System for recording event data for autonomous vehicles

Abstract

A system for event data recording for an autonomous vehicle is provided. [Solution] The present invention provides an operating method of an EDR system suitable for appropriately identifying the cause of a vehicle accident. A subsystem of an autonomous driving control system determines whether an event that satisfies a preset condition has occurred, and when an event occurrence is detected, transmits a trigger signal to the EDR system to trigger the recording of data items related to the event. The EDR system records data items that are useful for reconstructing a map of the external environment surrounding the autonomous driving vehicle at the time of the event occurrence and for reconstructing the vehicle's internal environment.

Description

[Technical Field]

[0001] The present invention relates to a system for recording event data in an autonomous vehicle. [Background technology]

[0002] The material described in this section merely provides background information regarding the present invention and may not constitute prior art.

[0003] An Event Data Recorder (EDR) is a data recording device that can record, save, and extract driving and collision information for a certain period of time before and after a crash or accident that meets certain conditions while the vehicle is in operation. It is generally built into the airbag control module (ACU) of a vehicle.

[0004] The EDR records items such as vehicle speed, braking status, engine RPM, accelerator pedal, throttle valve operation status, steering wheel angle, seat belt status, crash severity (Delta-V or Acceleration), tire pressure, gear position, and airbag deployment data.

[0005] Autonomous vehicles operate by having the autonomous driving system recognize the environment based on information collected from inside and outside the vehicle, determine (decide) actions depending on the situation, and control actuators, etc. Considering the possibility that an error occurring in the recognition-decision-control process in an autonomous vehicle could lead to an accident, the recording conditions and recording items of EDR systems used in general vehicles may not be suitable for properly investigating the cause of an accident involving an autonomous vehicle. Summary of the Invention [Problem to be solved by the invention]

[0006] An object of the present invention is to provide an operating method for an EDR system suitable for properly investigating the cause of an accident involving an autonomous vehicle. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, one aspect of the present invention provides a method for a vehicle (i.e., an autonomous vehicle) operating fully or partially in an autonomous driving mode to collect and record event data, the method comprising the steps of receiving a trigger signal from a subsystem of an autonomous driving system indicating the occurrence of one of a plurality of predefined events; collecting event data including at least data related to the recognition-judgment-control process of the autonomous driving system before and after the occurrence of the event; and recording the event data in an internal storage and uploading the event data to a remote server communicatively connected to the vehicle.

[0008] In one embodiment, the event data further includes at least one of camera images inside / outside the autonomous vehicle, occupant recognition data for the autonomous vehicle, software version information for an ECU installed in the autonomous vehicle, and information related to a recently used V2X message. In one embodiment, the event data further includes object recognition information (e.g., object position, class, relative speed, etc.) suitable for reconstructing an external environment map surrounding the autonomous vehicle before and after the occurrence of the event. In one embodiment, data items or recording periods constituting the event data are different for at least some of the multiple events.

[0009] In one embodiment, receiving the trigger signal includes receiving a trigger signal from a subsystem that performs autonomous navigation functions based at least in part on lane perception information, the trigger signal indicating that the autonomous vehicle has left its lane. In one embodiment, receiving the trigger signal includes receiving a trigger signal from a subsystem that performs autonomous navigation functions based at least in part on a time to collision (TTC), the trigger signal indicating that a collision cannot be avoided via braking based on the vehicle's current speed. In one embodiment, receiving the trigger signal includes receiving a trigger signal from a subsystem of the autonomous navigation system indicating that an emergency maneuver (EM) or a minimal risk maneuver (MRM) has been initiated. In one embodiment, receiving the trigger signal includes receiving a trigger signal from a subsystem of the autonomous navigation system indicating that an intrusion into a vehicle's internal network has been detected.

[0010] In one embodiment, the method further includes a step of extending the recording period while additionally recording the type of event that occurred and its occurrence time when a new trigger signal indicating the occurrence of a new event is received before the end of the recording period of the event data.

