Autonomous driving control methods and control units and systems for autonomous vehicles

Abstract

This invention provides a control unit and system for an autonomous vehicle, as well as an autonomous driving control method. The control unit includes: an acquisition module configured to acquire trip information of the user's current trip and historical traffic information related to the current trip; a determination module configured to determine the trip destination based on the trip information, and determine an autonomous driving mode matching the trip destination from a pre-set plurality of autonomous driving modes based on the trip destination; a comparison module configured to compare the time taken to complete a portion of the current trip with the historical average time taken to complete that portion, derived from the historical traffic information, during autonomous driving in the determined autonomous driving mode; and an adjustment module configured to dynamically adjust the driving style in the current autonomous driving mode based on the comparison result during autonomous driving.

Description

Technical Field

[0001] This invention relates to an autonomous driving solution designed based on user experience. Specifically, this invention relates to a control unit and a control system for autonomous vehicles, as well as a corresponding autonomous driving control method. Background Technology

[0002] In recent years, with the rapid increase in car demand, rising labor costs, and the emergence of problems such as difficulty in getting around and parking spaces, autonomous vehicles have received increasing attention. This is because autonomous vehicles can drop off a user at point A, immediately pick up another user at point B, and then take them to point C. Current research on autonomous driving mainly focuses on safety-related vehicle control technologies such as blind spot detection, lane keeping, and lane change assist. Therefore, existing autonomous driving solutions can safely transport users to their destinations, but they typically use a single algorithm based on a fixed driving style to adapt to all scenarios. However, different users may have different travel purposes. How can autonomous vehicles optimize the user experience to the greatest extent possible for different travel purposes? Current technology does not yet offer a satisfactory solution. Summary of the Invention

[0003] The following is a brief summary of one or more aspects to provide a basic understanding of such aspects. This summary is not a generalization of all aspects, nor is it intended to identify key or important elements of all aspects, nor to describe the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as an introduction to the more detailed descriptions that follow.

[0004] According to one aspect of the present invention, a control unit for an autonomous vehicle is provided, comprising: an acquisition module configured to acquire trip information of a user's current trip and historical traffic information related to the current trip; a determination module configured to determine a trip destination based on the trip information, and determine an autonomous driving mode matching the trip destination from a pre-set plurality of autonomous driving modes, the plurality of autonomous driving modes including a time-priority mode, a comfort-priority mode, a commuting mode, and an economy mode; a comparison module configured to compare the time taken to complete a portion of the current trip with a historical average time taken to complete that portion based on the historical traffic information during autonomous driving in the determined autonomous driving mode; and an adjustment module configured to dynamically adjust the driving style in the current autonomous driving mode based on the comparison result during autonomous driving, so that the time taken to complete a portion of the current trip is as close as possible to the historical average time.

[0005] According to one feasible implementation, each autonomous driving mode is defined by a combination of multiple logics including overtaking / lane changing logic, vehicle speed logic, and acceleration logic; the overtaking / lane changing logic includes an overtaking / lane changing success rate as a calibration parameter, which refers to the success rate of performing overtaking / lane changing based on the current traffic environment; the vehicle speed logic includes the speed limit of the current driving road as a calibration parameter; and the acceleration logic includes an acceleration threshold as a calibration parameter, which includes a safety threshold and a comfort threshold.

[0006] According to one feasible implementation, the plurality of autonomous driving modes are scalable, and the logic terms used to define each autonomous driving mode are scalable and / or adjustable.

[0007] According to one feasible implementation, in time-priority mode, the acceleration logic allows the vehicle acceleration to enter a range exceeding the comfort threshold but less than the safety threshold; and in comfort-priority mode and commuting mode, the acceleration logic limits the vehicle acceleration to not exceed the comfort threshold.

[0008] According to one feasible implementation, dynamically adjusting the autonomous driving style includes: making the driving style more aggressive or milder by adjusting the calibration parameters in the plurality of logics so that the time taken to complete part of the current journey is as close as possible to the historical average time.

[0009] According to one feasible implementation, dynamically adjusting the autonomous driving style includes: adjusting the driving style towards an aggressive direction by executing the overtaking logic and / or the lane-changing logic;

[0010] The overtaking logic includes: performing an overtaking maneuver when the overtaking success rate is greater than or equal to a predetermined overtaking success rate threshold; allowing the vehicle's acceleration to enter a range exceeding a comfort threshold but less than a safety threshold; and limiting the vehicle speed to remain within a predetermined range of the current lane's speed limit.

[0011] The lane change logic includes: performing a lane change when the lane change success rate is greater than or equal to a predetermined lane change success rate threshold, allowing the vehicle acceleration to enter a range exceeding the comfort threshold but less than the safety threshold, and limiting the vehicle speed to remain within a predetermined range of the current lane speed limit.

[0012] According to one feasible implementation, the adjustment module is further configured to: during autonomous driving in a determined autonomous driving mode, adjust the driving behavior in the current autonomous driving mode with a minimum adjustment unit based on user requests and / or the user's biometric feedback information, wherein the minimum adjustment unit refers to the smallest unit that adjusts the calibration parameters of the plurality of logics.

[0013] According to another aspect of the present invention, a control system for an autonomous vehicle is provided, comprising: a human-machine interface, a communication unit, a sensor unit, and a control unit, wherein optionally, the control unit is a control unit as described above.

[0014] In this configuration, at least one of the human-machine interface and the communication unit receives trip information of the user's current trip before autonomous driving begins; the communication unit is configured to receive historical traffic information related to the current trip; and the human-machine interface is configured to receive user input information during autonomous driving.

