CN114516327A - Self-learning vehicle following system and method based on driver behavior learning and surrounding environment - Google Patents
Self-learning vehicle following system and method based on driver behavior learning and surrounding environment Download PDFInfo
- Publication number
- CN114516327A CN114516327A CN202210173097.0A CN202210173097A CN114516327A CN 114516327 A CN114516327 A CN 114516327A CN 202210173097 A CN202210173097 A CN 202210173097A CN 114516327 A CN114516327 A CN 114516327A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- distance
- information
- following
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000006399 behavior Effects 0.000 title claims abstract description 15
- 230000004927 fusion Effects 0.000 claims abstract description 7
- 238000007499 fusion processing Methods 0.000 claims description 16
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 claims description 14
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 claims description 14
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 5
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 101100011375 Caenorhabditis elegans egl-4 gene Proteins 0.000 description 1
- 101000579123 Homo sapiens Phosphoglycerate kinase 1 Proteins 0.000 description 1
- KJWZYMMLVHIVSU-IYCNHOCDSA-N PGK1 Chemical compound CCCCC[C@H](O)\C=C\[C@@H]1[C@@H](CCCCCCC(O)=O)C(=O)CC1=O KJWZYMMLVHIVSU-IYCNHOCDSA-N 0.000 description 1
- 102100028251 Phosphoglycerate kinase 1 Human genes 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012360 testing method Methods 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
- B60W30/14—Adaptive cruise control
- B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
-
- 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
- B60W2420/403—Image sensing, e.g. optical camera
-
- 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
- B60W2552/05—Type of road, e.g. motorways, local streets, paved or unpaved roads
-
- 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
- B60W2552/53—Road markings, e.g. lane marker or crosswalk
-
- 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
- B60W2554/402—Type
-
- 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
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/40—High definition maps
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
- Y02T10/84—Data processing systems or methods, management, administration
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a self-learning vehicle following system and method based on driver behavior learning and surrounding environment, the system comprises an external environment sensing module and a domain controller, the external environment sensing module can collect road type information, distance and time distance information of surrounding target vehicles and lane line information and output the information to the domain controller, a target fusion unit of the domain controller outputs traffic flow information, target type and distance and road environment information of each lane after target sensing fusion, and when a driver runs in different road environments, the domain controller judges the road environment and traffic flow condition corresponding to the vehicle according to the information collected by the external environment sensing module of the vehicle, collects the time distance and distance between the vehicle and the target vehicle in real time, judges the vehicle following distance and/or vehicle following distance of the driver, and finally, and matching the following time distance or the following distance of the driver according to the road working condition of the current vehicle and the type of the target vehicle through the domain controller.
Description
Technical Field
The invention belongs to the field of intelligent auxiliary driving, and particularly relates to a self-learning vehicle following system and method based on driver behavior learning and surrounding environment.
Background
Along with the development of the intelligent driving technology of the automobile, more and more driving assistance technologies are produced in mass production on passenger cars, and the integration level of the driving assistance technologies is higher and higher. The driving assistance technology is a safety technology for assisting a driver in driving, and improves driving safety and comfort. As driving assistance techniques have become widespread, the continuity of the driving assistance techniques has been increasing.
At present, in mainstream driving assistance, the following distance of an intelligent driving system following a front vehicle is generally actively set by a driver, and the system cannot adjust the following distance according to the road environment in the whole following process, so that the vehicles have the conditions of long following distance at low speed and frequent jamming in a complex environment; the high-speed car-following is too close, and needs the driver to actively adjust, and in the process, the user experience is poor.
In order to solve the above problems, chinese patent publication No. 10964939 discloses an autonomous following system and method for an autonomous driving vehicle, including an environment sensing system, a main control system and a following decision system, where the environment sensing system detects environmental information of the vehicle and transmits the obtained signal to the main control system and the following decision system, and the main control system and the following decision system control the vehicle to run according to the information detected by the environment sensing system. Meanwhile, the Chinese patent also discloses a self-adaptive cruise system with driving style learning capability and an implementation method, and mainly describes how to obtain the driving style of a single driver, directly match the driving style with the cruise system, and match different following distances of the driver with the self-adaptive cruise system based on different road types, different vehicle speeds and different traffic flows. However, the two following methods cannot adjust the following time interval in real time according to different road types and road environments.
Disclosure of Invention
Aiming at the defects of the prior art, the technical problems to be solved by the invention are as follows: how to provide a self-learning vehicle following system and a method which can carry out matching according to the vehicle following distance of a driver under different road types and environments and the driving style of the driver and can self-adaptively adjust the vehicle following time distance.
