Vehicle driving assistance systems

Abstract

To provide a driving support system of a vehicle which can improve reproducibility when a driving operation or the like is reproduced and the vehicle is traveled by automatic driving on the basis of recorded travel data of the driving operation or the like by a driver.SOLUTION: A system is a driving support system 1 of a vehicle Ve which can perform manual driving travel and automatic driving travel. The driving support system includes: a storage section 12 which records content and amount of driving operations by a driver and a travel track of the vehicle during the manual driving travel on a prescribed path; and target travel behavior generation sections 14, 15 which generate control amount to be a target for allowing the automatic driving travel on the basis of the travel track so that the manual driving travel is reproduced and the vehicle is traveled when the vehicle is traveled on the prescribed path by the automatic driving travel on the basis of the driving operations and the travel track recorded in the storage section 12 and generate content and amount of operations of an operation device for braking, driving and steering the vehicle on the basis of the content and amount of the driving operations.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a vehicle driving assistance system that uses communication technology, and more particularly to a vehicle driving assistance system that allows a vehicle to drive automatically based on information related to past vehicle driving. [Background technology]

[0002] Patent Document 1 discloses a vehicle control device that includes a recording unit capable of recording multiple pieces of driving data related to vehicle operation, including steering, accelerator, and brake operations during vehicle operation, and that automatically drives the vehicle by performing steering, accelerator, and brake operations based on one piece of driving data selected by a user from the multiple pieces of driving data recorded in the recording unit. In the device of Patent Document 1, while the vehicle is being driven manually, the driver operates a switch or the like to start recording the driving data. After the driver stops recording the driving data by operating a switch or the like, a driving evaluation unit evaluates the recorded driving data and assigns an evaluation score. Furthermore, in the device of Patent Document 1, when an automatic driving mode is selected by a passenger, the vehicle is automatically driven based on the recorded driving data and data selected by the passenger from standard data, which is preset standard driving data. In this case, if the evaluation score of the loaded driving data is lower than a predetermined evaluation score, the device of Patent Document 1 automatically drives the vehicle based on the standard data. Patent Document 1 states that this configuration allows the vehicle to be driven autonomously based on driving data actually obtained by the driver, allowing passengers to experience autonomous driving with different feelings and improving the freedom of autonomous driving. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-032970 Summary of the Invention [Problem to be solved by the invention]

[0004] The device of Patent Document 1 is configured to record driving data, such as vehicle behavior resulting from driving operations performed by the driver, and automatically drive the vehicle based on the recorded driving data during automated driving. Therefore, when automated driving is performed, the recorded driving data is used in a feedforward manner to set target control variables for the drive power source, steering, and other components. However, road conditions and external conditions may differ between manual and automated driving. Furthermore, the acquired data may contain numerical errors, which may prevent the system from reproducing or executing an automated driving experience equivalent to the automated driving experience when the driving data was recorded. As a result, the system may be unable to accurately reproduce the vehicle's behavior and driving trajectory. Even if the vehicle reaches its destination through automated driving, the vehicle's behavior along the way may differ from that desired by the occupant.

[0005] The present invention has been made with a focus on the above-mentioned technical problems, and aims to provide a vehicle driving assistance system that can improve reproducibility when driving by reproducing driving operations, etc. through automatic driving based on driving data such as recorded driving operations by a driver. [Means for solving the problem]

[0006] In order to achieve the above object, the present invention provides a driving assistance system for a vehicle capable of manual driving in which the vehicle is driven by a driver's driving operation and automatic driving in which the vehicle is driven without the driver's driving operation, the system comprising: a memory unit that records the content and amount of the driver's driving operation and a driving trajectory of the vehicle while the vehicle is manually driven along a predetermined route; and a target driving behavior generation unit that generates a target driving behavior based on the content and amount of the driving operation and the driving trajectory recorded in the memory unit so that the vehicle can drive in an automatic driving manner while reproducing the manual driving when the vehicle is driven along the predetermined route, the target driving behavior generation unit generates target control amounts for causing the vehicle to drive automatically based on the driving trajectory, and generates target operation contents and amounts of operation of operating devices for braking, driving and steering the vehicle based on the content and amount of the driving operation. and a driving control unit that calculates a command value for causing the vehicle to travel in the autonomous driving mode based on the target traveling behavior generated by the target traveling behavior generation unit, the behavior of the vehicle when the vehicle is traveling in the autonomous driving mode, and a surrounding situation of the vehicle, and sets the command value to the vehicle, and when the traveling trajectory of the vehicle is within a predetermined range from a target trajectory that is a target traveling trajectory, based on the target traveling behavior generated by the target traveling behavior generation unit, the driving control unit corrects the target traveling behavior so as to give a higher priority to the content and amount of the driving operation than to the traveling trajectory. It is characterized by the above.

[0009] In addition, in the present invention, when the vehicle is driving autonomously based on the target driving behavior generated by the target driving behavior generation unit, if the driving trajectory of the vehicle deviates from a predetermined range centered on the target trajectory, the driving control unit may correct the target driving behavior so as to give a higher priority to the driving trajectory than the content and amount of the driving operation.

[0010] In addition, in the present invention, when the priority of either the content and amount of the driving operation or the driving trajectory is to be increased, the driving control unit may correct the target driving behavior based on a predetermined weight.

