Safe driving decision-making control system for intelligent connected vehicles based on mixed traffic environment

Abstract

The present invention belongs to the field of automobile safe driving and involves data analysis technology. It is used to solve the problem that the existing technology cannot independently analyze different types of environmental information and then generate optimized control decisions. Specifically, it is an intelligent connected vehicle safe driving decision-making control system based on a mixed traffic environment, including a perception module, a decision-making planning module and a control execution module connected in sequence. The perception module includes a static perception unit and a dynamic perception unit; the basic road condition information and dynamic environmental information of the intelligent connected vehicle are sent to the decision-making planning module; the present invention can collect the basic road condition information and dynamic environmental information of the intelligent connected vehicle respectively, and then generate corresponding control instructions according to the basic road condition information and dynamic environmental information through the decision-making planning module, mark the final safety instructions according to the safety priority of the control instructions, and conduct driving safety decision analysis in a comprehensive and complex mixed traffic environment.

Description

Technical Field

[0001] The present invention belongs to the field of automobile safe driving and relates to data analysis technology, specifically to an intelligent connected automobile safe driving decision-making control system based on a mixed traffic environment. Background Art

[0002] Intelligent connected vehicles integrate on-board sensors, communication networks and artificial intelligence technologies to achieve real-time information interaction between vehicles and roads, supporting environmental perception, collaborative decision-making and intelligent control, thereby improving driving safety and traffic efficiency.

[0003] The invention patent with announcement number CN116777062A discloses an adaptive fusion learning autonomous driving safety decision-making method for extreme difficult cases. The method achieves a safe and intelligent response to extreme difficult cases through real-time perception and extreme difficult case scene data collection, data preprocessing and feature classification extraction, model training and optimization, decision generation and real-time monitoring and feedback. It can analyze and predict the possibility and risks of various extreme difficult cases, generate and optimize safety decisions; however, there are many influencing factors in the car driving environment, including relatively static trajectory road condition information and dynamic distance information between vehicles. The existing technology is unable to independently analyze different types of environmental information and then generate the optimal control decision; resulting in the inability to timely and effectively screen and optimize abnormal links when there are risk hazards in the control decision.

[0004] In response to the above technical problems, this application proposes a solution. Summary of the Invention

[0005] The purpose of the present invention is to provide a safe driving decision-making and control system for intelligent connected vehicles in mixed traffic environments, which is used to solve the problem that existing technologies cannot independently analyze different types of environmental information and then generate optimized control decisions;

[0006] The technical problem to be solved by the present invention is: how to provide a safe driving decision-making control system for intelligent connected vehicles based on mixed traffic environments that can independently analyze different types of environmental information and then generate optimized control decisions.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An intelligent connected vehicle safe driving decision-making and control system based on a mixed traffic environment includes a perception module, a decision-making and planning module, and a control execution module connected in sequence. The perception module includes a static perception unit and a dynamic perception unit.

[0009] The static perception unit obtains the location and navigation route of the intelligent connected vehicle in real time, uploads the location and navigation route of the intelligent connected vehicle to the Internet of Vehicles, retrieves the basic road condition information of the nearest L1 meter in the intelligent connected vehicle's driving path through the Internet of Vehicles, and sends the basic road condition information of the intelligent connected vehicle to the decision-making and planning module;

[0010] Dynamic perception unit, which obtains the dynamic environment information of the intelligent connected vehicle in real time and sends the dynamic environment information of the intelligent connected vehicle to the decision-making and planning module;

[0011] The decision-making planning module retrieves the driving decision instruction sequence of the intelligent connected vehicle; compares the basic road condition information and dynamic environment information with the driving decision instruction sequence to obtain static control instructions and dynamic control instructions, marks the sequence numbers of the static control instructions and dynamic control instructions in the driving decision instruction sequence as static evaluation values and dynamic evaluation values, respectively, marks the safety instructions with the static evaluation values and dynamic evaluation values; and sends the safety instructions to the control execution module;

[0012] The decision-making planning module is also communicatively connected to the safety assessment platform. After generating a safety instruction, the decision-making planning module sends the safety instruction synchronously to the safety assessment platform. The safety assessment platform is communicatively connected to the safety assessment module and the decision optimization analysis module.