In order to solve the technical problem, the invention adopts the following technical scheme:
a self-learning vehicle following system based on driver behavior learning and surrounding environment is characterized by comprising an external environment sensing module and a domain controller, wherein the external environment sensing module can collect road type information, distance and time distance information of surrounding target vehicles and lane line information, and outputs the information to the domain controller, a target fusion unit of the domain controller is used for carrying out target sensing fusion and then outputting traffic flow information, target types and distances and road environment information of various lanes, and when a driver runs in different road environments, the domain controller judges the road environment and traffic flow conditions corresponding to the vehicle according to the information collected by the external environment sensing module of the vehicle, then the external environment sensing module is used for collecting the time distance and time distance between the vehicle and the target vehicles in real time, and a logic judgment module of the domain controller is used for judging the vehicle following distance and/or the vehicle following distance of the driver, and finally, matching the following time distance or the following distance of the driver according to the road working condition of the current vehicle and the type of the target vehicle through the domain controller.
The system can improve the matching degree of an intelligent driving system and the driving style of a driver, can improve the utilization rate of the driver to the system, can improve the satisfaction degree of the driver to the system, and can indirectly improve the future software payment willingness rate.
Furthermore, the external environment perception module comprises an ADAS map, a forward millimeter wave radar, a forward camera, a lateral millimeter wave radar and a lateral camera.
Further, the ADAS map is used for outputting road type information of a current road, where the road type includes a high-speed or express road section, an urban main road or national road section, an urban road, and a general road section; the forward camera is used for collecting image information in front of the vehicle and transmitting the identified image information to the domain controller for fusion processing; the side camera is used for acquiring image information of the side direction of the vehicle and outputting the image information to the domain controller for post-fusion processing; the forward millimeter wave radar and the lateral millimeter wave radar are used for screening reflection points of targets around the vehicle, forming target information and outputting the target information to the domain controller for post-fusion processing, and the target information is used for judging the traffic flow of the road.
Further, after the target information identified by the forward camera and the target information of the forward millimeter wave radar are fused, the distance, the time distance information and the target type of the front target are output; and the information collected by the forward millimeter wave radar, the lateral millimeter wave radar, the forward camera and the lateral camera is fused and then output the traffic flow of the current lane, the traffic flow of the left lane and the traffic flow of the right lane, and the road working conditions are judged according to the traffic flow information, wherein the road working conditions comprise congestion, slow running, blockage and no peripheral road. After adopting above-mentioned means, can be used to distinguish distance and the time distance that the driver followed the car under different road environment, promote the matching degree of intelligent driving system with the car distance.
A self-learning vehicle following method based on driver behavior learning and surrounding environment is characterized by comprising the following steps: s1, collecting the road type, the distance and time distance information of the target vehicles around the vehicle and the lane line information through an external environment sensing module, and outputting the information to a domain controller; s2, fusing the received information through a domain controller, and determining a target distance, a target time distance, a target type, lane information and traffic flow information; s3, judging the road condition according to the information after the fusion processing in the S2; s4, when the driver drives the vehicle independently, acquiring the following vehicle distance and the following vehicle distance of the driver on different road types, different road working conditions and facing different target vehicles in real time; and S5, after the cruise system is started, the domain controller matches the information obtained after the fusion processing in S2 and the real-time road working condition of the vehicle judged in S3 with the information recorded when the driver drives autonomously in S4, and determines the vehicle following time distance or the vehicle following distance. The system mainly adopts an intelligent driving sensor to learn the following style and habit of the driver when the driver drives the vehicle independently, and when the system finishes self-learning and the intelligent driving system is started, the following style of the driver in different environments is automatically matched.
Further, in S1, the external environment sensing module includes an ADAS map, a forward millimeter wave radar, a forward camera, a lateral millimeter wave radar, and a lateral camera, where the ADAS map is used to output road type information of a current road, and the road type includes a high-speed or express road section, an urban main road or national road section, an urban road, and a general road section; the front camera is used for collecting image information in front of the vehicle, the side camera is used for collecting image information in side direction of the vehicle, and the front millimeter wave radar and the side millimeter wave radar are used for screening reflecting points of targets around the vehicle and outputting target information.
Further, in S3, the determination process of the road condition is as follows: the domain controller outputs the road type of the current road through the ADAS map, and judges the current road working condition by combining the received vehicle flow speed in front of the current road or the received side vehicle flow speed, wherein the road working condition comprises a high-speed unblocked working condition, a high-speed congestion working condition, a main road unblocked working condition, a main road congestion working condition, a main road slow-moving working condition, an urban road unblocked working condition, an urban road congestion working condition, an urban road slow-moving working condition and a common road working condition.