[0011] In order to achieve the above-mentioned object, one aspect of the present invention provides a vehicle system including an autonomous driving system that controls a vehicle to operate fully or partially in an autonomous driving mode, a wireless communication system that enables communication between the vehicle and an external system, and an EDR system that collects and manages event data, wherein the EDR system is configured to (1) receive a trigger signal from a subsystem of the autonomous driving system that indicates the occurrence of one of a plurality of predefined events, (2) collect event data that includes at least data related to the recognition-judgment-control process of the autonomous driving system before and after the event occurrence, and (3) record the event data in an internal storage and upload the event data to a remote server via the wireless communication system. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a functional block diagram showing a vehicle according to an embodiment of the present invention. [Figure 2a] FIG. 1 is a conceptual diagram illustrating an example architecture in which an EDR system may be deployed in an autonomous vehicle. [Figure 2b] FIG. 1 is a conceptual diagram illustrating an example architecture in which an EDR system may be deployed in an autonomous vehicle. [Figure 2c] FIG. 1 is a conceptual diagram illustrating an example architecture in which an EDR system may be deployed in an autonomous vehicle. [Figure 3] 1 is a conceptual diagram illustrating the change in parameter D depending on the recognized lane geometry and the presence or absence of lane departure. [Figure 4] 1 is a flowchart illustrating a method for an LKAS system to determine the occurrence of an event that triggers an EDR system, according to one embodiment of the present invention. [Figure 5] 1 is a flowchart illustrating a method for determining an event occurrence that triggers an EDR system on a TTC basis, according to one embodiment of the present invention. [Figure 6a] FIG. 1 illustrates an exemplary scenario in which an emergency activation (EM) occurs in an autonomous driving system. [Figure 6b] FIG. 1 illustrates an exemplary scenario in which an emergency activation (EM) occurs in an autonomous driving system. [Figure 6c] FIG. 1 illustrates an exemplary scenario in which an emergency activation (EM) occurs in an autonomous driving system. [Figure 6d] FIG. 1 illustrates an exemplary scenario in which an emergency activation (EM) occurs in an autonomous driving system. [Figure 7] 1 is a flowchart illustrating a method for triggering recording of an EDR system according to initiation of a minimal risk activation (MRM), according to one embodiment of the present invention. [Figure 8] FIG. 1 is a diagram illustrating an example of an external environment map surrounding an autonomous vehicle. [Figure 9] FIG. 2 illustrates an example of autonomous driving data stored by an EDR system, according to one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, specific examples of embodiments of the present invention will be described in detail with reference to the drawings. When adding reference numerals to components in each drawing, it should be noted that the same components will be assigned the same reference numerals as much as possible even if they appear in different drawings. In describing the present invention, if it is determined that a detailed description of related known configurations or functions would obscure the gist of the present invention, such detailed description will be omitted.

[0014] Furthermore, terms such as "first," "second," "A," "B," "(a)," and "(b)" may be used to describe components of the present invention. These terms are used to distinguish the component from other components and do not limit the nature, order, or sequence of the components. Throughout this specification, when a part "includes" or "has" a certain component, this does not mean that it excludes other components, but that it may further include other components, unless otherwise specified. Furthermore, terms such as "unit," "module," and the like used in this specification refer to a unit that processes at least one function or operation, and are implemented in hardware, software, or a combination of hardware and software.

[0015] FIG. 1 is a functional block diagram showing a vehicle according to an embodiment of the present invention.

[0016] The vehicle is configured to operate fully or partially in an autonomous driving mode and is therefore referred to as an “autonomous vehicle.” For example, the autonomous driving system 120 receives information from the sensor system 110 and performs one or more control processes (e.g., setting the steering to avoid a detected obstacle) based on the received information in an automated manner.

[0017] Vehicles may be fully autonomous or partially autonomous. In partially autonomous vehicles, some functions are manually controlled by the driver, either temporarily or permanently. Furthermore, (partially or fully) autonomous vehicles may be configured to be switchable between a fully manual mode of operation and a partially and / or fully autonomous mode of operation.

[0018] The vehicle includes various functional systems, such as a sensor system 110, an autonomous driving system 120, a wireless communication system 130, and an intrusion detection system 140. The vehicle may include more or fewer (sub)systems, each of which may include multiple components. Furthermore, the (sub)systems of the vehicle may be interconnected. Thus, one or more of the above-mentioned functions of the vehicle may be separated into additional functional or physical components or combined into fewer functional or physical components.

[0019] The sensor system 110 includes one or more sensors configured to detect information about the environment surrounding the vehicle. For example, the sensor system 110 may include a global positioning system (GPS), a radar unit, a lidar unit, a camera, an inertial measurement unit (IMU), a microphone, etc. The sensor system 110 may further include sensors configured to monitor internal systems of the vehicle (e.g., a fuel gauge, engine oil temperature, wheel speed sensors, etc.).

[0020] The autonomous driving system 120 is configured to control the operation of a vehicle and its components. The autonomous driving system 120 includes a perception subsystem 121, a decision subsystem 122, and a control subsystem 123.

[0021] The perception subsystem 121 is configured to process and analyze data (e.g., images, video, depth data, etc.) captured by the sensor system to identify objects and / or features in the vehicle's environment, including lane information, traffic signals, other vehicles, pedestrians, obstacles, etc. The perception subsystem 121 uses sensor fusion algorithms, object recognition algorithms, video tracking, or other computer vision techniques. The sensor fusion algorithms provide various assessments based on the sensor system data. Assessments may include assessments of individual objects and / or features in the vehicle's environment, assessments of specific situations, and / or assessments of possible impacts on navigation based on the specific situations.

