Rule-based adaptive cruise control system for vehicle

Abstract

A rule-based adaptive cruise control system for determining a following behavior of a vehicle includes a plurality of perceived sensors for collecting perceived data representative of an environment around the vehicle, and one or more controllers in electronic communication with the plurality of perceived sensors. The one or more controllers classify the road profile as one of a plurality of road profiles based on the route plan and the perceived data, each road profile indicating a certain geometry of the road, classify detection of the preceding vehicle as one of a plurality of detection states based on the perceived data, the selected road profile and the selected detection state are classified as one of a plurality of scenes based on a set of classification rules, and a particular car following behavior is assigned based on the selected scene.

Description

Technical Field

[0001] The present disclosure relates to a rule-based adaptive cruise control system for a vehicle that determines vehicle following behavior based on a set of classification rules that take into account a road profile and a detection status of a leading vehicle. Background Art

[0002] Many vehicles include various driver assistance systems that support the driver in a variety of ways. For example, an adaptive cruise control (ACC) system can free the driver from conventional longitudinal vehicle control by ensuring that the host vehicle is within an acceptable separation distance from the vehicle immediately in front of the host vehicle (referred to as the lead vehicle). The adaptive cruise control system determines longitudinal control of the host vehicle based on the motion of the lead vehicle.

[0003] It should be understood that current adaptive cruise control systems do not take into account route planning information, but rather determine the behavior of the own vehicle based on perception data about the vehicle ahead and the target speed. The perception data about the vehicle ahead is collected by perception sensors such as cameras. Therefore, when the vehicle ahead temporarily leaves the field of view or cannot be detected by the perception sensors of the own vehicle due to road geometry, the adaptive cruise control system assumes that the vehicle ahead is no longer present and adjusts the speed of the own vehicle accordingly. For example, when the vehicle ahead passes through a steep angle, a steep hill, a roundabout, or a merging lane on the road, the vehicle ahead may temporarily leave the field of view of the perception sensors of the own vehicle, and the adaptive cruise control system may then instruct the own vehicle to increase its speed to meet the target speed. However, once the vehicle ahead returns to the field of view of the perception sensors, the adaptive cruise control system may instruct the own vehicle to reduce or change its speed. Therefore, the adaptive cruise control system may unnecessarily increase and decrease the speed of the vehicle, which increases energy consumption and may have an adverse impact on customer satisfaction.

[0004] Therefore, while adaptive cruise control systems achieve their intended purpose, there is a need in the art for an improved method of adjusting the speed of a host vehicle when the host vehicle's perception sensors temporarily fail to detect a leading vehicle. Summary of the invention

[0005] According to several aspects, a rule-based adaptive cruise control system for determining a following behavior of a vehicle is disclosed. The rule-based adaptive cruise control system includes a plurality of perception sensors for collecting perception data representing an environment around the vehicle, wherein the environment includes a road along which the vehicle is traveling, and the perception sensors include a field of view. The rule-based adaptive cruise control system also includes one or more controllers in electronic communication with the plurality of perception sensors. The one or more controllers execute instructions to receive a route plan and the perception data collected by the plurality of perception sensors. The one or more controllers classify a road profile into one of a plurality of road profiles based on the route plan and the perception data, each road profile indicating a geometric shape of the road. The one or more controllers classify a detection of a leading vehicle into one of a plurality of detection states based on the perception data, wherein the plurality of detection states indicate that the leading vehicle temporarily falls outside the field of view of the perception sensor due to a geometric shape associated with the road. The one or more controllers classify a selected road profile and a selected detection state into one of a plurality of scenarios based on a set of classification rules, and then assign a specific following behavior based on the selected scenario.

[0006] In another aspect, a leading vehicle is located immediately ahead of the vehicle along the road, wherein the rule-based adaptive cruise control system maintains a predetermined separation distance between the vehicle and the leading vehicle.

[0007] In yet another aspect, longitudinal control commands instructing the vehicle when to accelerate and decelerate are based on vehicle following behavior.

[0008] In one aspect, the set of classification rules is a set of conditional statements that classify the selected road profile and the selected detection state into a selected scene.