Further, in S5, when the cruise system is turned on, and when the vehicle speed is greater than the first threshold value, the domain controller matches the recorded following distance according to the current road condition where the vehicle is located and the type of the vehicle ahead, specifically, when the driver distance recorded by the system is between the safe distance and the maximum allowable distance, the system automatically performs following cruise by using the distance recorded by the system; when the driver time distance recorded by the system is smaller than the safe time distance, the system adopts the safe time distance to carry out vehicle following cruise; and when the driver time interval recorded by the system is larger than the allowed maximum time interval, the system adopts the maximum time interval to carry out following cruise.
Further, in S5, when the cruise system is turned on, and when the vehicle speed is less than the second threshold value and greater than 0, the system matches the following distance stored by the system according to the road condition of the current vehicle and the type of the vehicle ahead; specifically, when the distance, recorded by the system, between the driver and the vehicle is between the safe distance and the maximum allowable distance, the system automatically adopts the distance recorded by the system to carry out cruise with the vehicle; when the following distance of the driver recorded by the system is smaller than the safe distance, the system adopts the safe distance to carry out following cruise; and when the distance recorded by the system between the driver and the vehicle is larger than the allowed maximum distance, the system adopts the maximum allowed distance to carry out vehicle following cruise.
Drawings
FIG. 1 is a schematic diagram of a connection structure of a self-learning vehicle following system in an embodiment;
FIG. 2 is a schematic diagram of information sensing fusion processing of a domain controller in an embodiment;
FIG. 3 is a schematic diagram illustrating a road condition determination process under a high-speed or fast road in an embodiment;
FIG. 4 is a schematic diagram of a road condition determination process under a main road or a national road of an city in the embodiment;
FIG. 5 is a schematic diagram of a road condition determination process under an urban road in the embodiment;
FIG. 6 is a schematic diagram of a process that a domain controller learns the following time distance or following distance of a driver under different working conditions in an autonomous driving process;
FIG. 7 is a schematic diagram of a logic for adjusting a following distance or a following time distance under different working conditions when the cruise system is turned on.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
Example (b):
as shown in fig. 1, the self-learning vehicle following system and method provided by this embodiment includes an external environment sensing module and a domain controller, where the external environment sensing module is capable of collecting road type information, distance and time distance information of surrounding target vehicles and lane line information, and outputting the information to the domain controller, a target fusion unit of the domain controller performs target sensing fusion, and then outputs traffic flow information, target types and distances of various lanes and road environment information, and when a driver runs in different road environments, the domain controller determines a road environment and a traffic flow condition corresponding to the vehicle according to the information collected by the external environment sensing module of the vehicle, and then collects the time distance and the distance between the vehicle and the target vehicle in real time through the external environment sensing module, and finally, matching the vehicle following time distance or the vehicle following distance of the driver according to the road working condition and the type of the target vehicle where the current vehicle is located by the domain controller.
The self-learning car following method adopting the system comprises the following steps: s1, collecting the road type, the distance and time distance information of the target vehicles around the vehicle and the lane line information through an external environment sensing module, and outputting the information to a domain controller; s2, fusing the received information through a domain controller, and determining a target distance, a target time distance, a target type, lane information and traffic flow information; s3, judging the road condition according to the information after the fusion processing in the S2; s4, when the driver drives the vehicle independently, acquiring the following vehicle distance and the following vehicle distance of the driver on different road types, different road working conditions and facing different target vehicles in real time; and S5, after the cruise system is started, the domain controller matches the information obtained after the fusion processing in S2 and the real-time road working condition of the vehicle judged in S3 with the information recorded when the driver drives autonomously in S4, and determines the vehicle following time distance or the vehicle following distance.
As shown in fig. 1, the external environment sensing module includes an ADAS map, a forward millimeter wave radar, a forward camera, a lateral millimeter wave radar, and a lateral camera. The ADAS map is used for outputting road type information of a current road, wherein the road type comprises a high-speed or express road section, an urban main road or national road section, an urban road and a common road section; the forward camera is used for collecting image information in front of the vehicle and transmitting the identified image information to the domain controller for fusion processing; the side camera is used for acquiring image information of the side direction of the vehicle and outputting the image information to the domain controller for post-fusion processing; the forward millimeter wave radar and the lateral millimeter wave radar are used for screening reflection points of targets around the vehicle, forming target information and outputting the target information to the domain controller for post-fusion processing.