[0022] The judgment subsystem 122 judges actions (such as lane keeping, lane change, left / right turns, overtaking slow vehicles, U-turns, emergency stops, stopping on the shoulder, parking, etc.) for each driving situation (scenario) based on the various evaluations of the recognition subsystem 121. The judgment subsystem 122 also plans a route to the destination and a route to avoid obstacles.

[0023] The control subsystem 123 controls the movement of the vehicle by controlling actuators necessary for the vehicle to operate in accordance with the driving situation-specific behavior determined by the judgment subsystem 122. For example, the control subsystem 123 controls a steering unit configured to adjust the steering of the vehicle. As another example, the control subsystem 123 controls a throttle unit that controls the operating speed of the engine and / or motor, thereby controlling the speed of the vehicle. As yet another example, the control subsystem 123 controls a braking unit configured to decelerate the vehicle.

[0024] The subsystems (121, 122, 123) of the autonomous driving system 120 cooperate with each other to support various autonomous driving functions or Advanced Driver Assistance System (ADAS) functions, such as Adaptive Cruise Control (ACC), Lane Keeping Assist system (LKAS), Forward Collision-Avoidance Assist (FCA), Autonomous Emergency Braking (AEB), etc. The subsystems (121, 122, 123) of the autonomous driving system 120 are implemented as multiple electronic control units (ECUs) or computer systems in a vehicle that perform one or more autonomous driving functions.

[0025] The wireless communication system 130 enables communication between the vehicle and an external system (e.g., another vehicle or a server). For example, the wireless communication system 130 wirelessly communicates with one or more devices directly or via a communication network. The wireless communication system 130 can use one or more of a variety of wireless communication technologies, such as cellular communication (e.g., GSM, CDMA, LTE, 5G, etc.), IEEE 802.11 communication protocols (e.g., Wi-Fi, Bluetooth, ZigBee, etc.), or DRSC.

[0026] An Intrusion Detection System (IDS) 140 is configured to detect and respond to security threats to the vehicle's internal network.

[0027] The autonomous driving system 120, its subsystems (121, 122, 123), as well as other subsystems not shown in Figure 1, generate data indicating whether one or more autonomous driving features are currently active. For example, the autonomous driving system 120 generates data indicating whether an adaptive cruise control (ACC) feature is currently active. As another example, the autonomous driving system 120 generates data indicating whether the vehicle's driving is currently fully automated rather than manually controlled.

[0028] The vehicle additionally includes an EDR system 150 configured to receive data from various (sub)systems within the vehicle, including the sensor system 110. One or more (sub)systems provide data to the EDR system 150 via a data bus (e.g., a CAN bus, an Ethernet bus, etc.). The EDR system 150 collects data and / or analog signals provided or shared by each (sub)system from the data bus in real time. The EDR system 150 periodically samples data from the (sub)systems. The EDR system 150 generates a timestamp for each sampled data point.

[0029] One or more (sub)systems detect the occurrence of one or more predefined events and provide a trigger signal to the EDR system 150 to notify the occurrence of the event, thus triggering the EDR system to write data related to the event (hereinafter referred to as "EDR data") to non-volatile memory. Each trigger signal includes a unique identifier that can uniquely identify the associated event or trigger condition. For at least some trigger signals, the EDR system applies different recording data items and / or recording periods.

[0030] The vehicles are configured to upload the EDR data to a remote server (not shown) that collects and manages EDR data from multiple vehicles via wireless communication system 130. The remote server may be operated by the vehicle manufacturer or by a service provider that provides EDR data management services.

[0031] 2a, 2b, and 2c are conceptual diagrams illustrating an example architecture in which an EDR system may be deployed in an autonomous vehicle.

[0032] As shown in Figure 2a, an autonomous vehicle incorporates an EDR system specialized for the autonomous vehicle as a sub-module within the main controller (integrated ECU) of the autonomous vehicle. The EDR system can receive trigger signals notifying of event occurrences not only from the main controller but also from an airbag control module (ACM), an intrusion detection system (IDS), or other devices located outside the main controller. Furthermore, the autonomous vehicle may also include an EDR system that operates similarly to a conventional typical EDR system incorporated as a sub-module within the airbag controller (ACU).

[0033] As shown in Figure 2b, the EDR system in an autonomous vehicle may be incorporated as a sub-module in the airbag controller (ACU), similar to a typical conventional EDR system. The EDR system may receive trigger signals notifying of an event occurrence not only from the airbag controller (ACU) but also from the main controller of the autonomous driving system, an IDS system, or the like, which are located outside the airbag controller (ACU).

[0034] As shown in Figure 2c, an autonomous vehicle may be equipped with a separate electronic control unit (ECU) that performs the EDR function. The EDR system may receive a trigger signal from an airbag controller (ACU), the main controller of the autonomous driving system, an IDS system, or other device on the vehicle network, indicating the occurrence of an event.

