprises at least one target attribute of the current target; a decision module configured to match a target attribute of the current target with a pre-stored target attribute of at least one previous target, and to determine an operation policy for the current target based at least on the matching result; and an output interface configured to output a control instruction indicating the operation policy.
Description
Technical Field
The invention relates to an automobile driving auxiliary control technology, in particular to automatic distress obstacle avoidance control.
Background
With the continuous development of active safety technology and automatic driving technology, many automobile manufacturers are equipped with auxiliary controls such as Automatic Emergency Braking (AEB) systems for vehicles. AEB is based on environmental awareness sensors such as millimeter wave radar or the like to sense the risk of collision that a front may have with a traffic participant such as a vehicle, pedestrian, bicycle or other traffic participant and to avoid or mitigate the extent of the collision by following a predetermined operating strategy op_policy. Fig. 1 schematically illustrates the structure of a conventional AEB system, as shown AEB system 100 comprising an environment-aware sensor 101, a control unit 102 and an actuator 103. The environmental sensor 101 includes, for example, a front camera (FCam) and a Radar (RAD) (for example, a laser radar, an ultrasonic radar, etc.), and is used for detecting a target in a certain range in front of the vehicle, the control unit 102 serves as a control core, determines, based on the target detected by the environmental sensor 101, a risk level of the target according to a preset evaluation mode AccessMode (for example, an evaluation mode for a target being a moving target, an evaluation mode for a target being a stationary target, etc.), and adopts different operation strategies op_policy, which may include, for example, a multi-stage intervention, such as performing a one-stage intervention when the situation is not dangerous: emitting hearing or light early warning; in case of dangerous situations, a secondary intervention is adopted: comfort braking is adopted; three-level intervention is adopted in case of critical situation: emergency braking, steering, etc. According to the adopted operation strategy op_policy, the control unit 102 sends control instructions to the corresponding executing mechanism 103 to execute corresponding intervention operation, and the executing mechanism 103 may be a speaker system SS, a lighting system LS, a brake control system BS, etc.
Disclosure of Invention
The present invention contemplates an improved driving assistance control scheme that more enables more intelligent control of a vehicle by improving the ability to identify objects detected by an environmental awareness sensor. For example, the AEB system at present is used as a preventive active safety technique, which can identify the risk of collision in advance, completely avoid the collision or reduce the intensity of the collision as much as possible, but in practice, for some permanent fixed targets appearing in the sensor field of view, such as the hard shoulder at a certain corner on the loop or the height limiting pole in the parking lot where parking is often performed, according to the conventional evaluation mode accemode, the AEB system may evaluate the target as a very dangerous traffic participant, and thus, the emergency braking operation may be started each time the road section is passed or the parking lot is entered, and thus, unnecessary and unpleasant driving experience is inevitably brought to the user. According to the AEB system provided by the invention, the detected target can be identified in advance, so that the intervention operation strategy is adjusted when the repeated target is encountered, and the driving experience is improved.
According to one aspect of the invention there is provided a control device usable with an AEB system, comprising an input interface for receiving a detection signal for a current target from an ambient sensing sensor, wherein the detection signal comprises at least one target attribute of the current target; a decision module configured to match a target attribute of the current target with a pre-stored target attribute of at least one previous target, and to determine an operation policy for the current target based at least on the matching result; and the output interface is configured to output a control instruction indicating the operation strategy. The AEB system according to the invention comprises, in addition to the control device disclosed herein, the aforementioned context-aware sensors, actuators and the like.
According to an aspect of the present invention, there is provided a driving support control method including: acquiring at least one target attribute of a current target detected by an environment-aware sensor; matching the target attribute of the current target with the target attribute of at least one pre-stored previous target; an operational policy for the current target is determined based at least on the matching result.
According to yet another aspect of the present invention, there is provided a driving assistance system including an environment-aware sensor for detecting at least one target attribute of a current target; a memory for pre-storing target attributes and machine-executable instructions of at least one previous target; and a control device configured to implement the method of the present invention by executing the instructions.