As shown in fig. 2, after the target information identified by the forward camera is fused with the target information of the forward millimeter wave radar, the distance, the time distance information, and the target type of the forward target are output; and the information collected by the forward millimeter wave radar, the lateral millimeter wave radar, the forward camera and the lateral camera is fused and then output the traffic flow of the current lane, the traffic flow of the left lane and the traffic flow of the right lane, and the road working conditions are judged according to the traffic flow information, wherein the road working conditions comprise congestion, slow running, blockage and no peripheral road.
As shown in fig. 3 to 5, in S3, the road condition determination process is as follows: the domain controller outputs the road type of the current road through the ADAS map, and judges the current road working condition by combining the received vehicle flow speed in front of the current road or the received side vehicle flow speed, wherein the road working condition comprises a high-speed unblocked working condition, a high-speed congestion working condition, a main road unblocked working condition, a main road congestion working condition, a main road slow-moving working condition, an urban road unblocked working condition, an urban road congestion working condition, an urban road slow-moving working condition and a common road working condition.
As shown in fig. 3, under a high speed or express way, the road condition determining process is as follows: the ADAS map outputs the road type of the current road, and when the current road type is a high-speed or express way, the system judges that the current road is in a high-speed working condition; 1) in the case of a high-speed condition, if the flow speed in front of the own lane is > V1 (typical value: 60km/h, and can be calibrated according to specific requirements), the system judges that the current working condition is a high-speed smooth working condition GGK 1; 2) if the front traffic is between V1 and V2 (typical value: 30 km/h), if there is traffic on the right side, and the speed of the traffic is < V host vehicle + Δ V (typical value: 10 km/h), judging that the current working condition is a high-speed slow-moving working condition GGK2 by the system; if the front traffic flow is between V1 and V2 (typical value: 30 km/h), if the right side has traffic flow and the speed of the traffic flow is greater than V, the vehicle + delta V (typical value: 10 km/h), the system judges that the current working condition is a high-speed slow running working condition GGK 3; when the right side has no traffic flow and the left side has traffic flow, and the speed of the traffic flow is less than V, the vehicle is + delta V (typical value: 10 km/h), the system judges that the current working condition is a high-speed slow-moving working condition GGK 2; if the front traffic flow is between V1 and V2 (typical value: 30 km/h), if the left side has traffic flow and the speed of the traffic flow is greater than V, the vehicle + delta V (typical value: 10 km/h), the system judges that the current working condition is a high-speed slow running working condition GGK 3; when traffic flow does not exist on the left and right, the system judges that the current working condition is a high-speed slow-moving working condition GGK 4; 3) the current vehicle flow is less than V2, if there is a vehicle flow to the right, and the speed of the vehicle flow is < V host vehicle + Δ V (typical value: 10 km/h), judging that the current working condition is a high-speed congestion working condition GGK5 by the system; if the traffic flow in front is between V1 and V2 (typical value: 30 km/h), if the traffic flow exists on the right side and the speed of the traffic flow is greater than V, the vehicle + delta V (typical value: 10 km/h), the system judges that the current working condition is a high-speed congestion working condition GGK 6; when the traffic flow does not exist on the right side and the traffic flow exists on the left side, and the speed of the traffic flow is less than V, the speed of the vehicle is plus delta V (typical value: 10 km/h), the system judges that the current working condition is a high-speed congestion working condition GGK 5; if the traffic flow in front is between V1 and V2 (typical value: 30 km/h), if the traffic flow exists on the left side and the speed of the traffic flow is greater than V, the vehicle + delta V (typical value: 10 km/h), the system judges that the current working condition is a high-speed congestion working condition GGK 6; when the traffic flow does not exist on the left and the right, the system judges that the current working condition is the high-speed congestion working condition GGK 7.