[0015] The sensor unit includes at least a bio-information sensor for detecting the user's bio-feedback information during autonomous driving; and

[0016] The control unit is configured to determine the autonomous driving mode that matches the purpose of the current trip from a plurality of predetermined autonomous driving modes based on information from the human-machine interface, communication unit and sensor unit, and dynamically adjust the driving style in the current autonomous driving mode during the autonomous driving of the autonomous vehicle, so that the time taken to complete part of the current trip is as close as possible to the historical average time taken to complete that part based on the historical traffic information.

[0017] According to another aspect of the present invention, an autonomous driving control method is provided, optionally executed by a control unit and / or a control system as described above, the method comprising: acquiring trip information of a user's current trip and historical traffic information related to the current trip; determining the trip destination based on the trip information; determining an autonomous driving mode matching the trip destination from a plurality of pre-set autonomous driving modes based on the trip destination, the plurality of autonomous driving modes including a time-priority mode, a comfort-priority mode, a commuting mode, and an economy mode; during the autonomous driving process of the autonomous vehicle in the determined autonomous driving mode, comparing the time taken to complete a portion of the current trip with a historical average time taken to complete that portion based on the historical traffic information; and during the autonomous driving process, dynamically adjusting the driving style in the current autonomous driving mode based on the comparison result, so that the time taken to complete a portion of the current trip is as close as possible to the historical average time.

[0018] According to another aspect of the invention, a machine-readable storage medium is provided that stores executable instructions, which, when executed, cause a processor to perform the autonomous driving control method as described above. Attached Figure Description

[0019] The technical solution of the present invention will become clearer from the following detailed description taken in conjunction with the accompanying drawings. It is to be understood that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0020] Figure 1 This is an exemplary environment in which some embodiments of the present invention can be implemented.

[0021] Figure 2 This is a schematic block diagram of a control system for an autonomous vehicle according to a feasible embodiment of the present invention.

[0022] Figure 3 The diagram illustrates an automatic driving control process according to a feasible embodiment of the present invention.

[0023] Figure 4 The illustration schematically depicts an autonomous driving style adjustment process according to a feasible embodiment of the present invention.

[0024] Figure 5 This is a flowchart of an autonomous driving control method according to a feasible embodiment of the present invention. Detailed Implementation

[0025] This invention relates to an autonomous driving solution that can maximize the user experience by controlling and adjusting the autonomous driving mode and style, so that users can obtain the best riding experience.

[0026] Embodiments of the present invention are applicable to vehicles with autonomous driving capabilities. In the present invention, "autonomous driving vehicle" or "vehicle with autonomous driving capabilities" refers to a vehicle configured to operate without continuous intervention from a driver (e.g., steering, acceleration, braking, etc.).

[0027] In embodiments of the present invention, "autonomous driving" can include partial autonomous driving (e.g., autonomous driving with a safety driver or occasional human intervention) and fully autonomous driving (e.g., autonomous driving without a safety driver or without any human driver intervention). The autonomous driving capability of a vehicle can be achieved through an Advanced Driving Assistance System (ADAS) or an Autonomous Driving System (ADAS) installed in the vehicle.

[0028] Figure 1An environment in which some embodiments of the invention can be implemented is illustrated, which mainly includes a vehicle V equipped with a control system 100 for autonomous driving and external devices capable of wirelessly communicating with the vehicle V. These external devices may include roadside facilities R, a cloud server C, and the user's smart device S (e.g., the user's smartphone). Figure 1 The environment shown can be implemented as an autonomous driving ecosystem, where vehicle V can interconnect and exchange information with intelligent agents within this ecosystem. Vehicle V is a vehicle with autonomous driving capabilities, such as an autonomous vehicle. Vehicle V can be an autonomous taxi, an autonomous ride-hailing vehicle, an autonomous shared car, or an autonomous shuttle bus. It should be noted that this invention is not limited to... Figure 1 The specific architecture shown.

[0029] Figure 2 A control system 100 for an autonomous vehicle (hereinafter referred to as AD control system 100) according to an embodiment of the present invention is illustrated schematically. Figure 2 As shown, the AD control system 100 mainly includes a human-machine interface 10, a communication unit 20, a sensor unit 30, and a control unit 40 for autonomous vehicles (hereinafter referred to as the AD control unit 40). The following is a detailed description of each component of the AD control system 100.

[0030] The Human-Machine Interface (HMI) 10 is communicatively connected to the AD control unit 40. The HMI 10 is configured to enable information interaction between the user within the vehicle V and the vehicle's infotainment system. The HMI 10 can receive user input and transmit it to the AD control unit 40.

[0031] The human-computer interface 10 can utilize various human-computer interaction methods to enable information exchange between the in-vehicle user and the vehicle's infotainment system. These methods may include one or more of the following: touchscreen, automatic speech recognition (ASR), motion recognition (e.g., gesture recognition), eye recognition, and brainwave recognition.

[0032] In one embodiment, at the beginning of an autonomous driving trip, the human-machine interface 10 can receive trip information input by the user, which may include the starting point, destination, and expected arrival time. Then, the human-machine interface 10 transmits the received trip information to the AD control unit 40, so that the AD control unit 40 can determine the autonomous driving mode that matches the current trip's purpose from a pre-set set of various autonomous driving modes. During autonomous driving according to the determined mode, the human-machine interface 10 can receive adjustment messages input by the user, such as "steady," "faster," or "slower," so that the AD control unit 40 can adjust the parameters accordingly based on the user input. Next, the human-machine interface 10 transmits the received user expectations to the AD control unit 40, so that the AD control unit 40 can adjust the driving style in the current autonomous driving mode according to the user's expectations.

[0033] The communication unit 20 is capable of communicating with external devices of the vehicle V (e.g., wired and / or wireless communication connections). In other words, the vehicle V can interact with external devices via the communication unit 20. In one embodiment, the vehicle V and the external device can use any suitable wireless communication method (e.g., 3G / 4G / 5G, C-V2X, DSRC, Wi-Fi, Bluetooth) to exchange information. It should be noted that external devices refer to devices that are not part of the vehicle V, and there is no limitation on whether the physical location of the external device is inside or outside the vehicle. External devices include, for example, cloud servers, edge servers, roadside facilities, other vehicles capable of wirelessly communicating with the vehicle V, and electronic devices carried by the user capable of wirelessly communicating with the vehicle V (e.g., a smartphone carried by the user of the vehicle V).