[0009] On the other hand, the road profile includes the following: a straight profile, a curve profile, an uphill profile, and a downhill profile.

[0010] In yet another aspect, the straight contour indicates a level road.

[0011] In one aspect, the detection state includes a non-detected state, a detected state, and a detected but absent state.

[0012] On the other hand, the detected but disappeared state indicates that the leading vehicle temporarily left the field of view of the plurality of perception sensors while traveling along the road.

[0013] On the other hand, the following behavior instructs the vehicle to perform one of the following operations: follow a target speed, comply with standard adaptive cruise control behavior, reduce speed to negotiate a curve profile, follow the vehicle ahead to negotiate a curve profile according to a speed limit, negotiate a curve profile without sudden acceleration, negotiate an uphill profile without sudden acceleration, negotiate a downhill profile based on an allowed speed change, and negotiate a downhill profile without sudden acceleration.

[0014] In one aspect, the plurality of perception sensors include one or more of: one or more cameras, an inertial measurement unit (IMU), a global positioning system (GPS), radar, and LiDAR.

[0015] On the other hand, rule-based adaptive cruise control systems are part of advanced driver assistance systems (ADAS).

[0016] In another aspect, a method for determining a following behavior of a vehicle by a rule-based adaptive cruise control system is disclosed. The method includes receiving, by one or more controllers, a route plan and perception data collected by a plurality of perception sensors, wherein the perception data represents an environment surrounding the vehicle, and the environment includes a road along which the vehicle is traveling. The method includes classifying a road profile into one of a plurality of road profiles based on the route plan and the perception data, each road profile indicating a geometric shape of the road. The method also includes classifying a detection of a leading vehicle into one of a plurality of detection states based on the perception data, wherein the plurality of detection states indicates that the leading vehicle temporarily falls outside the field of view of the perception sensor due to a geometric shape associated with the road. The method includes classifying a selected road profile and a selected detection state into one of a plurality of scenarios based on a set of classification rules. Finally, the method includes assigning a specific following behavior based on the selected scenario.

[0017] In another aspect, a rule-based adaptive cruise control system for determining a following behavior of a vehicle is disclosed. The rule-based adaptive cruise control system includes a plurality of perception sensors for collecting perception data representing an environment around the vehicle, wherein the environment includes a road along which the vehicle is traveling, and the perception sensors include a field of view. One or more controllers are in electronic communication with the plurality of perception sensors. The one or more controllers execute instructions to receive a route plan and the perception data collected by the plurality of perception sensors. The one or more controllers execute instructions to classify a road profile into one of a plurality of road profiles based on the route plan and the perception data, each road profile indicating a geometric shape of the road. The one or more controllers classify a detection of a leading vehicle into one of a plurality of detection states based on the perception data, wherein the plurality of detection states indicate that the leading vehicle temporarily falls outside the field of view of the perception sensor due to a geometric shape associated with the road, and the leading vehicle is immediately ahead of the vehicle along the road, and wherein the rule-based adaptive cruise control system maintains a predetermined separation distance between the vehicle and the leading vehicle. The one or more controllers classify a selected road profile and a selected detection state into one of a plurality of scenarios based on a set of classification rules, and assign a specific following behavior based on the selected scenario, wherein a longitudinal control command indicating when the vehicle accelerates and decelerates is based on the following behavior.

[0018] On the other hand, the set of classification rules is a set of conditional statements that classify the selected road profile and the selected detection state into the selected scene.

[0019] In yet another aspect, the road profile includes the following: a straight profile, a curve profile, an uphill profile, and a downhill profile.

[0020] In one aspect, the straight contour indicates a level road.

[0021] On the other hand, the detection state includes a non-detected state, a detected state, and a detected but disappeared state.

[0022] In one aspect, the detected but disappeared state indicates that the leading vehicle temporarily left the field of view of the plurality of perception sensors while traveling along the road.