As shown in fig. 4, when the current road type is an urban arterial road or a national road, the system determines that the current road is a main road condition; 1) under the condition of main road working condition, if the vehicle flow speed in front of the vehicle road>V3 (typical value: 45km/h, can be calibrated according to the concrete requirement), the system judges the current working condition to be the main road smooth working condition ZGK 1; 2) if the traffic ahead is between V3 and V4 (typical value: 25 km/h), if there is traffic on the right side, and the speed of the traffic<VSelf vehicle+ delta V (typical value: 10 km/h), the system judges that the current working condition is a main road slow-driving working condition ZGK 2; if the traffic ahead is between V3 and V4 (typical value: 25 km/h), if there is traffic on the right side, and the speed of the traffic>VSelf-vehicle+ Δ V (typical value of Δ V: 10 km/h), the system judges that the current working condition is a main road slow-driving working condition ZGK 3; when there is no traffic flow on the right side and there is traffic flow on the left side, and the speed of the traffic flow<VSelf-vehicle+ Δ V (typical value of Δ V: 10 km/h), the system judges that the current working condition is a main road slow-driving working condition ZGK 2; if the front traffic is between V3 and V4 (typical value: 25 km/h), if there is traffic on the left side, and the speed of the traffic>VSelf-vehicle+ Δ V (typical value of Δ V: 10 km/h), the system judges that the current working condition is a main road slow-driving working condition ZGK 3; when the traffic flow does not exist on the left and the right, the system judges that the current working condition is a main road slow running working condition ZGK 4; 3) when the current traffic is less than V4, if there is traffic on the right side, and the speed of the traffic is <VSelf vehicle+ Δ V (typical value of Δ V: 10 km/h), the system judges that the current working condition is a main road congestion working condition ZGK 5; if the traffic ahead is between V3 and V4 (typical value: 30 km/h), if there is traffic on the right side, and the speed of the traffic>VSelf-vehicle+ Δ V (typical value: 10 km/h), the system judges that the current working condition is the main road congestion working condition ZGK 6; when there is no traffic flow on the right side and there is traffic flow on the left side, and the speed of the traffic flowDegree of rotation<VSelf-vehicle+ Δ V (typical value: 10 km/h), the system judges that the current working condition is the main road congestion working condition ZGK 5; if the traffic in front is between V3 and V4 (typical value: 30 km/h), if there is traffic on the left side, and the speed of the traffic>VSelf-vehicle+ Δ V (typical value: 10 km/h), the system judges that the current working condition is the main road congestion working condition ZGK 6; when the traffic flow does not exist on the left and the right, the system judges that the current working condition is the main road congestion working condition ZGK 7.
As shown in fig. 5, when the current road type is an urban road, the system determines that the current road is an urban road condition; 1) under the condition of urban road working condition, if the speed of the vehicle flow in front of the vehicle road>V5 (typical value: 30km/h, can be calibrated according to specific requirements), the system judges that the current working condition is an urban road unblocked working condition CGK 1; 2) if the forward traffic is at V5(V5 typical value: 30km/h, which can be calibrated according to specific requirements) and V6 (typical value of V6: 20 km/h), if there is traffic on the right and the speed of the traffic <VSelf-vehicle+ delta V (typical value of delta V: 10 km/h), the system judges that the current working condition is an urban road slow-driving working condition CGK 2; if the traffic in front is between V5 (typical value of V5: 30km/h, which can be calibrated according to specific requirements) and V6 (typical value of V6: 20 km/h), if there is traffic on the right side, and the speed of the traffic is between V5 (typical value of V5: 30 km/h)>VSelf-vehicle+ delta V (typical value of delta V: 10 km/h), the system judges that the current working condition is an urban road slow-driving working condition CGK 3; when there is no traffic flow on the right side and there is traffic flow on the left side, and the speed of the traffic flow<VSelf-vehicle+ delta V (typical value of delta V: 10 km/h), the system judges that the current working condition is an urban road slow-driving working condition CGK 2; if the front traffic is between V5 and V6 (typical value: 20 km/h), if there is traffic on the left side, and the speed of the traffic>VSelf-vehicle+ delta V (typical value: 10 km/h), the system judges that the current working condition is the urban road slow-driving working condition CGK 3; when traffic flow does not exist on the left and right, the system judges that the current working condition is an urban road slow running working condition CGK 4; 3) when the current traffic is less than V6, if there is traffic on the right side, and the speed of the traffic is<VSelf-vehicle+ delta V (typical value: 10 km/h), the system judges that the current working condition is the urban road congestion working condition CGK 5; if the forward traffic is between V5 and V6 (typical value: 20 km/h), if There is traffic flow on the right side, and the speed of the traffic flow>VSelf vehicle+ delta V (typical value: 10 km/h), the system judges that the current working condition is the urban road congestion working condition CGK 6; when there is no traffic flow on the right side and there is traffic flow on the left side, and the speed of the traffic flow<VSelf vehicle+ delta V (typical value: 10 km/h), the system judges that the current working condition is the urban road congestion working condition CGK 5; if the front traffic is between V5 and V6 (typical value: 20 km/h), if there is traffic on the left side, and the speed of the traffic>VSelf-vehicle+ Δ V (where a typical value of Δ V is 10km/h, Δ V is a variable value, and may be adjusted according to test data), and the system determines that the current working condition is an urban road congestion working condition CGK 6; when the traffic flow does not exist on the left and the right, the system judges that the current working condition is the urban road congestion working condition CGK 7.
When the current road type is not the above road type (such as a rural road), the general road condition PGK1 is output.