[0034] The communication unit 20 receives information from an external device and transmits the received information to the AD control unit 40. The information received from the external device and transmitted to the AD control unit 40 via the communication unit 20 may include:

[0035] (1) User Request. For example, a user sends an autonomous driving trip request to an autonomous vehicle cloud platform through their personal smart device. The cloud platform then forwards the user request to autonomous vehicles around the user, and the autonomous vehicles receive the user request through their communication units. The user request may include the user's current location, destination, and expected arrival time.

[0036] (2) User's trip calendar. For example, the AD control system obtains the user's trip calendar from the user's mobile phone through the communication unit, and determines the current autonomous driving trip information that needs to be executed from the user's trip calendar, which includes the origin, destination (end point) and expected arrival time.

[0037] (3) Historical data related to the user's journey. For example, the AD control system obtains historical data related to the currently required autonomous driving journey from a cloud server via the communication unit. This historical data includes historical average levels for the journey determined based on historical traffic flow, such as historical average travel time.

[0038] (4) Navigation information related to the current autonomous driving trip that needs to be performed, which may include high-definition maps (HD MAPs) for autonomous driving. This navigation information can be used for autonomous driving assistance.

[0039] (5) Environmental information and traffic information updated in real time to the cloud server. For example, environmental sensors at roadside facilities detect the environmental conditions and / or weather conditions around the vehicle and generate environmental information containing these conditions, which is then transmitted to the vehicle's communication unit via the communication unit at the roadside facility. For example, if a traffic accident occurs on a road segment that the autonomous driving trip may traverse, the accident information is updated to the cloud server and then distributed from the cloud server to the connected autonomous vehicles.

[0040] The sensor unit 30 may include an environmental sensor 31, a vehicle status sensor 32, and a bio-information sensor 33. Since the sensors in the sensor unit 30 are mounted on the vehicle V, they can also be referred to as on-board sensors. The information sensed by each sensor can be transmitted to the AD control unit 40 via the on-board bus.

[0041] Environmental sensor 31 is used to capture information about the environment or targets outside the vehicle. The environmental sensor may include cameras (e.g., single-target, multi-target, surround-view) and / or radar (e.g., lidar, ultrasonic radar, millimeter-wave radar). The camera can obtain environmental information around the vehicle V through image or video analysis, such as the relative distance between the vehicle and the roadside or obstacles. The radar can obtain the relative distance between the vehicle and the roadside or obstacles through analysis of radar waves or laser point clouds. The environmental sensor may include multiple environmental sensors disposed around the vehicle body, and this arrangement takes into account safety redundancy, i.e., ensuring that the environmental conditions around the vehicle can be fully collected.

[0042] Vehicle status sensor 32 is used to capture vehicle status information. Vehicle status sensor may include sensors that directly or indirectly measure vehicle status parameters, such as wheel speed sensors, suspension displacement sensors, acceleration sensors, steering angle sensors, etc.

[0043] The biometric sensor 33 may include one or more sensors installed in the vehicle for collecting user biometric feedback information. The biometric sensor 33 may include one or more of the following sensing devices: a camera, an infrared sensor, a fingerprint sensor, a pulse sensor, a heart rate sensor, a pupil detection device, and a body temperature detection device. Based on the detected user biometric information, the user's condition can be determined, such as health conditions like fever, motion sickness, or drowsiness; moods and feelings like high-speed stress, anxiety, or happiness; and user activities like reading, sleeping, or entertainment. The process of determining the user's condition can be executed in a processing chip integrated with the biometric acquisition unit 30 and the determination result can be transmitted to the AD control unit 40; it can also be executed in the vehicle V's ECU and the determination result can be transmitted to the AD control unit 40; or it can be executed within the AD control unit 40.

[0044] The AD control unit 40 is communicatively connected to the human-machine interface 10, the communication unit 20, and the sensor unit 30, respectively. The AD control unit 40 is configured to determine the autonomous driving mode based on information received from the human-machine interface 10, the communication unit 20, and the sensor unit 30, and dynamically adjust the autonomous driving style during the execution of the determined AD mode, so as to optimize the user experience to the greatest extent while ensuring that the vehicle V can complete its journey. In this way, the autonomous vehicle is no longer just an automated means of transportation, but can truly become an intelligent mobile space for the user.

[0045] See also Figure 2 The AD control unit 40 mainly includes an acquisition module 41, a determination module 42, a comparison module 43, and an adjustment module 44. The AD control unit 40 and its modules can be implemented in hardware, software, or a combination of both. For the hardware implementation, it can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), data signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic units designed to perform their functions, or combinations thereof. For the software implementation, it can be implemented using microcode, program code, or code segments, and can also be stored in machine-readable storage media such as storage components.

[0046] It is understood that the naming of the modules of the AD control unit 40 should be interpreted as a logical (functional) description, and not as a limitation on physical form or setting. In other words, one or more of the acquisition module 41, determination module 42, comparison module 43, and adjustment module 44 can be implemented in the same chip or circuit, or they can be set in different chips or circuits, and the present invention does not limit this.

[0047] In addition, two or more of these modules can be merged into one module. Any one of these modules can be further divided into multiple sub-modules.

[0048] In one embodiment, the AD control unit 40 may be implemented including a memory and a processor. The memory contains instructions that, when executed by the processor, cause the processor to perform the autonomous driving control method according to an embodiment of the present invention.