[0023] On the other hand, the following behavior instructs the vehicle to perform one of the following operations: follow a target speed, comply with standard adaptive cruise control behavior, reduce speed to negotiate a curve profile, follow the vehicle ahead to negotiate a curve profile according to a speed limit, negotiate a curve profile without sudden acceleration, negotiate an uphill profile without sudden acceleration, negotiate a downhill profile based on an allowed speed change, and negotiate a downhill profile without sudden acceleration.

[0024] In yet another aspect, the plurality of perception sensors includes one or more of: one or more cameras, IMU, GPS, radar, and LiDAR.

[0025] Further areas of applicability will become apparent from the description provided herein.It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way.

[0027] Figure 1 is a schematic diagram of a vehicle including a disclosed rule-based adaptive cruise control system according to an exemplary embodiment, the system including one or more controllers in electronic communication with a plurality of perception sensors;

[0028] Figure 2A According to an exemplary embodiment, Figure 1 The vehicle shown is traveling along a road and following a preceding vehicle around a curve;

[0029] Figure 2B According to an exemplary embodiment, Figure 1 The vehicle shown is following a preceding vehicle along a slope;

[0030] Figure 3 According to an exemplary embodiment Figure 1 a diagram of the software architecture of the one or more controllers shown; and

[0031] Figure 4 is a process flow diagram illustrating a method for determining vehicle following behavior via a rule-based adaptive cruise control system according to an exemplary embodiment. DETAILED DESCRIPTION

[0032] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses.

[0033] refer to Figure 1 , a schematic diagram of an exemplary rule-based adaptive cruise control system 10 for a vehicle 12 is shown. It should be understood that the vehicle 12 can be any type of vehicle, such as, but not limited to, a car, a truck, a sport utility vehicle, a van, or an RV. In one embodiment, the rule-based adaptive cruise control system 10 is part of an advanced driver assistance system (ADAS) for the vehicle 12. The rule-based adaptive cruise control system 10 includes one or more controllers 20 in electronic communication with a plurality of perception sensors 22, which are configured to collect perception data indicative of the environment surrounding the vehicle 12. In the example shown in FIG. Figure 1In the non-limiting embodiment shown, the plurality of perception sensors 22 include one or more cameras 30, an inertial measurement unit (IMU) 32, a global positioning system (GPS) 34, a radar 36, and a laser radar (LiDAR) 38, however, it should be understood that additional sensors may also be used. The one or more controllers 20 are also in electronic communication with one or more longitudinal controllers 24 that control the longitudinal motion of the vehicle 12. The one or more longitudinal controllers 24 may be, for example, a proportional integral derivative controller, a model predictive control (MPC) controller, or a sliding mode controller.

[0034] As described below, one or more controllers 20 of the rule-based adaptive cruise control system 10 determine the following behavior 86 of the vehicle 12 based on the perception data collected by the plurality of perception sensors 22 and the route plan indicating the route selected by the vehicle 12. The perception data collected by the plurality of perception sensors 22 indicates the detection state of the leading vehicle 50. The leading vehicle 50 is located immediately ahead of the vehicle 12 along the road 52 ( Figure 2A and Figure 2B ), wherein the rule-based adaptive cruise control system 10 maintains a predetermined separation distance between the vehicle 12 and the leading vehicle 50. The detection state indicates that the leading vehicle 50 is temporarily outside the field of view (FOV) of the perception sensor 22 due to the geometry associated with the road 52 ( Figure 2A and Figure 2B The following behavior 86 is transmitted to the one or more longitudinal controllers 24. The one or more longitudinal controllers 24 determine a longitudinal control command 90 instructing the vehicle 12 to accelerate or decelerate based on the following behavior 86.

[0035] Figure 2A and Figure 2B The vehicle 12 is shown following a leading vehicle 50 along a road 52, wherein the leading vehicle 50 is temporarily away from the plurality of perception sensors 22 ( Figure 1 ) of the field of view FOV, but without leaving the road 52. Figure 2A In the example shown, the geometry of the road 52 has a contour including a curve 54, wherein the leading vehicle 50 leaves the field of view FOV of the plurality of perception sensors 22 when passing through the curve 54 along the road 52. Figure 2B In the example shown, the road 52 extends along a slope 56 , and as the vehicle 12 climbs the slope 56 and the leading vehicle 50 travels down the slope 56 , the leading vehicle 50 leaves the field of view FOV of the perception sensor 22 .

