Intelligent automobile online safety monitoring and safety management model

Abstract

The invention discloses an intelligent automobile on-line safety monitoring and safety management model, which forms a safety brain MEIA model prototype with necessary functions of safety guarantee such as monitoring M, evaluation E, intervention I, good afternoon A and the like. By monitoring the states of various dynamic and static targets, traffic flow and the like in an operation design domain ODD and the states of modules such as AVSO, AVPO, AVCO and the like, monitoring the state of the AVMO, and performing self-monitoring, self-evaluation, active safety intervention and self-processing on the safety state of the AVMO, necessary safety equipment of the intelligent automobile is re-arranged in principle content.

Description

Technical Field

[0001] The present invention relates to the field of smart cars, and more specifically, to an online safety monitoring and safety management model for smart cars. Background Art

[0002] There are sensor defects and AI algorithm defects in the current autonomous driving system, which fail to fully consider the impact of the surrounding environment on safe driving. In addition, the current architecture has inherent defects in structure and function. In order to ensure the traceability of the entire driving safety process, the accountability of process management, and the clarity of responsibility; Therefore, it is necessary to redesign the architecture and propose a safety monitoring operation module and a safety redundancy architecture to make up for the structural defects of the current perception-planning-control serial architecture. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an online safety monitoring and safety management model for an intelligent vehicle, which solves the structural defects of the current perception S-planning P-control C serial architecture.

[0004] This model comprehensively considers the mandatory nature of policies / regulations and the mutual influence of safety stakeholders. Through redesigning the architecture and real-time monitoring, evaluation and intervention, the safety and operability of the autonomous driving system are fully supervised to ensure safety, traceability and integrity. The model is designed to ensure driving safety and solve the safety issues of smart cars.

[0005] In order to ensure that Level 3 and above automated driving systems (AD Systems) are safe when they are put on the market, a socially acceptable, technically reliable and complete safety assurance technology system must be established. This constitutes the overall goal of safety assurance during the development of AD systems. In this framework, safety is regarded as a codified concept of AD systems.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: an intelligent vehicle online safety monitoring and safety management model, namely the safety brain MEIA model, including the following functional features: The monitoring function covers three key aspects: scene awareness, driving awareness, and autonomous driving awareness. Scene awareness includes the recognition of scene clarity, scene complexity, and scene intensity. Driving awareness involves the recognition of road conditions, vehicle conditions, driving conditions, and passenger / cargo conditions. Autonomous driving awareness includes the recognition of sensor status, operation execution status, driving intention execution, and current driving intention.

[0007] The evaluation function covers four key aspects: scenario risk evaluation (SRE), compliance evaluation of intention (ComplianceEvaluation of Intention), safety evaluation of intention (Safety Evaluation of Intention) and safety evaluation of behavior (Safety Evaluation of Behavior). Specifically, scenario risk evaluation includes ODD (Operational Design Domain) identification, risk intuitive judgment and safety entropy evaluation. The evaluation of intention includes dual considerations of compliance and safety, involving compliance evaluations of traffic regulations and safe driving rules respectively. In addition, behavioral safety evaluation focuses on the safety evaluation of the vehicle's existing behavior, thereby ensuring that the behavior of the autonomous driving system in various scenarios meets safety standards.

[0008] Intervention functions include Constrained Plan and Safe Stop. Constrained Plan provides a series of constraints for the autonomous driving system by determining the safe decision boundary to ensure that the system's behavior is within a safe range. These constraints can include avoiding obstacles, complying with traffic regulations, and limiting speed. Safe Stop meets controllable parking conditions and can implement emergency parking when parking is required. Through reasonable parking decisions and control instructions, the safe stop function can ensure the safety and stability of the vehicle during the parking process.

[0009] The aftermath functions include key aspects such as security incident data collation and upload, sending alarms and rescue signals, high-voltage electrical safety management, low-voltage electrical safety management, and occupant escape support. Specifically, security incident data collation and upload covers the collation, upload, and background retrieval of behavioral safety incident data and accident data. In terms of sending alarms and rescue signals, important technologies include accident assessment to ensure that the accident situation can be quickly assessed in the event of an accident. High-voltage electrical safety management includes effective management of power battery and high-voltage motor power-off management and status monitoring. Low-voltage electrical safety management involves the management of low-voltage power supplies to ensure the safety of the system in terms of low-voltage electricity. In terms of occupant escape support, the technology covers the comprehensive management of the status of door locks, door and window glass, fans, seat belts, etc. to support the safe escape of occupants in emergency situations.