As shown in fig. 6, in S4, when the driver drives autonomously, the process of learning the following time distance or following distance of the driver under different working conditions by the domain controller is as follows:
when the driver drives the vehicle on the road, the time distance and the distance between the vehicle and the front vehicle are detected in real time, and when the vehicle speed is higher than the set speed >Vt (typical value of Vt is 10km/h, determined according to the system using the threshold of distance and time interval following), if the vehicle is a large vehicle (bus, plate truck, van, tank car, etc.), if the vehicle is keeping the current time interval for a stable travel time following the vehicle>T1 (typical value of T1 is 30s, linear calibration can be carried out according to different roads and vehicle speeds), and the following distance St (HGGKDS) of the driver under the current working condition is recordedT1~HGGKDST7，HZGKDST1~HZGKDST7，HCGKDST1~HCGKDST7，HPGKDST1) Stored within the system; when the front target is a non-big vehicle, if the vehicle keeps the current time interval stable running time following the front vehicle>T1 (30 s is typical value of T1, and can be linearly calibrated according to different roads and vehicle speeds) records following distance St (HGGKSS) of driver under current working condition T1~HGGKSST7，HZGKSST1~HZGKSST7，HCGKSST1~HCGKSST7，HPGKSST1）。
When the vehicle speed Vt is>Vehicle speed>0, 1) when the front target is a large vehicle, if the vehicle keeps the current time interval stable running time following the front vehicle>T1 (typical value: 30s, linear calibration according to different roads and vehicle speeds) for recording the following distance St (LGGKDS) of the driver under the current working condition T1~LGGKDST7,LZGKDST1~LZGKDST7,LCGKDST1~LCGKDST7,LPGKDST1) Stored within the system; 2) when the front target is a non-big vehicle, if the vehicle keeps the current time interval stable running time following the front vehicle >T1 (typical value: 30s, linear calibration based on different roads and vehicle speeds) records the following distance St (LGGKSS) of driver under current working condition T1~LGGKSST7,LZGKSST1~LZGKSST7,LCGKSST1~LCGKSST7,LPGKSST1）。
When the speed of the vehicle is 0, when the front target is a large vehicle, the distance between the vehicle and the front vehicle is kept, and the number of times of recording under the same working condition>C, recording the following cart parking distance St (SGGKDS) of the driver under different conditions according to the road conditionsT7,SZGKDST7,SCGKDST7,SPGKDST1) (ii) a When the front target is a non-large vehicle, recording the times under the same working condition>C (C is a system set value, and specific set data can be set according to real-time conditions), according to road working conditions, recording the following trolley parking distance St (SGGKSS) of a driver under different conditionsT7,SZGKSST7,SCGKSST7,SPGKSST1）。
As shown in fig. 7, in S5, when the cruise system is turned on, and the vehicle speed is greater than the first threshold, the domain controller matches the recorded following distance according to the road condition where the current vehicle is located and the type of the vehicle ahead, specifically, when the driver time distance recorded by the system is between the safe time distance and the maximum allowable time distance, the system automatically performs following cruise by using the time distance recorded by the system; when the time distance of the driver recorded by the system is smaller than the safe time distance, the system adopts the safe time distance to carry out following cruising; and when the driver time distance recorded by the system is larger than the allowed maximum time distance, the system adopts the maximum time distance to carry out following cruising.
When the vehicle speed is less than a second threshold value and greater than 0, the system matches the vehicle following distance stored by the system according to the road working condition of the current vehicle and the type of the front vehicle; specifically, when the distance, recorded by the system, between the driver and the vehicle is between the safe distance and the maximum allowable distance, the system automatically adopts the distance recorded by the system to carry out cruise following; when the following distance of the driver recorded by the system is smaller than the safe distance, the system adopts the safe distance to carry out following cruise; when the distance recorded by the system between the driver and the vehicle is larger than the allowable maximum distance, the system adopts the maximum allowable distance to carry out vehicle following cruising.
When the vehicle is in the following stop condition, the system matches the following stop distance stored by the system according to the road working condition of the current vehicle and the type of the vehicle in front, and specifically, when the following stop distance of the driver recorded by the system is between the safe following stop distance and the maximum allowable following stop distance, the system automatically adopts the following stop distance recorded by the system to control; when the following stopping distance of the driver recorded by the system is less than the safe following stopping distance, the system adopts the safe following stopping distance to control; when the system records that the driver's following stopping distance is greater than the allowed maximum following stopping distance, the system adopts the maximum allowed following stopping distance for control.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting the technical solutions, and although the present invention has been described in detail by referring to the preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions to the technical solutions of the present invention can be made without departing from the spirit and scope of the technical solutions, and all the modifications and equivalent substitutions should be covered by the claims of the present invention.