[0011] Furthermore, in the present invention, the predetermined weight may be set so that the closer the driving trajectory is to the target trajectory, the greater the weight of the content and amount of the driving operation, and so that the farther the driving trajectory is from the target trajectory, the greater the weight of the target trajectory. [Effects of the Invention]

[0012] According to the vehicle driving assistance system of the present invention, when a predetermined route is driven by manual driving operation, the driving data is recorded. The recorded driving data includes the vehicle's driving trajectory and the driving operation by the driver. The driving assistance system generates target behavior data for the vehicle to automatically drive along the predetermined route based on the recorded driving data. When the vehicle travels along the predetermined route, the driving assistance system automatically drives the vehicle based on the data. Therefore, the vehicle can be automatically driven while reproducing with high accuracy the driving operation by the driver and the vehicle's driving trajectory resulting from that driving operation. Therefore, the vehicle can be automatically driven according to the behavior desired by the occupant.

[0013] Furthermore, when generating data representing the target vehicle behavior, the driving assistance system is configured to generate control variables for driving, braking, and steering the vehicle based on the recorded driving trajectory, and to generate operation variables for devices for driving, braking, and steering the vehicle based on the driving operation. By reproducing the operation variables for the devices for driving, braking, and steering the vehicle, it is possible to reproduce the driver's preparatory actions, which are unlikely to appear in the vehicle behavior and driving trajectory, within the range of numerical error, and to drive the vehicle autonomously. Therefore, it is possible to drive the vehicle autonomously while reproducing manual driving operations with even higher accuracy.

[0014] Furthermore, when the vehicle is being driven autonomously based on the target driving behavior generated by the target driving behavior generation unit, if the vehicle's driving trajectory is within a predetermined range from the target trajectory, which is the target driving trajectory, the target driving trajectory is corrected so as to give higher priority to the content and amount of driving operation than the driving trajectory. Conversely, if the vehicle's driving trajectory deviates from the predetermined range, the target driving behavior is corrected so as to give higher priority to the driving trajectory than the content and amount of driving operation. This prevents or suppresses the vehicle's driving trajectory from deviating significantly from the target trajectory, and makes it possible to bring the behavior of the vehicle's operating devices closer to the behavior of the operating devices during manual driving.

[0015] Furthermore, when the priority of either the content and amount of driving operation or the driving trajectory is to be increased, the target driving behavior is corrected based on a predetermined weighting. The predetermined weighting is set so that the closer the driving trajectory is to the target trajectory, the greater the weighting of the content and amount of driving operation, and the further the driving trajectory is from the target trajectory, the greater the weighting of the target trajectory. With this configuration, the content and amount of driving operation performed by manual driving can be reproduced with higher accuracy, allowing the vehicle to be driven automatically. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a diagram illustrating an example of a vehicle equipped with a driving assistance system according to an embodiment of the present invention. [Figure 2] 1 is a block diagram illustrating a functional configuration of a driving assistance system according to an embodiment of the present invention. [Figure 3] 1 is a flowchart showing an example of control executed by the driving assistance system according to an embodiment of the present invention, and is a flowchart executed when recording travel data resulting from manual driving operations. [Figure 4] This is a flowchart showing an example of control performed by a driving assistance system in an embodiment of the present invention, and is a flowchart executed when manual driving is reproduced and automatic driving is performed based on recorded driving data. [Figure 5] FIG. 10 is a block diagram illustrating the functional configuration of a driving assistance system according to another embodiment of the present invention. [Figure 6] FIG. 10 is a block diagram illustrating the functional configuration of a driving assistance system according to still another embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0017] The present invention will be described below based on the embodiments shown in the drawings. Note that the embodiments described below are merely examples of specific embodiments of the present invention and are not intended to limit the present invention.

[0018] 1 and 2 show a vehicle driving assistance system 1 according to an embodiment of the present invention. The vehicle driving assistance system 1 according to the embodiment of the present invention is configured to record driving data when the vehicle Ve travels along a predetermined route or road by manual driving operation, and to cause the vehicle Ve to travel automatically based on the recorded driving data when the vehicle Ve travels along that predetermined road again.

[0019] As shown in FIG. 1, the vehicle Ve includes a driving force source 2, a braking device 3, wheels 4, a steering device 5, a detection unit 6, and a controller (electronic control device) 7. The vehicle Ve is capable of not only being driven manually but also being driven automatically by controlling the driving force, braking force, steering, and the like without the driver's operation. The vehicle Ve is configured to be able to select either a manual driving mode in which the vehicle is driven manually or an automatic driving mode in which the vehicle is driven automatically by computer control. The vehicle Ve is also configured to be able to recognize the driving environment and monitor the surrounding conditions based on map information and surrounding information received from an external source. That is, the vehicle Ve is provided with devices or apparatuses for acquiring various data and information necessary for the vehicle Ve to be driven manually or automatically. Therefore, the vehicle Ve is configured to independently control the vehicle in the forward and backward directions, i.e., acceleration control and deceleration control. The vehicle Ve may be any vehicle capable of being driven manually or automatically, and may be, for example, an existing general vehicle such as an internal combustion engine vehicle, a hydrogen-powered vehicle, a hybrid vehicle, or a fuel cell vehicle.

[0020] The driving force source 2 outputs torque to drive the wheels 4, i.e., torque for propelling the vehicle Ve. The driving force source 2 may include, for example, a conventionally known engine (internal combustion engine) or a motor-generator, or may include both. The driving force source 2 is configured to output torque according to the depression angle and depression force of an accelerator pedal 2a, which is located on the floor on the driver's seat side of the vehicle Ve, when the accelerator pedal 2a is operated.

[0021] The brake device 3 is a device similar to a conventionally known brake device, and is provided, for example, on each of the front and rear wheels 4 of the vehicle Ve. An example of the brake device 3 is a friction brake such as a disc brake, drum brake, or powder brake, and is configured to generate frictional force by hydraulic pressure or electromagnetic force, thereby generating a braking force in a direction to stop the rotation of each wheel 4. The brake device 3 is configured, for example, to output a braking force according to the depression angle and depression force of a brake pedal 3a disposed on the floor on the driver's seat side of the vehicle Ve, when the brake pedal 3a is operated.