[0013] Furthermore, the driving decision instruction sequence is a sequence obtained by sorting a number of driving instructions from low to high according to the safety level. The driving instructions include stopping, braking, decelerating, keeping speed, changing lanes, and overtaking; and the driving instructions correspond to the basic road condition information and dynamic environment information.

[0014] Furthermore, the marking process of the safety instruction includes: comparing the static evaluation value with the dynamic evaluation value: if the static evaluation value is less than the dynamic evaluation value, the static control instruction is marked as a safety instruction; if the static evaluation value is greater than or equal to the dynamic evaluation value, the dynamic control instruction is marked as a safety instruction.

[0015] Furthermore, the safety assessment module is used to evaluate and analyze the driving decision safety of intelligent connected vehicles: the intelligent connected vehicles connected to the safety assessment platform are marked as assessment objects, an assessment cycle is generated and the assessment cycle is divided into several assessment periods, the switching process of the safety instructions of the assessment object from a high-sequence state to a low-sequence state during the assessment period is extracted and marked as an assessment process, and the assessment process is marked as a risk process or a safety process; the ratio of the number of risk processes marked during the assessment period to the number of assessment processes is marked as the risk coefficient of the assessment period, and the risk coefficient is used to determine whether the driving decision safety of the assessment object during the assessment period meets the requirements.

[0016] Furthermore, the specific process of marking the evaluation process as a risk process or a safety process includes: determining whether the evaluation process meets the risk characteristics: if so, the evaluation process is marked as a risk process; if not, the evaluation process is marked as a safety process; the risk characteristics include that the duration of the evaluation process is less than M1 seconds and the difference between the high sequence number and the low sequence number is not less than two.

[0017] Furthermore, the specific process of determining whether the driving decision safety of the evaluation object during the evaluation period meets the requirements includes: comparing the risk coefficient with a preset risk threshold: if the risk coefficient is less than the risk threshold, then it is determined that the driving decision safety of the evaluation object during the evaluation period meets the requirements; if the risk coefficient is greater than or equal to the risk threshold, then it is determined that the driving decision safety of the evaluation object during the evaluation period does not meet the requirements, generating a decision optimization analysis signal and sending the decision optimization analysis signal to the decision optimization analysis module through the safety evaluation platform.

[0018] Furthermore, the decision optimization analysis module is used to optimize and analyze the safe driving decision-making process of intelligent connected vehicles: the preceding safety instructions of the risk process correspond to the static control instructions and the dynamic control instructions in the planning analysis in the driving decision instruction sequence and are marked as J-1 and D-1 respectively, and the subsequent safety instructions of the risk process correspond to the static control instructions and the dynamic control instructions in the planning analysis in the driving decision instruction sequence and are marked as J-2 and D-2 respectively; by marking the difference between J-2 and J-1 and the difference between D-2 and D-1 as the static optimization value and the dynamic optimization value respectively, the static optimization value and the dynamic optimization value are compared and an optimization signal is generated through the comparison results.

[0019] Furthermore, the specific process of comparing the static optimization value with the dynamic optimization value includes: if the static optimization value is less than the dynamic optimization value, a dynamic optimization signal is generated and the dynamic optimization signal is sent to the administrator's mobile terminal through the security assessment platform; if the static optimization value is greater than the dynamic optimization value, a static optimization signal is generated and the static optimization signal is sent to the administrator's mobile terminal through the security assessment platform; if the static optimization value is equal to the dynamic optimization value, a bidirectional optimization signal is generated and the bidirectional optimization signal is sent to the administrator's mobile terminal.

