Collision avoidance steering control strategy for autonomous driving

Abstract

The present application relates generally to an evasive steering control strategy for autonomous driving. A vehicle includes a system for operating the vehicle. The system includes a perception sensor and a processor. The perception sensor is configured to detect a remote object in a road segment. The processor is configured to determine a repulsive potential associated with the remote object, determine an attractive potential based on an estimated position of a lane marker, determine a trajectory of the vehicle based on the repulsive potential and the attractive potential, create a cost function for the vehicle based on the trajectory and at least one candidate steering command, perform an optimization process on the cost function to determine an optimal steering command for the vehicle from the at least one candidate steering command, and control movement of the vehicle along the road segment using the optimal steering command.

Description

Technical Field

[0001] This subject matter relates to vehicles, and more specifically, to systems and methods for controlling the trajectory of a vehicle in the absence of information about lane markings on the road in which it is traveling. Background Technology

[0002] Autonomous vehicles include perception sensors that provide information that can be used to plan a trajectory for the vehicle and move along that trajectory. For example, radar sensors can provide spatial information about remote objects, such as remote vehicles and pedestrians. Digital cameras can provide information about lane markings, etc. Therefore, it is desirable to provide a system and method for planning trajectories that can be used when lane marking information is unavailable. Summary of the Invention

[0003] In one exemplary embodiment, a method for operating a vehicle is disclosed. A remote object is detected in a road segment. A repulsive potential associated with the remote object is determined. An attractor potential is determined based on the estimated position of lane markings. The trajectory of the vehicle is determined based on the repulsive and attractor potentials. A cost function is created for the vehicle based on the trajectory and at least one candidate steering command. An optimization process is performed on the cost function to determine an optimal steering command for the vehicle based on the at least one candidate steering command. The optimal steering command is used to control the movement of the vehicle along the road segment.

[0004] In addition to one or more features described herein, the method also includes determining the repulsive potential based on the reciprocal of the distance between the vehicle and the remote object.

[0005] In addition to one or more features described herein, the method also includes defining a radius of consciousness and determining the repulsive potential as one of the following: proportional to the reciprocal of the distance between the vehicle and the remote object when the distance between them is less than or equal to the radius of consciousness, and zero when the distance is greater than the radius of consciousness.

[0006] In addition to one or more features described herein, the method also includes using the estimated lateral distance between the vehicle and the lane markings to determine the attractor potential.

[0007] In addition to one or more features described herein, the method also includes determining the estimated location of the lane markings by performing a Galilean transformation on the vehicle's current position using the vehicle's longitudinal velocity and the vehicle's lateral velocity at the vehicle's current position.

[0008] In addition to one or more features described herein, the method also includes creating the cost function when either a camera malfunction occurs at the vehicle or the road segment lacks lane markings.

[0009] In addition to one or more features described herein, controlling the movement of a vehicle also includes controlling the lateral movement of the vehicle.

[0010] In another exemplary embodiment, a system for operating a vehicle is disclosed. The system includes a sensing sensor and a processor. The sensing sensor is configured to detect a remote object in a road segment. The processor is configured to determine a repulsive potential associated with the remote object, determine an attractor potential based on an estimated position of lane markings, determine a trajectory of the vehicle based on the repulsive and attractor potentials, create a cost function for the vehicle based on the trajectory and at least one candidate steering command, perform an optimization process on the cost function to determine an optimal steering command for the vehicle from the at least one candidate steering command, and control the movement of the vehicle along the road segment using the optimal steering command.

[0011] In addition to one or more features described herein, the processor is also configured to determine the repulsive potential based on the reciprocal of the distance between the vehicle and the remote object.

[0012] In addition to one or more features described herein, the processor is also configured to define a consciousness radius and determine the repulsive potential as one of the following: proportional to the reciprocal of the distance between the vehicle and the remote object when the distance between them is less than or equal to the consciousness radius, and zero when the distance is greater than the consciousness radius.

[0013] In addition to one or more features described herein, the processor is also configured to determine the attractor potential using the estimated lateral distance between the vehicle and the lane markings.

[0014] In addition to one or more features described herein, the processor is also configured to determine the estimated location of the lane markings by performing a Galilean transformation on the vehicle's current position using the vehicle's longitudinal velocity and the vehicle's lateral velocity at the vehicle's current position.

[0015] In addition to one or more features described herein, the processor is also configured to create a cost function when a camera failure occurs at the vehicle and there is no failure in the lane markings of the road segment.