[0022] The steering device 5 adjusts the traveling direction of the vehicle Ve by the driver operating the steering wheel 5a. The steering device 5 is similar to a conventionally known steering device, for example, a rack-and-pinion type electric power steering device (EPS) provided with an electric assist mechanism.

[0023] The detection unit 6 is a device or apparatus for acquiring various data and information required for controlling the vehicle Ve. The detection unit 6 includes an internal sensor 8 for acquiring data related to the traveling of the vehicle Ve itself and an external sensor 9 for acquiring information outside the vehicle Ve. The internal sensor 8 includes an inertial measurement unit (IMU) 8a capable of detecting the angle or angular velocity and acceleration of the vehicle Ve while traveling, a vehicle speed sensor 8b for detecting the vehicle speed from the rotational speed of the wheels 4, a motor resolver 8c for detecting the rotational angle of the motor, and a master cylinder pressure sensor 8d for detecting the hydraulic pressure acting on the master cylinder of the brake device 3. The IMU 8a is located at the center of gravity of the vehicle Ve and detects the acceleration and angle (or angular velocity) about the three axes of the vehicle Ve—forward / backward, lateral, and vertical—and outputs a signal indicating the detection result to the traveling control unit. The external sensor 9 includes a camera 9a for capturing captured images and a LiDAR 9b for acquiring information about objects based on data on reflected laser light.

[0024] As shown in Fig. 1, the controller 7 mainly comprises a processor 10, a communication unit 11, and a storage unit 12. The controller 7 is configured to perform calculations according to a predetermined program using data input from various sensors 8 and 9 provided in the vehicle Ve, external data, and pre-stored data, and to output the results of the calculations as control command signals. In the controller 7 according to the embodiment of the present invention, the processor 10 loads a program stored in a recording medium into a work area of ​​the storage unit 12, executes the program, and performs various controls through the execution of the program, thereby performing functions that meet predetermined purposes.

[0025] The processor 10 is a central processing unit, such as a CPU or a DSP, and is configured to control the controller 7 and perform various information processing operations.

[0026] The communication unit 11 is a wireless communication circuit connected to other vehicles, a server (not shown), etc., so as to be able to communicate data via wireless communication. This wireless communication circuit performs communication using cellular communication (mobile communication) such as 5G or 4G (LTE). Note that the wireless communication circuit may also perform communication using narrowband communication such as DSRC.

[0027] The storage unit 12 is configured to store various programs and various data, and includes, for example, RAM and ROM. As described above, the storage unit 12 has a working area for the processor 10 to execute the programs. The storage unit 12 may also include an auxiliary storage unit such as an EPROM, a hard disk drive, or a portable recording medium, i.e., a removable medium.

[0028] The memory unit 12 records data such as the driving operations by the driver and the driving trajectory of the vehicle Ve when the vehicle Ve is driven in manual driving mode. The memory unit 12 acquires data related to the driving operations by the driver while the vehicle Ve is traveling based on data acquired from the various sensors 8 and 9 described above. Specifically, the memory unit 12 acquires the operation amounts and operation speeds of the accelerator pedal 2a, the brake pedal 3a, and the steering wheel 5a. The memory unit 12 also records the driving trajectory, including the behavior of the vehicle Ve while traveling, based on data acquired from the various sensors 8 and 9 described above and the position information acquisition unit 13 described later.

[0029] The memory unit 12 also stores multiple pieces of driving data. For example, when the vehicle Ve travels the same route under the driving operations of multiple drivers, the memory unit 12 stores multiple pieces of driving data corresponding to each of the travels. Therefore, the stored driving data may include, for example, driving data of an experienced driver who performs driving operations such as starting, stopping, and turning of the vehicle Ve in a way that makes the passengers feel comfortable, and driving data of a driver who is currently training to be able to smoothly perform steering, acceleration, and braking operations of the vehicle Ve.

[0030] The detection unit 6, controller 7, and each actuator and sensor configured as described above are electrically connected to each other, for example, by a CAN or a wire harness, and output an electrical signal corresponding to the acquired detection value or calculated value to the controller 7 as detection data.

[0031] As shown in FIG. 2, the controller 7 also includes a position information acquisition unit 13, a target state calculation unit 14, a target state generation unit 15, and a driving control unit 16 at appropriate locations in the above-mentioned processor 10, communication unit 11, and memory unit 12.

[0032] The location information acquisition unit 13 acquires information about the current location of the vehicle Ve from a location information service. An example of such a location information service is GPS, which is one of the GNSS satellite positioning systems that receive signals emitted from satellites to estimate or identify the current location.

[0033] The target state calculation unit 14 calculates parameters related to the behavior of the vehicle Ve that is to be targeted when the vehicle Ve travels an automatic driving along a predetermined route, based on travel data obtained when the vehicle travels an predetermined route in manual driving mode and stored in the memory unit 12. Specifically, the target state generation unit 15 calculates control variables and operation variables related to driving, braking, and steering required to automatically drive the vehicle Ve with behavior similar to that of manual driving, based on data such as multiple parameters acquired by the various sensors 8 and 9 and stored in the memory unit 12. In other words, the target state calculation unit 14 analyzes the driving operations and travel trajectory of manual driving from values ​​acquired from the various sensors 8 and 9. The target state calculation unit 14 includes a target travel trajectory calculation unit 14a and a target vehicle state calculation unit 14b.