[0020] The present invention has the following beneficial effects:

[0021] The perception module collects basic road condition information and dynamic environmental information for intelligent connected vehicles. The decision-making and planning module then generates corresponding control instructions based on these information. The final safety instructions are marked according to their safety priorities. This process integrates complex mixed traffic environments for driving safety decision analysis, ensuring driving safety.

[0022] The safety assessment module can evaluate and analyze the safety of driving decisions of intelligent connected vehicles. The risk level of safety instructions in each assessment period is analyzed in a periodic and time-division monitoring manner to obtain a risk coefficient. The risk coefficient is used to evaluate the safety of driving decisions in the assessment period, and optimization analysis is triggered in a timely manner when safety anomalies occur.

[0023] The decision optimization analysis module can be used to optimize and analyze the safe driving decision-making process of intelligent connected vehicles. The sequence numbers of static control instructions and dynamic control instructions in the driving decision instruction sequence during the risk process can be numerically analyzed to obtain static optimization values and dynamic optimization values. The optimization measures for safe driving decisions can be directly marked according to the static optimization values and dynamic optimization values to improve optimization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0025] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0026] Figure 2 This is a system block diagram of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0027] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0028] Example 1: Figure 1-Figure 2 As shown, the intelligent connected vehicle safe driving decision control system based on a mixed traffic environment includes a perception module, a decision planning module and a control execution module connected in sequence. The perception module includes a static perception unit and a dynamic perception unit; the perception module is communicatively connected to the Internet of Vehicles.

[0029] The static perception unit is used to perceive and analyze the static traffic environment during the driving process of the intelligent connected vehicle: obtain the position and navigation route of the intelligent connected vehicle in real time, upload the position and navigation route of the intelligent connected vehicle to the vehicle network, and retrieve the basic road condition information of the nearest L1 meter in the driving path of the intelligent connected vehicle through the vehicle network. The basic road condition information includes: sharp bends with a curvature radius less than L2 meters, bends with a curvature radius greater than or equal to L2 meters, landslides, tunnels, and traffic volume greater than L3 in the driving path; the basic road condition information of the intelligent connected vehicle is sent to the decision planning module. It should be noted that different basic road condition information corresponds to different safety levels. For example, the safety level of "including landslides" is lower. When landslides are included, it can correspond to "braking" in the driving decision instruction sequence. For example, the safety level of "including tunnels" is higher than that of landslides. When tunnels are included, it can correspond to "slowing down" in the driving decision instruction program. Among them, L1, L2 and L3 are all numerical constants, and the specific values of L1, L2 and L3 are set by the management personnel.

[0030] The dynamic perception unit is used to perceive and analyze the dynamic traffic environment during the driving process of the intelligent connected vehicle: obtain the dynamic environmental information of the intelligent connected vehicle in real time, the dynamic environmental information includes: the distance between the intelligent connected vehicle and the vehicle in front is less than K1 meter and the driving speed of the intelligent connected vehicle is not less than K2 kilometers per hour, the minimum distance between the intelligent connected vehicle and the nearest car in the lanes on both sides is less than K3 meters, the rainfall when the intelligent connected vehicle is driving is higher than K4 mm and the driving speed of the intelligent connected vehicle is not less than K5 kilometers per hour; the dynamic environmental information of the intelligent connected vehicle is sent to the decision-making and planning module Similar to the basic road condition information, different information in the dynamic environment information corresponds to different safety levels. For example, "whether the distance between the intelligent networked vehicle and the vehicle in front is less than K1 meters and the driving speed of the intelligent networked vehicle is not less than K2 kilometers per hour" means that the vehicle speed is high and the distance to the vehicle in front is close, and its safety level is extremely low. Therefore, when the judgment result of this information is consistent, it can correspond to "brake stop" in the driving decision instruction sequence; K1, K2, K3, K4 and K5 are all numerical constants, and the specific values of K1, K2, K3, K4 and K5 are set by the management personnel.