Drawings
FIG. 1 is a schematic diagram of a prior art AEB system;
FIG. 2 is a schematic illustration of an AEB system according to an example of the invention;
FIG. 3 is a flow chart of a method of driving assistance control according to an example of the invention;
fig. 4 is a flowchart of a driving assistance control method according to another example of the invention.
Like reference numerals refer to like elements throughout the present application.
Detailed Description
The method and system provided by the embodiment of the invention are described in detail below with reference to the accompanying drawings. While the preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Fig. 2 is a schematic diagram of a driving assistance system according to an example of the present invention, in which the driving assistance system may be implemented as an AEB system, and this is described as an example, but it should be noted that the present invention is not limited to application to the AEB system. AEB system 200 includes context aware sensors 101, control device 110, and actuators 103 as shown. The environment sensing sensor 101 comprises a front-end camera FCam or radar RAD, such as a lidar, an ultrasonic radar, a millimeter wave radar, etc., for detecting a current target in a range in front of the vehicle. In the present invention, the sensors are not limited to the above examples, but include any combination of one or more sensors that can be used to detect environmental targets, so as to improve the performance and reliability of the AEB function under complex road conditions and reduce the risk of malfunction. For example, the combination of millimeter wave radar and a camera can ensure the adaptability under various weather conditions and fully utilize the advantages of the camera for object identification.
As shown, the control device 110 includes an input interface 1101, a decision module 1102, and an output interface 1103. The input interface 1101 receives a detection signal for the current object C from the context-aware sensor 101, wherein the detection signal comprises at least one object property ATTR of the current object C, where the object property may be a position Location of the detected object C, which may be either an absolute physical position of the object, e.g. its GPS coordinates etc., or a relative position of the object C with respect to the current vehicle, e.g. a lateral distance dx and a longitudinal distance dy of the object C with respect to the vehicle when the radar finds the object C. The decision module 1102 is configured to match the target attribute ATTR of the current target C with the target attribute of at least one previous target stored in advance, and to determine an operation Policy op_policy for the current target C based at least on the matching result, and to generate a corresponding control instruction. The output interface 1103 is configured to output a control instruction indicating the operation Policy op_policy generated by the decision module 1102, where the control instruction is provided to the execution mechanism 1103, so as to control the execution mechanism 1103 to execute a corresponding operation according to the determined operation Policy op_policy.
In one example of the present invention, as shown in fig. 2, the decision module 1102 includes the control unit 102 and the arbitration unit 104, where the control unit 102 may operate in a conventional mode, for example, based on the target detected by the environmental sensor 101, determine the risk level of the target according to a preset evaluation mode, and accordingly take different operation policies op_policy and generate corresponding control instructions. The arbitration unit 104 acts as an auxiliary control unit to pre-screen the detected targets to determine the nature of the detected targets and thereby determine whether to trigger the control unit 102 to perform a conventional evaluation mode or an evaluation mode of degraded operation. According to an example of the invention, the arbitration unit 104 receives from the input interface 1101 one or more target properties ATTR of the current target C detected by the context-aware sensor 101, where the target properties may be the position Location of the detected target C, which may be either the absolute physical position of the target, e.g. its GPS coordinates etc., or the relative position of the target C with respect to the current vehicle, e.g. the lateral distance dx and the longitudinal distance dy of the target C with respect to the vehicle when the radar finds the target C. Here, the object attribute ATTR may also be a moving state MovState of the object, obstacle Probability Profile, profile feature, object Height, and the like. The movement state MovState here includes whether the target C is stationary or moving, its moving speed, etc., which can be measured by radar, for example; the Probability of obstacle Probability is then the likelihood that the detected object constitutes an obstacle, which attribute may be determined by the control unit 102 based on, for example, the image provided by the camera, analyzed with an existing object recognition pattern algorithm, and provided to the arbitration unit 104. The Profile defines the Profile of the object C, such as a vehicle, a pedestrian, a fixed object obstacle, such as an isolation pier or a height limiting rod, and the height Heigth represents the height of the object C, and it is easy to understand that parameters such as the Profile and the height Heigth can be measured by the radar or determined by analyzing the object image captured by the camera. In the present invention, the target attribute ATTR and the number of attributes available are not limited to the above examples, but any other attribute that can be determined by detection or analysis by the sensor 101 may also be utilized. In the following description, c1_attr= { c1_location, c1_movstate, c1_profile, c1_height } is described as an attribute of the current target C1.