[0049] In one embodiment, the AD control unit 40 can be implemented as in-vehicle software. This in-vehicle software can be located in the vehicle's domain controller or electronic control unit.

[0050] Figure 3 An automatic driving control process 300 according to an embodiment of the present invention is shown. This process can be executed in the AD control unit 40 or in the AD control system 100 described above. The above description of the AD control unit 40 and the AD control system 100 also applies here.

[0051] In box 302, the acquisition module 41 acquires the user's current trip information and related historical traffic information. There may be various ways to acquire trip information; several examples are given below.

[0052] In one embodiment, a user can input trip information into the human-machine interface 10, which is then transmitted to the acquisition module 41. For example, a user in a vehicle can input trip information, including the destination and expected arrival time, into the in-vehicle voice interaction interface; or, the user can input trip information, including the destination and expected arrival time, into the in-vehicle touchscreen.

[0053] In another embodiment, the user's schedule is read from the user's mobile phone via the communication unit 20, and the user's travel information is obtained based on it. For example, the user's schedule is read from the user's mobile phone via the communication unit 20, and the user's travel information is obtained based on it.

[0054] In another embodiment, a user request containing trip information is received via communication unit 20. For example, a user is outside the vehicle and sends a trip request to an autonomous vehicle cloud platform (e.g., an autonomous taxi management platform), which includes the start point, destination, and expected arrival time of the trip. The platform then forwards the user's trip request to an autonomous vehicle located near the start point. Vehicle V then receives the request via communication unit 20, sends a message indicating agreement to execute the trip, and proceeds to the start point to pick up the user.

[0055] Historical information related to the trip can be retrieved from the cloud server via the communication unit. This historical information may include historical traffic data related to the trip segment. Historical traffic data can be stored in the cloud server and distributed to vehicle V. Historical traffic data can be obtained by analyzing and integrating traffic data uploaded to the cloud server by various networked traffic participants.

[0056] In block 304, the determining module 42 determines a suitable mode from a set of preset autonomous driving modes based on the user's trip information. For example, the determining module 42 determines the trip's purpose based on the trip information and selects an autonomous driving mode suitable for that purpose from a set of preset autonomous driving modes.

[0057] Several preset autonomous driving modes include time-priority mode, comfort-priority mode, commuter mode, and economy mode. The following is an explanation of each autonomous driving mode.

[0058] Time priority mode

[0059] Time-priority mode focuses on the time required to complete an autonomous driving trip. It's suitable for scenarios such as traveling to transportation hubs like airports, train stations, and bus stations, or when time is tight before attending a business meeting. In these scenarios, the goal is to reach the destination in the shortest possible time while maintaining maximum comfort. Thus, the autonomous driving system can employ a more aggressive driving mode (style) to complete the trip, while adhering to traffic regulations.

[0060] Comfort-first mode

[0061] Comfort-first mode prioritizes comfort throughout the journey. It's suitable for scenarios such as traveling with friends, sleeping, or listening to music. In these situations, compared to a time-first mode that aims to reach the destination quickly, the focus is on maximizing comfort rather than rushing. This allows the autonomous driving system to complete the journey in a more relaxed mode (style) while adhering to traffic regulations.

[0062] Commuting mode

[0063] Commuting mode can be applied to scenarios such as traveling between home and the office. In such scenarios, autonomous driving behavior can strike a balance between arriving as quickly as possible and comfort; that is, improving comfort while ensuring that the destination can be reached within the normal commute time.

[0064] economic model

[0065] The economic mode prioritizes energy conservation. It's suitable for scenarios such as long-distance travel, limited availability of refueling and charging stations along the way, or low fuel levels. In these situations, the trip aims to be driven in the most energy-efficient manner (e.g., most fuel-efficient or most electricity-efficient). This reduces the number of times you need to refuel or charge on long journeys, thus alleviating range anxiety.

[0066] Each autonomous driving mode is defined by a combination of control logic. The control logic used to define the autonomous driving mode may include the following combined limitations: speed logic, acceleration logic, energy consumption logic, overtaking logic, and navigation logic.

[0067] These logical constraints can be implemented using calibration parameters. For example, overtaking logic includes the overtaking success rate as a calibration parameter. Speed ​​logic includes the speed limit of the current road as a calibration parameter. Acceleration logic includes acceleration thresholds as calibration parameters, which include safety thresholds and comfort thresholds.

[0068] "Overtaking success rate" refers to the estimated success rate of overtaking in the current traffic scenario. This success rate can be set at a passing threshold of 60%, meaning a 60% overtaking success rate represents the critical value for successful overtaking under the current circumstances. The overtaking success rate is related to the overtaking space in the current situation (e.g., the distance between the vehicle (V) and the vehicles in front and behind), relative speed, road width curvature, and environmental complexity (the number of traffic participants on other roads). For example, the larger the overtaking space, the higher the overtaking success rate; conversely, the smaller the overtaking space, the lower the overtaking success rate. The methods for limiting the overtaking space and calculating the overtaking success rate can be implemented in various ways, and this invention does not limit these methods.

[0069] "Lane change success rate" refers to the estimated success rate of performing a lane change in the current traffic scenario. This success rate can be set at a passing threshold of 60%, meaning a 60% lane change success rate represents the critical value for successful lane changes in the current situation. The lane change success rate is related to the lane change space in the current situation (e.g., the distance between the vehicle (V) and adjacent vehicles in the lane to which it is changing, and the speed of those adjacent vehicles). For example, the larger the lane change space, the higher the lane change success rate; conversely, the smaller the lane change space, the lower the lane change success rate. The methods for limiting the lane change space and calculating the lane change success rate can be implemented in various ways, and this invention does not limit these methods.