[0031] The basic road condition information and dynamic environment information of the intelligent connected vehicle are collected separately, and then the decision-making planning module generates corresponding control instructions based on the basic road condition information and dynamic environment information. The final safety instructions are marked according to the safety priority of the control instructions. In this process, the complex mixed traffic environment is integrated to conduct driving safety decision analysis to ensure driving safety.

[0032] The decision planning module is used to plan and analyze the safe driving decisions of intelligent connected vehicles: retrieve the driving decision instruction sequence of the intelligent connected vehicle, which is a sequence obtained by sorting several driving instructions from low to high according to safety level. The driving instructions include stopping, braking, deceleration, speed control, lane change, and overtaking; and the driving instructions correspond to the basic road condition information and dynamic environment information; compare the basic road condition information with the driving decision instruction sequence to obtain static control instructions, and compare the dynamic environment information with the driving decision instruction sequence to obtain dynamic control instructions, mark the serial numbers of the static control instructions and the dynamic control instructions in the driving decision instruction sequence as static evaluation values and dynamic evaluation values respectively, and compare the static evaluation value with the dynamic evaluation value: if the static evaluation value is less than the dynamic evaluation value, the static control instruction is marked as a safe instruction; if the static evaluation value is greater than or equal to the dynamic evaluation value, the dynamic control instruction is marked as a safe instruction; and the safe instruction is sent to the control execution module.

[0033] After receiving the safety instructions, the control execution module controls the intelligent connected vehicle according to the safety instructions.

[0034] Embodiment 2: The decision planning module is further communicatively connected to a security assessment platform. After generating a security instruction, the decision planning module synchronously sends the security instruction to the security assessment platform. The security assessment platform is communicatively connected to the security assessment module and the decision optimization analysis module.

[0035] The safety assessment module is used to evaluate and analyze the safety of driving decisions of intelligent connected vehicles: the intelligent connected vehicles connected to the safety assessment platform are marked as assessment objects, an assessment cycle is generated and divided into several assessment periods, and the switching process of the safety instructions of the assessment object from the high-sequence number state to the low-sequence number state during the assessment period is extracted and marked as an assessment process, and it is determined whether the assessment process meets the risk characteristics: if so, the assessment process is marked as a risk process; if not, the assessment process is marked as a safety process; the risk characteristics include that the duration of the assessment process is less than M1 seconds and the difference between the high sequence number and the low sequence number is not less than two, M1 is a numerical constant, and the specific value of M1 is set by the management personnel; the risk process marked within the assessment period is The ratio of the number of processes to the number of evaluation processes is marked as the risk coefficient of the evaluation period, and the risk coefficient is compared with the preset risk threshold: if the risk coefficient is less than the risk threshold, it is determined that the driving decision safety of the evaluation object in the evaluation period meets the requirements; if the risk coefficient is greater than or equal to the risk threshold, it is determined that the driving decision safety of the evaluation object in the evaluation period does not meet the requirements, and a decision optimization analysis signal is generated and sent to the decision optimization analysis module through the safety assessment platform; the risk degree of the safety instructions in each evaluation period is analyzed in a periodic time-division monitoring manner to obtain the risk coefficient, and the driving decision safety in the evaluation period is evaluated by the risk coefficient, and the optimization analysis is triggered in time when the safety is abnormal.