[0010] Technical effects and advantages of the present invention: The modules will integrate safety assurance functions such as monitoring, assessment, intervention and follow-up to achieve full supervision of SOTIF (Safety, Operability, Traceability and Integrity). By building such a safety brain (MEIA) model prototype, all-round protection can be provided for safe driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is a structural block diagram of an intelligent vehicle online safety monitoring and safety management model of the present invention.

[0012] Figure 2 The present invention is a flow chart of a smart car online safety monitoring and safety management model.

[0013] Figure 3 The present invention is a structural diagram of an intelligent vehicle online safety monitoring (AVMO) system.

[0014] Figure 4 This is a simulation diagram of a monitoring example of an intelligent vehicle online safety monitoring and safety management model of the present invention.

[0015] Figure 5 This is a simulation diagram of an online safety monitoring and safety management model evaluation for a smart car according to the present invention.

[0016] Figure 6 This is a simulation diagram of an intervention of an intelligent vehicle online safety monitoring and safety management model according to the present invention.

[0017] Figure 7 This is a post-processing simulation diagram of an intelligent automobile online safety monitoring and safety management model of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] according to Figure 1-7 A smart car online safety monitoring and safety management model is shown, referring to Figure 1 , showing a structural block diagram of an intelligent vehicle online safety monitoring and safety management model of the present invention, the safety brain MEIA model includes a series of technical penetration behaviors of monitoring M, evaluation E, intervention I, and aftermath A; The monitoring is used to obtain comprehensive road conditions, predict vehicle operation conditions, define dynamic constraints, and extract key information; The evaluation is used for scenario risk assessment, intention compliance assessment, intention safety assessment and behavior safety assessment; The intervention is used to determine the safety decision boundary, provide a series of constraints, and implement reasonable parking decisions and control instructions; The aftertreatment is used to record and upload data, construct dangerous situations in autonomous driving scenarios, and perform post-processing on accidents or unexpected events.

[0020] Reference Figure 2 , showing a flow chart of an intelligent vehicle online safety monitoring and safety management model of the present invention. During the operation of the safety brain MEIA model, the monitoring function covers three key aspects: scene awareness, driving awareness and automatic driving awareness, and comprehensively recognizes the driving scene, covering scene clarity, complexity, intensity, road conditions, vehicle conditions, etc., as well as the recognition of sensor status, operation execution status, etc.; the evaluation function covers four key aspects: scene risk assessment, intention compliance assessment, intention safety assessment and behavior safety assessment, to ensure compliance with traffic regulations and safe driving rules; the intervention function includes constraint decision-making and safe parking, and ensures that the system behavior is within a safe range by setting decision boundaries and implementing safe parking; the aftermath function includes key aspects such as safety event data collation and uploading, sending alarms and rescue signals, high-voltage electrical safety management, low-voltage electrical safety management, and occupant escape support, to ensure that the system can handle the aftermath in a timely manner after an accident occurs.

[0021] Reference Figure 3 , according to the AVMO module function of the British PAS standard, the vehicle is monitored. The first type of behavior is to monitor the operation design domain (ODD), including geographical location, road characteristics, weather and lighting, etc. The second type of behavior is to monitor the vehicle operation, including perception, decision-making, and control status. The third type of behavior is self-monitoring, including the identification of vehicle faults. The fourth type of behavior generates parking instructions, and based on the information obtained from the beacon system, requests the AVPO to stop as soon as possible on the basis of reducing the risks to passengers and other traffic participants. The fifth type of behavior generates parking control, which can directly control the vehicle to stop as soon as possible.

[0022] Reference Figure 4, is the M-monitoring module in the MEIA model. The specific functions of scene awareness SA are scene clarity recognition, scene complexity recognition and scene intensity recognition, air conditions (rain, snow, fog, dust, light, wind), traffic control signals, road markings, communication connection capabilities, road networks, traffic participating vehicles, vulnerable traffic participants, directions, speeds, and distances of each traffic participant, etc. By monitoring the above elements, it is possible to recognize regional and climatic differences, and to self-learn online, combined with communication connection means, to achieve the empowerment of scene clarity and element integrity. Combined with the types of various traffic bodies and their density, relative speed, relative distance, etc., according to general traffic rules and social constraints, the complexity of the scene is estimated, and its quantitative heat map index is formed. Combined with the change rate of 1D-2D TTC, the degree of change in the scene's traversable domain is judged, and a quantifiable scene intensity expression index is formed as an evaluation index for measuring the AV vehicle's ability to adapt to scenes under different ODDs. The specific functions of driving awareness DA include recognizing road conditions, vehicle conditions, driving conditions, and passenger / cargo conditions. Adopting stereo vision + radar reflection + chassis suspension vibration point and other multi-dimensional methods, the road conditions are comprehensively perceived as the basis for adjusting the vehicle speed, predicting the abnormal noise source of the vehicle's online operation and its functional safety, defining the safe control boundary of the vehicle chassis dynamics constraints, and predicting the relative position and change area of ​​the current working point in the entire safety domain, timely predicting and controlling, monitoring and safety warnings for the passengers' riding posture, evaluating the impact of passengers / cargo on vehicle dynamics, and evaluating the passenger comfort and behavior range affected by vehicle behavioral dynamics. The specific function of autonomous driving awareness AA is to recognize the sensor status, operation execution status, driving intention execution status and current driving intention. Each sensor performs regular and online self-diagnosis, self-calibration and self-adjustment based on its absolute calibration object; each sensor can verify each other, recognize trajectory following deviation, TTC deviation, distance deviation, etc., recognize the current horizontal and vertical driving intention, evaluate the planning ability, and re-empower.