The arbitration unit 104 matches the target attribute c1_attr of the current target C1 with the target attribute p_attr of at least one previous target P stored in advance, for example with the attribute p1_attr of the target P1 stored in advance in the database 105 shown in fig. 2. In the present invention, the database 105 may be located either locally within the AEB system 200 for access by the arbitration unit 104 or remotely, such as in the cloud, so that the arbitration unit 104 is accessible via the internet of vehicles.
The database 105 stores the target attribute p1_attr of the previous target P1, where the attribute p1_attr includes at least { p1_location, p1_movstate, p1_profile, p1_height }, and the like. The arbitration unit 104 determines whether the current target C1 has occurred before by attribute matching. In one implementation, if the target attribute c1_attr of the current target C1 does not match the target attribute p1_attr of the previous target P1, where the mismatch refers to any of the target attributes { c1_location, c1_movstate, c1_profile, c1_height } does not match the corresponding attribute in { p1_location, p1_movstate, p1_profile, p1_height }, then it is determined that the current target C1 does not match the previous target P1, i.e., the currently detected target C1 has not been encountered before. For example, c1_location indicates that the current target C1 is present at the (dx=5 meters, dy=4 meters) heading of the current vehicle, while p1_location indicates that the previous target P1 was present at the (dx=8 meters, dy=6 meters) heading of the vehicle, then the arbitration unit 104 may determine that the current target C1 does not match the previous target P1, and thus does not continue the match determination of other attributes. Of course, other target attributes may be preferentially judged in practice, for example, whether the moving state MovState matches or not may be preferentially judged, if p1_movstate does not match c1_movstate, the matching process is ended and it is judged that the current target C1 does not match the previous target P1; if the P1_MovState matches the C1_MovState, then the matching process of other attributes { C1_location, C1_profile, C1_height } and { P1_location, P1_profile, P1_height } may be continued. It should be noted here that in order to avoid transmission by reason of thisThe sensor detects the influence of errors such as image processing on the matching result, and when the attributes are matched, a certain redundancy is set for each attribute according to the invention. For example, for a moving state MovState, when the value of P1_movState is zero, i.e., the previous target P1 is a stationary target, and C1_movState indicates that the detected current target is a moving target and the speed is 5cm/s, since the difference in moving speeds of C1_movState and P1_movState is less than the speed threshold V set for the moving state movState THR =10 cm/s, so c1_movstate is considered to be substantially the same as or matched to p1_movstate. The speed threshold V set here THR May be based on actual experience.
In this embodiment, when the arbitration unit 104 determines that the current target C1 does not match the previous target P1, the Trigger signal Trigger1 is generated, whereby the control unit 102 autonomously evaluates the target in the conventional evaluation mode, by evaluating the target based on the characteristics of the target C1 detected by the environment-aware sensor 101, determines the risk level of the target as RR0, and makes a corresponding operation Policy as op_policy_0, such operation Policy op_policy_0 may include, for example, controlling the speaker or the light system in the vehicle to emit an audible or light warning when the situation is not dangerous, controlling the brake system to take a comfortable brake when the situation is dangerous, controlling the brake control system to perform one-level up to three-level intervention such as emergency braking or steering when the situation is dangerous, and the like, based on the received Trigger signal Trigger 1. Accordingly, the control unit 102 generates a control instruction corresponding to the operation Policy op_policy_0, and controls the execution mechanism 103 to execute different levels of intervention operations suitable for different dangerous situations through the output interface 1103. In the present embodiment, the actuator 103 is not limited to the speaker or the light system, the brake control system, and the like, which are exemplified above, but may be other means known in the art or often employed.
