RAILWAY PLANNING SYSTEM THAT CALCULATES A LATERALLY OFFSET RAILWAY FOR A VEHICLE

Abstract

A path planning system that calculates a laterally offset path based on a maximum allowable in-track lateral offset with respect to the center of a vehicle's host lane includes one or more controllers, which contain one or more processors that execute instructions to monitor perception data collected by multiple perception sensors until an offset event is detected that requires the vehicle to deviate from an original path. In response to the detection of the offset event, the one or more controllers calculate a non-linear error component of the maximum allowable in-track lateral offset.The one or more controllers update the vehicle's laterally offset path with the maximum permissible in-track lateral offset and apply a rate limiter to the maximum permissible in-track lateral offset in real time, while instructing the vehicle to travel along the laterally offset path.

Description

INTRODUCTION

[0001] The present disclosure relates to a path planning system for a vehicle that calculates a laterally offset path based on a maximum permissible in-track lateral offset measured with respect to the center of the vehicle's host lane. The maximum permissible in-track lateral offset is dynamically adjusted based on a non-linear error generated in real time as the vehicle deviates from the laterally offset path.

[0002] Autonomous vehicles employ motion planning and control to determine trajectories that define a vehicle's position, speed, and acceleration over time. It should be noted that the vehicle's trajectory should result in minimal lateral acceleration and jerk, be collision-free, and also be feasible and rational. Specifically, the feasibility of a trajectory can be achieved by providing closed-loop feedback from the control logic to the planning logic, where the control logic communicates its internal parameters to the planning logic. However, there are many cases in which the performance of a control system can deviate from normal operation due to a variety of factors, including, but not limited to, malfunctioning components, weakening of mechanical components, and disturbances with an extended time horizon.An example of a disturbance with an extended time horizon is oscillating vehicle behavior, which may be caused by a section of road experiencing besiege buildup or by repeated gusts of wind from the same direction.

[0003] Thus, while current systems achieve their intended purpose, the state of the art requires the ability to recognize the true performance of a control system based on real-time observations and to adjust the vehicle's trajectory based on these real-time observations. SUMMARY

[0004] According to several aspects, a path planning system is disclosed that calculates a laterally offset path based on a maximum permissible in-track lateral offset with respect to the center of a vehicle's host lane. The path planning system includes one or more controllers that receive perception data indicating an external environment surrounding the vehicle, collected by multiple perception sensors integrated into the vehicle. The one or more controllers include one or more processors that execute instructions to monitor the perception data collected by the multiple perception sensors until an offset event is determined that requires the vehicle to deviate from an initial path.In response to a detection of the offset event, the one or more controllers calculate a non-linear error component of the maximum allowable in-track lateral offset with respect to the center of a host lane. This non-linear error component is calculated as a function of a target lane position error over a relevant time window. The one or more controllers calculate the maximum allowable in-track lateral offset based on the host lane width, the vehicle width, the target lane position error, and a buffer distance. The maximum allowable in-track lateral offset is dynamically adjusted based on a non-linear error generated in real time as the vehicle deviates from the laterally offset path.The one or more controllers compare the maximum allowable in-track lateral offset with a mediated in-track lateral offset value, where the mediated in-track lateral offset value and the maximum allowable in-track lateral offset are both oriented in the same direction. In response to a determination that the mediated in-track lateral offset value is greater than the maximum allowable in-track lateral offset, the one or more controllers update the vehicle's laterally offset path with the maximum allowable in-track lateral offset and apply a rate limiter to the maximum allowable in-track lateral offset in real time while directing the vehicle to travel along the laterally offset path.

[0005] In another aspect, one or more controllers execute commands in response to a determination that the mediated in-track lateral offset value is equal to or less than the maximum permissible in-track lateral offset, update the vehicle's laterally offset path with the mediated in-track lateral offset value, and apply a rate limiter to the mediated in-track lateral offset value in real time while instructing the vehicle to travel along the laterally offset path.

[0006] In a further aspect, the target lane position error is determined based on an effective value solution attempt.

[0007] In one aspect, the target lane position error is determined by the following: TgtLane_Position_Error=∑Buffer 0Max​ Sample buffer sizeTgtErr2Max Sample Buffer Size, where TgtLane_Position_Error represents the target lane position error, Max Sample Buffer Size represents a maximum number of allocated data samples, and TgtErr represents an error between a planned target vehicle position and an actual lateral vehicle position.

[0008] In one aspect, the target lane position error is determined based on a standard deviation solution attempt.

[0009] In another aspect, the target lane position error is determined by the following: TgtLane_Position_Error=∑Buffer 0Max sample buffer size(TgtErr−TgtErr_Mean)2Max Sample Buffer size, where TgtLane_Position_Error represents the target lane position error, Max Sample Buffer Size represents a maximum number of allocated data samples, and TgtErr_Mean represents a cumulative average error between a planned target vehicle position and an actual lateral vehicle position.