[0023] Reference Figure 5 , is the E-assessment in the MEIA model of the safety brain, which identifies ODD, makes risk intuitive judgments, and evaluates safety entropy based on M-monitoring data. It conducts driving intention compliance assessment based on AA perception information and intentions, conducts safe driving rules compliance assessment based on SA, DA, and AA data, and conducts safety assessment based on DA and AA data.

[0024] Reference Figure 6, is the I-intervention in the MEIA model of the safety brain. In vehicle constraint decisions, based on SA, DA, and AA data, the boundaries of the safe driving envelope are confirmed, boundary constraints are provided for safety decisions, and the traffic flow environment environment envelope and safe operation envelope for safe driving are evaluated and boundaries are determined, and boundary outputs are provided. When safe parking is required, if the controllable parking conditions are met, the current vehicle status, ODD scene status, and the status of vehicle cargo and passengers should be considered, and even the impact on traffic flow during the process of reaching the minimum risk position should be considered to select the best parking safety strategy; when the danger is unavoidable and escalates, and the controllable parking conditions are not met, this emergency parking measure is taken, combining multiple ISO / ECE / NHTSA and other rules with scene perception results to perform safe parking.

[0025] Reference Figure 7 , which is the A-aftermath in the MEIA model of the safety brain, including safety event data collation and upload, sending alarms and rescue signals, high-voltage electrical safety management, low-voltage electrical safety management and occupant escape support. Among them, safety event data collation and upload, according to the degree of change of driving safety indicators, the relevant events are collated, recorded, uploaded, and retrieved to evaluate the rationality of driving strategies and the rationality of response capabilities; sending alarms and rescue signals is used to evaluate the accident status of occupants and vulnerable road users inside and outside the car, and timely sending alarms and rescue signals; high-voltage electrical safety management determines the possible location of the high-voltage electrical leakage source based on empirical data such as collision speed and angle, and timely controls or cuts off in an orderly manner, and according to the collision damage estimation and vehicle position, timely arranges evacuation of traffic flow and drives to move to a safe ground; low-voltage electrical safety management guarantees basic communications, necessary sensors and available signal lights; occupant escape support supports intelligent control of door locks for occupant escape, necessary breaking of window glass, automatic management of fan poisoning gas (including necessary environmental perception before collision), automatic release of seat belts or pre-tightening to prevent secondary collisions, etc.

Claims

1. A smart car online safety monitoring and safety management model, characterized by: The model includes monitoring M, evaluation E, intervention I, and aftercare A, and obtains the MEIA model of the security brain for self-monitoring, self-evaluation, active security intervention, and self-processing of its own security status; The monitoring is used to monitor the various dynamic and static targets, traffic flow status, and the status of modules such as AVSO (autonomous driving vehicle perception system), AVPO (autonomous driving vehicle path planning system), and AVCO (autonomous driving vehicle control system) in the operation design domain (ODD) by AVMO (autonomous driving vehicle safety brain); The Evaluation is used by AVMO (autonomous vehicle safety brain) to perform low-level self-monitoring and self-assessment of its own safety status. It also includes the assessment of some operational design domain (ODD) boundaries to ensure the safety and effectiveness of the system in various situations. The Intervention is used to ensure the vehicle's own safety status by proactively intervening in safety to deal with various situations based on low-level self-monitoring and self-assessment by AVMO (autonomous vehicle safety brain); The aftertreatment is used for the ability of AVMO (autonomous driving vehicle safety brain) to self-monitor and self-process its own safety status, and also includes the follow-up processing after an accident or unexpected event.