If the arbitration unit 104 determines that the target attribute c1_attr of the target C1 matches the target attribute p1_attr of the previous target P1, where the matching refers to all the attributes { c1_location, c1_movstate, c1_profile, c1_height } and { p1_location, p1_movstate, p1_profile, p1_height } to be compared are the same or within a predetermined error threshold, it is determined that the current target C1 matches the previous target P1, i.e., the currently detected target C1 was previously encountered and stored in the database 105 of the AEB system, and thus the arbitration unit 104 generates a Trigger signal Trigger2 to inform the control unit 102 that there is a high likelihood that the currently detected target is a permanent target located at a fixed Location. Thus, the control unit 102 may determine that the current target may be a permanent target based on the received Trigger signal Trigger2, so that the risk level of the target may be reduced to be RR1, where the risk level RR1 is smaller than RR0, and a corresponding operation Policy op_policy_1 may be formulated, for example, the operation Policy op_policy_1 may include controlling a speaker or a light system in the vehicle to emit an audible or light warning when the situation is not dangerous, and controlling at most a brake system to take a comfortable braking when the situation is dangerous. Since the control unit 102 already knows that the current target may have been historically processed and that the risk level is not high, the operation strategy op_policy_1 does not contain high risk coping operations such as initiating emergency braking or steering. Thus, the control unit 102 generates a control instruction corresponding to the operation Policy op_policy_1, and controls the execution mechanism 103 through the output interface 1103 to execute intervention operations suitable for different dangerous situations of decreasing the dangerous level.
According to one implementation of the present invention, when the arbitration unit 104 determines that the current target C1 matches the previous target P1, the target attributes { c1_location, c1_movstate, c1_profile, c1_height } of the current target C1 may be stored in the database 105, for example as { p2_location, p2_movstate, p2_profile, p2_height }, wherein the current target C1 may be registered as another previous target P2 in the database 105. Previous targets P1, P2 and their attributes are stored in association in database 105 and may be indexed with the same identity ID. The identity ID here is used to uniquely identify the objects P1 and P2, and may be, for example, a numerical feature ID calculated according to a predetermined algorithm based on the Profile feature Profile of the object.
According to one example of the present invention, when there are multiple associated previous targets P (e.g., multiple having the same feature ID) in the database 105Prior targets), the arbitration unit 104 may choose to match the current target with the most recently stored prior targets in the database. For example, when the arbitration unit 104 receives the object attribute { c2_location, c2_movstate, c2_profile, c2_height } of the current object C2 acquired again by the context aware sensor from the input interface 1101, the unique identification ID of the object C2 may be determined based on the Profile feature c2_profile thereof, and when two previous objects P1 and P2 exist in the database 105 using the ID, the arbitration unit 104 may select to match the object attribute { c2_location, c2_movstate, c2_profile, c2_height } of the object C2 with the object attribute { p2_location, p2_movstate, p2_profile, p2_height } of the object P2. When the target attributes of C2 and P2 do not match, the arbitration unit 104 may generate the Trigger signal Trigger1 as described above, so that the control unit 102 autonomously determines the risk level of the target, e.g., RR0, according to the conventional evaluation mode AccessMode, and makes a corresponding operation Policy, e.g., op_policy_0, based on the received Trigger signal Trigger 1. But when the arbitration unit 104 determines that the target attributes of C2 and P2 match, another Trigger signal Trigger3 may be generated. The control unit 102 can know that the current target C2 has been detected twice at the same position based on the Trigger signal Trigger3, and is a permanent target located at a fixed position. The control unit 102 may thus reduce the risk level of the target C2, for example RR2, where the risk level RR2 is smaller than RR1, and formulate a corresponding operation Policy op_policy_2, for example, the operation Policy op_policy_2 may only include controlling a speaker or a lighting system in the vehicle to emit audible or light warning, and no further operations are performed. Thus, the control unit 102 generates a control instruction corresponding to the operation Policy op_policy_2, and controls the execution mechanism 103 to execute an intervention operation suitable for a lower risk level through the output interface 1103. In other implementations of the invention, the control unit 102 may also set the risk level RR2 to zero directly based on the Trigger signal Trigger3, so that the control unit 102 does not generate any control instruction, and thus does not Trigger the actuator 103 to perform any pre-warning operation, or when the target C is detected more than 2 times by the predetermined number of times threshold N THR In the time-course of which the first and second contact surfaces,the risk level RR is set to zero.