[0036] The decision optimization analysis module is used to optimize and analyze the safe driving decision-making process of intelligent connected vehicles: the preceding safety instructions of the risk process correspond to the static control instructions and the dynamic control instructions in the planning analysis in the driving decision instruction sequence and are marked as J-1 and D-1 respectively, and the subsequent safety instructions of the risk process correspond to the static control instructions and the dynamic control instructions in the planning analysis in the driving decision instruction sequence and are marked as J-2 and D-2 respectively; by marking the difference between J-2 and J-1 and the difference between D-2 and D-1 as the static optimization value and the dynamic optimization value respectively, the static optimization value is compared with the dynamic optimization value: if the static optimization value is less than the dynamic optimization value, a dynamic optimization signal is generated and the dynamic optimization value is increased. The optimization signal is sent to the manager's mobile terminal through the safety assessment platform; if the static optimization value is greater than the dynamic optimization value, a static optimization signal is generated and sent to the manager's mobile terminal through the safety assessment platform; if the static optimization value is equal to the dynamic optimization value, a bidirectional optimization signal is generated and sent to the manager's mobile terminal; the safe driving decision-making process of intelligent connected vehicles is optimized and analyzed, and the sequence numbers of static control instructions and dynamic control instructions in the driving decision instruction sequence during the risk process are numerically analyzed to obtain static optimization values and dynamic optimization values. The optimization measures for safe driving decisions are directly marked according to the static optimization values and dynamic optimization values to improve optimization efficiency.

[0037] The intelligent connected vehicle safe driving decision control system based on a mixed traffic environment, when working, senses and analyzes the static traffic environment during the driving process of the intelligent connected vehicle and obtains basic road condition information, senses and analyzes the dynamic traffic environment during the driving process of the intelligent connected vehicle and obtains dynamic environment information, retrieves the driving decision instruction sequence of the intelligent connected vehicle, compares the basic road condition information with the driving decision instruction sequence to obtain static control instructions, compares the dynamic environment information with the driving decision instruction sequence to obtain dynamic control instructions, and marks the sequence numbers of the static control instructions and the dynamic control instructions in the driving decision instruction sequence as static, respectively. Evaluation value and dynamic evaluation value, mark the safety instructions through static evaluation value and dynamic evaluation value; generate an evaluation cycle and divide the evaluation cycle into several evaluation periods, extract the switching process of the safety instructions of the evaluation object from a high-numbered state to a low-numbered state during the evaluation period and mark it as an evaluation process, mark the evaluation process as a safe process or a risky process, mark the ratio of the number of risk processes marked in the evaluation period to the number of evaluation processes as the risk coefficient of the evaluation period, judge whether the driving decision safety of the evaluation object during the evaluation period meets the requirements through the risk coefficient, and perform optimization analysis if it does not meet the requirements.

[0038] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

[0039] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0040] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A safe driving decision-making and control system for intelligent connected vehicles based on mixed traffic environments, comprising a perception module, a decision-making and planning module, and a control execution module connected in sequence, characterized in that: The perception module includes a static perception unit and a dynamic perception unit; The static perception unit obtains the location and navigation route of the intelligent connected vehicle in real time, uploads the location and navigation route of the intelligent connected vehicle to the Internet of Vehicles, retrieves the basic road condition information of the nearest L1 meter in the intelligent connected vehicle's driving path through the Internet of Vehicles, and sends the basic road condition information of the intelligent connected vehicle to the decision-making and planning module; Dynamic perception unit, which obtains the dynamic environment information of the intelligent connected vehicle in real time and sends the dynamic environment information of the intelligent connected vehicle to the decision-making and planning module; The decision-making planning module retrieves the driving decision instruction sequence of the intelligent connected vehicle; compares the basic road condition information and dynamic environment information with the driving decision instruction sequence to obtain static control instructions and dynamic control instructions, marks the sequence numbers of the static control instructions and dynamic control instructions in the driving decision instruction sequence as static evaluation values and dynamic evaluation values, respectively, marks the safety instructions with the static evaluation values and dynamic evaluation values; and sends the safety instructions to the control execution module; The decision-making planning module is also communicatively connected to the safety assessment platform. After generating a safety instruction, the decision-making planning module sends the safety instruction synchronously to the safety assessment platform. The safety assessment platform is communicatively connected to the safety assessment module and the decision optimization analysis module.