Claims (9)
1. A self-learning vehicle following system based on driver behavior learning and surrounding environment is characterized by comprising an external environment sensing module and a domain controller, wherein the external environment sensing module can collect road type information, distance and time distance information of surrounding target vehicles and lane line information and output the information to the domain controller, a target fusion unit of the domain controller is used for sensing and fusing targets and outputting traffic flow information, target types and distances and road environment information of various lanes, when a driver runs in different road environments, the domain controller judges the road environment and traffic flow conditions corresponding to the vehicle according to the information collected by the external environment sensing module of the vehicle, then the external environment sensing module is used for collecting the time distance and distance between the vehicle and the target vehicles in real time, and a logic judgment module of the domain controller is used for judging the vehicle following distance and/or the vehicle following distance of the driver, and finally, matching the following time distance or the following distance of the driver according to the road working condition of the current vehicle and the type of the target vehicle through the domain controller.
2. The self-learning vehicle following system based on driver behavior learning and surrounding environment of claim 1, wherein the external environment awareness module comprises an ADAS map, a forward millimeter wave radar, a forward camera, a lateral millimeter wave radar, and a lateral camera.
3. The self-learning vehicle following system based on driver behavior learning and surrounding environment as claimed in claim 2, wherein the ADAS map is used to output road type information of a current road, the road type including a high speed or express road section, an urban main road or national road section, an urban road, and a general road section; the forward camera is used for collecting image information in front of the vehicle and transmitting the identified image information to the domain controller for fusion processing; the side camera is used for acquiring image information of the side direction of the vehicle and outputting the image information to the domain controller for post-fusion processing; the forward millimeter wave radar and the lateral millimeter wave radar are used for screening reflection points of targets around the vehicle, forming target information and outputting the target information to the domain controller for post-fusion processing.
4. The self-learning vehicle following system based on driver behavior learning and surrounding environment as claimed in claim 3, wherein the target information identified by the forward camera and the target information of the forward millimeter wave radar are fused to output the distance, time distance information and target type of the forward target; and the information collected by the forward millimeter wave radar, the lateral millimeter wave radar, the forward camera and the lateral camera is fused and then output the traffic flow of the current lane, the traffic flow of the left lane and the traffic flow of the right lane, and the road working conditions are judged according to the traffic flow information, wherein the road working conditions comprise congestion, slow running, blockage and no peripheral road.
5. A self-learning vehicle following method based on driver behavior learning and surrounding environment is characterized by comprising the following steps: s1, collecting the road type, the distance and time distance information of the target vehicles around the vehicle and the lane line information through an external environment sensing module, and outputting the information to a domain controller; s2, fusing the received information through a domain controller, and determining a target distance, a target time distance, a target type, lane information and traffic flow information; s3, judging the road condition according to the information after the fusion processing in the S2; s4, when the driver drives the vehicle independently, acquiring the following vehicle distance and the following vehicle distance of the driver on different road types, different road working conditions and facing different target vehicles in real time; and S5, after the cruise system is started, the domain controller matches the information obtained after the fusion processing in S2 and the real-time road working condition of the vehicle judged in S3 with the information recorded when the driver drives autonomously in S4, and determines the vehicle following time distance or the vehicle following distance.
6. The self-learning vehicle following method based on driver behavior learning and surrounding environment as claimed in claim 5, wherein in S1, the external environment sensing module comprises ADAS map, forward millimeter wave radar, forward camera, lateral millimeter wave radar and lateral camera, the ADAS map is used to output road type information of the current road, the road type comprises high speed or express road section, city main road or national road section, city road and general road section; the front camera is used for collecting image information in front of the vehicle, the side camera is used for collecting image information in side direction of the vehicle, and the front millimeter wave radar and the side millimeter wave radar are used for screening reflecting points of targets around the vehicle and outputting target information.
7. The self-learning vehicle following method based on driver behavior learning and surrounding environment as claimed in claim 6, wherein in S3, the determination of road condition is as follows: the domain controller outputs the road type of the current road through the ADAS map, and judges the current road working condition by combining the received vehicle flow speed in front of the current road or the received lateral vehicle flow speed, wherein the road working condition comprises a high-speed unblocked working condition, a high-speed congestion working condition, a main road unblocked working condition, a main road congestion working condition, a main road slow running working condition, an urban road unblocked working condition, an urban road congestion working condition, an urban road slow running working condition and a common road working condition.