[0034] The target driving trajectory calculation unit 14a calculates a driving trajectory of the vehicle Ve driven manually based on the position history of the vehicle Ve acquired from the position information acquisition unit 13 while the vehicle Ve is driving in the manual driving mode. That is, the target driving trajectory calculation unit 14a calculates a driving trajectory followed by the vehicle Ve while driving in the manual driving mode based on the recorded driving data. When calculating the driving trajectory, if a plurality of pieces of driving data when the vehicle Ve has traveled a predetermined route are stored in the storage unit 12, the target driving trajectory calculation unit 14a may be configured to calculate a target driving trajectory for each of the plurality of pieces of driving data, or to calculate the target driving trajectory by integrating or averaging the plurality of pieces of driving data.

[0035] The target vehicle state calculation unit 14b calculates operation parameters of operation devices related to the driver's driving operation when traveling a predetermined route, based on driving data recorded by the various sensors 8 and 9 in the manual driving mode. The operation devices include the accelerator pedal 2a, the brake pedal 3a, and the steering wheel 5a. The target vehicle state calculation unit 14b calculates not only driving operations that appear in the behavior of the vehicle Ve, but also the operation amount and operation speed of driving operations that do not appear in the behavior of the vehicle Ve. For example, the operation of the steering wheel 5a when the driver turns the vehicle Ve may include a slight operation of the steering wheel 5a just before the vehicle Ve actually starts turning, which does not appear in the behavior of the vehicle Ve. The target vehicle state calculation unit 14b is configured to calculate the steering angle and steering speed of the steering wheel 5a resulting from such a slight operation. In addition, similar to the target driving trajectory calculation unit 14a, when multiple driving data for driving a predetermined route are stored in the memory unit 12, the target vehicle state calculation unit 14b may calculate operation parameters based on one manual driving operation selected by the driver, or may calculate operation parameters by averaging the driving data.

[0036] The target state generation unit 15 generates target data for autonomous driving of the vehicle Ve based on the parameters calculated by the target state calculation unit 14 and the surrounding conditions of the vehicle Ve and the behavior of the vehicle Ve acquired from various sensors 8, 9, etc. during actual driving. Specifically, the target state generation unit 15 calculates target control amounts when controlling each actuator of the vehicle Ve, and target operation amounts and operation speeds when operating each operating device, thereby generating a target driving behavior of the vehicle. When the vehicle Ve travels along a predetermined route, the surrounding conditions of the vehicle Ve may differ between when the vehicle is traveling by manual driving operation and when the vehicle is traveling by autonomous driving operation due to the presence of obstacles or pedestrians on the predetermined route. Therefore, if the vehicle Ve travels autonomously only using parameters calculated based on recorded driving data, there is a possibility that the vehicle Ve will not be able to reproduce the driving trajectory and driving operation based on those parameters due to obstacles, etc. Therefore, the target state generation unit 15 is configured to generate final target data taking into account the calculated parameters and the detected actual surrounding conditions. The target state generating unit 15 has a target traveling trajectory generating unit 15a and a target vehicle state generating unit 15b.

[0037] The target driving trajectory generating unit 15a generates a target trajectory, which is a driving trajectory that the vehicle Ve should aim for during autonomous driving, based on the driving trajectory calculated by the target driving trajectory calculating unit 14a and the actual surrounding conditions of the vehicle Ve. For example, when the target driving trajectory generating unit 15a acquires information about an obstacle that is not included in the driving data and exists ahead of the vehicle Ve, the target driving trajectory generating unit 15a generates an appropriate driving trajectory as a target trajectory to avoid the obstacle based on the size of the obstacle, the presence of an oncoming vehicle, etc.

[0038] The target vehicle state generating unit 15b generates target operation parameters, which are operation amounts and operation speeds that should be targeted by the operation device during autonomous driving, based on the operation parameters calculated by the target vehicle state calculating unit 14b and the actual behavior and surrounding conditions of the vehicle Ve. As described above, while the vehicle Ve is traveling, it becomes necessary to change the behavior of the vehicle Ve due to obstacles on the route, road surface conditions, etc., and therefore the target vehicle state generating unit 15b generates operation parameters in response to such changes.

[0039] The target state generation unit 15 generates target data for the vehicle Ve based on the target trajectory and target operation parameters generated by the target driving trajectory generation unit 15a and the target vehicle state generation unit 15b. For example, the target state generation unit 15 is configured to construct a model based on recorded driving data and actual conditions, and generate target data by sequentially solving an optimization problem while driving based on the model. For example, the target state generation unit 15 inputs the driving trajectory and driving operation of the vehicle Ve measured during manual driving and recorded in the storage unit 12, as well as data on the actual behavior of the vehicle Ve and surrounding conditions acquired by various sensors 8 and 9, and outputs a prediction model of the vehicle Ve to be followed during autonomous driving (online) based on the input data. The prediction model is set as the target behavior of the vehicle Ve during autonomous driving. When generating the prediction model, the target state generation unit 15 may preferentially refer to control based on the target trajectory and supplementarily use operation based on the target operation parameters. For example, a prediction model may be generated such that the control amount based on the target trajectory of the device to be controlled matches the target value, and the content and amount of operation based on the target operation parameters are controlled to be kept within certain upper or lower limits, thereby giving a higher priority to the target trajectory and a lower priority to the target operation parameters. Alternatively, the target state calculation unit 14 may change whether to prioritize the target trajectory or the driving operation when setting target data, depending on the vehicle Ve and the surrounding conditions. The target state calculation unit 14 and the target state generation unit 15 described above correspond to the target driving behavior generation unit in this embodiment of the present invention.