[0035] Diversification of EDR trigger conditions Conventional EDR systems are configured to record predefined data items upon receiving an event trigger signal from an airbag control unit (ACU). Such an event is, in particular, a traffic collision. A collision is detected, for example, when the deployment of an irreversible safety device, such as an airbag or pretensioner, is triggered. A collision is also detected when acceleration or deceleration exceeding a predefined threshold (e.g., a speed change of 8 km / h or more within 150 ms) occurs. Such trigger conditions used for general vehicles may not be suitable for properly determining the cause of an accident in an autonomous vehicle. The present invention proposes various event trigger conditions suitable for autonomous vehicles and data items suitable for reconstructing the environment inside and outside the vehicle surrounding the event. According to the present invention, a subsystem of an autonomous driving control system determines whether an event that meets a predefined event condition has occurred and transmits an event trigger signal to the EDR system if an event is detected.

[0036] (1) Leaving the lane Among ADAS (Advance Driver Assistance System) technologies, when the Lane Keeping Assist System (LKAS) is activated, lane recognition is performed correctly, but when it is determined that the vehicle has deviated significantly from the lane, the EDR system will be triggered to record.

[0037] The computer vision system analyzes image data output from the camera sensor to recognize lanes and provides lane recognition information to the lane keeping system. Lane recognition information includes lane geometry parameters such as the distance to lane markings, heading angle, and curvature. Lane recognition information is provided in the form of a road equation in the form of a cubic function (y=Ax^3+Bx^2+Cx+D) that represents the relative movement between the vehicle and lane. Here, A represents the curvature rate, B represents the curvature, C represents the heading angle, and D represents the lateral offset. The lane recognition information also includes a quality signal that indicates the reliability of lane geometry measurement. The quality signal is classified into four levels: Very Low Quality, Low Quality, High Quality, and Very High Quality.

[0038] 3 is a conceptual diagram illustrating the change in parameter D (=0, 0.5) depending on the recognized lane geometry and the presence or absence of lane departure. According to one embodiment of the present invention, the magnitude of parameter D, which indicates the lateral distance between the vehicle and the lane and is included in the lane perception information, is used to determine the degree of lane departure, and a trigger signal is generated to trigger recording by the EDR system when excessive lane departure is detected.

[0039] FIG. 4 is a flowchart illustrating a method for an LKAS system to determine the occurrence of an event that triggers an EDR system, according to one embodiment of the present invention.

[0040] The LKAS system receives lane perception information from a computer vision system while driving (S410). The LKAS system determines whether a quality signal indicating the reliability of lane geometry measurement included in the lane perception information is equal to or greater than a preset level (e.g., "High Quality") (S420).

[0041] If the quality signal is equal to or higher than a preset level (e.g., "High Quality") ("Yes" in S420), the LKAS system determines whether a parameter D, which indicates the lateral distance between the vehicle and the lane included in the lane perception information, exceeds a preset threshold (threshold, thr) (S430). If parameter D exceeds the preset threshold ("Yes" in S430), the LKAS system generates a trigger signal to trigger recording by the EDR system (S450).

[0042] If the quality signal is below a preset level (e.g., "High Quality") ("No" in S420), the LKAS system performs sensor fusion, i.e., determines whether the vehicle has departed from its lane using data acquired from various sensors (e.g., GPS, camera, radar, and lidar sensors) (S440). For example, the LKAS system may map the vehicle's position information on a precision map, use data acquired from a camera sensor for the vehicle's surround view monitor (SVM), or determine a virtual lane based on the positions of other vehicles recognized using a radar or lidar sensor, and then determine whether the vehicle has departed from its lane based on the virtual lane. When the LKAS system detects a lane departure based on sensor fusion ("Yes" in S440), it generates a trigger signal to trigger recording by the EDR system (S450).

[0043] (2) Time to Collision (TTC) Time to Collision (TTC) is one of the most widely used metrics for determining the likelihood of a collision with an obstacle (vehicle or pedestrian) in front or behind the vehicle. TTC is used not only by Forward Collision-Avoidance Assist (FCA) systems, but also to measure the risk of a collision with obstacles around the vehicle. For example, when there is a close-range cut-in vehicle, TTC is the criterion for determining whether the vehicle should accelerate or decelerate.

[0044] TTC is generally defined as "relative distance / relative speed," and vehicle acceleration may be considered to more accurately measure the risk of collision. Autonomous driving systems calculate TTC by estimating the relative distance and relative speed of obstacles ahead using radar sensors, camera sensors, lidar sensors, ultrasonic sensors, or a combination of these data fusion techniques. Alternatively, more accurate TTC calculations can be performed using the position and speed of surrounding vehicles obtained through V2V communication. Direct acquisition of surrounding vehicle steering angles and braking status values ​​through V2V communication allows prediction of surrounding vehicle movements much earlier than environmental sensors can. Furthermore, V2V communication can provide information about surrounding vehicles even when visibility is poor.