[0036] Figure 3is a diagram of the architecture of the one or more controllers 20. The one or more controllers 20 include a perception module 60, a scene classification module 62, and a behavior module 64. The perception module 60 includes a road profile submodule 66 and a vehicle detection submodule 68. Figure 1 and Figure 3 The road profile submodule 66 receives the route plan and the perception data collected by the plurality of perception sensors 22 representing the environment surrounding the vehicle 12, wherein the environment includes the road 52 ( Figure 2A and Figure 2B The vehicle detection submodule 68 receives perception data representing the environment surrounding the vehicle 12 collected by the plurality of perception sensors 22 .

[0037] refer to Figure 1 , Figure 2A and Figure 2B The road profile submodule 66 of the perception module 60 maps the road 52 ( Figure 2A and Figure 2B ) is classified as one of a plurality of road profiles 80, wherein each road profile 80 indicates a certain geometric shape of the road 52. Figure 3 In the non-limiting embodiment shown, the road profile 80 includes a straight profile 80A, a curved profile 80B, an uphill profile 80C, and a downhill profile 80D. The straight profile 80A indicates a level road, where the front vehicle 50 is always within the field of view FOV of the plurality of perception sensors 22. In contrast, it should be understood that the curved profile 80B, the uphill profile 80C, and the downhill profile 80D indicate a profile that may cause the front vehicle 50 to temporarily leave the field of view FOV of the plurality of perception sensors 22 while still traveling along the road 52.

[0038] The vehicle detection submodule 68 of the perception module 60 of one or more controllers 20 receives the plurality of perception sensors 22 ( Figure 1 ) classifies the detection of the leading vehicle 50 as one of a plurality of detection states 82. Specifically, the detection state 82 indicates that the leading vehicle 50 is temporarily outside the field of view FOV of the perception sensor 22 due to the geometry of the road 52. Figure 3 In the illustrated embodiment, the detection state 82 includes an undetected state 82A indicating that the perception sensor 22 has not detected the front vehicle 50, a detected state 82B, and a detected but missing state 82C. The detected but missing state 82C indicates that the front vehicle 50 is not detected by the perception sensor 22. Figure 2A or Figure 2B A situation is shown in which a leading vehicle 50 temporarily leaves the field of view FOV of the plurality of perception sensors 22 while traveling along the road 52 due to the geometry of the road 52 .

[0039] The scene classification module 62 of the one or more controllers 20 receives the selected road profile 80 determined by the road profile submodule 66 of the perception module 60 and the selected detection state 82 determined by the vehicle detection submodule 68 of the perception module 60. The scene classification module 62 of the one or more controllers 20 classifies the selected road profile 80 and the selected detection state 82 into one of a plurality of scenes 84 based on a set of classification rules, wherein the set of classification rules considers the profile of the road 52 ( Figure 2A and Figure 2B ) and the detected state of the preceding vehicle 50. Each scenario 84 corresponds to a specific following behavior 86 that dictates the operation of the vehicle 12, wherein the behavior module 64 assigns a specific following behavior 86 based on the selected scenario 84. The following behavior 86 is then sent to Figure 1 , wherein one or more longitudinal controllers 24 determine a longitudinal control command 90 .

[0040] The set of classification rules is a set of conditional statements or if-then rules that classify the selected road profile 80 determined by the road profile submodule 66 of the perception module 60 and the selected detection state 82 determined by the vehicle detection submodule 68 of the perception module 60 into a selected scene 84. Figure 3 In the example shown, the scene classification module 62 includes twelve different scenes 84A-84L. Each scene 84 corresponds to a specific vehicle following behavior 86.