2. The smart car online safety monitoring and safety management model according to claim 1 is characterized by: The monitoring mentioned above is to comprehensively understand the clarity, complexity and intensity of driving scenes, improve the ability of autonomous driving vehicles to cope with different scenes, and at the same time, enhance the driving awareness and safety performance of vehicles through multi-dimensional perception of road conditions, prediction of vehicle operation conditions and definition of dynamic constraints. In addition, through sensor self-diagnosis and calibration, redundant safety mechanisms and real-time monitoring and evaluation, the awareness and safety performance of autonomous driving systems are improved; Specifically, it can firstly perceive and evaluate air conditions (rain, snow, fog, dust, light, wind) to understand the impact of different air conditions on sensors and perception models. Secondly, it can also understand traffic signals and signs, including new types of signals and regional differences. It also has the ability of extended understanding and semantic reasoning to cope with the differentiated road markings and signs in different regions. In order to achieve the transmission and understanding of information, communication connection means are combined to realize the information transmission between vehicles, including the transmission of V2V information. In addition, the ability to identify different types of traffic participants, such as vehicles, pedestrians, and bicycles, and understand their intrinsic properties, such as the type of goods transported and their explosiveness, can also estimate the size and movement ability of traffic participants, providing more accurate information for the model. In terms of traffic flow, the density and speed of traffic flow are identified to provide support for the assessment of traffic conditions, and the complexity of the scene is quantified to form a heat map indicator to intuitively express the complexity of the scene, and this indicator is used as one of the capability evaluation indicators of AV vehicles.

3. The smart car online safety monitoring and safety management model according to claim 1 is characterized by: The evaluation includes scenario risk assessment, intention compliance assessment, intention safety assessment and behavior safety assessment to improve the safety performance of the autonomous driving system; Specifically, the results of SA (scenario awareness), DA (driving awareness) and AA (autonomous driving awareness) are integrated to conduct a comprehensive assessment of the current scenario to determine whether it exceeds the response range of the autonomous driving system and calculate the scenario's danger index. This involves the judgment of scenario risks and the assessment of resilience boundaries, the assessment of intention compliance and safety, the formulation of a safe driving rules compliance assessment strategy, and the assessment of behavioral safety performance bandwidth. At the same time, the compliance of driving intentions is assessed using the perception information and intentions provided by AA. In addition, based on the data from SA, DA and AA, an assessment of safe driving rules compliance is conducted to ensure that the system meets safety requirements during driving.

4. The smart car online safety monitoring and safety management model according to claim 1 is characterized by: The intervention is based on evaluating and determining the traffic environment and safe operation range, combining rules and scene perception to achieve safe restraint decision-making and safe parking; Specifically, based on SA (scenario awareness), DA (driving awareness) and AA (autonomous driving awareness) data, the boundaries of the safe driving envelope are confirmed to provide boundary constraints for safety decisions. When confirming the boundaries, the current vehicle status, ODD (operational design domain) scenario status, and the status of the vehicle's cargo and passengers are considered. In addition, the impact on traffic flow during the minimum risk position process must also be considered. When the danger is unavoidable and escalates, and the controllable parking conditions are not met, emergency parking measures are taken. This measure is intended to ensure safety in emergency situations and reduce potential risks.

5. The smart car online safety monitoring and safety management model according to claim 1 is characterized by: The aftertreatment records and uploads data, so that the system can construct dangerous situations in autonomous driving scenarios and evaluate their distribution inside / outside the operational design domain, using these new scenario cases to improve the safety of the autonomous driving system and ensure the escape support of the occupants; Specifically, the data elements of the ADS data recorder based on VMAD-SG3 can store incident-triggered data for efficient reconstruction of standard format scenes and automatic assessment of accident severity. Data analysis and post-processing can enhance corner case discovery and model updates, and form new safety rule recommendations. In terms of accident response, based on empirical data such as collision speed and angle, the possible location of the high-voltage electrical leakage source can be determined, and corresponding control or orderly cut-off measures can be taken. At the same time, based on the collision damage estimate and vehicle location, timely arrangements can be made to evacuate traffic flow and drive the vehicle to a safe ground. To ensure the safety of passengers, intelligent door lock control to support passenger escape, window glass breaking when necessary, automatic management of fan poisoning gas (including environmental perception before collision), and automatic release of seat belts or pre-tightening of seat belts can be implemented to prevent secondary collisions. After an accident or accident, the safety brain of the autonomous driving system can self-monitor and process, and perform necessary data storage, uploading and feedback to minimize the occurrence of unknown risks.

Images