[0045] The primary purpose of FCA and similar collision mitigation systems is to mitigate the damage caused by a collision. In other words, the basic concept is to mitigate damage by reducing collision energy as much as possible through pre-crash braking even if a collision does occur. When traveling at low speeds, emergency braking can be applied immediately before a collision, bringing the vehicle to a halt before an accident occurs. However, at medium speeds or above, where inertia is relatively high, it may be difficult to avoid a collision even with normal FCA operation. However, because emergency braking is applied immediately before a collision, a significant portion of the velocity energy is already offset in the actual collision situation, thereby mitigating the damage caused by the accident.

[0046] According to one embodiment of the present invention, if the TTC is very short or if it is determined that a collision cannot be avoided even if emergency braking is performed at the current speed standard, recording of the EDR system is triggered before an actual collision occurs.

[0047] FIG. 5 is a flowchart illustrating a method for determining the occurrence of an event that triggers an EDR system on a TTC basis, according to one embodiment of the present invention.

[0048] A subsystem of the autonomous driving system (e.g., an FCA or similar collision mitigation system) calculates the TTC (S510) and determines whether the calculated TTC is extremely short (S520). For example, the subsystem determines whether the calculated TTC is shorter than a preset threshold (e.g., 2 seconds).

[0049] If the subsystem determines that the calculated TTC is extremely short (i.e., the calculated TTC is shorter than the set threshold, "Yes" in S520), it will immediately generate a trigger signal to trigger recording in the EDR system (S550), and at the same time, the subsystem will control the braking system to perform emergency braking.

[0050] If the calculated TTC is not shorter than the preset threshold ("NO" in S520), the subsystem determines whether a collision cannot be avoided by braking based on the vehicle's current speed (S530). For example, the subsystem may determine that a collision cannot be avoided if the deceleration required to avoid the collision exceeds a predetermined maximum deceleration (critical deceleration) of the vehicle. Alternatively, the subsystem may determine that a collision cannot be avoided if it determines that the vehicle's current speed exceeds a critical speed. If the subsystem determines that a collision cannot be avoided by braking based on the vehicle's current speed ("YES" in S530), it generates a trigger signal to trigger recording in the EDR system (S550).

[0051] If the deceleration required to avoid a collision does not exceed the vehicle's predetermined maximum deceleration (limit deceleration) ("No" in S530), the subsystem repeatedly performs a comparison between the required deceleration and the vehicle's limit deceleration (corresponding to the vehicle's speed after braking, etc.) until the next TTC is determined (S540).

[0052] (3) Situations in which an Emergency Maneuver (EM) was activated An Emergency Maneuver (EM) is an action taken by an autonomous driving system in the event of a sudden, unexpected event that puts the vehicle at risk of colliding with another object, with the aim of avoiding or mitigating a collision.

[0053] The autonomous driving system senses whether a sudden, unexpected event puts the vehicle in imminent danger of collision, for example, with a road user in front of or to the side of the vehicle. If there is too little time to safely return control to the driver, emergency maneuver (EM) is automatically initiated. To avoid or mitigate the imminent collision, emergency maneuver (EM) performs protective deceleration up to the vehicle's maximum braking capacity or performs automatic avoidance maneuver. When emergency maneuver (EM) begins, the autonomous driving system generates a trigger signal that triggers recording in the EDR system.

[0054] 6a-6d illustrate some example scenarios in which an emergency activation (EM) occurs in an autonomous driving system.

[0055] - Distance control not possible (longitudinal control not possible, see Figure 6a): If a collision risk is predicted during lane keeping and distance control, the Forward Collision-Avoidance Assist (FCA) system's emergency braking function may be activated. However, if the preceding vehicle suddenly brakes or comes to an emergency stop due to a rear-end collision and a collision risk is predicted between the vehicle and the preceding vehicle, emergency braking will be performed up to the vehicle's maximum braking performance in a shorter time than the FCA system's emergency braking.

[0056] - Lane keeping control not possible (lateral control not possible, see Figure 6b): If the vehicle is predicted to leave the current lane and collide with a vehicle in a nearby lane due to a defect in the Motor-Driven Power Steering (MDPS), etc., emergency braking will be performed.

[0057] - Engine stop while driving (longitudinal and lateral control not possible, see Figure 6c): If the engine stops during lane keeping and distance keeping control, emergency braking will be performed immediately.

[0058] - Dangerous situation after avoiding a forward obstacle (see Figure 6d): If the vehicle's behavior becomes abnormal after the avoidance of a forward obstacle is initiated (for example, if the vehicle leaves its lane or is unable to return to the road), emergency braking is immediately performed.