[0016] In addition to one or more features described herein, controlling the movement of a vehicle also includes controlling the lateral movement of the vehicle.

[0017] In yet another exemplary embodiment, a vehicle is disclosed. The vehicle includes a sensing sensor, an actuator, and a processor. The sensing sensor is configured to detect a remote object in a road segment. The actuator controls the movement of the vehicle. The processor is configured to determine a repulsive potential associated with the remote object, determine an attractor potential based on an estimated position of lane markings, determine a trajectory of the vehicle based on the repulsive and attractor potentials, create a cost function for the vehicle based on the trajectory and at least one candidate steering command, perform an optimization process on the cost function to determine an optimal steering command for the vehicle from the at least one candidate steering command, and send the optimal steering command to the actuator to control the movement of the vehicle along the road segment.

[0018] In addition to one or more features described herein, the processor is also configured to determine the repulsive potential based on the reciprocal of the distance between the vehicle and the remote object.

[0019] In addition to one or more features described herein, the processor is configured to define a consciousness radius and determine the repulsive potential as one of the following: proportional to the reciprocal of the consciousness radius when the distance between the vehicle and the remote object is less than or equal to the consciousness radius, and zero when the distance is greater than the consciousness radius.

[0020] In addition to one or more features described herein, the processor is also configured to determine the attractor potential using the estimated lateral distance between the vehicle and the lane markings.

[0021] In addition to one or more features described herein, the processor is also configured to determine the estimated location of the lane markings by performing a Galilean transformation on the vehicle's current position using the vehicle's longitudinal velocity and the vehicle's lateral velocity at the vehicle's current position.

[0022] In addition to one or more features described herein, the processor is also configured to create a cost function when a camera failure occurs at the vehicle and there is no failure in the lane markings of the road segment.

[0023] The above-described features and advantages, as well as other features and advantages, of this disclosure will become apparent when taken in conjunction with the accompanying drawings and the following detailed description. Attached Figure Description

[0024] Other features, advantages, and details appear only as examples in the following detailed description, which is described in detail with reference to the accompanying drawings, in which:

[0025] Figure 1 An autonomous vehicle with a trajectory planning system according to an exemplary embodiment is shown;

[0026] Figure 2 A top view of a road segment in an illustrative embodiment is shown;

[0027] Figure 3A top view of a road segment without lane markings or center lines is shown;

[0028] Figure 4 A top view of the road segment is shown, with remote objects marked for trajectory planning purposes;

[0029] Figure 5 A top view of a road segment with a trajectory generated using the method disclosed herein is shown;

[0030] Figure 6 A block diagram depicting the operation of an advanced driver assistance system (ADAS) in the absence of lane marking data and centerline data in an illustrative embodiment is shown.

[0031] Figure 7 Exemplary scenarios depicting various remote vehicles associated with the master vehicle are shown;

[0032] Figure 8 This is a top view of the main vehicle and illustrates a method for estimating the location of lane markings using the methods disclosed herein; and

[0033] Figure 9 This is a top view of the road segment, showing various attractor potentials based on the generated lane marking locations. Detailed Implementation

[0034] The following description is exemplary in nature only and is not intended to limit this disclosure, its application, or use. It should be understood that throughout the drawings, corresponding reference numerals denote the same or corresponding parts and features.

[0035] According to an exemplary embodiment, Figure 1 An autonomous vehicle 10 with a trajectory planning system 100 is shown. Typically, the trajectory planning system 100 determines a trajectory for autonomous driving of the autonomous vehicle 10. The autonomous vehicle 10 typically includes a chassis 12, a body 14, front wheels 16, and rear wheels 18. The body 14 is mounted on the chassis 12 and substantially surrounds the components of the autonomous vehicle 10. The body 14 and the chassis 12 may together form a frame. The front wheels 16 and the rear wheels 18 are each rotatably connected to the chassis 12 near a corresponding corner of the body 14.

[0036] In various embodiments, trajectory planning system 100 is incorporated into autonomous vehicle 10. Autonomous vehicle 10 is, for example, a vehicle automatically controlled to transport passengers from one location to another. Autonomous vehicle 10 is depicted as a passenger car in the illustrated embodiment, but it should be understood that any other vehicle, including motorcycles, trucks, SUVs, RVs, etc., may also be used. At various levels, autonomous vehicle can assist the driver in a variety of ways, such as warning signals indicating impending risk situations, indicators enhancing the driver's situational awareness by predicting the movement of other agents that could potentially cause a collision. Autonomous vehicle 10 has different levels of intervention or control over the vehicle, ranging from coupled assisted vehicle control to complete control of all vehicle functions. In exemplary embodiments, autonomous vehicle 10 is a so-called Level 4 or Level 5 automation system. Level 4 system indicates "high automation," referring to the driving mode-specific performance of the automated driving system for all aspects of a dynamic driving task, even if the human driver does not respond appropriately to intervention requests. Level 5 system indicates "full automation," referring to the full-time performance of the automated driving system for all aspects of a dynamic driving task under all road and environmental conditions that can be managed by a human driver.