[0070] The "acceleration threshold" can include two types of thresholds: a safety threshold and a comfort threshold. When the acceleration of vehicle V exceeds the safety threshold, the vehicle's autonomous driving behavior will not meet the safety requirements for vehicle operation, which is not permitted. When the acceleration of vehicle V exceeds the comfort threshold but is less than the safety threshold, the vehicle's autonomous driving behavior will cause discomfort to the occupants, but it still meets the safety requirements for vehicle operation. This is permitted in emergency situations or when aggressive driving is required.

[0071] It is understood that vehicle acceleration can include lateral acceleration and longitudinal acceleration. Accordingly, acceleration thresholds also include critical values ​​for lateral acceleration and longitudinal acceleration respectively, each of which is subject to the above limitations.

[0072] It is understood that safety and comfort thresholds can be determined based on factors such as ergonomics, traffic regulations, and vehicle models. This invention does not limit how these thresholds are determined.

[0073] The logical constraints of each autonomous driving mode are described below with examples.

[0074] Logical constraints of time priority mode

[0075] Maintaining the legally permitted maximum speed has a high priority; that is, keeping the speed as close as possible to the speed limit of the current road.

[0076] - In situations where the speed maintenance requirements cannot be met, overtaking or lane changing has high priority. For example, once the success rate of overtaking or lane changing is greater than a predetermined threshold (which can be equal to or higher than the passing score for overtaking / lane changing success rate), an overtaking or lane changing decision is made.

[0077] - No limit on energy consumption.

[0078] - Allow vehicle acceleration (longitudinal and lateral acceleration) to enter a range that exceeds the comfort threshold but is less than the safety threshold.

[0079] Logical constraints of comfort-first mode

[0080] - Ensure that the vehicle's acceleration (lateral and longitudinal acceleration) does not exceed the comfort threshold as much as possible; that is, keep the vehicle's acceleration within the comfort range. This has a high priority.

[0081] - Overtaking or lane-changing logic has low priority. For example, an overtaking decision is only made when the current speed is too low (e.g., less than 70% of the current road speed limit) and the success rate of overtaking is high (e.g., much higher than the passing score for overtaking success rate).

[0082] - No limit on energy consumption.

[0083] Logical constraints of commuting mode

[0084] Ensuring that commuting time conforms to historical averages has high priority. This means ensuring that the current commute time (e.g., the estimated commute time based on current traffic conditions and vehicle speed) falls within the tolerance range of historical average commuting times, or that the time taken to complete a portion of the current commute does not exceed the historical average time taken to complete that portion based on the aforementioned historical traffic information. If the above requirements cannot be met, overtaking / lane changing has high priority. For example, an overtaking / lane changing decision is made once the overtaking / lane changing success rate exceeds a predetermined threshold (this threshold could be equal to or higher than the passing score for overtaking / lane changing success rate).

[0085] - The autonomous driving behavior in this mode should not consume too much energy, in order to reduce range anxiety or driving anxiety during the journey.

[0086] - The vehicle's acceleration (lateral and longitudinal acceleration) does not exceed the comfort threshold, that is, the vehicle's acceleration is kept within the comfort range.

[0087] Logical constraints of economic models

[0088] - Keep energy consumption at a low level, that is, the energy consumption of autonomous driving behavior in this mode is relatively low compared to other modes.

[0089] The autonomous driving mode is scalable, meaning that in addition to the autonomous driving modes described above, additional autonomous driving modes can be set according to specific application scenarios and user needs, and similar logical constraints can be applied to the additional autonomous driving modes.

[0090] The logic used to define each autonomous driving mode is adjustable and / or extensible. That is, each of the constraints in the above combined logic constraints is adjustable; and, in addition to the logic constraints described above, additional logic constraints can be set according to specific application scenarios and user needs.

[0091] Table 1 below describes several implementations of autonomous driving modes and their limiting logic. In Table 1, "-" indicates no limitation, "a" indicates no limitation, and "b" indicates no limitation. x "a" represents the lateral acceleration of the vehicle. y "a" represents the longitudinal acceleration of the vehicle. x-uncom "a" represents the critical value of uncomfortable lateral acceleration. y-uncom "a" represents the critical value of uncomfortable longitudinal acceleration. x-unsafe "a" represents the critical value of unsafe lateral acceleration. y-unsafe "" indicates the critical value of unsafe longitudinal acceleration, and "speed limit" indicates the speed limit of the road on which the vehicle travels.

[0092] Table 1

[0093]

[0094]

[0095] In one embodiment, the determination module 42 can analyze the trip information to determine the purpose of the trip. For example, based on the origin and destination, the purpose of the trip can be determined as commuting, catching a flight, traveling, attending a meeting, etc. Next, the determination module 42 can determine, based on the trip purpose, the factors that need to be prioritized for this segment of the trip are the shortest time, the highest comfort, or the lowest energy consumption, and based on this, determine a suitable autonomous driving mode from a predetermined number of autonomous driving modes, so that the vehicle can perform autonomous driving behavior in the determined autonomous driving mode.

[0096] In box 306, the comparison module 43 compares the real-time monitored actual level of autonomous driving with the historical average level for that trip to obtain a comparison result indicating whether the actual level is higher or lower than or equal to the historical average level.

[0097] For example, during the autonomous driving process of an autonomous vehicle in a defined autonomous driving mode, the comparison module 43 compares the time taken to complete a portion of the current journey with the historical average time taken to complete that portion, derived from the historical traffic information.

[0098] The actual level of autonomous driving can be represented by the time taken to complete the portion of the journey in real time, as monitored under the current autonomous driving mode. The historical average level can be represented by the average time taken to complete the same portion of the journey, derived from historical traffic flow data. It should be noted that the historical average level is derived by combining all historical data from both autonomous driving and human driving. That is, the actual driving level according to embodiments of the present invention will be compared with the historical average level under all traffic scenarios for that road segment.