[0040] For example, when the vehicle Ve is turning manually and the road surface conditions cause a relatively large slippage of the wheels 4 in the vehicle Ve's driving lane, the driving data affected by the slippage may be recorded in the storage unit 12. In such a case, the driver's operation of the brake pedal 3a and the steering wheel 5a during the slippage is the driver's intended operation and is intended to follow the driving route. However, the vehicle Ve's driving position and driving trajectory may deviate in the direction opposite to the turning direction of the vehicle Ve due to the slippage of the wheels 4. In such a case, if the target state generation unit 15 causes the vehicle Ve to automatically drive using target data that prioritizes reference to the target trajectory, the vehicle may behave differently from the behavior desired by the occupants. Therefore, in such a case, the target state generation unit 15 prioritizes data related to the driver's driving operation, such as by referring to map data, to set target parameters for the vehicle Ve. If it is determined that a driving operation has been initiated to correct the vehicle Ve's driving position based on the recorded driving trajectory and driving operation, the subsequent driving trajectory and driving operation will be intended to correct the vehicle Ve's driving position. Therefore, in such a case, the vehicle Ve may be automatically driven to gradually return to the driving trajectory and operation parameters in the target data, taking into consideration pre-stored map data and the actual surrounding conditions of the vehicle Ve. Thereafter, for example, when the difference between the actual driving position of the vehicle Ve and the driving position based on the manual driving operation falls within a predetermined range, the automatic driving based on the generated target data may be resumed.

[0041] The driving control unit 16 controls the vehicle Ve to drive autonomously based on the target data generated by the target state generation unit 15, so as to follow the prediction model generated by the target state generation unit 15. That is, the driving control unit 16 sets each control value in the prediction model of the vehicle Ve in a feedforward manner as a command value for each device in the vehicle Ve, thereby controlling devices required for autonomous driving, such as actuators to be controlled, so that each actual control value in the vehicle Ve coincides with each control value in the prediction model. Such devices mainly include devices that control the steering, braking, and driving of the vehicle Ve, as described above, and operating devices that perform operations related to steering, braking, and driving. That is, the driving control unit 16 calculates and sets command values ​​for actually controlling the vehicle Ve based on the target data, the prediction model, the actual situation of the vehicle Ve, and the like.

[0042] For example, unexpected changes in the behavior of the vehicle Ve due to road conditions or other factors may occur while the vehicle Ve is traveling. Even though the actuators and operating devices are controlled according to the calculated command values, the actual trajectory of the vehicle Ve may deviate significantly from the target trajectory. In other words, the actual trajectory of the vehicle Ve may deviate from a predetermined range centered on the target trajectory. In such a case, although the trajectory of the vehicle Ve deviates from the target trajectory, the command values ​​for controlling the devices are likely to be values ​​close to the target control parameters. In such a case, the traveling control unit 16 corrects the command values ​​so that the trajectory of the vehicle Ve is aligned with the target trajectory, even if the parameters of the actual devices are values ​​that correspond to the calculated command values. In other words, even if the actuators and operating devices of the vehicle are controlled differently from the calculated command values, when the trajectory of the vehicle Ve deviates from the predetermined range centered on the target trajectory, the command values ​​are corrected to control the vehicle Ve with a priority on returning the trajectory of the vehicle Ve to the target trajectory.

[0043] In this way, when the traveling trajectory of the vehicle Ve deviates relatively significantly from the target trajectory due to an external factor or the like, even if the control of each device of the vehicle Ve is maintained based on the command values, there is a high possibility that the behavior of the vehicle Ve will differ from the behavior during manual driving operation. In order to prevent or suppress such a situation, when the traveling trajectory of the vehicle Ve deviates from the target trajectory, the traveling control unit 16 corrects the command values ​​and stabilizes the behavior of the vehicle Ve while controlling the traveling trajectory of the vehicle Ve to be a trajectory that follows the target trajectory.

[0044] The correction amount may be set based on the deviation between a predetermined driving trajectory of the vehicle Ve and a target trajectory, and the deviation between the control value and the command value of each actuator, etc. For example, a weight is set so that the deviation in the driving trajectory is smaller relative to the deviation in the command value, and the weight is increased as the deviation in the driving trajectory is larger. In other words, the weight is set so that the closer the driving trajectory is to the target trajectory, the more the automated driving conforms to the content and amount of driving operation, and the further the driving trajectory is from the target trajectory, the more the automated driving conforms to the target trajectory. When a deviation such as that described above occurs, the driving control unit 16 determines the correction amount for the target trajectory and the command value based on the weight. By correcting the command value of each parameter in this way, the behavior of the vehicle Ve can be stabilized while the vehicle Ve can be driven automatically in accordance with both the driving trajectory and the content and amount of driving operation.

[0045] Conversely, when the actual travel trajectory of the vehicle Ve is within a predetermined range centered on the target trajectory, the vehicle Ve may be controlled by, for example, giving priority to the command values ​​related to the operation content and amount of the operation device. In other words, even if the travel trajectory of the vehicle Ve deviates from the target trajectory, as long as it is within the predetermined range, the command values ​​to the operation device may be given priority to control the vehicle Ve. With such a configuration, the vehicle Ve can be automatically driven while reflecting the behavior intended by the driver or passengers as much as possible.

[0046] When driving the vehicle Ve in the autonomous driving mode based on the recorded driving data, the driving control unit 16 always acquires information about the actual conditions of the vehicle Ve and its surroundings. For example, the recorded driving data may include data in which the vehicle Ve is forced to cross a lane boundary line to avoid an obstacle or the like. If the driving data recorded in such a driving mode were to be reproduced, the vehicle Ve would exhibit an obstacle-avoiding behavior even when there is no obstacle. Therefore, to avoid such a situation, the driving control unit 16 is configured to always acquire information about the actual conditions and automatically drive the vehicle Ve so that the vehicle Ve can travel appropriately.