[0037] As shown, the autonomous vehicle 10 typically includes a propulsion system 20, a transmission system 22, a steering system 24, a braking system 26, a sensor system 28, an actuator system 30, and a controller 34. In various embodiments, the propulsion system 20 may include an internal combustion engine, an electric motor such as a traction motor, and / or a fuel cell propulsion system. The transmission system 22 is configured to transmit power from the propulsion system 20 to the front wheels 16 and the rear wheels 18 according to a selectable speed ratio. According to various embodiments, the transmission system 22 may include a stepped automatic transmission, a continuously variable transmission (CVT), or other suitable transmission. The braking system 26 is configured to provide braking torque to the front wheels 16 and the rear wheels 18. In various embodiments, the braking system 26 may include friction brakes, brake-by-wire brakes, regenerative braking systems (such as electric motors), and / or other suitable braking systems. The steering system 24 influences the position of the front wheels 16 and the rear wheels 18.

[0038] Sensor system 28 includes one or more sensing devices 40a-40n that sense observable conditions of the external and / or internal environment of autonomous vehicle 10. Sensing devices 40a-40n may include, but are not limited to, radar, lidar, global positioning system, optical camera, thermal camera, ultrasonic sensor, and / or other sensors. Sensing devices 40a-40n acquire measurements or data related to various objects or agents 50 within the vehicle environment. Such agents 50 may be, but are not limited to, other vehicles, pedestrians, bicycles, motorcycles, etc., as well as non-moving objects. Sensing devices 40a-40n may also acquire traffic data, such as information about traffic signals and signs.

[0039] The actuator system 30 includes one or more actuator devices 42a-42n that control one or more vehicle features, such as, but not limited to, the propulsion system 20, the transmission system 22, the steering system 24, and the braking system 26. In various embodiments, vehicle features may also include interior and / or exterior vehicle features, such as, but not limited to, doors, trunk, and cabin features, such as ventilation, music, lighting, etc. (not numbered).

[0040] The controller 34 includes a processor 44 and a computer-readable storage device or medium 46. The processor 44 may be any custom or commercially available processor, central processing unit (CPU), graphics processing unit (GPU), auxiliary processor among several processors associated with the controller 34, semiconductor-based microprocessor (in the form of a microchip or chipset), macroprocessor, any combination thereof, or any device typically used for executing instructions. The computer-readable storage device or medium 46 may include volatile and non-volatile storage, such as read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM). KAM is persistent or non-volatile memory that can be used to store various operational variables when the processor 44 is powered off. The computer-readable storage device or medium 46 may be implemented using any of many known memory devices, such as PROM (programmable read-only memory), EPROM (electrical PROM), EEPROM (electrically erasable PROM), flash memory, or any other electrical, magnetic, optical, or combined memory device capable of storing data, some of which represents executable instructions used by the controller 34 in controlling the autonomous vehicle 10.

[0041] The instructions may include one or more separate programs, each comprising an ordered list of executable instructions for implementing logical functions. When executed by processor 44, the instructions receive and process signals from sensor system 28, execute logic, calculations, methods, and / or algorithms for automatically controlling components of autonomous vehicle 10, and generate control signals to actuator system 30 based on the logic, calculations, methods, and / or algorithms to automatically control components of autonomous vehicle 10. The instructions may also execute logic, calculations, methods, and / or algorithms for placing an artificial potential field around a remote object using methods disclosed herein, planning a vehicle trajectory based on the artificial potential field, and moving the vehicle along the trajectory.

[0042] Figure 2A top view 200 of road segment 202 in an illustrative embodiment is shown. Road segment 202 includes a carriageway 204 defined by a first road boundary 206 and a second road boundary 208 along the outer edges of the road segment. The first road boundary 206 and the second road boundary 208 may be physical edges or solid lines indicating the sides of the carriageway 204. A centerline 210 divides the carriageway 204 into two-way traffic. For traffic moving in a first direction, lane markings 212 divide traffic into a first lane 214 and a second lane 216. A single lane (i.e., a third lane 218) exists for traffic moving in a second direction opposite to the first direction.