According to the scheme of the present invention, when the risk level RR2 of the target C2 is set to zero and the next time the environmental awareness sensor 101 detects the same target (e.g., the target C3), the arbitration unit 104 may directly send a trigger signal for ignoring the target C3 to the control unit 102, so that the control unit 102 will ignore the target and not generate any control instruction for triggering, and thus not trigger any operation. For example, in an alternative implementation, the control unit 102 may also store the risk level RR determined for each detected target, e.g. C1, C2, etc., in the database 105, whereby when the arbitration unit 104 determines that the risk level RR of a previous target having the same ID or a match has been set to zero based on the identity ID of the currently detected target and a record in the database 105, a ignore current target trigger signal may be issued directly to the control unit 102, whereby the control unit 102 does not respond to the currently detected target. Thus, it is apparent that the present invention can avoid the same excessive operations that are taken because the target is always considered as a dangerous target, and thus enhance the driving riding experience, compared to the prior art in which the control unit 102 performs the same operation strategy, e.g., op_policy_0, whenever the same obstacle target is encountered.
According to another aspect of the present invention, the arbitration unit 104 may be further configured to pre-determine whether the matching is required before the matching of each target attribute is performed, so as to achieve the purposes of saving time and avoiding resource waste. As one example, the arbitration unit 104 may determine whether a match is required based on an attribute of the current target, such as speed, detected by the sensor, thereby making a preliminary determination of whether the current target is likely to be the same target. For example when the current speed C1_MovState of the target C1 is greater than a certain predetermined speed threshold V THR When the speed c1_movstate of C1 is not a fixed rule but random, the current target C1 is determined to be an opportunistic target, so the arbitration unit 104 does not perform subsequent target attribute matching any more, for example, may directly send out a Trigger1 signal, so that the control unit 102 may operate in a normal mode. At C1 speedThe degree C1_MovState is smaller than the speed threshold V THR For example zero, the arbitration unit 104 proceeds with matching of the respective target attributes of the current target C1 and the previous target P.
FIG. 3 is a flow chart of an assistance control method implemented by a driving assistance control system according to an example of the invention. In step 301, a plurality of properties of the current target C1, such as { c1_location, c1_movstate, c1_property, c1_profile, c1_height }, are obtained from the context aware sensor 101.
In step 303, the object attributes { c1_location, c1_movstate, c1_profile, c1_height } of the current object C1 are matched with the object attributes { p1_location, p1_movstate, p1_profile, p1_height } of the previous object P1 stored in advance one by one. If it is determined in step 303 that any one of the target attributes of the target C1 does not match the corresponding target attribute of the target P1, it may be determined that the target C1 does not match the target P1, a Trigger signal Trigger1 is generated, and the process proceeds to step 305.
In step 305, based on the received Trigger signal Trigger1, the target is autonomously evaluated according to the conventional evaluation mode AccessMode, by based on the characteristics of the target C1 detected by the environment sensing sensor 101, the risk level of the target is determined to be RR0, and a corresponding operation Policy is made to be op_policy_0, for example, and a control instruction corresponding to the operation Policy case op_policy_0 is generated. In step 309, the control instruction generated in step 305 is output to control the actuator 103 to act according to the formulated operation Policy op_policy_0 until the intervention operation of three levels is triggered.
If it is determined in step 303 that all of the object attributes { C1_location, C1_MovState, C1_Problank, C1_Profile, C1_height } of the object C1 match the corresponding object attributes of the object P1, it may be determined that the object C1 matches the object P1, i.e., the current object C1 is the previously occurring object, thus generating the Trigger signal Trigger2, and the process proceeds to step 307.