[0010] In a further aspect, the buffer distance between a lane boundary of the host lane and a satisfaction boundary arranged along the host lane is measured, with the lane boundary being positioned along a side of the host lane opposite the location of the offset event.

[0011] In one aspect, the maximum permissible track-internal lateral offset is determined based on the following: Max Allowed Lateral Offset=(Lane Width−Host vehicle width)2−TgtLane_Position_Error−Buffer, where TgtLane_Position_Error represents the target lane position error, Lane Width represents the lane width of the host lane, Host vehicle width represents the width of the vehicle, and Buffer represents the buffer distance.

[0012] In another aspect, the mediated track-internal lateral offset value represents a current transverse offset value of the laterally offset path of the vehicle.

[0013] In yet another aspect, the offset event is one of the following: a moving obstacle that moves into an adjacent lane and affects the host lane, an aggressive road curvature, a driver request and reaction to avoid oncoming traffic.

[0014] In one aspect, the offset event is the moving obstacle traveling in the adjacent lane, where the moving obstacle is another vehicle.

[0015] In another aspect, the one or more controllers store a one-dimensional lookup table that specifies rate limiter values ​​based on the target lane position error.

[0016] In a further aspect, one or more controllers execute commands to monitor the perception data collected by the multiple perception sensors, which indicate the external environment surrounding the vehicle, until the presence of a lateral obstacle located in an adjacent lane is detected. In response to the detection of a lateral obstacle, they determine that the vehicle is about to perform a lane change maneuver. During the lane change maneuver, the vehicle follows a laterally offset lane change path to move from the host lane to an adjacent lane, and the adjacent lane containing the lateral obstacle is adjacent to the neighboring lane.

[0017] In one aspect, one or more controllers execute commands to, in response to a determination of the presence of the lateral obstacle and a determination that the vehicle is about to perform the lane change maneuver, calculate an estimated lateral separation distance between the vehicle and the lateral obstacle based on an initial trajectory of the vehicle, compare the estimated lateral separation distance with a lateral separation distance threshold measured between the vehicle and the lateral obstacle, and, in response to a determination that the estimated lateral separation distance is less than the lateral separation distance threshold, calculate a target lane lateral offset error.

[0018] In another aspect, one or more controllers execute commands to compare the target lane lateral offset error with a threshold of the maximum allowable error value and, in response to a determination that the target lane lateral offset error is less than the threshold of the maximum allowable error value, to calculate a lateral offset correction value, the lateral offset correction value maintaining the lateral separation distance threshold measured between the vehicle and the lateral obstacle while the vehicle follows the laterally offset lane change path.

[0019] In a further aspect, a method for calculating a laterally offset path based on a maximum permissible in-lane lateral offset with respect to the center of a vehicle's host lane is disclosed. The method includes monitoring, by one or more controllers, perception data collected by multiple perception sensors until the occurrence of an offset event is determined, requiring the vehicle to deviate from its original path. Upon determining the occurrence of the offset event, the method includes calculating a non-linear error component of the maximum permissible in-lane lateral offset with respect to the center of a host lane. The non-linear error component is calculated as a function of a target lane position error over a relevant time window.The method involves calculating the maximum permissible in-track lateral offset based on the host lane width, the vehicle width, the target lane position error, and a buffer distance. The maximum permissible in-track lateral offset is dynamically adjusted based on a non-linear error generated in real time as the vehicle deviates from the laterally offset path. The method includes comparing the maximum permissible in-track lateral offset with a mediated in-track lateral offset value, where the mediated in-track lateral offset value and the maximum permissible in-track lateral offset are both oriented in the same direction.The procedure includes, in response to a determination that the mediated in-track lateral offset value is greater than the maximum permissible in-track lateral offset, updating the vehicle's laterally offset path with the maximum permissible in-track lateral offset and applying a rate limiter to the maximum permissible in-track lateral offset in real time while instructing the vehicle to travel along the laterally offset path.

[0020] In another aspect, the procedure further includes, in response to a determination that the mediated in-track lateral offset value is equal to or less than the maximum permissible in-track lateral offset, updating the vehicle's laterally offset path with the mediated in-track lateral offset value and applying a rate limiter to the mediated in-track lateral offset value in real time while instructing the vehicle to travel along the laterally offset path.

[0021] In a further aspect, the procedure includes determining the target lane position error based on an effective value solution attempt.

[0022] In one aspect, the procedure includes determining the target lane position error based on a standard deviation solution attempt.