[0099] In determining the historical average level, historical data from the same day of the week or the same holiday as the current driving time can be considered. For example, the determination of the historical average level can consider the following factors: (1) If the current autonomous driving time is Wednesday morning, then historical traffic flow data from Wednesday morning is selected from the historical data to calculate the historical average level (this calculation method is particularly helpful for cities that apply odd-even license plate restrictions); (2) If the current autonomous driving time is National Day, then historical traffic flow data from previous National Day holidays is selected from the historical data to calculate the historical average level.

[0100] Below, we will use an example to more clearly illustrate the comparison between the actual level and the historical average level.

[0101] In one embodiment, assuming the current autonomous driving mode is commuter mode, it is detected that the vehicle took 10 minutes to reach the location of 1 / 5 of the journey in time-priority mode. If, according to historical traffic flow data, the historical average time to complete 1 / 5 of the journey is 15 minutes, it indicates that the actual performance is higher than the historical average; if, according to historical traffic flow data, the historical average time to complete 1 / 5 of the journey is 8 minutes, it indicates that the actual performance is lower than the historical average; if, according to historical traffic flow data, the historical average time to complete 1 / 5 of the journey is exactly 10 minutes, it indicates that the actual performance is equal to the historical average.

[0102] In box 308, the adjustment module 44 adjusts the driving style in the current autonomous driving mode based on the comparison results, so that the actual level is as close as possible to the historical average level. Specifically, when the actual level is lower than the historical average level, the driving style is adjusted towards an aggressive direction. When the actual level is higher than the historical average level, the driving style is adjusted towards a more moderate direction. When the actual level is equal to the historical average level, the current driving style remains unchanged.

[0103] Driving style can be adjusted by modifying one or more logic-defined calibration parameters in the current autonomous driving mode. For example, depending on whether the adjustment direction is aggressive, moderate, or unchanged, the overtaking logic, speed logic, acceleration logic, and overtaking / lane-changing logic can all be adjusted in the direction of aggressive, moderate, or unchanged.

[0104] In one embodiment, in a commuting scenario, the strategy for adjusting the algorithm is to make the time taken to complete part of the current journey as close as possible to the historical average time taken to complete that part, derived from the historical traffic information.

[0105] In one embodiment, in a comfort-first scenario, the strategy for adjusting the algorithm is to avoid aggressive driving strategies, use gentler overtaking and lane-changing logic, maintain linear acceleration changes, and avoid entering uncomfortable acceleration ranges.

[0106] In one embodiment, in a time-priority scenario, the strategy for adjusting the algorithm is as follows: allowing a more aggressive driving style, more aggressive overtaking and lane-changing logic, driving at a speed as close as possible to the speed limit of the current lane, and allowing acceleration to enter a range that exceeds the comfort threshold but is less than the safety threshold.

[0107] When actual performance is below historical averages in time-priority and commuter modes, it is especially important to adjust the driving style towards a more aggressive approach to ensure that the journey can reach the destination within the expected timeframe.

[0108] To achieve a more aggressive driving style, one can change lanes or overtake based on the current traffic conditions. Figure 4 An exemplary process 400 for adjusting driving style is illustrated schematically. This process 400 can be performed in the AD control unit 40.

[0109] See Figure 4 In box 402, autonomous vehicles perform autonomous driving in commuter mode or time-priority mode.

[0110] In box 404, it is determined whether the actual performance level under the current autonomous driving mode is lower than the historical average. For example, this determination can be made by checking whether the time taken to reach the current location exceeds the average time based on historical data.

[0111] If it is determined in box 404 that the actual level is not lower than the historical average level (i.e., the actual level is greater than or equal to the historical average level), return to box 402 and continue the current autonomous driving.

[0112] If the actual level is determined to be lower than the historical average in box 404, proceed to box 406.

[0113] In box 406, execute the speed-maintaining logic: if there are no vehicles ahead, maintain the vehicle speed at a predetermined percentage of the current road speed limit (e.g., 90% of the current road speed limit). If there are vehicles ahead, proceed to box 408.

[0114] In box 408, the following logic is executed: Maintain following while the speed of the vehicle in front is greater than or equal to a predetermined percentage of the current road speed limit (e.g., 90% of the current road speed limit). Proceed to box 410 when the speed of the vehicle in front is less than that predetermined percentage of the current road speed limit.

[0115] In box 410, overtaking or lane changing is performed based on traffic regulations and the current traffic scenario.

[0116] When it is determined in box 410 that an overtaking maneuver is to be performed, proceed to box 412.

[0117] In box 412, the overtaking logic is executed: when the overtaking success rate is greater than or equal to a predetermined overtaking success rate threshold (e.g., 80%), overtaking is executed; when the overtaking success rate is less than the predetermined overtaking success rate threshold, the overtaking opportunity is waited for, that is, the overtaking is executed when the overtaking success rate is greater than or equal to 80%.

[0118] After overtaking, proceed to box 414.

[0119] In box 414, the acceleration logic is executed: allowing acceleration (longitudinal and lateral acceleration) to enter the range that exceeds the comfort threshold but is less than the safety threshold.

[0120] After the acceleration logic is executed, the process returns to block 406 to execute the speed maintenance logic, and then repeats the above loop until the AD control unit 40 makes a decision to end the adjustment process.

[0121] If a lane change is determined to be performed in box 410, proceed to box 416.

[0122] In box 416, the lane-changing logic is executed: when the lane-changing success rate is greater than or equal to a predetermined lane-changing success rate threshold (e.g., 80%), the lane-changing is executed; when the lane-changing success rate is less than the predetermined lane-changing success rate threshold, the lane-changing opportunity is waited for, that is, the lane-changing is executed when the lane-changing success rate is greater than or equal to the predetermined lane-changing success rate threshold.

[0123] After changing lanes, proceed to box 418.

[0124] In box 418, the acceleration logic is executed: allowing acceleration (longitudinal and lateral acceleration) to enter the range that exceeds the comfort threshold but is less than the safety threshold.