In step 307, based on the received Trigger signal Trigger2, it is confirmed that the current target may be a permanent target, so that the risk level for the target C1 may be reduced, for example, to RR1, where the risk level RR1 is smaller than RR0, and a corresponding operation Policy op_policy_1 is formulated. Then, step 309 is entered, and a control command is output to control the actuator 103 to act according to the formulated operation Policy op_policy_1, where the operation Policy op_policy_1 does not include a third-level handling operation triggering a high risk of emergency braking or steering.
Fig. 4 shows a flow chart of a driving assistance control method performed by the AEB system of another example of the present invention, taking still the current target C1 as an example. In step 401, a plurality of attributes of the current target C1, such as { C1_location, C1_MovState, C1_Proability, C1_Profile, C1_height }, are obtained from the context awareness sensor 101.
In step 403, it is determined whether a match is required, i.e. whether a match condition is met, based on at least one attribute of the target C1, e.g. the motion state of the target C1 is determined based on the velocity c1_movstate. When the speed C1_MovState of the target C1 is greater than a predetermined speed threshold V THR When the speed c1_movstate of the target C1 is not a fixed rule but a random one, it is determined that the current target C1 does not satisfy the matching condition (i.e. the determination result is no 'N'), and the current target C1 is an opportunistic target, so that the subsequent target attribute matching is not performed any more, and the process directly proceeds to step 405. At step 405, the aeb system operates in a normal mode, for example, determines that the risk level of the target C1 is RR0, and makes a corresponding operation Policy of op_policy_0, and generates a control instruction adapted to the operation Policy op_policy_0. Then, in step 407, a control instruction corresponding to the operation Policy op_policy_0 is output to control the execution mechanism 103 to execute risk coping operations adapted to different dangerous situations according to the op_policy_0.
If it is determined in step 403 that the current target C1 satisfies the matching condition (i.e., the determination result is 'Y'), step 409 is entered where it is determined whether the previous target is stored in advance. If it is determined in step 409 that the previous target was not found (i.e., the current target C1 was first encountered), step 405 is entered and the subsequent operations described above are performed. If it is confirmed in step 409 that a previous target is found and there are a plurality of previous targets, the attribute of the previous target updated recently is extracted, for example, when two previous targets P1 and P2 are stored in advance, the attribute { p2_location, p2_movstate, p2_probability, p2_profile, p2_height } of the target P2 is set up, and step 411 is entered.
In step 411, the object attributes { c1_location, c1_movstate, c1_profile, c1_height } of the object C1 and the attributes { p2_location, p2_movstate, p2_profile, p2_height } of the object P2 are matched one by one. If it is determined in step 411 that any one of the target attributes of the target C1 does not match the corresponding target attribute of the target P2, it may be determined that the target C1 does not match the target P2, and step 405 is entered to perform the subsequent operations as described above. Otherwise, if it is determined in step 411 that all the attributes of the target C1 match the corresponding attributes of the target P2, step 413 is entered.
At step 413, it is confirmed whether the current target C1 and its attributes need to be stored for evaluating subsequently encountered targets, e.g., whether the number of currently stored previous targets P reaches a number threshold N THR Or whether the risk level of the nearest previous target P has been marked zero in the AEB system. If it is determined in step 413 that the target has met the condition, then step 415 is entered, where the AEB system determines that the risk level RR of the current target C1 is zero, thus creating an operation Policy op_policy that is ignored for the current target C1.
If it is determined in step 413 that the target does not meet the condition, then step 417 is entered, the AEB system stores the attributes { C1_location, C1_MovState, C1_Probability, C1_Profile, C1_height } for target C1, and then step 415 is entered.
At step 415, the aeb system confirms that the current target C1 may be a permanent target based on the matching result of step 411, thus formulating an operation Policy op_policy_1 with a reduced risk level, e.g., RR1, and generating corresponding control instructions. Thus, in step 407, control instructions are output to control the actuator 103 to operate according to the strategy op_policy_1, but without triggering high risk handling operations like emergency braking or steering.