[0023] In another aspect, a path planning system is disclosed that calculates a laterally offset path based on a maximum permissible in-track lateral offset with respect to the center of a vehicle's host lane. The path planning system includes one or more controllers that receive perception data indicating an external environment surrounding the vehicle, collected by multiple perception sensors integrated into the vehicle. The controller(s) include one or more processors that execute instructions to monitor the perception data collected by the multiple perception sensors until an offset event is determined that necessitates the vehicle deviating from its original path.In response to a detection of the offset event, the one or more controllers calculate a non-linear error component of the maximum allowable in-track lateral offset with respect to the center of a host lane. This non-linear error component is calculated as a function of a target lane position error over a relevant time window. The one or more controllers calculate the maximum allowable in-track lateral offset based on the host lane width, the vehicle width, the target lane position error, and a buffer distance. The maximum allowable in-track lateral offset is dynamically adjusted based on a non-linear error generated in real time as the vehicle deviates from the laterally offset path.The one or more controllers compare the maximum allowable in-track lateral offset with a mediated in-track lateral offset value, where the mediated in-track lateral offset value and the maximum allowable in-track lateral offset are both oriented in the same direction. In response to a determination that the mediated in-track lateral offset value is greater than the maximum allowable in-track lateral offset, the one or more controllers update the vehicle's laterally offset path with the maximum allowable in-track lateral offset. The one or more controllers apply a rate limiter to the maximum allowable in-track lateral offset in real time while directing the vehicle to travel along the laterally offset path.The one or more controllers monitor the perception data collected by the multiple perception sensors, which indicate the external environment surrounding the vehicle, until the presence of a lateral obstacle located in an adjacent lane is detected. In response to the detection of a lateral obstacle, the one or more controllers determine that the vehicle is about to perform a lane change maneuver. During the lane change maneuver, the vehicle follows a laterally offset lane change path to move from the host lane to an adjacent lane, and the adjacent lane containing the lateral obstacle is contiguous with the neighboring lane.In response to a determination of the presence of a lateral obstacle and a determination that the vehicle is about to execute the lane change maneuver, the one or more controllers calculate an estimated lateral separation distance between the vehicle and the lateral obstacle based on an initial trajectory of the vehicle. The one or more controllers compare the estimated lateral separation distance to a lateral separation distance threshold measured between the vehicle and the lateral obstacle. In response to a determination that the estimated lateral separation distance is less than the lateral separation distance threshold, the one or more controllers calculate a target lane lateral offset error.One or more controllers compare the target lane lateral offset error with a threshold of the maximum allowable error value and, in response to a determination that the target lane lateral offset error is less than the threshold of the maximum allowable error value, calculate a lateral offset correction value, the lateral offset correction value maintaining the lateral separation distance threshold measured between the vehicle and the lateral obstacle while the vehicle follows the laterally offset lane change path.

[0024] Further areas of application will become apparent from the description provided here. It should be understood that the description and specific examples serve only for illustration and are not intended to limit the scope of this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described here serve only for illustration and are not intended to limit the scope of the present disclosure in any way; they show: Fig. 1 a schematic diagram of the disclosed path planning system for a vehicle, which includes one or more controllers in electronic communication with multiple perception sensors, according to an exemplary embodiment; Fig. 2 a schematic diagram of the vehicle, which is in Fig. 1 is shown and, in response to a detection of the presence of a moving obstacle affecting the host lane, travels along a host lane while following a laterally offset path, according to an exemplary embodiment; Fig. 3 a schematic diagram of the laterally offset path which is in Fig. 2 is shown, and an actual path of the vehicle according to an exemplary embodiment; Fig. 4 a schematic diagram of a planned target vehicle position and the actual lateral vehicle position according to an exemplary embodiment; Fig. 5 a process flow diagram illustrating a method for determining and executing the laterally offset path of the vehicle, according to an exemplary embodiment; Fig. 6 a schematic diagram of the vehicle performing a lane-change maneuver by following an initial path, wherein an emerging side threat is located in an adjacent lane, according to an exemplary embodiment; and Fig. 7 a schematic diagram of the vehicle, which is in Fig. 6 is shown and performs the lane-changing maneuver by following a laterally offset path, according to an exemplary embodiment. DETAILED DESCRIPTION

[0026] The following description is merely exemplary and is not intended to limit the present disclosure, application or uses.

[0027] With reference to Fig. Figure 1 illustrates a schematic diagram of a vehicle 10 incorporating the disclosed trajectory planning system 12. It should be acknowledged that the vehicle 10 can be, but is not limited to, any type of vehicle, such as a sedan, truck, SUV, van, or motorhome. It should also be acknowledged that the trajectory planning system 12 is part of an autonomous driving system. Specifically, the trajectory planning system 12 can be part of a fully autonomous driving system, such as an automated driving system (ADS), or alternatively, a semi-autonomous driving system, such as an advanced driver assistance system (ADAS). The trajectory planning system 12 includes one or more controllers 20 in electronic communication with multiple perception sensors 22 configured to collect perception data specifying an external environment 14 surrounding the vehicle 10.In the non-restrictive embodiment, the one in . Fig. As shown in Figure 1, the multiple perception sensors 22 include one or more in-vehicle cameras 30, an inertial measurement unit (IMU) 32, a global positioning system (GPS) 34, radar 36 and LiDAR 38; however, it should be acknowledged that different or additional sensors may also be used.