[0043] The primary vehicle 220 is located in the first lane 214. The first remote vehicle 222 is located in the second lane 216 and moves in the same direction as the primary vehicle 220. The second remote vehicle 224 is located in the third lane 218 and moves in the opposite direction to the primary vehicle 220. The third remote vehicle 226 is located in front of the primary vehicle 220 in the first lane 214 and moves in the same direction as the primary vehicle. The trajectory 228 of the primary vehicle 220 is also shown, based on knowledge of remote objects, lane markings, center lines, etc.

[0044] It should be understood that road segment 202, including lane configuration and vehicle positions within lanes, is shown for illustrative purposes only. The methods disclosed herein are applicable to road segments with different configurations, numbers of vehicles, and vehicle positions.

[0045] Figure 3 A top view 300 of road segment 202 without lane markings or a center line is shown. For various reasons, the sensors at the main vehicle 220 cannot detect the center line 210 and lane markings 212 of road segment 202. The first road boundary 206, the second road boundary 208, the first remote vehicle 222, the second remote vehicle 224, and the third remote vehicle 226 are still detected.

[0046] Figure 4 A top view 400 of road segment 202 is shown, which has remote objects marked for trajectory planning purposes. Remote objects that the primary vehicle wants to avoid are marked as repulsion objects (e.g., R1, R2, R3), while locations where the primary vehicle wants to stop nearby are marked as attraction objects (e.g., A1). A first remote vehicle 222 is marked as a first repulsion object (R1). A second remote vehicle 224 is marked as a second repulsion object (R2). A third remote vehicle 226 is marked as a third repulsion object (R3). A first road boundary 206 is marked as a fourth repulsion object (R4), and a second road boundary 208 is marked as a fifth repulsion object (R5). A single attraction object A1 is shown based on the estimated lane marking positions.

[0047] Figure 5 A top view 500 of a road segment 202 with a trajectory generated using the method disclosed herein is shown. To plan the trajectory of the master vehicle 220, repulsion radii are modeled using artificial potentials that exert repulsive forces on the master vehicle, and attraction radii are modeled using artificial potentials that exert attractive forces on the master vehicle. As an example, potential lines 502, 504, 506, and 508 surround a first repulsion radii (R1). The repulsive force associated with each potential line decreases with radial distance from the first repulsion radii (R1). The attractive force of the attraction radii increases quadratically with distance from the attraction radii. A trajectory is planned that avoids the individual repulsion radii and remains near the attraction radii. The trajectory is calculated based on the position and intensity of the potential lines.

[0048] Figure 6 A block diagram 600 is shown illustrating the operation of an Advanced Driver Assistance System (ADAS) in the absence of lane marking data and centerline data in an illustrative embodiment. The system includes a perception system 602, a field generator 604, and a model prediction controller 606. The perception system 602 may include radar, lidar, GPS, IMU, and / or other perception systems, providing information about the relationship between the primary vehicle and various objects within its environment. The perception system 602 does not provide data about lane markings or road markings. This lack of lane marking information may be due to the loss or malfunction of cameras or optical sensors, or due to driving on road sections without these markings.

[0049] Field generator 604 generates artificial potential fields (e.g., ...) associated with various objects in the environment (such as remote vehicles, pedestrians, cyclists, guardrails, etc.). Figure 5(Sch shown). A potential field is provided to the model predictive controller 606. The model predictive controller 606 uses the potential field to define the vehicle's trajectory. Repulsive and attractor potentials can be combined to form the total potential of the road segment, and the trajectory can be generated along the minimum or maximum potential of the total potential. The model predictive controller 606 uses a plant model 608 for the vehicle, various adaptive weights 610 for the potential, and steering and steering constraints 612 to determine the steering trajectory. The model predictive controller 606 creates a cost function based on the trajectory and candidate steering commands provided from the steering system. For example, candidate steering commands can be steering wheel angles, but can also include acceleration and deceleration terms. Candidate steering commands are used to estimate the predicted steering path at the vehicle's future position. The cost function can be calculated by determining the attractive and repulsive forces on the vehicle at the future position. The cost function can be calculated for multiple candidate steering commands. The model predictive controller 606 performs an optimization procedure on the cost function to determine the optimal steering command that moves the master vehicle along the trajectory. The optimal steering command is associated with the minimum cost selected from the optimization procedure. The model predictive controller 606 can provide optimal steering commands to various actuators of the vehicle (i.e., actuator devices 42a-42n) to move the master vehicle along a trajectory. Moving the master vehicle along the trajectory may include controlling the lateral movement of the master vehicle.