[0125] After the acceleration logic is executed, the process returns to block 406 to execute the speed maintenance logic, and then repeats the above loop until the AD control unit 40 makes a decision to end the adjustment process.

[0126] Furthermore, the AD control unit 40 can be configured with control logic such that in an emergency, when a lane change or overtaking is required, but the success rate of the lane change or overtaking does not meet the aforementioned threshold, but is between the passing value and the aforementioned threshold (e.g., between 60% and 80%), the AD control unit 40 still allows the lane change or overtaking to be performed. Moreover, the number of such "exceptions" is limited to a predetermined threshold (e.g., 10% of the total number of lane changes and overtakings during the entire adjustment process).

[0127] It is understood that the above parameter values, thresholds, and percentages (e.g., 90% of the current road speed limit, 80% overtaking success rate, 80% lane change success rate, and 10% of the total number of attempts) are all adjustable. The above values ​​are merely examples, and the present invention is not limited thereto.

[0128] Additionally, the following situation may occur: after receiving a user's request, the autonomous vehicle informs the user of the pick-up location and then proceeds to that location. The time it takes for the autonomous vehicle to reach the location and pick up the user may exceed the originally planned time to complete the requested trip. In this case, the driving style can be adjusted towards a more aggressive approach.

[0129] In block 310, the adjustment module 44 adjusts the autonomous driving behavior in a minimum adjustment unit based on user input commands and / or user biofeedback information.

[0130] "Minimum adjustment unit" refers to the smallest unit for adjusting the calibration parameters of the multiple logic components. For example, when adjusting the speed logic, if the minimum adjustment unit for the speed logic is set to 5%, then each speed adjustment should be ±5% of the current vehicle speed.

[0131] In one embodiment, the user inputs commands such as "shorten time," "improve comfort," and "reduce energy consumption" through the human-machine interface 10. The adjustment module makes corresponding adjustments to driving behavior based on the received user input commands. For example, upon receiving a user command to "shorten time," the adjustment module can increase the speed in the smallest adjustment unit (e.g., 5%). If the user continues to input the "shorten time" command, the speed is increased in increments of the smallest adjustment unit each time. Of course, the speed adjustment should not exceed the corresponding speed limit threshold.

[0132] In another embodiment, based on user biofeedback information detected by bio-information sensors, the user's condition is determined, such as the user having a fever, the user reading, etc. The adjustment module then makes corresponding adjustments to the driving behavior based on the determined user condition. For example, if it is determined that the user is reading, the adjustment module can reduce the acceleration by a minimum adjustment unit (e.g., 5%) to make the vehicle enter a smoother driving condition suitable for reading.

[0133] Figure 5 A flowchart of an automatic driving control method according to an embodiment of the present invention is shown. This method can be executed by the AD control unit 40 or the AD control system 100 described above; therefore, the related descriptions above also apply here.

[0134] See Figure 5 In step S510, the user of the autonomous vehicle obtains the current trip information of the user and the historical traffic information related to the current trip.

[0135] In step S520, the destination of the trip is determined based on the trip information.

[0136] In step S530, based on the trip destination, an autonomous driving mode matching the trip destination is determined from a plurality of pre-set autonomous driving modes, including time priority mode, comfort priority mode, commuting mode and economy mode.

[0137] In step S540, during the autonomous driving process of the autonomous vehicle in a determined autonomous driving mode, the time taken to complete part of the current journey is compared with the historical average time taken to complete that part based on the historical traffic information.

[0138] In step S550, during the autonomous driving process, the driving style in the current autonomous driving mode is dynamically adjusted based on the comparison results so that the time taken to complete part of the current trip is as close as possible to the historical average time.

[0139] The present invention also provides a machine-readable storage medium storing executable instructions that, when executed, cause a processor to perform the above-described automatic driving control method 500.

[0140] It is understood that all the modules described above can be implemented in various ways. These modules can be implemented as hardware, software, or a combination thereof. Furthermore, any of these modules can be further functionally divided into sub-modules or combined together.

[0141] It is understood that processors can be implemented using electronic hardware, computer software, or any combination thereof. Whether these processors are implemented as hardware or software will depend on the specific application and the overall design constraints imposed on the system. As an example, the processor, any portion of the processor, or any combination of processors provided in this invention can be implemented as a microprocessor, microcontroller, digital signal processor (DSP), field-programmable gate array (FPGA), programmable logic device (PLD), state machine, gate logic, discrete hardware circuitry, and other suitable processing units configured to perform the various functions described in this disclosure. The functionality of the processor, any portion of the processor, or any combination of processors provided in this invention can be implemented as software executed by a microprocessor, microcontroller, DSP, or other suitable platform.

[0142] It is understood that software should be broadly considered as representing instructions, instruction sets, code, code segments, program code, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, running threads, procedures, functions, etc. Software may reside on a computer-readable medium. Computer-readable media may include, for example, memory, which may be, for example, magnetic storage devices (e.g., hard disks, floppy disks, magnetic stripes), optical disks, smart cards, flash memory devices, random access memory (RAM), read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), registers, or removable disks. Although memory is shown as separate from the processor in several aspects set forth in this disclosure, memory may also reside within the processor (e.g., in caches or registers).

[0143] While some embodiments have been described above, these embodiments are given by way of example only and are not intended to limit the scope of the invention. The appended claims and their equivalents are intended to cover all modifications, substitutions, and alterations made within the scope and spirit of the invention.