[0028] Fig. Figure 2 is a diagram of vehicle 10, which is in Fig. 1 is shown and travels along a lane 40. As in Fig. As can be seen in Figure 2, the carriageway 40 is divided into two lanes 42, with a moving obstacle 44 traveling in a right-hand or adjacent lane 42A, the vehicle 10 traveling in a left-hand or host lane 42B, and several lane boundaries 46 defining the lanes 42A and 42B. The dashed lines of the lane boundaries 46 indicate traversable markings, while solid lines of the lane boundaries 46A indicate non-traversable lane boundaries 46. Fig. Figure 2 illustrates a laterally offset path 50 of the vehicle 10, which was determined by the path planning system 12 ( Fig. 1), wherein the laterally offset track 50 uses as a basis a maximum permissible in-track lateral offset with respect to a center 52 of the host lane 42B, along which the vehicle 10 travels. The one or more controllers 20 of the track planning system 12 ( Fig. 1) Calculate the laterally offset path 50 in response to a determination of the occurrence of an offset event that requires the vehicle 10 to deviate from an original path. It should be noted that the maximum permissible in-lane lateral offset with respect to the center 52 of the host lane 42B is dynamically adjusted based on a non-linear error generated in real time when the vehicle 10 deviates from the laterally offset path 50. Specifically, the non-linear error represents the deviation between the laterally offset path 50 and an actual path 60 (which is defined in Fig. 3 shown) of vehicle 10.

[0029] Some examples of offset events that require vehicle 10 to deviate from its original path include, but are not limited to, a moving obstacle that shifts into an adjacent lane and affects host lane 42B, aggressive road curvature, a driver request, and a reaction to avoid oncoming traffic. Some examples of driver requests include, but are not limited to, a maneuver to avoid construction site objects such as buoys or barriers, creating an offset away from an obstacle, and avoiding potholes. In the example given in Fig. As shown in Figure 2, the offset event is the moving obstacle 44, which is another vehicle. Specifically, the moving obstacle 44 is a semi-trailer truck interfering with the host lane 42B along which the vehicle 10 is traveling. The host lane 42B is bounded by a non-crossable lane boundary 46C to the left of the vehicle 10, the non-crossable lane boundary 46C representing a limit to the lateral position of the vehicle 10 within the host lane 42B. It should be noted that the maximum permissible in-lane lateral offset compensates for overshoot introduced by control errors, while also maintaining a lateral position of the vehicle 10 within its host lane 42B as the vehicle 10 travels along the laterally offset lane 50.

[0030] As in Fig. As can be seen in Figure 2, the maximum permissible lateral offset within the track, determined by the track planning system 12, is limited by a buffer distance 56, the buffer distance 56 being measured between the non-traversable lane boundary 46C of the host track 42B and a satisfaction boundary 58 arranged along the host track 42B. The non-traversable lane boundary 46C is positioned along the side of the host track 42B opposite the location where the offset event occurs. The buffer distance 56 is arranged along the host track 42B and is dimensioned to ensure that the vehicle 10 does not operate along the non-traversable lane boundary 46C when the laterally offset track 50 is executed.Accordingly, the satisfaction limit 58 is positioned to ensure that the vehicle 10 does not operate along the non-crossable lane boundary 46C when the laterally offset lane 50 is executed. It should be noted that the maximum permissible lane-internal lateral offset ensures that the vehicle 10 maintains its lateral position within its host lane 42B of travel while operating within the satisfaction limit 58.

[0031] Referring to both Fig. 1 as well Fig. Section 2 will now describe how to determine the maximum permissible lateral offset within the lane. The one or more controllers 20 of the vehicle 10 can monitor the perception data that specifies the external environment 14 surrounding the vehicle 10 in order to detect the offset event. For example, as in Fig. As can be seen in Figure 2, the one or more controllers 20 determine that the moving obstacle 44 (the semi-trailer truck) is affecting the host lane 42B along which the vehicle 10 is traveling. In response to a determination of the offset event, the one or more controllers 20 of the vehicle 10 can then confirm that the autonomous driving features have been activated. The one or more controllers 20 of the path planning system 12 can then position the vehicle 10 in the host lane 42B of the journey to avoid contact with the lane boundaries 46 and the satisfaction limit 58, and to prevent overshoot introduced by the control error when the vehicle 10 travels along the laterally offset path 50.