[0047] The driving assistance system 1 for the vehicle Ve according to the embodiment of the present invention configured as described above records driving data when the vehicle Ve is driven by a driver's driving operations. When the vehicle Ve is driven in the autonomous driving mode, if there is a record of driving data based on manual driving operations on the driving route, the driving assistance system 1 is configured to cause the vehicle Ve to drive autonomously based on the recorded driving data. That is, when the vehicle Ve is driven again in the autonomous driving mode on a predetermined road that has been driven once in the manual driving mode, the driving assistance system 1 is configured to perform autonomous driving so as to replicate the driving operations performed by the driver in the manual driving mode. Specifically, the driving assistance system 1 records, as driving data, at least the driving trajectory in the manual driving mode and the content and amount of the driver's driving operations. When the vehicle Ve is driven again in the autonomous driving mode on a predetermined road, the driving assistance system 1 controls the vehicle Ve to replicate the recorded driving trajectory and manual driving operations. In this case, not only the steering, braking, acceleration, and other controls of the vehicle Ve are replicated, but also the operation of the corresponding operating devices. For example, when the vehicle Ve turns, the steering wheel 5a is operated to reproduce the operation speed and amount of the steering wheel 5a during manual driving. That is, data related to the operation of the steering wheel 5a performed by manual driving is also recorded, and when the vehicle Ve is driven by automatic driving, not only the steering amount and steering speed of the vehicle Ve but also the operation of the steering wheel 5a are reproduced.

[0048] An example of this control will be described with reference to the flowcharts shown in Figures 3 and 4. The flowcharts shown in Figures 3 and 4 are executed by the appropriate components described above in the driving assistance system 1 according to the embodiment of the present invention. The flowchart shown in Figure 3 shows control for recording driving data, including driving operations by the driver, when the vehicle Ve is driven in manual driving mode, and generating a target state for the vehicle Ve based on the recorded driving data. In step S1, it is determined that the manual driving mode has been selected as the driving mode for the vehicle Ve. This determination of the driving mode of the vehicle Ve is performed, for example, by the driver pressing a predetermined switch installed on the instrument panel of the vehicle Ve or operating a touch panel to switch the driving mode of the vehicle Ve to manual driving mode.

[0049] If the determination in step S1 is YES because the manual driving mode has been selected as the driving mode of the vehicle Ve, the process proceeds to step S2, where it is determined whether or not to record driving data. In step S2, it is determined whether or not to record driving data, such as manual driving operations during driving and driving trajectory. As in step S1, the determination of whether or not to record driving data may be made by the driver operating a predetermined switch or touch panel installed on the instrument panel of the vehicle Ve. If the determination in step 1 or step S2 is NO because the manual driving mode has not been selected as the driving mode of the vehicle Ve, or because recording of driving data has not been selected, this flowchart is temporarily terminated without executing the subsequent control.

[0050] If the driver has selected to record the driving data and the determination in step S2 is YES, the process proceeds to step S3, where the recording of the driving data is started. In step S3, data related to the driving trajectory of the vehicle Ve and data related to the driving operation of the driver are mainly recorded in the memory unit 12.

[0051] The storage unit 12 acquires data related to the current position of the vehicle Ve acquired by the position information acquisition unit 13 while the vehicle Ve is traveling. The position information acquisition unit 13 acquires data related to the current position of the vehicle Ve, for example, at regular intervals of time or regular distances, and records the position history of the vehicle Ve, i.e., the traveling trajectory. The regular intervals of time or regular distances are set to intervals that allow the vehicle Ve to travel in an autonomous driving mode by referring only to the recorded position history of the vehicle Ve or by also referring to the map information stored in the storage unit 12, and that allow the target traveling trajectory calculation unit 14a to generate a target trajectory.

[0052] The storage unit 12 also acquires data related to the driving operation of the driver obtained by various sensors mounted on the vehicle Ve while the vehicle Ve is traveling. The data related to the driving operation includes, for example, the operation amount and operation speed of the steering wheel 5a, the brake pedal 3a, and the accelerator pedal 2a.

[0053] After starting the recording of the traveling data in this way, the process proceeds to step S4, where it is determined whether or not to end the recording of the traveling data. The determination in step S4 may be made, for example, as in step S2, by the driver operating a predetermined switch or touch panel installed on the instrument panel or the like of the vehicle Ve. Alternatively, the recording may be ended when the ignition is turned off. If the determination in step S4 is NO because such a switch or the like has not been operated, the process returns to step S3, and the recording of the traveling data continues.

[0054] On the other hand, if the answer to step S4 is affirmative because the driver has performed an operation to end the recording of the driving mode, the process proceeds to step S5, where the recording of the driving mode is ended.

[0055] After recording the driving mode, the process proceeds to step S6, where parameters related to the behavior of the vehicle Ve are calculated based on the recorded driving data. Specifically, in step S6, control variables and operation variables related to driving, braking, and steering required for the vehicle Ve to be driven autonomously with behavior similar to that of manual driving are calculated based on data acquired by various sensors 8, 9, etc. In other words, in step S6, target parameters for each actuator are calculated so that when a predetermined route driven in manual driving mode is driven again in automatic driving mode, the driving trajectory and driving operation in manual driving mode can be reproduced. Once the parameter calculation is completed and the calculation of data for generating a prediction model is completed, the process in step S6 ends, and this flowchart is temporarily terminated.

[0056] Next, the control when the vehicle Ve is driven in an automatic driving mode using the data calculated by executing the flowchart shown in Fig. 3 will be described with reference to Fig. 4. As shown in Fig. 4, in step S11, it is determined that the automatic driving mode has been selected as the driving mode. If the determination in step S11 is NO because the manual driving mode has been selected as the driving mode, for example, the flowchart is temporarily ended without executing the subsequent control.