[0041] In such Figure 3 In the example shown, eight different following behaviors 86A-86H are shown. In an embodiment, following behavior 86A instructs the vehicle 12 to follow a target speed, following behavior 86B instructs the vehicle 12 to follow a standard adaptive cruise control behavior, following behavior 86C instructs the vehicle 12 to reduce speed to pass through a curved profile, following behavior 86D instructs the vehicle 12 to follow the front vehicle 50 to pass through a curved profile according to a speed limit, following behavior 86E instructs the vehicle 12 to pass through a curved profile without sudden acceleration, following behavior 86F instructs the vehicle 12 to pass through an uphill profile without sudden acceleration, following behavior 86G instructs the vehicle 12 to pass through a downhill profile based on an allowed speed change, and following behavior 86H instructs the vehicle 12 to pass through a downhill profile without sudden acceleration. Standard adaptive cruise control behavior refers to automatically adjusting the vehicle speed to maintain a predetermined spacing or distance from the vehicle ahead. Sudden acceleration is triggered by a temporary loss of detection of the vehicle ahead 50 and refers to acceleration that falls outside an acceptable range, where the acceptable acceleration range is selected based on occupant comfort. Sudden acceleration may result in system-activated corrective braking, driver intervention, or driver discomfort due to approaching a leading vehicle 50 or negotiating a curve too sharply.

[0042] As an example, when the selected road profile 80 is a straight profile 80A and the selected detection state 82 is a not detected state 82A indicating that the perception sensor 22 does not detect the front vehicle 50, the scene classification module 62 of the one or more controllers 20 classifies the selected road profile 80 and the selected detection state 82 as a selected scene 84A, which corresponds to a following behavior 86A indicating that the vehicle 12 follows the target speed. As another example, when the selected road profile 80 is a curved profile 80B and the selected detection state 82 is a detected state 82B, the scene classification module 62 of the one or more controllers 20 classifies the selected road profile 80 and the selected detection state 82 as a selected scene 84E, which corresponds to a following behavior 86D indicating that the vehicle 12 follows the front vehicle 50 to pass the curved profile according to the speed limit. In yet another example, when the selected road profile 80 is a curve profile 80B and the selected detection state 82 is a detected but disappeared state 82C, the scene classification module 62 of one or more controllers 20 classifies the selected road profile 80 and the selected detection state 82 as a selected scene 84F, which corresponds to a following behavior 86E indicating that the vehicle 12 passes through the curve profile without sudden acceleration.

[0043] Figure 4 is a process flow diagram illustrating a method 400 for determining a following behavior 86 via a rule-based adaptive cruise control system 10. Figures 1 to 4 , the method 400 may begin at decision block 402. In decision block 402, the one or more controllers 20 continuously monitor the perception data of the plurality of perception sensors 22. In response to receiving the perception data and the route plan, the method 400 proceeds to block 404.

[0044] In block 404, the road profile submodule 66 of the perception module 60 of the one or more controllers 20 maps the contour of the road 52 (e.g., Figure 2A and Figure 2B 4 ) is classified into one of a plurality of road profiles 80 , each of which indicates a certain geometry of the road 52 . The method 400 may then proceed to block 406 .

[0045] In block 406, the vehicle detection submodule 68 of the perception module 60 of the one or more controllers 20 classifies the detection of the leading vehicle 50 into one of a plurality of detection states 82 based on the perception data, wherein the plurality of detection states indicates that the leading vehicle 50 is temporarily outside of the field of view FOV of the perception sensor 22 due to geometry associated with the road 52. The method 400 may then proceed to block 408.

[0046] In block 408 , the scene classification module 62 of the one or more controllers 20 classifies the selected road profile 80 and the selected detection state 82 into one of the plurality of scenes 84 based on a set of classification rules. The method 400 may then proceed to block 410 .

[0047] In block 410 , the behavior module 64 of the one or more controllers 20 assigns a specific following behavior 86 based on the selected scenario 84 . The method 400 may then terminate.

[0048] Referring generally to the accompanying drawings, the disclosed rule-based adaptive cruise control system provides various technical effects and benefits. Specifically, the disclosed rule-based adaptive cruise control system determines the following behavior of the host vehicle based on a set of classification rules that take into account the road profile and the detection status of the leading vehicle, which results in reducing abnormal or sudden acceleration and deceleration situations that may occur in situations where the adaptive cruise control system is currently available. Reducing sudden acceleration and deceleration situations can improve energy consumption and provide a more natural and comfortable driving experience for vehicle occupants.