[0059] (4) Situations in which MRM (Minimum Risk Maneuver) was activated If an autonomous vehicle malfunctions, such as a faulty autonomous driving sensor, if the Intrusion Detection System (IDS) detects an intrusion into the vehicle's internal network, or if manual control from the driver is required for other reasons, the autonomous driving system will request the driver to take over control.

[0060] Minimal Risk Maneuver (MRM) refers to a procedure that is automatically performed by an autonomous driving system with the aim of minimizing traffic risks, for example if the driver does not respond to a transition demand.

[0061] After issuing a transfer request, the autonomous driving system detects whether the driver resumes manual control. If the driver does not resume manual control within a certain time, MRM is initiated immediately. MRM ends when the vehicle detects that the driver has taken over manual control of the vehicle. MRM automatically takes one of the following actions: (a) 4 m / s 2 (b) Slowing the vehicle within the lane at the following deceleration rates; and (b) Stopping the vehicle in a lane other than the express lane (for example, a slow lane, an emergency lane, or the side of the road).

[0062] The initiation of an MRM triggers recording in the EDR system. MRM control operates in various ways depending on the cause of the event, and sometimes situations with long event durations occur. Depending on the cause of the MRM initiation, the recording method of the EDR system may also differ.

[0063] In one embodiment, if the MRM is initiated without the driver responding to a transition demand, the EDR system continuously stores information about the autonomous driving system's perception-decision-control process while the MRM is running.

[0064] In one embodiment, when an MRM is initiated due to a fault in an autonomous driving sensor, the ID of the failed sensor and the time of the failure are stored, and recording in the EDR system is activated until the user receives driving control.

[0065] In one embodiment, the threshold of the decision criteria or trigger condition for determining the occurrence of an event that triggers EDR system recording is lowered from the moment MRM starts, thereby increasing sensitivity to events. For example, before MRM starts, EDR system recording is triggered when a sudden acceleration or deceleration indicating a speed change of 8 km / h or more is detected within 150 ms, and while MRM is running, EDR system recording is triggered when a sudden acceleration or deceleration indicating a speed change of 4 km / h or more is detected within 150 ms.

[0066] FIG. 7 is a flow chart illustrating a method for triggering recording in an EDR system by initiating an MRM, according to one embodiment of the present invention.

[0067] When the occurrence of a situation that may cause the start of MRM is detected (S710), the autonomous driving system estimates the duration of MRM control based on the situation that may cause the start of MRM (S720). If the estimated duration is shorter than a preset threshold (S7 2 0 "short"), the autonomous driving system immediately triggers recording of the EDR system (S750).

[0068] If the estimated duration is longer than a preset threshold (S7 2If the determination is affirmative ("long" at S740), the autonomous driving system lowers the threshold of the decision criteria or trigger condition for determining the occurrence of an event that triggers recording of the EDR system (S730). The autonomous driving system then applies the relaxed decision criteria or trigger condition threshold and monitors the occurrence of an event that triggers recording of the EDR system (S740). When the autonomous driving system detects the occurrence of an event that meets the relaxed decision criteria ("Yes" at S740), it triggers recording of the EDR system (S750).

[0069] On the other hand, when various trigger signals are used to trigger recording in an EDR system, a new trigger signal occurs before the EDR system finishes recording data in response to one of the trigger signals. When multiple trigger signals occur consecutively in this way, the EDR system extends the data recording time while preserving the type of event (or trigger signal) that occurred and the time of that event. The trigger signal includes an identifier that uniquely identifies the type of event. In this case, the data items recorded during the extended time period may be the same or fewer than the data items recorded during the time period corresponding to the first trigger signal.

[0070] (5) When a security threat to the vehicle network is detected The vehicle includes an Intrusion Detection System (IDS) configured to detect and respond to security threats to the vehicle's internal network, and the IDS generates a trigger signal that triggers recording by the EDR system when it detects an intrusion into the vehicle's internal network.

[0071] Thus, when an EDR system is configured to receive various trigger signals, the EDR system will apply different recording data items and / or writing periods to at least some of the trigger signals.

[0072] EDR Data Elements Suitable for Autonomous Vehicles Since autonomous vehicles operate by having the autonomous driving system recognize the environment based on information collected from inside and outside the vehicle, determine (decide) actions depending on the situation, and control actuators, etc., if an error occurs during the recognition-decision-control process, it can lead to an accident. Therefore, in order to properly investigate the cause of an autonomous vehicle accident, it is preferable to record and store information about the recognition-decision-control process of the autonomous vehicle.

[0073] The present invention provides EDR data items suitable for determining the cause of an event that occurred in an autonomous vehicle. In particular, these data items are useful for reconstructing a map of the external environment surrounding the autonomous vehicle at the time of the event (as shown in FIG. 8) and reconstructing the vehicle's internal environment.