[0057] On the other hand, if the autonomous driving mode is selected as the driving mode and the determination in step S11 is YES, the process proceeds to step S12, where it is determined that a destination has been set. If the determination in step S12 is NO because a destination has not been set, the process waits until a destination is set by the driver.

[0058] If the determination in step S12 is YES because the destination has been set, the process proceeds to step S13, where it is determined that referable manual driving driving data is stored along the planned driving route from the current position to the destination. In step S13, it is sufficient that driving data is stored along at least a portion of the planned driving route from the current position to the destination. If the determination in step S13 is NO because there is no section along the planned driving route that includes driving data, this flowchart is temporarily terminated without executing the subsequent control.

[0059] If the determination in step S13 is YES because there is a section on the planned driving route that includes driving data, the process proceeds to step S14, where it is determined whether or not to drive using that driving data. In step S14, the driver is notified that there is usable driving data on the planned driving route, and is prompted to choose whether or not to drive the vehicle Ve in autonomous driving using that driving data. If the determination in step S14 is NO because the driver operates a predetermined switch or touch panel and selects to drive the vehicle Ve in autonomous driving without using driving data, this flowchart is temporarily terminated without executing any subsequent control.

[0060] If the driver has selected to drive the vehicle Ve automatically using the driving data and the determination in step S14 is YES, the process proceeds to step S15, where generation of a target state for the vehicle Ve begins. In step S15, a prediction model that will be the target when the vehicle Ve drives automatically is generated based on the data calculated in step S6 and the actual surrounding conditions of the vehicle Ve. After the prediction model is generated, the process proceeds to step S16.

[0061] In step S16, target parameters for each device required for actually driving the vehicle Ve autonomously are calculated to follow the generated prediction model. In step S16, command values ​​for parameters related to the control of the vehicle Ve, such as driving, braking, and steering, and parameters related to the operation of the devices for operating these controls are calculated so that the vehicle Ve behaves in the same manner as the prediction model.

[0062] After completing the processing of step S16 by calculating such command values, the processing proceeds to step S17, where each command value is set as a target value for the device to be controlled in the autonomous driving, and autonomous driving is started. In step S17, for example, if driving data from the current position to the destination is recorded, target command values ​​are sequentially calculated and set, and autonomous driving is performed. If the driving data is for only a portion of the planned driving route, the passenger is notified immediately before reaching that portion of the route, and autonomous driving based on the driving data is started. In this way, this flowchart ends once autonomous driving that reproduces the behavior of the vehicle Ve based on the recorded manual driving operation has started.

[0063] According to a driving assistance system 1 for a vehicle Ve in an embodiment of the present invention, when the vehicle Ve travels along a predetermined route through manual driving operations, the driving data is recorded. The recorded driving data includes the vehicle Ve's driving trajectory and the driver's driving operations. Based on the recorded driving data, the driving assistance system 1 generates target data, which is a target behavior for the vehicle Ve to travel along the predetermined route through automatic driving. When automatic driving using the target data is selected when traveling along the predetermined route, the driving assistance system 1 sets the target data or causes the vehicle Ve to travel automatically so as to follow a predictive model using the target data. When generating the target behavior of the vehicle Ve, the driving assistance system 1 is configured to generate control amounts for driving, braking, and steering the vehicle Ve based on the recorded driving trajectory, and to generate operation amounts for driving, braking, and steering the vehicle Ve based on the driving operations. Therefore, by tracking the recorded driving trajectory, the driving position and speed of the vehicle Ve can be reproduced, and by tracking the driver's driving operations, the behavior of the vehicle Ve and the driver's preparatory actions that do not often appear on the driving trajectory can be reproduced, allowing the vehicle Ve to be driven autonomously. Specifically, when the vehicle Ve drives to track the position information plotted on the driving trajectory, it may travel in a straight line through sections between position information that are adjacent in time or distance. In such a section where the vehicle Ve drives in a straight line, by tracking driving operations such as the operation of the steering wheel 5a, the vehicle Ve can be driven autonomously by accurately reproducing behavior such as preparatory actions for turning the vehicle Ve. Therefore, the passenger can ride the vehicle Ve to their destination according to the desired behavior of the vehicle Ve.

[0064] Furthermore, this driving assistance system 1 can train other drivers to master driving operations or assist other drivers in their driving operations. For example, along a predetermined route, driving data of an experienced driver who is capable of driving operations such as starting, stopping, and turning of the vehicle Ve in a manner that makes the passengers feel comfortable, as described above, is recorded in the storage unit 12. Based on the recorded driving data, the target state generation unit 15 generates target data for the vehicle Ve. Then, with a driver undergoing training sitting in the driver's seat, the vehicle Ve is automatically driven along a predetermined route based on command values ​​generated by the driving control unit 16 for each device that controls the behavior of the vehicle Ve. The above-described configuration can accurately reflect driving operations (preparatory movements) related to steering and braking / driving force, which would fall within the range of numerical error if only the driving trajectory were referenced. Therefore, the driver undergoing training can experience the driving operations and driving trajectory of an experienced driver from the driver's seat, thereby improving the driver undergoing training's driving proficiency. Similarly, the driving operations of a driver in training can be assisted by partially reproducing the driving operations of an experienced driver to assist the driving operations of the driver in training while the vehicle Ve is in operation.