[0049] A controller may refer to an electronic circuit, a combinatorial logic circuit, a field programmable gate array (FPGA), a (shared, dedicated or grouped) processor that executes code, or a combination of some or all of the above, or a portion of an electronic circuit, a combinatorial logic circuit, a field programmable gate array (FPGA), a (shared, dedicated or grouped) processor that executes code, or a combination of some or all of the above, such as a system on a chip. In addition, the controller may be microprocessor-based, such as a computer having at least one processor, memory (RAM and / or ROM), and associated input and output buses. The processor may operate under the control of an operating system residing in the memory. The operating system may manage computer resources so that a computer program code embodied as one or more computer software applications (e.g., applications residing in the memory) may have instructions executed by the processor. In an alternative embodiment, the processor may execute the application directly, in which case the operating system may be omitted.

[0050] The description of the present disclosure is merely exemplary in nature, and variations that do not depart from the gist of the present disclosure are intended to fall within the scope of the present disclosure. These variations should not be regarded as departing from the spirit and scope of the present disclosure.

Claims

1. A rule-based adaptive cruise control system for determining a vehicle following behavior, the rule-based adaptive cruise control system comprising: a plurality of perception sensors for collecting perception data representative of an environment surrounding the vehicle, wherein the environment includes a road along which the vehicle is traveling and the perception sensors include a field of view; one or more controllers in electronic communication with the plurality of sensory sensors, the one or more controllers executing instructions to: receiving a route plan and the perception data collected by the plurality of perception sensors; classifying the profile of the road into one of a plurality of road profiles based on the route plan and the perception data, each of the road profiles indicating a geometric shape of the road; classifying detection of a leading vehicle into one of a plurality of detection states based on the perception data, wherein the plurality of detection states indicates that the leading vehicle is temporarily outside of a field of view of the perception sensor due to geometry associated with the road; classifying the selected road profile and the selected detection state into one of a plurality of scenarios based on a set of classification rules; and Assign specific following behaviors based on the selected scenario.

2. The rule-based adaptive cruise control system according to claim 1, wherein: The leading vehicle is located immediately ahead of the vehicle along the road, and wherein the rule-based adaptive cruise control system maintains a predetermined separation distance between the vehicle and the leading vehicle.

3. The rule-based adaptive cruise control system according to claim 1, wherein: Longitudinal control commands instructing the vehicle when to accelerate and decelerate are based on the following behavior.

4. The rule-based adaptive cruise control system according to claim 1, wherein: The set of classification rules is a set of conditional statements that classify the selected road profile and the selected detection state into the selected scene.

5. The rule-based adaptive cruise control system according to claim 1, wherein: The road profile includes the following: a straight line profile, a curve profile, an uphill profile and a downhill profile.

6. The rule-based adaptive cruise control system according to claim 5, wherein: The straight contour indicates a level road.

7. The rule-based adaptive cruise control system according to claim 1, wherein: The detection status includes an undetected state, a detected state, and a detected but disappeared state.

8. The rule-based adaptive cruise control system of claim 1, wherein: The detected but disappeared state indicates that the leading vehicle temporarily leaves the field of view of the plurality of perception sensors while traveling along the road.

9. The rule-based adaptive cruise control system of claim 1, wherein: The following behavior instructs the vehicle to perform one of: follow a target speed, comply with standard adaptive cruise control behavior, reduce speed to pass a curve profile, follow the leading vehicle to pass a curve profile according to a speed limit, pass a curve profile without sudden acceleration, pass an uphill profile without sudden acceleration, pass a downhill profile based on an allowed speed change, and pass a downhill profile without sudden acceleration.

10. The rule-based adaptive cruise control system of claim 1, wherein: The plurality of perception sensors include one or more of: one or more cameras, an inertial measurement unit (IMU), a global positioning system (GPS), radar, and LiDAR.

Images