[0032] The one or more controllers 20 can then calculate the maximum permissible in-track lateral offset. Specifically, the one or more controllers 20 can first calculate the non-linear error component of the maximum permissible in-track lateral offset, where the non-linear error component is a feedforward expression that compensates for the overshoot introduced by the control error. It should be noted that the non-linear error component is calculated as a function of a target lane position error over a relevant time window. The target lane position error is a moving average of an error between the laterally offset lane 50 and the actual lane 60 (which is in Fig. Figure 3 shows the vehicle 10 over the relevant time window, which is measured while the vehicle 10 travels along the laterally offset track 50. The relevant time window is a duration over which the data samples are collected. In many applications, the relevant time window can be in the range of approximately one to thirty seconds; however, the relevant time window can also be adjusted outside this range. For example, to make the path planning system 12 more responsive to a single impulse, the relevant time window is shortened.

[0033] It should be noted that the non-linear error component of the maximum permissible in-lane lateral offset can be calculated based on a multitude of different solution attempts. In a non-restrictive embodiment, the target lane position error is determined based on an RMS solution attempt. As in Fig. As can be seen in Figure 3, the actual track 60 of the vehicle 10 contains a sinusoidal profile. In the embodiment shown in Figure 3, the actual track 60 of the vehicle 10 has a sinusoidal profile. Fig. As shown in Figure 3, the target lane position error of the laterally offset path 50 is calculated based on the RMS solution method. It should be noted that the RMS solution method, in order to determine the target lane position error, takes into account the sinusoidal profile of the actual path 60 of the vehicle 10, since a moving average would yield virtually no error. Fig. Figure 3 illustrates a path error 62 of vehicle 10. As in Fig. As can be seen in Figure 3, the path error 62 shrinks as the vehicle 10 follows the laterally offset path 50, or is reduced in size because a pre-control compensation is applied to reduce overshoot.

[0034] The RMS solution attempt to determine the target lane position error is calculated based on Equation 1, which is structured as follows: TgtLane_Position_Error=∑Buffer 0Max Sample buffer sizeTgtErr2Max Sample Buffer Size, where TgtLane_Position_Error represents the target lane position error, Max Sample Buffer Size represents a maximum number of data samples allocated for the target lane position error, and TgtErr is the error between a planned target vehicle position 70 ( Fig. 4) and represents an actual lateral vehicle position 74.

[0035] In another embodiment, the one or more controllers 20 can calculate the target lane position error based on a standard deviation solution attempt. To determine the target lane position error, the standard deviation solution attempt is calculated based on Equation 2, which is as follows: TgtLanePositionError =∑Buffer 0Max sample buffer size(TgtErr−TgtErr_Mean)2Max Sample Buffer size where TgtErr_Mean is a cumulative average of the error between the planned target vehicle position 70 ( Fig. 4) and the actual lateral vehicle position 74 ( Fig. 4) represents.

[0036] When the one or more controllers 20 calculate the target lane position error, they can then calculate the maximum permissible in-lane lateral offset. The maximum permissible in-lane lateral offset uses a lane width of the host lane 42B along which the vehicle 10 travels, a width of the vehicle 10, the target lane position error, and the buffer distance 56 as a basis ( Fig. 2) In one embodiment, the maximum permissible track-internal lateral offset is determined on the basis of equation 3, which is formulated as follows: Max Allowed Lateral Offset=(Lane Width−Host vehicle width)2−TgtLane_Position_Error−Buffer, where Lane Width represents the lane width of the host lane 42B along which vehicle 10 travels, Host vehicle width represents the width of vehicle 10, and Buffer represents the buffer distance 56.

[0037] The one or more controllers 20 can then compare the maximum permissible in-track lateral offset with a mediated in-track lateral offset value, where the mediated in-track lateral offset value and the maximum permissible in-track lateral offset are both oriented in the same direction. The mediated in-track lateral offset value represents the current lateral offset value of the laterally offset track 50 of the vehicle 10. In response to a determination that the mediated in-track lateral offset value is greater than the maximum permissible in-track lateral offset, the one or more controllers 20 update the laterally offset track 50 of the vehicle 10 with the maximum permissible in-track lateral offset in the appropriate direction. Otherwise, the one or more controllers 20 update the laterally offset track 50 of the vehicle with the mediated in-track lateral offset value in the appropriate direction.

[0038] It should be noted that the one or more controllers 20 can apply a rate limiter to either the maximum permissible in-track lateral offset or the mediated in-track lateral offset value in real time, while instructing the vehicle 10 to travel along the laterally offset path 50 to reduce steering oscillations and the severity of path overshoot. The speed at which the rate limiter is applied uses the difference between the laterally offset path 50 and the actual path 60 (which is in Fig. Figure 3) of vehicle 10 serves as the basis. Specifically, as the difference between the laterally offset path 50 and the actual path 60 of vehicle 10 increases, the application of the rate limiter becomes slower. For example, when there is a relatively small difference between the laterally offset path 50 and the actual path 60 of vehicle 10, the rate limiter speed can be increased. In a non-restrictive embodiment, the one or more controllers 20 store a one-dimensional lookup table that specifies rate limiter values ​​based on the target lane position error.