Although in the above embodiments, the components in the control device 110 are implemented in the form of modules or units, the present invention is not limited thereto, and each unit or module disclosed herein may also be implemented in the form of an integrated circuit ASIC, software, firmware, and combinations thereof. For example, in another example of the invention, a machine-readable medium for carrying out AEB operations is provided, on which is stored software program code implementing the method steps or elements of any of the above embodiments. Examples of such machine-readable media include magnetic disks, optical disks, nonvolatile memory cards, and the like.
Some embodiments of the invention are described above in connection with the accompanying drawings. It should be noted that not all the steps in the above-mentioned processes are necessary, and some steps may be omitted according to actual needs. In addition, the execution sequence of the steps is not fixed, and can be adjusted according to the needs. Furthermore, while the invention has been illustrated and described in detail in the drawings and in the preferred embodiments, the invention is not limited to the disclosed embodiments, and it will be appreciated by those skilled in the art that the various embodiments described above may be combined to produce further embodiments of the invention, which are also within the scope of the invention.
Claims (21)
1. A control apparatus comprising:
an input interface for receiving a detection signal for a current target from an environmental awareness sensor, wherein the detection signal comprises at least one target attribute of the current target;
a decision module configured to match a target attribute of the current target with a pre-stored target attribute of at least one previous target, and to determine an operation policy for the current target based at least on the matching result;
and the output interface is configured to output a control instruction indicating the operation strategy.
2. The control device of claim 1, wherein the decision module comprises:
an arbitration unit configured to perform a match between the target attribute of the current target and the target attribute of the previous target, wherein if the target attribute of the current target does not match the target attribute of the previous risk target, a first trigger signal is generated, and if the target attribute of the current target matches the target attribute of the previous target, a second trigger signal is generated,
a control unit configured to determine a first operation strategy having a first risk level based at least on the first trigger signal, and to determine a second operation strategy having a second risk level based at least on the second trigger signal, wherein the first risk level is higher than the second risk level.
3. The control apparatus according to claim 2, wherein said arbitration unit performs said matching operation only when at least one attribute of said current target satisfies a predetermined condition.
4. A control device according to one of claims 1-3, wherein said at least one previous target comprises at least a first previous target and a second previous target, wherein said first previous target and second previous target have the same target properties, said first previous target having said first risk level and said second previous target having a third risk level, wherein said second risk level is smaller than the third risk level.
5. The control device of claim 4, wherein the output interface outputs the control instructions to an actuator to implement the operating strategy.
6. The control device of claim 5, wherein if it is determined that the target attribute of the current target matches the target attribute of the previous target, the arbitration unit is further configured to:
generating a second trigger signal indicating that the second risk level is zero if it is determined that the number of stored previous targets having the same target property reaches a predetermined number, wherein the executing mechanism does not execute any operation based on a second operation policy determined by the control unit thereby; otherwise
If it is determined that the number of stored previous targets having the same target attribute does not reach the predetermined number, the current target is stored in the memory as another previous target.
7. The control device of claim 6, wherein the target attribute comprises at least one of:
a location;
a moving state;
obstacle probability;
profile features;
height of the steel plate.
8. The control device according to claim 7, wherein the predetermined condition includes: the movement state indicates that the movement speed of the current target is less than or equal to a predetermined value.
9. A control device according to one of claims 1-3, wherein said second trigger signal indicates that said current target is a false risk target for which said first operating strategy is not applicable.
10. A driving assistance control method, comprising:
acquiring at least one target attribute of a current target detected by an environment-aware sensor;
matching the target attribute of the current target with the target attribute of at least one pre-stored previous target;
an operational policy for the current target is determined based at least on the matching result.
11. The method of claim 10, further comprising outputting respective control instructions to control performing respective operations based on the determined operating strategy.
12. The method of claim 11, wherein,
determining a first operation strategy with a first risk level if the target attribute of the current target does not match the target attribute of the previous risk target;
and if the target attribute of the current target matches the target attribute of the previous target, determining a second operation strategy with a second risk level, wherein the first risk level is higher than the second risk level.