[0074] EDR data according to an embodiment of the present invention includes software versions, autonomous driving data, camera images inside / outside the vehicle, passenger perception data, V2X messages, etc.

[0075] The software version indicates the software version of each electronic control unit (ECU) installed in the vehicle. The occupant perception data indicates the driver's state (e.g., distracted, drowsy, unresponsive), the presence of passengers, etc. Furthermore, the EDR data includes information about recent V2X messages exchanged between the infrastructure and surrounding vehicles via V2X communication.

[0076] As illustrated in FIG. 9, the autonomous driving data includes <recognition data>, <judgment data>, and <control data>.

[0077] The "cognitive data" of the autonomous driving data includes the following information:

[0078] Classification of detected obstacles: includes information on dynamic obstacles (e.g., object classes such as pedestrians, bicycles, motorcycles, cars, buses, etc.) that are recognized as having the potential to cause accidents when driving a vehicle.

[0079] - Lane perception information: includes lane geometry parameters (curvature, curvature rate, heading angle, lateral offset) output from the computer vision system, and a quality indicator indicating the reliability of the lane geometry measurement.

[0080] - Vehicle location information and used positioning technology: Information on the used positioning technology includes, for example, GPS, V2X, whether a precise map is available, and the version of the precise map used.

[0081] -Perceived Time To Collision (TTC)

[0082] The "judgment data" of the autonomous driving data includes the following information:

[0083] - Whether autonomous driving functions (LKA, FCA, etc.) can be activated

[0084] - Object data analyzed after surrounding recognition: Includes recognized object class, x, y coordinates / size / relative speed (using sensor fusion), vehicle speed and direction, etc. This data is useful for reconstructing a map of the external environment surrounding the autonomous vehicle at the time of the event.

[0085] - Action scenarios for determined driving conditions (horizontal and vertical scenarios): For example, keeping the vehicle lane, changing lanes, turning left / right, U-turns, emergency stops, stopping on the shoulder of the road, parking, cutting in from nearby vehicles, cutting out from vehicles ahead, etc.

[0086] The <control data> of the autonomous driving data includes the following information:

[0087] - Driver control information: Actuator control information such as steering wheel torque and acceleration / deceleration pedals

[0088] -Autonomous driving control information: Desired deceleration / acceleration, desired steering angle

[0089] The exemplary embodiments described above may be implemented in many different ways. As an example, the various methods, apparatus, systems, and subsystems described herein may be implemented by a general-purpose computer having a processor, memory, disks or other mass storage, communication interfaces, input / output (I / O) devices, and other peripherals. The general-purpose computer functions as an apparatus for performing the methods described above by loading software instructions into a processor and then executing the instructions to perform the functions described herein.

[0090] The functional components described herein are labeled "units" or "modules" to emphasize their implementation independence. For example, a module may be implemented as a hardware circuit including custom very-large-scale integration (VLSI) circuits or gate arrays, logic chips, transistors, or other semiconductors. A module may also be implemented as a programmable hardware device such as a field programmable gate array (FPGA), programmable array logic, programmable logic device, or the like.

[0091] Meanwhile, various methods described herein may be embodied as instructions stored on a non-transitory recording medium that can be read and executed by one or more processors. Non-transitory recording media include, for example, any type of recording device that stores data in a form readable by a computer system. For example, non-transitory recording media include storage media such as erasable programmable read-only memory (EPROM), flash drives, optical drives, magnetic hard drives, solid-state drives (SSDs), etc.

[0092] The above description is merely illustrative of the technical concept of the present invention, and various modifications and variations are possible by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the above-described embodiments are for illustrative purposes only and do not limit the technical concept of the present invention, and the scope of the technical concept of the present invention is not limited by these embodiments.

[0093] CROSS-REFERENCE TO RELATED APPLICATION This patent application claims priority to patent application number 10-2019-0151529 filed in Korea on November 22, 2019, and patent application number 10-2020-0155377 filed in Korea on November 19, 2020, both of which are incorporated herein by reference in their entireties. [Explanation of symbols]

[0094] 110 Sensor System 120 Autonomous Driving System 121 Cognitive Subsystem 122 Decision Subsystem 123 Control Subsystem 130 Wireless Communication Systems 140 Intrusion Detection System 150 EDR systems 124 Second rear cover 143 Support surface 151 First Bracket 152 Second Bracket 161 First board assembly 162 Second board assembly 163 Camera Assembly 171 Battery No. 1 172 Second Battery 180 Wiring materials 190 Antenna