[0039] Fig. Figure 5 is a process flow diagram illustrating a procedure 500 for executing the laterally offset path 50 of the vehicle 10. With reference to Fig. 1- Fig. 2 and Fig. 5. Procedure 500 can begin in decision block 502. In decision block 502, the one or more controllers 20 of the path planning system 12 continue monitoring the perception data collected by the multiple perception sensors 22 until the occurrence of the offset event is determined, which requires the vehicle to deviate from its original path. For example, as in Fig. As can be seen in Figure 2, one or more controllers 20 determine that the moving obstacle 44 (the semi-trailer truck) is interfering with the host lane 42B along which the vehicle 10 is traveling. The procedure 500 can then proceed to decision block 504.

[0040] In decision block 504, in response to a determination that the offset event has occurred, one or more controllers 20 of the vehicle 10 confirm that the autonomous driving features for the vehicle 10 have been activated. In response to a determination that the autonomous driving features have not been activated, procedure 500 can then terminate. Otherwise, procedure 500 can proceed to block 506.

[0041] In block 506, the one or more controllers 20 of the path planning system 12 position the vehicle 10 in the host lane 42B of the journey to avoid contact with the lane boundaries 46 and the satisfaction limit 58, and to prevent overshoot introduced by the control error while the vehicle 10 travels along the laterally offset path 50. The procedure 500 can then proceed to block 508.

[0042] In block 508, the one or more controllers 20 can first calculate the non-linear error component of the maximum permissible in-lane lateral offset. It should be noted that the non-linear error component is calculated as a function of a target lane position error over a relevant time window. As explained above, the target lane position error can be calculated based on a variety of different solution attempts. Procedure 500 can then proceed to block 510.

[0043] In block 510, the one or more controllers 20 calculate the maximum permissible in-lane lateral offset based on the lane width of the host lane 42B along which the vehicle 10 travels, the width of the vehicle 10, the target lane position error, and the buffer distance 56. Specifically, in one embodiment, the maximum permissible in-lane lateral offset is determined based on equation 3 above. The procedure 500 can then proceed to decision block 512.

[0044] In decision block 512, the one or more controllers 20 compare the maximum allowable in-track lateral offset with the mediated in-track lateral offset value. In response to a determination that the mediated in-track lateral offset value is greater than the maximum allowable in-track lateral offset, procedure 500 may proceed to block 514. In block 514, the one or more controllers 20 update the laterally offset path 50 of vehicle 10 with the maximum allowable in-track lateral offset determined in block 510, and procedure 500 may then proceed to block 516. In block 516, the one or more controllers 20 apply a rate limiter to the maximum lateral offset in real time while instructing vehicle 10 to travel along the laterally offset path 50. Procedure 500 may then terminate.

[0045] Returning to decision block 512, in response to a determination that the mediated in-track lateral offset value is equal to or less than the maximum allowable in-track lateral offset, procedure 500 can proceed to block 518. In block 518, the one or more controllers 20 update the laterally offset path 50 of the vehicle 10 with the mediated in-track lateral offset value, and procedure 500 can then proceed to block 520. In block 520, the one or more controllers 20 apply a rate limiter to the mediated in-track lateral offset value in real time while instructing the vehicle 10 to travel along the laterally offset path 50. Procedure 500 can then terminate.

[0046] Referring to both Fig. 1 as well Fig. In a further embodiment, the path planning system 12 receives at least one side separation distance threshold value K1 (which is in Fig. (as shown in Figure 7) between vehicle 10 and a lateral obstacle 144, while vehicle 10 performs a lane-change maneuver to move from the host lane 42B to an adjacent lane 42A. As shown in Fig. As can be seen in Figure 6, the lateral obstacle 144 is located in an adjacent lane 42C, which is positioned next to the neighboring lane 42A. The lateral obstacle 144 represents a moving object that can affect the neighboring lane 42A while the vehicle 10 is performing the lane-changing maneuver. Specifically, in the embodiment shown in Figure 6, the lateral obstacle 144 is located in an adjacent lane 42C, which is positioned next to the neighboring lane 42A. Fig. Figure 6 shows the lateral obstacle 144 as an automobile that is not centered along the center 52 of the host lane 42B; however, it should be acknowledged that other moving obstacles traveling along the adjacent lane 42C can also be used.

[0047] Fig. Figure 6 illustrates an original track 190 while vehicle 10 performs the track change maneuver, with the original track 190 skipping the side separation distance threshold K1. Fig. Figure 7 illustrates the original track 190 and a laterally offset lane-change track 150. Vehicle 10 follows the laterally offset lane-change track 150 while performing the lane-change maneuver to move from the host lane 42B to the adjacent lane 42A. As shown in Fig. As can be seen in Figure 7, the laterally offset lane change lane 150 incorporates the lateral separation distance threshold K1, which is measured between the vehicle 10 and the moving obstacle 144. The laterally offset lane change lane 50 is offset with respect to the center 52 of the adjacent lane 42A in order to maintain the lateral separation distance threshold K1.