Claims

1. A control unit for an autonomous vehicle, comprising: The acquisition module is configured to acquire the user's current trip information and related historical traffic information for the autonomous vehicle. The determination module is configured to select an AD mode suitable for the current trip from multiple predefined autonomous driving (AD) modes, including time priority mode, comfort priority mode, commuting mode and economy mode. Each of the multiple predefined AD modes includes a combination of multiple logic constraints, including overtaking logic, lane changing logic, speed logic and acceleration logic. The overtaking logic includes an overtaking success rate threshold expressed as a percentage of overtaking success rate, and the lane changing logic includes a lane changing success rate threshold expressed as a percentage of lane changing success rate. The comparison module is configured to, during autonomous driving in a selected autonomous driving mode, compare the time taken to complete a portion of the current journey with the historical average time taken to complete that portion, derived from the historical traffic information; and The adjustment module is configured to dynamically adjust the driving style of the autonomous vehicle based on comparison results by adjusting one or more threshold parameters among the overtaking logic, lane changing logic, speed logic, and acceleration logic. This makes the driving style more aggressive or more moderate relative to the driving style defined by a combination of overtaking logic, lane changing logic, speed logic, and acceleration logic, in order to minimize the difference between the time required for the autonomous vehicle to complete part of the current journey in the selected AD mode and the historical average time.

2. The control unit as claimed in claim 1, wherein, The vehicle speed logic includes the speed limit of the current road as a calibration parameter; and The acceleration logic includes acceleration thresholds as calibration parameters, which include safety thresholds and comfort thresholds.

3. The control unit as claimed in claim 2, wherein, The multiple autonomous driving modes are scalable, and the logical terms used to define each autonomous driving mode are scalable and / or adjustable.

4. The control unit as claimed in claim 2, wherein, In time-priority mode, the acceleration logic allows the vehicle acceleration to enter a range exceeding the comfort threshold but falling below the safety threshold; and In comfort-first mode and commuter mode, the acceleration logic limits the vehicle acceleration to no more than the comfort threshold.

5. The control unit as claimed in claim 2, wherein, Dynamically adjusting the autonomous driving style includes: adjusting the driving style towards a more aggressive direction by executing the overtaking logic and / or the lane-changing logic; The overtaking logic includes: performing an overtaking maneuver when the overtaking success rate is greater than or equal to a predetermined overtaking success rate threshold; allowing the vehicle's acceleration to enter a range exceeding a comfort threshold but less than a safety threshold; and limiting the vehicle speed to remain within a predetermined range of the current lane's speed limit. The lane change logic includes: performing a lane change when the lane change success rate is greater than or equal to a predetermined lane change success rate threshold, allowing the vehicle acceleration to enter a range exceeding the comfort threshold but less than the safety threshold, and limiting the vehicle speed to remain within a predetermined range of the current lane speed limit.

6. The control unit as claimed in claim 2, wherein, The adjustment module is also configured to: During autonomous driving in a defined autonomous driving mode, the driving behavior in the current autonomous driving mode is adjusted by a minimum adjustment unit based on user requests and / or the user's biometric feedback information. The minimum adjustment unit refers to the smallest unit that adjusts the calibration parameters of the multiple logics.

7. An autonomous vehicle, comprising: The human-computer interaction interface is configured to receive trip information of the current trip of the user in the autonomous vehicle; The communication unit is configured to receive historical traffic information related to the current journey; as well as The autonomous driving control unit includes: The acquisition module is configured to acquire the trip information and the historical traffic information; The determination module is configured to select an AD mode suitable for the current trip from multiple predefined autonomous driving (AD) modes, including time priority mode, comfort priority mode, commuting mode and economy mode. Each of the multiple predefined AD modes includes a combination of multiple logic constraints, including overtaking logic, lane changing logic, speed logic and acceleration logic. The overtaking logic includes an overtaking success rate threshold expressed as a percentage of overtaking success rate, and the lane changing logic includes a lane changing success rate threshold expressed as a percentage of lane changing success rate. The comparison module is configured to, during autonomous driving in a selected autonomous driving mode, compare the time taken to complete a portion of the current journey with the historical average time taken to complete that portion, derived from the historical traffic information; and The adjustment module is configured to dynamically adjust the driving style of the autonomous vehicle based on comparison results by adjusting one or more threshold parameters among the overtaking logic, lane changing logic, speed logic, and acceleration logic. This makes the driving style more aggressive or more moderate relative to the driving style defined by a combination of overtaking logic, lane changing logic, speed logic, and acceleration logic, in order to minimize the difference between the time required for the autonomous vehicle to complete part of the current journey in the selected AD mode and the historical average time.

8. The autonomous vehicle of claim 7, further comprising a sensor unit configured to collect information about environmental conditions, vehicle conditions, and user conditions, wherein, The adjustment module is also configured to dynamically adjust the driving style of the autonomous vehicle based on the collected information.

9. An automatic driving control method, comprising: Obtain trip information for the current trip of the user of the autonomous vehicle, as well as historical traffic information related to the current trip; Select the appropriate AD mode for the current trip from a plurality of predefined autonomous driving (AD) modes, including time priority mode, comfort priority mode, commuter mode and economy mode. Each of the plurality of predefined AD modes contains a combination of multiple logic constraints, including overtaking logic, lane changing logic, speed logic and acceleration logic. The overtaking logic includes an overtaking success rate threshold expressed as an overtaking success rate percentage, and the lane changing logic includes a lane changing success rate threshold expressed as a lane changing success rate percentage. During autonomous driving in the selected autonomous driving mode, the time taken to complete the current portion of the journey is compared with the historical average time taken to complete that portion, derived from the historical traffic information; and Based on the comparison results, the driving style of the autonomous vehicle is dynamically adjusted by regulating one or more threshold parameters among the overtaking logic, lane changing logic, speed logic, and acceleration logic. This makes the driving style more aggressive or more moderate compared to the driving style defined by a combination of overtaking logic, lane changing logic, speed logic, and acceleration logic, in order to minimize the difference between the time required for the autonomous vehicle to complete part of the current journey in the selected AD mode and the historical average time.

10. A machine-readable storage medium having instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform the method of claim 9.

Images