2. The intelligent connected vehicle safe driving decision control system based on mixed traffic environment according to claim 1 is characterized in that: The driving decision instruction sequence is a sequence of several driving instructions sorted from low to high according to the safety level. The driving instructions include stopping, braking, deceleration, speed control, lane change and overtaking; and the driving instructions correspond to the basic road condition information and dynamic environment information.

3. The intelligent connected vehicle safe driving decision control system based on mixed traffic environment according to claim 2 is characterized in that: The marking process of the safety instruction includes: comparing the static evaluation value with the dynamic evaluation value: if the static evaluation value is less than the dynamic evaluation value, the static control instruction is marked as a safety instruction; if the static evaluation value is greater than or equal to the dynamic evaluation value, the dynamic control instruction is marked as a safety instruction.

4. The intelligent connected vehicle safe driving decision control system based on mixed traffic environment according to claim 3 is characterized in that: The safety assessment module is used to evaluate and analyze the driving decision safety of intelligent connected vehicles. It marks the intelligent connected vehicles connected to the safety assessment platform as assessment objects, generates an assessment cycle, and divides the assessment cycle into several assessment periods. The switching process of the assessment object's safety instructions from a high-order state to a low-order state during the assessment period is extracted and marked as an assessment process, and the assessment process is marked as a risk process or a safety process. The ratio of the number of risk processes marked in the evaluation period to the number of evaluation processes is marked as the risk coefficient of the evaluation period. The risk coefficient is used to determine whether the driving decision safety of the evaluation object in the evaluation period meets the requirements.

5. The intelligent connected vehicle safe driving decision control system based on mixed traffic environment according to claim 4 is characterized in that: The specific process of marking the assessment process as a risk process or a safety process includes: determining whether the assessment process meets the risk characteristics: if so, the assessment process is marked as a risk process; if not, the assessment process is marked as a safety process; the risk characteristics include that the duration of the assessment process is less than M1 seconds and the difference between the high sequence number and the low sequence number is not less than two.

6. The intelligent connected vehicle safe driving decision control system based on mixed traffic environment according to claim 5 is characterized in that: The specific process of determining whether the driving decision safety of the assessment object during the assessment period meets the requirements includes: comparing the risk coefficient with the preset risk threshold: if the risk coefficient is less than the risk threshold, it is determined that the driving decision safety of the assessment object during the assessment period meets the requirements; if the risk coefficient is greater than or equal to the risk threshold, it is determined that the driving decision safety of the assessment object during the assessment period does not meet the requirements, generating a decision optimization analysis signal and sending the decision optimization analysis signal to the decision optimization analysis module through the safety assessment platform.

7. The intelligent connected vehicle safe driving decision control system based on mixed traffic environment according to claim 6 is characterized in that: The decision optimization analysis module is used to optimize and analyze the safe driving decision process of the intelligent connected vehicle: the preceding safety instructions of the risk process correspond to the static control instructions and the dynamic control instructions in the planning analysis in the driving decision instruction sequence and are marked as J-1 and D-1 respectively, and the subsequent safety instructions of the risk process correspond to the static control instructions and the dynamic control instructions in the planning analysis in the driving decision instruction sequence and are marked as J-2 and D-2 respectively; by marking the difference between J-2 and J-1 and the difference between D-2 and D-1 as the static optimization value and the dynamic optimization value respectively, the static optimization value and the dynamic optimization value are compared, and an optimization signal is generated based on the comparison results.

8. The intelligent connected vehicle safe driving decision control system based on mixed traffic environment according to claim 7 is characterized in that: The specific process of comparing the static optimization value with the dynamic optimization value includes: if the static optimization value is less than the dynamic optimization value, a dynamic optimization signal is generated and sent to the administrator's mobile terminal through the security assessment platform; if the static optimization value is greater than the dynamic optimization value, a static optimization signal is generated and sent to the administrator's mobile terminal through the security assessment platform; if the static optimization value is equal to the dynamic optimization value, a bidirectional optimization signal is generated and sent to the administrator's mobile terminal.

Images