[0048] It should be noted that the original path 190 of vehicle 10 does not account for an overshoot 186 oriented towards the lateral obstacle 144 located in the adjacent lane 42C, the overshoot 186 being caused by a cumulative destination lane lateral offset error. However, as ordered in Fig. As can be seen in Figure 7, the overshoot 186 affects the vehicle 10 during the execution of the lane-change maneuver in the immediate vicinity of the lateral obstacle 144. Therefore, in response to a determination that the vehicle 10 is performing a lane-change maneuver and the presence of the lateral obstacle 144 in the adjacent lane 42C, one or more controllers 20 of the path planning system 12 calculate the laterally offset lane-change path 150 (which is in Fig. 7 is shown), which compensates for the overshoot of 186.

[0049] With reference to Fig. 1, Fig. 6 and Fig. 7. The one or more controllers 20 of the vehicle 10 can monitor the perception data collected by the multiple perception sensors 22, which indicate the external environment 14 surrounding the vehicle 10, in order to detect the presence of the lateral obstacle 144. The one or more controllers 20 can then determine, based on any number of trials, that the vehicle 10 is about to perform a lane change maneuver. For example, in one embodiment, the one or more controllers 20 determine that the vehicle 10 is about to perform a lane change maneuver in response to a determination that a user has selected a lane change indicator.

[0050] In response to a determination of the presence of the lateral obstacle 144 based on the perception data, and in response to a determination that the vehicle 10 is about to perform the lane change maneuver, the one or more controllers 20 then calculate an estimated lateral separation distance between the vehicle 10 and the lateral obstacle 144 based on the vehicle 10's original path 190. The estimated lateral separation distance represents the magnitude of the difference between an estimated position 184 of the lateral obstacle 144 and an estimated target position 182 of the vehicle 10, which is shown as a phantom line (estimated lateral separation distance = abs (estimated position 184 - estimated target position 182)). The estimated target position 182 of the vehicle 10 uses driving along the vehicle 10's original path 190 as its basis.

[0051] The estimated position 184 of the lateral obstacle 144 represents a lateral position of an opposite edge 192 of the lateral obstacle 144, wherein the opposite edge 192 of the lateral obstacle 144 faces the vehicle 10. In the exemplary embodiment, as illustrated, the opposite edge 192 of the lateral obstacle 144 is oriented to the left. The estimated target position 182 of the vehicle 10 represents a lateral position of an opposite edge 194 of the vehicle 10, which faces the lateral obstacle 144. In the example, as shown in the figures, the opposite edge 194 is oriented to the right.

[0052] The one or more controllers 20 can then compare the estimated side separation distance with the side separation distance threshold K1, which is a calibratable value set to accommodate the 95th percentile of customers who are part of a bell curve distribution. In response to a determination that the estimated side separation distance is less than the side separation distance threshold K1, the one or more controllers 20 can then calculate a target lane side offset error. The target lane side offset error is a moving average of an error between the side-offset lane change path 150 and an actual path of the vehicle 10 over a time window, the time window being measured while the vehicle 10 is performing the lane change maneuver. It should be noted that the target lane side offset error is based on a variety of different solution attempts, such as...can be calculated using the effective value solution attempt or the standard deviation solution attempt.

[0053] The one or more controllers 20 can then compare the target lane lateral offset error with a threshold of the maximum permissible error value K2, which is a calibratable value determined on the basis of real test data. In one embodiment, the one or more controllers 20 store a lookup table containing maximum permissible error thresholds based on real test data.

[0054] In response to a determination that the target lane lateral offset error is less than the threshold of the maximum permissible error value K2, the one or more controllers 20 can then calculate a lateral offset correction value that compensates for the overshoot 186 that occurs in the original path 190 of the vehicle 10, where the lateral offset correction value is the lateral separation distance threshold K1 (see in Fig. 7), which is measured between the vehicle 10 and the lateral obstacle 144, while the vehicle 10 follows the laterally offset lane change path 150. In one embodiment, the lateral offset correction value is the amount of the difference between the estimated lateral separation distance and the lateral separation distance threshold value K1 (lateral offset correction = abs (estimated lateral separation distance - lateral separation distance threshold value K1)).

[0055] With reference to the figures in general, the disclosed path planning system provides various technical effects and benefits. Specifically, the disclosed path planning system provides a solution for dynamically adjusting the maximum permissible in-track lateral offset for the laterally offset path based on a non-linear error, wherein the non-linear error is generated in real time when the vehicle deviates from the laterally offset path. It should also be noted that the path planning system takes into account defined limits while determining the laterally offset path. Furthermore, the path planning system can also be used to maintain a lateral separation distance threshold between the vehicle and a lateral obstacle when the vehicle performs a lane-change maneuver to switch from the host lane to an adjacent lane.