[0050] The model predictive controller 606 generates a cost function that is the sum of the errors between the repulsive and attractive fields at the predicted future location. As an example, Figure 5 The cost function for the illustrative scenario shown is illustrated in equation (1):

[0051]

[0052] The first three terms in the summation represent the repulsive potential fields of the first remote vehicle 222, the second remote vehicle 224, and the third remote vehicle 226, respectively. The fourth term in the summation is the actuator potential field. The fifth term relates to the change in steering angle over the discrete time step. The sixth term describes the difference between the candidate steering wheel angle and the reference steering wheel angle. The summation is performed over p time steps, where p is the prediction range of the model predictive controller 606.

[0053] Refer to the first item ( c1 is the detection confidence coefficient, w1 is a weight term scaled based on historical data, and It is the main vehicle (i.e., the lateral coordinate y of the main vehicle). k The distance potential between the first remote vehicle 222 (i.e., the first repulsor R1) and the first remote vehicle 222. The second and third terms are similar to the first term.

[0054] Figure 7An exemplary scenario 700 depicting various remote vehicles associated with the main vehicle 220 is shown. Circle 702 defines the radius of consciousness r. R The first object 704 is outside circle 702, and the second object 706 is inside circle. The distance potential ∈ for any remote object is given by equation (2):

[0055]

[0056] Where d is the Euclidean distance between the primary vehicle and the remote vehicle, and r R It is the radius of consciousness, k R It is the repulsion constant. The Euclidean distance d is given by equation (3):

[0057]

[0058] Where a i These are the position coordinates of the main vehicle, b i These are the position coordinates of the remote object. The potential is zero when the distance *d* is greater than or equal to the radius of consciousness. When the distance is less than the radius of consciousness *r*... R Time, the reciprocal of the Euclidean distance (1 / d) and the reciprocal of the radius of consciousness (1 / r) R The difference is proportional. Therefore, for the first object 704, the potential is zero, and for the second object 706, the potential is k. R (1 / d-1 / r R ).

[0059] Furthermore, in the cost function of equation (1), the fourth term This includes the detection confidence coefficient c4, the weight term w4 scaled based on historical data, and the distance potential based on the estimated lateral distance between the main vehicle and the lane markings. As shown in equation (4):

[0060] ∈=k A (yA) 2 Equation (4)

[0061] Where k A y is the attraction constant, y is the lateral coordinate of the vehicle, and A is the lateral coordinate of the attractor.

[0062] Figure 8This is a top view 800 of the main vehicle 220, and illustrates a method for estimating the position of lane markings using the method disclosed herein. Top view 800 shows a path 802 traveled by the main vehicle 220 over N time steps. The main vehicle 220 is at the current position {0} at the current time step t. The Nth position {N} indicates the position where reliable information about the lane markings was last received. For example, this could be the position where the relevant sensing sensor malfunctioned. The method uses a series of Galilean transformations through intermediate positions (i.e., {1}, {2}, ...) to determine the calculated position (position {N}) of the lane markings at time tN. The velocity transformation from the vehicle's body-centered reference frame to the road segment's reference frame is shown in equations (5)-(7):

[0063]

[0064] Where V x It is the longitudinal velocity of the vehicle centered on the vehicle body, V y ψ is the lateral velocity of the vehicle centered on the vehicle body, ψ is the yaw angle of the vehicle, and x gbl and y gbl These are the global coordinates of the vehicle in the coordinate system at the initial step size.

[0065] For the vehicle's speed (i.e., longitudinal speed V) in the last N time steps x and lateral velocity V y The coordinates of the vehicle's center of gravity (CG) are stored in memory by the main vehicle and used for the Galilean transformation. Over time, the longitudinal and lateral coordinates of the vehicle at time tN can be determined by applying the Galilean transformation through each of the positions ({0}, {1}, {2}, …{N}). The coordinates of the vehicle's center of gravity (CG) resulting from the Galilean transformation are shown in equations (8) and (9):

[0066]

[0067] Where x CG and y CG It is the position of the vehicle's center of gravity, V x,t V represents the distance t from the walking distance. x , and V y,t V represents the distance t from the walking distance. y Where t ranges from 0 to Δt. Terms within the triangular term. Calculate the cumulative sum of the changes in heading over time. Once the position (x) at tN is determined by the Galilean transformation... CG ,y CGThis position can then be compared with the last known position received at time tN to determine the estimated position 804 of the lane marking at time tN. The estimated position 804 can then be used to generate the attraction field 806.