8. The self-learning vehicle following method based on driver behavior learning and surrounding environment as claimed in claim 5, 6 or 7, wherein in step S5, when the cruise system is turned on, when the vehicle speed is greater than a first threshold value, the domain controller matches the recorded vehicle following distance according to the current road condition of the vehicle and the type of the vehicle ahead, specifically, when the driver time distance recorded by the system is between the safe time distance and the maximum allowable time distance, the system automatically adopts the time distance recorded by the system to perform the vehicle following cruise; when the driver time distance recorded by the system is smaller than the safe time distance, the system adopts the safe time distance to carry out vehicle following cruise; and when the driver time interval recorded by the system is larger than the allowed maximum time interval, the system adopts the maximum time interval to carry out following cruise.
9. The self-learning vehicle following method based on driver behavior learning and surrounding environment as claimed in claim 5, 6 or 7, wherein in step S5, when the cruise system is turned on, and when the vehicle speed is less than a second threshold value and greater than 0, the system matches the vehicle following distance stored by the system according to the road condition of the current vehicle and the type of the vehicle ahead; specifically, when the distance, recorded by the system, between the driver and the vehicle is between the safe distance and the maximum allowable distance, the system automatically adopts the distance recorded by the system to carry out cruise following; when the following distance of the driver recorded by the system is smaller than the safe distance, the system adopts the safe distance to carry out following cruise; when the distance recorded by the system between the driver and the vehicle is larger than the allowable maximum distance, the system adopts the maximum allowable distance to carry out vehicle following cruising.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210173097.0A CN114516327A (en) | 2022-02-24 | 2022-02-24 | Self-learning vehicle following system and method based on driver behavior learning and surrounding environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210173097.0A CN114516327A (en) | 2022-02-24 | 2022-02-24 | Self-learning vehicle following system and method based on driver behavior learning and surrounding environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114516327A true CN114516327A (en) | 2022-05-20 |
Family
ID=81599810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210173097.0A Withdrawn CN114516327A (en) | 2022-02-24 | 2022-02-24 | Self-learning vehicle following system and method based on driver behavior learning and surrounding environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114516327A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114889594A (en) * | 2022-05-25 | 2022-08-12 | 重庆长安汽车股份有限公司 | Method and system for realizing automatic following of vehicle based on UWB technology |
| CN115346397A (en) * | 2022-07-18 | 2022-11-15 | 岚图汽车科技有限公司 | Traffic flow positioning passing method, system, storage medium and equipment |
-
2022
- 2022-02-24 CN CN202210173097.0A patent/CN114516327A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114889594A (en) * | 2022-05-25 | 2022-08-12 | 重庆长安汽车股份有限公司 | Method and system for realizing automatic following of vehicle based on UWB technology |
| CN115346397A (en) * | 2022-07-18 | 2022-11-15 | 岚图汽车科技有限公司 | Traffic flow positioning passing method, system, storage medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10838423B2 (en) | Intelligent vehicle navigation systems, methods, and control logic for deriving road segment speed limits | |
| US11772652B2 (en) | Cooperative adaptive cruise control system based on driving pattern of target vehicle | |
| CN112477884B (en) | Automatic driving control method and device and vehicle | |
| EP3342668A2 (en) | Cooperative adaptive cruise control system based on driving pattern of target vehicle | |
| JP7205154B2 (en) | Display device | |
| US11912286B2 (en) | Driving risk identification model calibration method and system | |
| US20100315217A1 (en) | Driving support device and program | |
| CN114516327A (en) | Self-learning vehicle following system and method based on driver behavior learning and surrounding environment | |
| CN110114253A (en) | Controller of vehicle, control method for vehicle and program | |
| CN110329259B (en) | Vehicle automatic following system and method based on multi-sensor fusion | |
| JP6930152B2 (en) | Autonomous driving system | |
| CN112406820B (en) | Multi-lane enhanced automatic emergency braking system control method | |
| CN101434234A (en) | Vehicle control device, vehicle control method, and computer program | |
| CN105501221A (en) | Self-adaptive cruise system and control method based on vehicle to vehicle communication | |
| WO2019030916A1 (en) | Traffic lane information management method, running control method, and traffic lane information management device | |
| CN111736605B (en) | Automobile automatic driving and doubling safety control method | |
| KR20140078436A (en) | Sensor fusion system and method thereof | |
| CN112373474B (en) | Lane line fusion and transverse control method, system, vehicle and storage medium | |
| CN113763702A (en) | V2V-based humanization-friendly front collision early warning system and early warning method | |
| JP5076852B2 (en) | Travel control device | |
| CN111376901A (en) | Vehicle control method and device and vehicle | |
| JP2006160032A (en) | Driving state determination device and its method | |
| TW201617256A (en) | Drive mode judging device and method applied to vehicle energy management | |
| CN220430132U (en) | Vehicle collision early warning system | |
| US20240042998A1 (en) | Traveling control apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220520 |