Claims

1. 1. A method for collecting and recording event data in a vehicle operating fully or partially in an autonomous driving mode, comprising: An EDR (Event Data Recorder) system that collects and manages the event data, receiving a trigger signal from a subsystem of an autonomous driving system indicating the occurrence of one of a plurality of predefined events; collecting event data including at least data related to the recognition-judgment-control process of the autonomous driving system before and after the occurrence of the event indicated by the trigger signal for a predetermined recording period; recording the event data in an internal repository and uploading the event data to a remote server in communication with the vehicle; The step of receiving the trigger signal includes: receiving a trigger signal from a subsystem of the autonomous driving system indicating that an intrusion into a vehicle internal network has been detected; receiving a trigger signal from a subsystem of the autonomous driving system indicating that an emergency maneuver (EM) or a minimal risk maneuver (MRM) has been initiated; When the autonomous driving system receives a trigger signal indicating that the MRM has started, the autonomous driving system increases sensitivity to the event by lowering a threshold value of a decision criterion or a trigger condition for determining the occurrence of an event that triggers recording of the EDR system from the moment the MRM starts, compared to before the MRM started; further comprising a step of extending the recording period while additionally recording the type and time of the event that has occurred when a new trigger signal indicating the occurrence of a new event is received before the end of the recording period of the event data, The method of claim 1, wherein the data items recorded during the extended recording interval are equal to or less than the data items recorded during the recording interval corresponding to the first received trigger signal.

2. The event data is 2. The method of claim 1, further comprising at least one of a camera image of an interior or exterior of the vehicle, occupant perception data of the vehicle, software version information of an ECU installed in the vehicle, and information related to recently used V2X messages.

3. The event data is 10. The method of claim 1, further comprising object recognition information suitable for reconstructing a map of the external environment surrounding the vehicle before and after the occurrence of the event.

4. The method of claim 1 , wherein the data items or recording periods constituting the event data are different for at least some of the plurality of events.

5. The event data is 10. The method of claim 1, wherein the information is recorded and uploaded along with information indicating an associated event or trigger condition.

6. The step of receiving the trigger signal includes:

10. The method of claim 1, further comprising receiving a trigger signal from a subsystem that performs autonomous navigation functions based at least in part on lane perception information, the trigger signal indicating that the vehicle has left its lane.

7. The step of receiving the trigger signal includes:

10. The method of claim 1, further comprising receiving a trigger signal from a subsystem that performs autonomous navigation functions based at least in part on a time to collision (TTC) indicating that a collision cannot be avoided through braking based on a current speed of the vehicle.

8. As a vehicle system, an autonomous driving system that controls a vehicle to operate fully or partially in an autonomous driving mode; a wireless communication system that enables communication between the vehicle and an external system; an EDR (Event Data Recorder) system that collects and manages event data; The EDR system includes: (1) receiving a trigger signal from a subsystem of the autonomous driving system indicating the occurrence of one of a plurality of predefined events; (2) collecting event data including at least data related to the recognition-judgment-control process of the autonomous driving system before and after the occurrence of the event indicated by the trigger signal for a predetermined recording period; and (3) recording the event data in an internal storage and uploading the event data to a remote server via the wireless communication system; The trigger signal is a trigger signal received from a subsystem of the autonomous driving system indicating that an intrusion into the vehicle's internal network has been detected; a trigger signal received from a subsystem of the autonomous driving system indicating that an emergency maneuver (EM) or a minimal risk maneuver (MRM) has been initiated; When the autonomous driving system receives a trigger signal indicating that the MRM has started, the autonomous driving system increases sensitivity to the event by lowering a threshold value of a decision criterion or a trigger condition for determining the occurrence of an event that triggers recording of the EDR system from the moment the MRM starts, compared to before the MRM started; The EDR system includes: if a new trigger signal indicating the occurrence of a new event is received before the end of the recording period of the event data, extending the recording period while additionally recording the type of the event that occurred and the time of its occurrence; The vehicle system according to claim 1, wherein the data items recorded during the extended recording period are equal to or less than the data items recorded during the recording period corresponding to the first received trigger signal.

9. The event data is 9. The vehicle system of claim 8, wherein the information is recorded and transmitted along with information indicating an associated event or trigger condition.

10. The trigger signal is 10. The vehicle system of claim 8, further comprising a trigger signal received from a subsystem that performs autonomous driving functions based at least in part on lane perception information, the trigger signal indicating that the vehicle has left its lane.

11. The trigger signal is 10. The vehicle system of claim 8, further comprising a trigger signal received from a subsystem that performs autonomous navigation functions based at least in part on a time to collision (TTC), the trigger signal indicating that a collision cannot be avoided through braking based on a current speed of the vehicle.

12. The EDR system includes: The vehicle system according to claim 8, characterized in that the electronic control unit is incorporated as a functional module in a main controller or an airbag controller (Airbag Control Unit (ACU)) of the autonomous driving system, or is connected to an internal vehicle network as a separate electronic control unit (Electronic Control Unit).

Images