[0068] Figure 9 This is a top view 900 of road segment 202, which shows various attractor potentials 902a-902h based on the generated lane marking positions.

[0069] Returning to equation (1), the steering wheel angle u is used as the input to the cost function. The steering wheel angle at time step k is given as u. k It is subject to various constraints, as shown in equations (10)-(11):

[0070]

[0071] The terms “a” and “an” do not indicate a limitation of quantity, but rather that at least one of the referenced items is present. Unless the context clearly indicates otherwise, the term “or” means “and / or”. Throughout the specification, the reference to “aspect” means that a particular element described in connection with that aspect (e.g., a feature, structure, step, or characteristic) is included in at least one aspect described herein and may or may not be present in other aspects. Furthermore, it should be understood that the described elements may be combined in any suitable manner in the aspects.

[0072] When an element, such as a layer, film, region, or substrate, is referred to as being “on” another element, it can be directly on the other element, or there may be intermediate elements present. Conversely, when an element is referred to as being “directly” on another element, there are no intermediate elements present.

[0073] Unless otherwise stated herein, all test standards are the most recent standards in force up to the date of filing of this application, or, if priority is claimed, the date of filing of the earliest priority application in which a test standard appears.

[0074] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0075] While the foregoing disclosure has been described with reference to exemplary embodiments, those skilled in the art will understand that various changes can be made and elements can be substituted with equivalents without departing from its scope. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of this disclosure without departing from the basic scope of this disclosure. Therefore, it is intended that this disclosure be limited to the specific embodiments disclosed, but will include all embodiments falling within its scope.

Claims

1. A method of operating a vehicle, comprising: Detect remote objects within the road segment; Determine the repulsive potential associated with the remote object; The attractor potential is determined based on the estimated position of the lane markings; The trajectory of the vehicle is determined based on the repulsive potential and the attractor potential; A cost function is created for the vehicle based on the trajectory and at least one candidate steering command; An optimization process is performed on the cost function to determine the optimal steering command for the vehicle based on the at least one candidate steering command; and The optimal steering command is used to control the movement of the vehicle along the road segment.

2. The method of claim 1, further comprising defining a radius of consciousness and determining the repulsive potential as one of: (i) proportional to the reciprocal of the distance when the distance between the vehicle and the remote object is less than or equal to the radius of consciousness; and (ii) zero when the distance is greater than the radius of consciousness.

3. The method of claim 1, further comprising using the estimated lateral distance between the vehicle and the lane marking to determine the attractor potential.

4. The method of claim 1, further comprising determining the estimated position of the lane marking by performing a Galilean transformation on the current position of the vehicle using the longitudinal velocity of the vehicle and the lateral velocity of the vehicle at the current position of the vehicle.

5. The method of claim 1, further comprising creating the cost function when one of the following occurs: (i) a camera malfunction occurs at the vehicle; and (ii) there are no lane markings on the road segment.

6. A system for operating a vehicle, comprising: A sensing sensor configured to detect remote objects in the road segment; The processor is configured as follows: Determine the repulsive potential associated with the remote object; The attractor potential is determined based on the estimated position of the lane markings; The trajectory of the vehicle is determined based on the repulsive potential and the attractor potential; A cost function is created for the vehicle based on the trajectory and at least one candidate steering command; An optimization process is performed on the cost function to determine the optimal steering command for the vehicle based on the at least one candidate steering command; and The optimal steering command is used to control the movement of the vehicle along the road segment.

7. The system of claim 6, wherein the processor is further configured to define a radius of consciousness and determine the repulsive potential as one of: (i) proportional to the reciprocal of the distance when the distance between the vehicle and the remote object is less than or equal to the radius of consciousness; and (ii) zero when the distance is greater than the radius of consciousness.

8. The system of claim 6, wherein the processor is further configured to determine the attractor potential using the estimated lateral distance between the vehicle and the lane marking.

9. The system of claim 6, wherein the processor is further configured to determine the estimated position of the lane marking by performing a Galilean transformation on the current position of the vehicle using the longitudinal velocity of the vehicle and the lateral velocity of the vehicle at the current position of the vehicle.

10. The system of claim 6, wherein the processor is further configured to create the cost function when one of the following occurs: (i) a camera failure occurs at the vehicle; and (ii) there are no lane markings on the road segment.

Images