[0056] The modules can refer to or be part of an electronic circuit, a combinational logic circuit, a field-programmable gate array (FPGA), a processor (shared, dedicated, or grouped) that executes code, or a combination of some or all of the above, such as in a system on a chip. Additionally, the modules can be microprocessor-based, such as a computer that has at least one processor, main memory (RAM and / or ROM), and associated input and output buses. The processor can operate under the control of an operating system residing in memory. The operating system can manage computer resources such that computer program code, embodied as one or more computer software applications, such as an application residing in main memory, can instruct the processor to execute instructions.In an alternative embodiment, the processor can execute the application directly, in which case the operating system can be omitted.

[0057] The description of the present revelation is merely exemplary, and it is intended that variations that do not deviate from the main content of the present revelation remain within its scope. Such variations should not be considered a deviation from the idea and scope of the present revelation. legend

[0058] In the drawing figures, N stands for no and Y for yes.

Claims

[1] A path planning system that calculates a laterally offset path based on a maximum permissible in-track lateral offset with respect to the center of a host lane of a vehicle, wherein the path planning system comprises: one or more controllers that receive perception data indicating an external environment surrounding the vehicle, collected by multiple perception sensors that are part of the vehicle, wherein the one or more controllers contain one or more processors that execute instructions to: Monitoring the perception data collected by the multiple perception sensors until the occurrence of a displacement event is determined, which requires the vehicle to deviate from an original path; In response to a determination of the occurrence of the offset event, a non-linear error component of the maximum permissible in-lane lateral offset with respect to the center of a host lane is calculated, wherein the non-linear error component is calculated as a function of a target lane position error over a relevant time window; Calculating the maximum permissible in-track lateral offset based on a track width of the host lane, a vehicle width, the target lane position error, and a buffer distance, wherein the maximum permissible in-track lateral offset is dynamically adjusted based on a non-linear error generated in real time as the vehicle deviates from the laterally offset path; Comparing the maximum permissible in-track lateral offset with an average in-track lateral offset value, wherein the average in-track lateral offset value and the maximum permissible in-track lateral offset are both oriented in the same direction; In response to a determination that the mediated in-track lateral offset value is greater than the maximum permissible in-track lateral offset, update the laterally offset path of the vehicle with the maximum permissible in-track lateral offset; and Applying a rate limiter to the maximum permissible in-lane lateral offset in real time while instructing the vehicle to travel along the laterally offset path. [2] Path planning system according to claim 1, wherein the one or more controllers execute commands to: In response to a determination that the mediated in-track lateral offset value is equal to or less than the maximum permissible in-track lateral offset, update the laterally offset path of the vehicle with the mediated in-track lateral offset value; and Applying a rate limiter to the mediated in-lane lateral offset value in real time while instructing the vehicle to travel along the laterally offset path. [3] Railway planning system according to claim 1, wherein the target lane position error is determined on the basis of an effective value solution attempt. [4] Track planning system according to claim 3, wherein the target track position error is determined by the following: TgtLane_Position_Error=∑Buffer 0Max Sample buffer sizeTgtErr2Max Sample Buffer Size, where TgtLane_Position_Error represents the target lane position error, Max Sample Buffer Size represents a maximum number of allocated data samples, and TgtErr represents an error between a planned target vehicle position and an actual lateral vehicle position. [5] Railway planning system according to claim 1, wherein the target lane position error is determined on the basis of a standard deviation solution attempt. [6] Track planning system according to claim 5, wherein the target track position error is determined by the following: TgtLane_Position_Error=∑Buffer 0Max sample buffer size(TgtErr−TgtErr_Mean)2Max Sample Buffer size, where TgtLane_Position_Error represents the target lane position error, Max Sample Buffer Size represents a maximum number of allocated data samples, and TgtErr_Mean represents a cumulative average error between a planned target vehicle position and an actual lateral vehicle position. [7] Path planning system according to claim 1, wherein the buffer distance between a lane boundary of the host lane and a satisfaction boundary arranged along the host lane is measured and the lane boundary is positioned along a side of the host lane opposite the location of the occurrence of the offset event. [8] Track planning system according to claim 1, wherein the maximum permissible track-internal lateral offset is determined on the basis of the following: Max Allowed Lateral Offset=(Lane Width−Host vehicle width)2−TgtLane_Position_Error−Buffer, where TgtLane_Position_Error represents the target lane position error, Lane Width represents the lane width of the host lane, Host vehicle width represents the width of the vehicle, and Buffer represents the buffer distance. [9] Path planning system according to claim 1, wherein the mediated track-internal lateral offset value represents a current transverse offset value of the laterally offset path of the vehicle. [10] Lane planning system according to claim 1, wherein the offset event is one of the following: a moving obstacle moving in an adjacent lane and affecting the host lane, aggressive road curvature, a driver request, and a reaction to avoid oncoming traffic.

Images