[0065] Furthermore, this driving assistance system 1 allows the driver in training to experience his or her own driving operations. For example, the driver in training described above drives a predetermined route by manual driving operations and records the driving data at that time. Target data is then generated based on the recorded driving data. Then, with the driver in training sitting in the driver's seat, the vehicle is automatically driven along the predetermined route based on command values ​​generated by the driving control unit 16 for each device that controls the behavior of the vehicle Ve. In this way, the driver in training can experience the driving operations and driving trajectory he or she performed, and can objectively experience his or her own driving, braking, steering, etc.

[0066] In the above-described embodiment, a single vehicle Ve is configured to record driving data and perform autonomous driving based on target data. However, this configuration is not limiting, and these processes may be performed by multiple vehicles. FIG. 5 illustrates another embodiment of the present invention, in which the vehicle that records driving data and calculates the vehicle's target state is different from the vehicle that automatically drives based on the target data. As shown in FIG. 5, in this embodiment, a first vehicle Ve1, which is traveling (online), records driving data when it manually drives a predetermined route, and then transmits the driving data to a second vehicle Ve2, which is stopped (offline). Based on the received driving data, the second vehicle Ve2 calculates parameters related to the behavior of the target vehicle Ve to automatically drive while reproducing the behavior during manual driving, and transmits the parameters to the first vehicle Ve1. The first vehicle Ve1 generates a target state for the first vehicle Ve1 based on the received parameters, and automatically drives the first vehicle Ve1 based on the target state.

[0067] 6 shows another embodiment of the present invention in which the vehicle that records the driving data, the vehicle that calculates the target state of the vehicle, and the vehicle that is automatically driven based on the target data are all different. In this embodiment, a first vehicle Ve1 that is manually driven (online) records driving data of a predetermined route and transmits the data to a second vehicle Ve2 that is stopped (offline). Based on the received driving data, the second vehicle Ve2 calculates parameters related to the behavior of the target vehicle Ve to automatically drive the vehicle while reproducing the behavior of the vehicle during manual driving, and transmits the parameters to a third vehicle Ve3 that is currently running (online). The third vehicle Ve3 generates a target state for the third vehicle Ve3 based on the received parameters, and automatically drives the third vehicle Ve3 based on the target state. With this configuration, even if the third vehicle Ve3 has never driven on a route, data can be obtained from the first vehicle Ve1 traveling on that route via the second vehicle Ve2, allowing the third vehicle Ve3 to drive automatically while reproducing the behavior of the first vehicle Ve1 when it was driven manually.

[0068] Even with this configuration, it is possible to train other drivers in driving operations or to assist other drivers in driving operations, as described above. For example, the above-mentioned experienced driver gets into the first vehicle Ve1 and records driving data through manual driving. Then, the driver in training sits in the driver's seat of the third vehicle Ve3 and reproduces that driving data to experience autonomous driving. Therefore, the above-mentioned effects can be achieved even if the experienced driver and the driver in training do not get into the same vehicle Ve.

[0069] Although the embodiments of the present invention have been described above, the present invention is not limited to the above examples and may be modified as appropriate within the scope of achieving the object of the present invention. For example, the analysis of the behavior of the manually driven vehicle Ve based on the driving data may be performed by an external server or the like. [Explanation of symbols]

[0070] 1. Driving assistance systems 6. Detection unit 7 Controller 12 Storage section 14 Target state calculation unit 15. Target state generation unit 16 Travel control unit Vehicle

Claims

1. A driving assistance system for a vehicle capable of manual driving in which the vehicle is driven by a driver's operation and automatic driving in which the vehicle is driven without the driver's operation, a memory unit that records the content and amount of the driving operation of the driver and the traveling trajectory of the vehicle while the vehicle is being manually driven along a predetermined route; a target driving behavior generating unit that generates a target driving behavior based on the content and amount of the driving operation and the driving trajectory recorded in the storage unit so that the vehicle can travel in a manner that reproduces the manual driving when traveling along the predetermined route by the automatic driving, the target driving behavior generation unit generates target control amounts for causing the vehicle to travel in the autonomous driving mode based on the driving trajectory, and generates target operation contents and amounts of operation devices for braking, driving, and steering the vehicle based on the contents and amounts of the driving operations; a driving control unit that calculates a command value for causing the vehicle to drive in the autonomous driving mode based on the target driving behavior generated by the target driving behavior generation unit, the behavior of the vehicle when the vehicle is being driven in the autonomous driving mode, and a surrounding situation of the vehicle, and sets the command value in the vehicle; When the vehicle is traveling in the autonomous driving mode based on the target traveling behavior generated by the target traveling behavior generating unit, if the traveling trajectory of the vehicle is within a predetermined range from a target trajectory that is a target traveling trajectory, the traveling control unit corrects the target traveling behavior so as to give a higher priority to the content and amount of the driving operation than to the traveling trajectory. A vehicle driving assistance system characterized by:

2. 2. A vehicle driving assistance system according to claim 1, When the vehicle is traveling in the autonomous driving mode based on the target traveling behavior generated by the target traveling behavior generating unit, if the traveling trajectory of the vehicle deviates from a predetermined range centered on the target traveling trajectory, the traveling control unit corrects the target traveling behavior so as to give a higher priority to the traveling trajectory than the content and amount of the driving operation. A vehicle driving assistance system characterized by:

3. 3. A driving assistance system for a vehicle according to claim 1 or 2, The driving control unit corrects the target driving behavior based on a predetermined weight when the priority of either the content and amount of the driving operation or the driving trajectory is to be increased. A vehicle driving assistance system characterized by:

4. 4. A vehicle driving assistance system according to claim 3, The predetermined specific gravity is The closer the driving trajectory is to the target trajectory, the greater the weight of the content and amount of the driving operation is determined; The farther the running path is from the target path, the greater the weight of the target path is determined. A vehicle driving assistance system characterized by:

Images