13. The method of claim 12, wherein the matching operation is performed when at least one attribute of the current target satisfies a predetermined condition.
14. The method of one of claims 10 to 13, wherein the at least one previous target comprises at least a first previous target and a second previous target, wherein the first previous target and the second previous target have the same target attribute, the first previous target has the first risk level, and the second previous target has a third risk level, wherein the second risk level is less than the third risk level.
15. The method of claim 14, wherein if the target attribute of the current target matches the target attribute of the previous target:
setting a second risk level to zero if it is determined that the number of stored previous targets having the same target attribute reaches a predetermined number; otherwise
Storing the current target as another previous target.
16. The method of claim 15, wherein the target attributes comprise at least one of:
a location;
a moving state;
obstacle probability;
profile features;
height of the steel plate.
17. The method of claim 16, wherein the predetermined condition comprises: the movement state indicates that the movement speed of the current target is less than or equal to a predetermined value.
18. The method of claim 17, wherein the first operating strategy comprises a response to initiating Automatic Emergency Braking (AEB).
19. The method of claim 18, wherein the second trigger signal indicates that the current target is a false risk target that does not apply the first operating policy.
20. A control apparatus comprising:
a processor configured to implement the method of any of claims 10-19 by executing instructions.
21. A machine-readable storage medium having stored therein instructions which, when executed by a machine, cause the machine to carry out the method of any of claims 10-19.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111403780.0A CN116161020A (en) | 2021-11-24 | 2021-11-24 | Auxiliary driving control method, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111403780.0A CN116161020A (en) | 2021-11-24 | 2021-11-24 | Auxiliary driving control method, equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116161020A true CN116161020A (en) | 2023-05-26 |
Family
ID=86409959
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111403780.0A Pending CN116161020A (en) | 2021-11-24 | 2021-11-24 | Auxiliary driving control method, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116161020A (en) |
-
2021
- 2021-11-24 CN CN202111403780.0A patent/CN116161020A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6404634B2 (en) | Consistent behavior generation of predictive advanced driver assistance systems | |
US9656667B2 (en) | Method for minimizing automatic braking intrusion based on collision confidence | |
US11713041B2 (en) | Control system and control method for driving a motor vehicle | |
JP6822752B2 (en) | Driving assistance technology for active vehicle control | |
US8457359B2 (en) | Method and assistance system for detecting objects in the surrounding area of a vehicle | |
JP4517972B2 (en) | Obstacle determination device and method | |
JP4023228B2 (en) | In-vehicle obstacle detection device | |
US20150239472A1 (en) | Vehicle-installed obstacle detection apparatus having function for judging motion condition of detected object | |
KR20190040550A (en) | Apparatus for detecting obstacle in vehicle and control method thereof | |
US10319226B2 (en) | Vehicle control device | |
JP6301440B2 (en) | Object detection system and object detection method | |
JP2009237898A (en) | Image recognition device | |
JP2014241036A (en) | Vehicle driving assist system | |
JP5130959B2 (en) | Vehicle ambient environment detection device | |
US20170349171A1 (en) | Controlling a protection device of a motor vehicle | |
JP2003151095A (en) | Device for recognizing obstruction for vehicle | |
CN116161020A (en) | Auxiliary driving control method, equipment and medium | |
CN112991817B (en) | Adaptive object in-path detection model for automatic or semi-automatic vehicle operation | |
CN114364588B (en) | Vehicle collision determination device | |
CN113447921A (en) | Method for identifying a vehicle environment | |
US20220334246A1 (en) | Object tracking method | |
US12024165B2 (en) | Evaluation apparatus for evaluating a trajectory hypothesis for a vehicle | |
JP7438393B2 (en) | Other vehicle behavior prediction/diagnosis device and other vehicle behavior prediction/diagnosis method | |
CN112440986B (en) | Driving control method, pedestrian AEB system, intelligent driving automobile, controller and computer readable storage medium | |
JP2004348249A (en) | Outside recognition device for vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |