An automatic driving and control system for intelligent public transportation vehicles

Abstract

The present invention provides an automatic driving and control system for an intelligent public transport vehicle, belonging to the technical field of intelligent public transport vehicles, the system includes a cloud subsystem and a vehicle-side subsystem, the vehicle-side subsystem includes a collaborative control module, an in-vehicle monitoring module and an automatic driving control module. The cloud subsystem can determine the reference comfort threshold of the intelligent public transport vehicle under a variety of preset working conditions based on vehicle parameters and road condition information, and the collaborative control module can correct the reference comfort threshold under the target working condition according to the passenger image data collected by the in-vehicle monitoring module when determining that the intelligent public transport vehicle enters any target working condition among the multiple preset working conditions, and obtain the target comfort threshold under the target working condition, so that the automatic driving control module can control the driving of the intelligent public transport vehicle based on the target comfort threshold, thereby fully ensuring the comfort and safety of passengers riding the intelligent public transport vehicle, and effectively improving the riding experience of passengers.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent public transport vehicles, and in particular to an automatic driving and control system for an intelligent public transport vehicle. Background Art

[0002] With the continuous advancement of autonomous driving technology and the increasing demand for intelligent transportation in society, the development of intelligent public transportation vehicles will continue to advance and become an important part of the city's intelligent transportation system.

[0003] In related technologies, smart public transportation vehicles can use on-board sensors to sense the surrounding environment, analyze the sensed information, formulate driving strategies, and then control the acceleration, braking and steering of the vehicle according to the formulated driving strategies to ensure that the vehicle travels safely along the predetermined route.

[0004] However, due to the fact that the smart bus has a long and high body, has poor adaptability to road conditions during driving, and requires frequent stops and starts, the comfort and safety of passengers riding in the smart bus is greatly reduced, resulting in a poor riding experience for passengers. Summary of the invention

[0005] The embodiment of the present invention provides an automatic driving and control system for an intelligent public transportation vehicle, and the present invention adopts the following technical solutions:

[0006] The present invention provides an automatic driving and control system for an intelligent public transport vehicle, the system comprising a cloud subsystem and a vehicle subsystem; the vehicle subsystem comprises a collaborative control module, an in-vehicle monitoring module and an automatic driving control module;

[0007] The collaborative control module is used to send a data acquisition request for the target operation route to the cloud subsystem when it is determined that the intelligent public transport vehicle enters the target operation route;

[0008] The cloud subsystem is used to respond to the data acquisition request and feed back to the collaborative control module a control parameter data packet of the intelligent public transport vehicle on the target operation route; wherein the control parameter data packet is determined by the cloud subsystem based on the vehicle parameters of the intelligent public transport vehicle and the road condition information of the target operation route; the control parameter data packet includes a reference comfort threshold value of the intelligent public transport vehicle under a plurality of preset working conditions, and the reference comfort threshold value represents a vehicle motion parameter that satisfies the comfort of passengers;

[0009] The collaborative control module is further configured to send a passenger data acquisition instruction to the in-vehicle monitoring module when it is determined that the intelligent public transport vehicle enters any target operating condition among the multiple preset operating conditions;

[0010] The in-vehicle monitoring module is used to obtain passenger image data of passengers in the intelligent public transport vehicle in response to the passenger data acquisition instruction, and send the passenger image data to the collaborative control module;

[0011] The collaborative control module is further configured to correct the reference comfort threshold under the target operating condition based on the passenger image data to obtain a target comfort threshold under the target operating condition, and send the target comfort threshold to the automatic driving control module;

[0012] The automatic driving control module is used to control the intelligent public transport vehicle to travel based on the target comfort threshold when the intelligent public transport vehicle is in the target operating condition.

[0013] In one embodiment of the present invention, the road condition information includes the road type and road image data of the target running route; the vehicle parameters include the spring stiffness coefficient, the shock absorber damping coefficient and / or the suspension geometry parameter of the suspension system;

[0014] The cloud subsystem includes a vehicle performance determination module, a benchmark threshold acquisition module and a reference threshold determination module;

[0015] The vehicle performance determination module is used to determine the ride comfort of the intelligent public transport vehicle based on the spring stiffness coefficient, the shock absorber damping coefficient and / or the suspension geometric parameter;

[0016] The reference threshold acquisition module is used to determine the reference comfort threshold of the intelligent public transport vehicle under multiple preset working conditions based on the road type and the riding comfort;

[0017] The reference threshold determination module is used to correct the benchmark comfort threshold based on the road image data to obtain the reference comfort threshold of the intelligent public transport vehicle under multiple preset working conditions.

[0018] In one embodiment of the present invention, the reference threshold determination module includes a road image recognition submodule and a reference threshold correction submodule;

[0019] The road image recognition submodule is used to determine the aging factor of the target running route based on the road image data; the aging factor represents the aging degree of the target running route;

[0020] The reference threshold correction submodule is used to correct the reference comfort threshold based on the aging factor to obtain a reference comfort threshold of the intelligent public transport vehicle under a variety of preset working conditions.

[0021] In one embodiment of the present invention, the road image recognition submodule includes a road feature extraction unit and a first model recognition unit;

[0022] The road feature extraction unit is used to extract features from the road image data to obtain multi-dimensional wear feature data; the multi-dimensional wear feature data includes road surface wear feature data and road marking wear feature data;

[0023] The first model recognition unit is used to input the multi-dimensional wear feature data into a pre-trained road aging recognition model, and output an aging factor of the target running route; the road aging recognition model is trained based on the multi-dimensional wear feature data of sample road image data.

[0024] In one embodiment of the present invention, the plurality of preset operating conditions include an acceleration operating condition, a deceleration operating condition, a lane changing operating condition and a turning operating condition;

[0025] The automatic driving control module is used to determine the running track of the intelligent public transport vehicle and send the running track to the collaborative control module;

[0026] The collaborative control module is further used to determine the target operating condition of the intelligent public transport vehicle among the multiple preset operating conditions based on the operating trajectory and the driving status data of the intelligent public transport vehicle.

[0027] In one embodiment of the present invention, the driving state data includes vehicle speed change rate, longitudinal acceleration, lateral acceleration, steering wheel angle and steering wheel angle change rate;

[0028] The collaborative control module includes an acceleration condition determination submodule, a deceleration condition determination submodule, a lane change condition determination submodule and a turning condition determination submodule;

[0029] The acceleration operating condition determination submodule is used to determine that the target operating condition is the acceleration operating condition when the vehicle speed change rate is greater than an upper threshold value and the longitudinal acceleration is a positive value;

[0030] The deceleration operating condition determination submodule is used to determine that the target operating condition is the deceleration operating condition when the vehicle speed change rate is less than a lower threshold value and the longitudinal acceleration is a negative value;

[0031] The lane-changing operating condition determination submodule is used to determine that the target operating condition is the lane-changing operating condition when the lateral acceleration is greater than an acceleration threshold, the steering wheel angle change rate is greater than an angle change rate threshold, and the running trajectory indicates that the intelligent public transport vehicle crosses the lane;

[0032] The turning condition determination submodule is used to determine that the target condition is the turning condition when the steering wheel angle is greater than an angle threshold and the trajectory curvature of the running trajectory is greater than a curvature threshold.

[0033] In one embodiment of the present invention, the collaborative control module further includes a first reference threshold determination submodule, a second reference threshold determination submodule, a third reference threshold determination submodule and a fourth reference threshold determination submodule;

[0034] The first reference threshold determination submodule is used to determine, when the target operating condition is determined to be the acceleration operating condition, that the reference comfort threshold under the acceleration operating condition includes a longitudinal acceleration threshold and a longitudinal jerk threshold;

[0035] The second reference threshold determination submodule is used to determine, when it is determined that the target operating condition is the deceleration operating condition, that the reference comfort threshold under the deceleration operating condition includes a braking deceleration threshold and a braking jerk threshold;

[0036] The third reference threshold determination submodule is used to determine, when the target operating condition is determined to be the lane changing operating condition, that the reference comfort thresholds under the lane changing operating condition include a lane changing acceleration threshold, a centering acceleration threshold, a lateral acceleration threshold, and a lateral jerk threshold;

[0037] The fourth reference threshold determination submodule is used to determine, when it is determined that the target operating condition is the turning operating condition, that the reference comfort thresholds under the turning operating condition include a lateral acceleration threshold when entering a turn, a longitudinal acceleration threshold when exiting a turn, a lateral acceleration threshold, and a longitudinal jerk threshold.

[0038] In one embodiment of the present invention, the collaborative control module includes a passenger image recognition submodule and a reference threshold correction submodule;

[0039] The passenger image recognition submodule is used to determine a passenger risk factor based on the passenger image data; the passenger risk factor represents the passenger's riding safety level;

[0040] The reference threshold correction submodule is used to correct the reference comfort threshold under the target operating condition based on the passenger risk factor to obtain the target comfort threshold under the target operating condition.

[0041] In one embodiment of the present invention, the passenger image recognition submodule includes a passenger feature extraction unit and a second model recognition unit;

[0042] The passenger feature extraction unit is used to extract features from the passenger image data to obtain multi-dimensional passenger feature data; the multi-dimensional passenger feature data includes age feature data, gender feature data and standing passenger density data;

[0043] The second model recognition unit is used to input the multi-dimensional passenger feature data into a pre-trained passenger risk recognition model and output the passenger risk factor; the passenger risk recognition model is trained based on the multi-dimensional passenger feature data of sample passenger image data.

[0044] In one embodiment of the present invention, the vehicle-side subsystem further includes a voice prompt module;

[0045] The automatic driving control module is further configured to send the preset working condition to the collaborative control module when it is determined that the predicted motion parameter of the intelligent public transport vehicle under any of the preset working conditions exceeds the target comfort threshold under the preset working condition;

[0046] The collaborative control module is further used to determine a target voice prompt instruction corresponding to the preset working condition, and send the target voice prompt instruction to the voice prompt module;

[0047] The voice prompt module is used to respond to the target voice prompt instruction and output the target voice prompt information corresponding to the target voice prompt instruction; the target voice prompt information is used to prompt passengers that the intelligent public transport vehicle is about to enter the preset operating condition.

[0048] In summary, the automatic driving and control system of the above-mentioned intelligent public transportation vehicle has the following technical effects:

[0049] An automatic driving and control system for an intelligent public transport vehicle provided by an embodiment of the present invention, wherein a cloud subsystem can obtain a control parameter data packet of the intelligent public transport vehicle in a target operating route based on the vehicle parameters of the intelligent public transport vehicle and the road condition information of the target operating route, the control parameter data packet including the reference comfort threshold of the intelligent public transport vehicle under a plurality of preset operating conditions, and in response to a data acquisition request sent by a collaborative control module, the control parameter data packet is fed back to the collaborative control module; the collaborative control module can correct the reference comfort threshold under the target operating condition according to the passenger image data sent by the in-vehicle monitoring module when determining that the intelligent public transport vehicle enters any target operating condition among a plurality of preset operating conditions, and obtain the target comfort threshold under the target operating condition; the automatic driving control module can control the intelligent public transport vehicle to travel based on the target comfort threshold when the intelligent public transport vehicle is in the target operating condition. The embodiment of the present invention can realize the dynamic adjustment of the target comfort threshold under various preset operating conditions by comprehensively considering the vehicle parameters of the intelligent public transport vehicle, the road condition information of the target operating route and the passenger image data, and then can determine the appropriate target comfort threshold for automatic driving control when the intelligent public transport vehicle is in any preset operating condition. In this way, during the operation of the smart public transport, the comfort and safety of passengers riding the smart public transport can be fully guaranteed, thereby effectively improving the passengers' riding experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic structural diagram of an automatic driving and control system for an intelligent public transportation vehicle provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The technical solution of the present invention will be described below in conjunction with the accompanying drawings.

[0052] It should be noted that buses are usually designed to carry more passengers, so the seating and space layout does not focus on personal comfort as much as private cars, which makes passengers more likely to feel uncomfortable when riding on buses.

[0053] Specifically, due to their large size, long and high body, buses have poor adaptability to uneven road surfaces during driving, resulting in more bumps; buses need to start and stop frequently and stop at stations, and frequent acceleration and deceleration can easily cause passengers to feel uncomfortable; buses are often very crowded during peak hours, and many passengers need to stand, and passengers who lack support are prone to lose balance during driving; when the bus is driving, passengers sit relatively high, and as the bus turns, slows down, and other changes, some passengers may feel motion sickness.

[0054] In related technologies, smart public transport vehicles are usually equipped with various on-board sensors (such as cameras, radars, laser radars, etc.) to detect the external environment and implement the automatic driving of smart public transport vehicles according to fixed automatic driving strategies. When controlling the vehicle to accelerate, brake, and turn, the passenger status in the vehicle is not considered, and the vehicle motion parameters cannot be changed according to the passenger status, which in turn affects the comfort and safety of passengers riding in smart public transport vehicles, resulting in a poor riding experience for passengers.

[0055] Based on this, the present invention aims to provide an automatic driving and control system for an intelligent public transport vehicle. First, a cloud subsystem is used to obtain a control parameter data packet of the intelligent public transport vehicle in the target operating route based on the vehicle parameters of the intelligent public transport vehicle and the road condition information of the target operating route. The control parameter data packet includes the reference comfort threshold value of the intelligent public transport vehicle under multiple preset working conditions; then, the collaborative control module is used to correct the reference comfort threshold value under the target working condition according to the passenger image data sent by the in-vehicle monitoring module when determining that the intelligent public transport vehicle enters any target working condition among the multiple preset working conditions, so as to obtain the target comfort threshold value under the target working condition; finally, the automatic driving control module is used to control the driving of the intelligent public transport vehicle based on the target comfort threshold value when the intelligent public transport vehicle is in the target working condition. In this way, by comprehensively considering the vehicle parameters of the intelligent public transport vehicle, the road condition information of the target operating route and the passenger image data, the dynamic adjustment of the target comfort threshold value under various preset working conditions can be realized, and then when the intelligent public transport vehicle is in any preset working condition, the appropriate target comfort threshold value can be determined for automatic driving control, so as to fully ensure the comfort and safety of passengers riding the intelligent public transport vehicle, and effectively improve the riding experience of passengers.

[0056] Reference Figure 1 An embodiment of the present invention provides a structural diagram of an automatic driving and control system of an intelligent public transportation vehicle, the system includes a cloud subsystem 100 and a vehicle-side subsystem 200; the vehicle-side subsystem 200 includes an in-vehicle monitoring module 201, a collaborative control module 202 and an automatic driving control module 203.

[0057] In this embodiment, the collaborative control module 202 is used to send a data acquisition request for the target operating route to the cloud subsystem 100 when it is determined that the intelligent public transportation vehicle enters the target operating route.

[0058] In a specific implementation, the collaborative control module 202 can obtain the GPS (Global Positioning System) information of the intelligent public transport in real time through the high-precision positioning device equipped by the intelligent public transport, and then determine whether the intelligent public transport has entered the target operation route based on the GPS information. Specifically, the collaborative control module 202 can determine the GPS track of the intelligent public transport based on the GPS information of the intelligent public transport, and then determine that the intelligent public transport has entered the target operation route when the GPS track is on the target operation route.

[0059] In this embodiment, once the collaborative control module 202 detects that the intelligent public transport vehicle enters the target operating route, it will send a data acquisition request containing the route identifier of the target operating route to the cloud subsystem 100. After receiving the data acquisition request, the cloud subsystem 100 can determine the target operating route where the intelligent public transport vehicle is currently located based on the route identifier.

[0060] In this embodiment, the cloud subsystem 100 is used to respond to the data acquisition request and feed back the control parameter data packet of the intelligent public transportation vehicle on the target operation route to the collaborative control module 202.

[0061] It should be noted that the control parameter data packet is determined by the cloud subsystem 100 based on the vehicle parameters of the smart bus and the road condition information of the target operating route. The control parameter data packet includes reference comfort thresholds of the smart bus under various preset operating conditions. The reference comfort thresholds represent vehicle motion parameters that meet passenger comfort.

[0062] Specifically, the vehicle parameters represent vehicle parameters related to passenger comfort. Since the suspension system is an important component that affects the ride comfort of the vehicle, the suspension system parameters can be used as vehicle parameters. Different models of smart public transportation vehicles can correspond to different vehicle parameters. The cloud subsystem 100 can determine the vehicle parameters corresponding to the vehicle identification based on the vehicle identification of the smart public transportation vehicle.

[0063] Specifically, the road condition information refers to road condition information related to passenger comfort. As the road is used for a longer period of time, the road will age and wear to a certain extent, and the greater the degree of aging, the greater the impact on passenger comfort. Therefore, by analyzing the road condition information, the degree of aging of the target route can be determined.

[0064] In this embodiment, the cloud subsystem 100 can determine appropriate control parameter data packets for smart buses of different models for different operating routes by comprehensively considering the vehicle parameters of the smart bus and the road condition information of the target operating route.

[0065] In this embodiment, the plurality of preset operating conditions may include an acceleration condition, a deceleration condition, a lane change condition, and a turning condition. Different preset operating conditions may correspond to different types of reference comfort thresholds. For example, in an acceleration condition, the corresponding reference comfort threshold may include a longitudinal acceleration threshold; in a turning condition, the corresponding reference comfort threshold may include a longitudinal acceleration threshold.

[0066] In this embodiment, the collaborative control module 202 is further configured to send a passenger data acquisition instruction to the in-vehicle monitoring module 201 when it is determined that the intelligent public transportation vehicle enters any target operating condition among a plurality of preset operating conditions.

[0067] It should be noted that the reference comfort threshold is the comfort threshold when the cloud subsystem 100 does not consider the passenger status. In the actual driving process of the vehicle, different passenger status often corresponds to different comfort requirements and safety requirements. For example, the older the passenger is and the more standing passengers there are, the smoother the intelligent public transport vehicle needs to travel. Therefore, the collaborative control module 202 will also obtain the passenger image data of the passengers in the intelligent public transport vehicle through the in-vehicle monitoring module 201 to analyze the passenger status and modify the reference comfort threshold according to the passenger status.

[0068] In a specific implementation, the collaborative control module 202 will detect the real-time working condition of the smart bus. Once it is detected that the smart bus enters any target working condition among multiple preset working conditions, it will control the in-vehicle monitoring module 201 to collect passenger image data.

[0069] In this embodiment, the in-vehicle monitoring module 201 is used to obtain passenger image data of passengers in the intelligent public transportation vehicle in response to a passenger data acquisition instruction, and send the passenger image data to the collaborative control module 202 .

[0070] In this embodiment, in order to realize the comprehensive collection of the status of passengers in the vehicle, the in-vehicle monitoring module 201 can collect passenger image data by configuring the first monitoring device and the second monitoring device in the vehicle. The first monitoring device is set at the front of the vehicle to collect passenger image data from the front to the rear of the vehicle; the second monitoring device is set at the rear of the vehicle to collect passenger image data from the rear to the front of the vehicle.

[0071] In this embodiment, the in-vehicle monitoring module 201 can send the passenger image data collected by the first monitoring device and the second monitoring device at the same time to the in-vehicle monitoring module 201 based on the timestamp of the passenger image data, so that the in-vehicle monitoring module 201 can perform a complete passenger feature analysis.

[0072] In this embodiment, the collaborative control module 202 is also used to correct the reference comfort threshold under the target operating condition based on the passenger image data, obtain the target comfort threshold under the target operating condition, and send the target comfort threshold to the automatic driving control module 203.

[0073] In this embodiment, the collaborative control module 202 can accurately obtain the passenger characteristic data of the passengers in the vehicle by performing feature analysis on the passenger image data, and then correct the reference comfort threshold under the target working condition based on the passenger characteristic data.

[0074] In one example, the reference comfort threshold under the acceleration condition is the longitudinal acceleration threshold. The cloud subsystem 100 determines that the longitudinal acceleration threshold of the intelligent public transport vehicle under the acceleration condition is 0.18g based on the vehicle parameters of the intelligent public transport vehicle and the road condition information of the target operation route. The collaborative control module 202 identifies that there are a standing passengers, b young passengers aged 1 to 12 years old, and c elderly passengers aged over 60 years old in the vehicle by performing feature analysis on the passenger image data. At this time, after the longitudinal acceleration threshold is corrected by the above passenger characteristics, the longitudinal acceleration threshold under the acceleration condition is obtained to be 0.14g. In this way, the reference comfort threshold under any preset condition can be corrected according to the real-time status of the passengers in the vehicle to obtain the vehicle motion parameters that can actually meet the comfort of the passengers. It should be noted that if it is detected that there are no passengers in the vehicle, that is, in the empty vehicle state, the longitudinal acceleration threshold under the acceleration condition can be increased from 0.18g to 0.2g to improve the operating efficiency in the empty vehicle state.

[0075] In this embodiment, the automatic driving control module 203 is used to control the intelligent public transport vehicle to travel based on the target comfort threshold when the intelligent public transport vehicle is in the target operating condition.

[0076] It should be noted that the automatic driving control module 203 is mainly responsible for controlling the vehicle to accelerate, brake and turn, so as to realize automatic driving operation of the smart bus on the target route.

[0077] In this embodiment, after receiving the target comfort threshold sent by the collaborative control module 202, the automatic driving control module 203 will use the target comfort threshold as a constraint condition for vehicle driving to control the driving of the intelligent public transport vehicle. For example, when the longitudinal acceleration threshold under the acceleration condition is 0.14g, the automatic driving control module 203 will limit the actual longitudinal acceleration of the intelligent public transport vehicle to less than 0.14g after the intelligent public transport vehicle enters the acceleration condition. In this way, it can effectively ensure that the vehicle will not generate a large longitudinal acceleration during the acceleration process, thereby effectively avoiding the occurrence of discomfort and falling injuries of passengers, thereby improving the comfort and safety of passengers.

[0078] In this embodiment, the automatic driving control module 203 can also remove the restriction of the target comfort threshold when determining that the intelligent public transport vehicle is in an emergency state, such as emergency braking or emergency obstacle avoidance, to ensure the driving safety of the intelligent public transport vehicle; when the intelligent public transport vehicle is not in an emergency state, it continues to control the driving of the intelligent public transport vehicle based on the target comfort threshold. In this way, the driving safety of the intelligent public transport vehicle can be ensured while the comfort and safety of the passengers can be guaranteed to the greatest extent.

[0079] In this embodiment, by comprehensively considering the vehicle parameters of the intelligent public transport, the road condition information of the target operation route, and the passenger image data, the target comfort threshold under various preset working conditions can be dynamically adjusted, and then when the intelligent public transport is in any preset working condition, the appropriate target comfort threshold can be determined for automatic driving control. In this way, during the operation of the intelligent public transport, the comfort and safety of passengers riding in the intelligent public transport can be fully guaranteed, thereby effectively improving the passenger riding experience.

[0080] In a feasible implementation manner, the road condition information includes the road type and road image data of the target running route; the vehicle parameters include the spring stiffness coefficient, the shock absorber damping coefficient and / or the suspension geometry parameters of the suspension system.

[0081] In this embodiment, the cloud subsystem 100 includes a vehicle performance determination module, a benchmark threshold acquisition module and a reference threshold determination module.

[0082] In this embodiment, the vehicle performance determination module is used to determine the ride comfort of the intelligent public transport vehicle based on the spring stiffness coefficient, the shock absorber damping coefficient and / or the suspension geometry parameter.

[0083] It should be noted that the spring stiffness coefficient is used to control the degree of deformation of the vehicle when it is subjected to vertical load. When the stiffness is low, the vehicle is relatively soft when driving and provides better comfort, but too low a stiffness may lead to poor handling; the shock absorber damping coefficient is used to control the energy dissipation capacity of the vehicle when vibration occurs. Appropriate damping can reduce the shaking of the vehicle when the road surface is uneven and improve comfort; the suspension geometry parameters affect the stability and dynamic response of the vehicle, and may include parameters such as track width, wheelbase, length and angle of the suspension link.

[0084] In a specific implementation, the riding comfort of the smart public transport can be determined by conducting a real road condition test on the smart public transport to collect riding feedback data and dynamic response data.

[0085] In a specific implementation, a dynamic model of an intelligent public transport vehicle can be constructed based on the spring stiffness coefficient, the shock absorber damping coefficient and / or the suspension geometry parameters, and the motion of the intelligent public transport vehicle can be described by a differential equation, and the acceleration response and the passenger motion state can be collected, and then the riding comfort of the intelligent public transport vehicle can be quantified based on the acceleration response and the passenger motion state. Among them, the acceleration response is used to evaluate the vibration feeling of the passengers in the vehicle, which can be measured by calculating the root mean square value of the vehicle body acceleration; the passenger motion state represents the passenger feeling, which can be measured by parameters such as roll angle and pitch angle.

[0086] In this embodiment, by comprehensively considering the spring stiffness coefficient, shock absorber damping coefficient and suspension geometric parameters of the suspension system which are closely related to the vehicle riding comfort, the riding comfort can be accurately quantified. The riding comfort indicates the comfort level of passengers riding in the intelligent public transport vehicle.

[0087] In this embodiment, the reference threshold value acquisition module is used to determine the reference comfort threshold value of the intelligent public transport vehicle under various preset working conditions based on the road type and the riding comfort.

[0088] In this implementation, the road types may include Bus Rapid Transit (BRT) corridors, dedicated bus lanes, bus priority lanes, urban trunk roads, and mixed lanes, etc., according to the order of road comfort from high to low. Among them, the Bus Rapid Transit corridor has dedicated lanes and priority signals, which can reduce congestion and improve driving stability and speed; the dedicated bus lanes run on dedicated lanes to avoid mixing with other vehicles, which can provide a relatively smooth and stable riding experience; although the urban trunk roads have a large volume of traffic, they are usually well-equipped with traffic signals and road facilities, which can provide a relatively stable driving experience, but may still be affected by traffic jams; mixed lanes refer to lanes where buses and other vehicles run together, which may be affected by other vehicles, especially during peak traffic hours.

[0089] In this embodiment, based on the road type of the target operating route, the road comfort of the target operating route can be determined, and then by comprehensively considering the road comfort and ride comfort, the benchmark comfort threshold of the intelligent public transport vehicle under various preset operating conditions of the target operating route can be determined.

[0090] In this embodiment, the reference threshold determination module is used to correct the reference comfort threshold based on the road image data to obtain the reference comfort threshold of the intelligent public transport vehicle under various preset working conditions.

[0091] In this embodiment, considering that the target operation route will experience a certain degree of aging and wear as the use time increases, the reference threshold determination module will identify the aging degree of the target operation route based on the road image data, and then correct the reference comfort threshold according to the aging degree of the target operation route to obtain the reference comfort threshold of the intelligent public transport vehicle under various preset working conditions. Among them, the road image data is collected according to the preset update cycle, so as to achieve timely update of the reference comfort threshold; the road image data can be collected using any intelligent public transport vehicle running on the target operation route, or it can be collected using a dedicated data collection vehicle.

[0092] In a specific implementation, the road image recognition submodule includes a road feature extraction unit and a first model recognition unit.

[0093] In this embodiment, the road feature extraction unit is used to extract features from the road image data to obtain multi-dimensional wear feature data, wherein the multi-dimensional wear feature data may specifically include road surface wear feature data and road marking wear feature data.

[0094] In the specific implementation, the road image data can be processed through computer vision algorithms to extract features such as cracks, peeling, and dents, thereby obtaining multi-dimensional wear feature data; or, the road image data can be classified and identified using a trained feature extraction model to achieve automated extraction of multi-dimensional wear feature data.

[0095] It should be noted that the road wear characteristic data is used to reflect the wear of the road surface; the road marking wear characteristic data is used to reflect the wear of the bus markings. The more serious the road wear, the more serious the bumps during the driving of the smart bus; the more serious the wear of the bus markings, the more it will affect the recognition efficiency and control accuracy of the automatic driving module, and also affect the comfort of passengers.

[0096] In this embodiment, the first model recognition unit is used to input the multi-dimensional wear feature data into a pre-trained road aging recognition model, and output an aging factor of the target running route.

[0097] In this embodiment, the road aging recognition model is obtained by training based on the multi-dimensional wear feature data of the sample road image data. Specifically, the road aging recognition model can be trained in the following manner: obtaining sample road image data of the sample road, the sample road image data including the aging factor label of the sample road; extracting features from the sample road image data to obtain multi-dimensional wear feature data of the sample road image data, inputting the multi-dimensional wear feature data of the sample road image data into the initial road aging recognition model for training, and obtaining the predicted aging factor output by the initial road aging recognition model; then calculating the loss function value based on the predicted aging factor and the corresponding aging factor label, and iteratively updating the network parameters of the initial road aging recognition model based on the loss function value until the initial road aging recognition model meets the training cutoff condition, thereby obtaining a pre-trained road aging recognition model.

[0098] In this embodiment, by analyzing the multi-dimensional wear characteristic data using the trained road aging recognition model, the aging factor of the target running route can be determined quickly and accurately.

[0099] In this embodiment, the reference threshold correction submodule is used to correct the reference comfort threshold based on the aging factor to obtain the reference comfort threshold of the intelligent public transport vehicle under various preset working conditions.

[0100] In a specific implementation, the road image recognition submodule can update the aging factor of the target running route according to a preset update cycle, so that the reference threshold correction submodule can realize the synchronous correction of the reference comfort threshold.

[0101] In a feasible implementation manner, the multiple preset operating conditions include an acceleration condition, a deceleration condition, a lane changing condition, and a turning condition.

[0102] In this embodiment, the automatic driving control module 203 is used to determine the running trajectory of the intelligent public transportation vehicle and send the running trajectory to the collaborative control module 202.

[0103] In a specific implementation, the automatic driving control module 203 can generate the running track of the intelligent public transport vehicle according to a preset track generation algorithm. The specific generation process of the running track is referred to the prior art and will not be repeated here.

[0104] In this embodiment, the collaborative control module 202 is further used to determine the target operating condition of the intelligent public transport vehicle among a plurality of preset operating conditions based on the operating trajectory and the driving status data of the intelligent public transport vehicle.

[0105] In this embodiment, the collaborative control module 202 can effectively identify the acceleration and deceleration conditions by analyzing the driving status data of the intelligent public transport vehicle; and can effectively identify the lane changing and turning conditions by comprehensively considering the driving status data and the running trajectory.

[0106] In a specific implementation, the driving status data includes vehicle speed change rate, longitudinal acceleration, lateral acceleration, steering wheel angle and steering wheel angle change rate.

[0107] In this embodiment, the cooperative control module 202 includes an acceleration condition determination submodule, a deceleration condition determination submodule, a lane change condition determination submodule and a turning condition determination submodule.

[0108] In this embodiment, the acceleration operating condition determination submodule is used to determine that the target operating condition is an acceleration operating condition when the vehicle speed change rate is greater than an upper threshold value and the longitudinal acceleration is a positive value.

[0109] In this embodiment, the deceleration condition determination submodule is used to determine that the target condition is a deceleration condition when the vehicle speed change rate is less than the lower threshold and the longitudinal acceleration is a negative value. The upper threshold is greater than the lower threshold. Specifically, the upper threshold can be set to a positive value and the lower threshold can be set to a negative value.

[0110] In this embodiment, by comprehensively considering the vehicle speed change rate and the longitudinal acceleration, it is possible to accurately identify the acceleration condition and the deceleration condition, thereby effectively avoiding misjudgment.

[0111] In this embodiment, the lane-changing condition determination submodule is used to determine that the target condition is a lane-changing condition when the lateral acceleration is greater than the acceleration threshold, the steering wheel angle change rate is greater than the angle change rate threshold, and the running trajectory indicates that the intelligent public transport vehicle crosses the lane.

[0112] In this embodiment, by comprehensively considering the lateral acceleration, the steering wheel angle change rate and the running trajectory, accurate identification of the lane changing condition can be achieved, thereby effectively avoiding misjudgment.

[0113] In this embodiment, the turning condition determination submodule is used to determine that the target condition is a turning condition when the steering wheel angle is greater than the angle threshold and the trajectory curvature of the running trajectory is greater than the curvature threshold.

[0114] In this embodiment, by comprehensively considering the steering wheel angle and the trajectory curvature of the running trajectory, accurate identification of the turning condition can be achieved, thereby effectively avoiding misjudgment.

[0115] In a feasible implementation, the collaborative control module 202 further includes a first reference threshold determination submodule, a second reference threshold determination submodule, a third reference threshold determination submodule, and a fourth reference threshold determination submodule.

[0116] In this implementation, the first reference threshold determination submodule is used to determine, when it is determined that the target operating condition is an acceleration operating condition, that the reference comfort threshold under the acceleration operating condition includes a longitudinal acceleration threshold and a longitudinal jerk threshold.

[0117] It should be noted that the longitudinal jerk is the derivative of the longitudinal acceleration, which is used to characterize the rate of change of the longitudinal acceleration and is a quantity that describes how the longitudinal acceleration changes over time. In other words, the longitudinal acceleration represents the first-order derivative of the longitudinal velocity under acceleration conditions, while the longitudinal jerk represents the second-order derivative of the longitudinal velocity under acceleration conditions.

[0118] In this embodiment, by using the longitudinal acceleration threshold and the longitudinal jerk threshold together as the reference comfort threshold under the acceleration condition, the comfort of the passengers under the acceleration condition can be further ensured.

[0119] In this embodiment, the second reference threshold determination submodule is used to determine, when it is determined that the target operating condition is a deceleration operating condition, that the reference comfort threshold under the deceleration operating condition includes a braking deceleration threshold and a braking jerk threshold.

[0120] It should be noted that the braking jerk is the derivative of the braking deceleration, which is used to characterize the rate of change of the braking deceleration and is a quantity that describes how the braking deceleration changes over time. In other words, the braking deceleration represents the first-order derivative of the longitudinal speed under deceleration conditions, and the braking jerk threshold represents the second-order derivative of the longitudinal speed under deceleration conditions.

[0121] In this embodiment, by using the braking deceleration threshold and the braking jerk threshold together as the reference comfort threshold under the deceleration condition, the comfort of the passengers under the deceleration condition can be further ensured.

[0122] In this embodiment, the third reference threshold determination submodule is used to determine the reference comfort threshold under the lane changing condition, including the lane changing acceleration threshold, the centering acceleration threshold, the lateral acceleration threshold and the lateral jerk threshold, when the target condition is determined to be the lane changing condition.

[0123] It should be noted that the lane change acceleration refers to the acceleration of the vehicle when changing lanes, and the lane change acceleration can be determined based on the longitudinal acceleration and lateral acceleration of the vehicle when changing lanes; the return acceleration refers to the acceleration of the vehicle when returning to the center, and the return acceleration threshold can be determined based on the longitudinal acceleration and lateral acceleration of the vehicle when returning to the center. The lateral jerk is the derivative of the lateral acceleration, which is used to characterize the rate of change of the lateral acceleration and is a quantity that describes how the lateral acceleration changes over time, that is, the lateral acceleration represents the first-order derivative of the lateral velocity under the lane change condition, and the lateral jerk represents the second-order derivative of the lateral velocity under the lane change condition.

[0124] In this embodiment, by using the lane changing acceleration threshold, the centering acceleration threshold, the lateral acceleration threshold and the lateral jerk threshold as reference comfort thresholds under lane changing conditions, the comfort of passengers under lane changing conditions can be further ensured.

[0125] In this embodiment, the fourth reference threshold determination submodule is used to determine the reference comfort threshold under the turning condition, including the lateral acceleration threshold when entering the turn, the longitudinal acceleration threshold when exiting the turn, the lateral acceleration threshold and the longitudinal jerk threshold, when the target condition is determined to be a turning condition.

[0126] It should be noted that the lateral acceleration when entering a curve represents the lateral acceleration of the vehicle when entering a curve; the longitudinal acceleration threshold when exiting a curve represents the longitudinal acceleration of the vehicle when exiting a curve; the longitudinal jerk is the derivative of the longitudinal acceleration, which is used to characterize the rate of change of the longitudinal acceleration. It is a quantity that describes how the longitudinal acceleration changes with time, that is, the longitudinal acceleration represents the first-order derivative of the longitudinal velocity under the turning condition, and the longitudinal jerk represents the second-order derivative of the longitudinal velocity under the turning condition.

[0127] In a specific implementation, the fourth reference threshold determination submodule can identify a curve trajectory in the running trajectory, and determine the lateral acceleration of the intelligent public transport vehicle at the starting point of the curve trajectory as the lateral acceleration when entering the curve, and determine the longitudinal acceleration of the intelligent public transport vehicle at the end point of the curve trajectory as the longitudinal acceleration when exiting the curve.

[0128] In this embodiment, by using the lateral acceleration threshold when entering a curve, the longitudinal acceleration threshold when exiting a curve, the lateral acceleration threshold and the longitudinal jerk threshold as reference comfort thresholds under turning conditions, the comfort of passengers under turning conditions can be further ensured.

[0129] In a feasible implementation manner, the collaborative control module 202 includes a passenger image recognition submodule and a reference threshold correction submodule.

[0130] In this embodiment, the passenger image recognition submodule is used to determine the passenger risk factor based on the passenger image data. The passenger risk factor represents the safety level of the passenger in the vehicle. The larger the passenger risk factor, the higher the risk of the passenger in the vehicle.

[0131] In this embodiment, the passenger image recognition submodule can obtain passenger characteristic data of passengers in the vehicle by performing characteristic analysis on the passenger image data, and then determine appropriate passenger risk factors based on the passenger characteristic data.

[0132] In a specific implementation, the passenger image recognition submodule includes a passenger feature extraction unit and a second model recognition unit.

[0133] In this embodiment, the passenger feature extraction unit is used to extract features from the passenger image data to obtain multi-dimensional passenger feature data; wherein the multi-dimensional passenger feature data includes age feature data, gender feature data and standing passenger density data.

[0134] It should be noted that the age characteristic data is used to reflect the age of each passenger; the gender characteristic data is used to reflect the gender of each passenger; and the standing passenger density data is used to reflect the density of standing passengers, which can be determined based on the ratio of the number of standing passengers to the standing area of ​​the smart bus.

[0135] In a specific implementation, a pre-trained age recognition model can be used to identify passenger image data to obtain age feature data; a pre-trained gender recognition model can be used to identify passenger image data to obtain gender feature data; a pre-trained posture recognition model can be used to identify passenger image data to identify the number of standing passengers in a standing position, and then based on the number of standing passengers and the standing area of ​​the intelligent public transport vehicle, the standing passenger density data is determined. Among them, the age recognition model, the gender recognition model, and the posture recognition model are all obtained by training based on their corresponding training samples, which can be referred to, and the specific model training process can be omitted.

[0136] In this embodiment, the second model recognition unit is used to input multi-dimensional passenger feature data into a pre-trained passenger risk recognition model, and output a passenger risk factor; wherein the passenger risk recognition model is trained based on multi-dimensional passenger feature data of sample passenger image data.

[0137] Specifically, the passenger risk identification model can be trained in the following manner: obtaining sample passenger image data, the sample road image data including a passenger risk factor label; performing feature extraction on the sample passenger image data to obtain multi-dimensional passenger feature data of the sample passenger image data, inputting the multi-dimensional passenger feature data of the sample passenger image data into the initial passenger risk identification model for training, and obtaining a predicted passenger risk factor output by the initial passenger risk identification model; then calculating a loss function value based on the predicted passenger risk factor and the corresponding passenger risk factor label, and iteratively updating the network parameters of the initial passenger risk identification model based on the loss function value until the initial passenger risk identification model meets the training cutoff condition, thereby obtaining a pre-trained passenger risk identification model.

[0138] In this embodiment, by using the trained passenger risk identification model to conduct a comprehensive analysis of age characteristic data, gender characteristic data and standing passenger density data, the passenger risk factor can be determined quickly and accurately.

[0139] In this embodiment, the reference threshold correction submodule is used to correct the reference comfort threshold under the target operating condition based on the passenger risk factor to obtain the target comfort threshold under the target operating condition.

[0140] In a specific implementation, since the passenger risk factor represents the risk level of the passengers in the car, the larger the passenger risk factor is, the higher the risk of the passengers in the car. At this time, the reference comfort threshold under the target operating condition can be corrected to a greater extent.

[0141] Exemplarily, taking the longitudinal acceleration threshold under acceleration conditions as an example, if there are more elderly passengers and young passengers, more female passengers and / or a higher density of standing passengers, the longitudinal acceleration threshold in the target comfort threshold will be smaller.

[0142] In this embodiment, whenever the intelligent public transport vehicle enters any target operating condition among a plurality of preset operating conditions, the collaborative control module 202 can dynamically correct the reference comfort threshold under the target operating condition according to the passenger image data, thereby obtaining various target comfort thresholds that can actually meet the passenger comfort, thereby always ensuring the driving stability of the vehicle during the operation of the intelligent public transport vehicle and improving the riding experience of passengers.

[0143] In a feasible implementation manner, the vehicle-side subsystem 200 further includes a voice prompt module.

[0144] In this embodiment, the automatic driving control module 203 is also used to send the preset working condition to the collaborative control module 202 when it is determined that the predicted motion parameter of the intelligent public transportation vehicle under any preset working condition exceeds the target comfort threshold under the preset working condition.

[0145] In this embodiment, considering that the intelligent public transport vehicle is in an emergency state, such as emergency braking or emergency obstacle avoidance, in order to ensure driving safety, the automatic driving control module 203 cannot control the vehicle motion parameters within the target comfort threshold. Therefore, it will avoid passengers from feeling uncomfortable by reminding them in advance.

[0146] In a specific implementation, the automatic driving control module 203 will plan the running trajectory and determine the predicted motion parameters at a certain time in the future when controlling the driving of the intelligent public transport vehicle. If the automatic driving control module 203 detects that the predicted motion parameters of the intelligent public transport vehicle under any preset working condition inevitably exceed the target comfort threshold under the preset working condition, the prompt mechanism will be triggered.

[0147] For example, when the target comfort threshold under the acceleration condition is the longitudinal acceleration threshold, the longitudinal acceleration threshold is 0.14g, and the automatic driving control module 203 needs to control the longitudinal acceleration of the intelligent public transport vehicle to 0.25g to avoid other vehicles. At this time, the automatic driving control module 203 will send the condition identifier representing the acceleration condition to the collaborative control module 202. Different condition identifiers correspond to different preset conditions.

[0148] In this embodiment, the collaborative control module 202 is further used to determine the target voice prompt instruction corresponding to the preset working condition, and send the target voice prompt instruction to the voice prompt module.

[0149] In this embodiment, after determining the preset working condition that the intelligent public transport vehicle is currently in, the collaborative control module 202 further determines the target voice prompt instruction corresponding to the preset working condition. In a specific implementation, the collaborative control module 202 stores an instruction comparison table, which is used to store different voice prompt instructions corresponding to different preset working conditions.

[0150] In this embodiment, the voice prompt module is used to respond to the target voice prompt instruction and output the target voice prompt information corresponding to the target voice prompt instruction.

[0151] In a specific implementation, the collaborative control module 202 stores a voice information comparison table, which is used to store different voice prompt information corresponding to different voice prompt instructions. The target voice prompt information is used to prompt passengers that the intelligent public transport vehicle is about to enter a preset working condition.

[0152] For example, if the predicted motion parameters under the acceleration condition inevitably exceed the target comfort threshold under the acceleration condition, the target voice prompt information may be output as: Please note that the vehicle is about to accelerate.

[0153] In this embodiment, by giving voice prompts to passengers in advance before the vehicle enters the preset operating condition, on the one hand, the passengers can have a psychological anticipation for the preset operating condition, and will not experience sudden discomfort due to the vehicle's sudden large acceleration, deceleration, gear shifting or turning; on the other hand, after learning that the preset operating condition is about to be entered, the passengers can adjust their posture in time to adapt to the upcoming preset operating condition. For example, standing passengers can hold the support group or hanging ring in advance, which can effectively prevent the standing passengers from falling when the vehicle enters the preset operating condition.

[0154] In this embodiment, when the vehicle is in normal operating conditions, by determining a suitable target comfort threshold and controlling the driving of the intelligent public transport vehicle based on the target comfort threshold, the comfort and safety of passengers can be fully guaranteed under normal operating conditions; when the vehicle is in an abnormal preset operating condition, by giving voice prompts in advance, the comfort and safety of passengers can be improved under abnormal conditions.

[0155] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer program or instruction can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instruction can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0156] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0157] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0158] Those of ordinary skill in the art will appreciate that the submodules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0159] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and sub-modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0160] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of submodules is only a logical function division, and there may be other division methods in actual implementation, such as multiple submodules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or submodules, which can be electrical, mechanical or other forms.

[0161] The submodules described as separate components may or may not be physically separated, and the components shown as submodules may or may not be physical submodules, that is, they may be located in one place, or they may be distributed on multiple network submodules. Some or all of the submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] In addition, each functional submodule in each embodiment of the present invention may be integrated into one processing submodule, or each submodule may exist physically separately, or two or more submodules may be integrated into one submodule.

[0163] If the function is implemented in the form of a software function submodule and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0164] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An automatic driving and control system for an intelligent public transport vehicle, characterized in that: The system includes a cloud subsystem and a vehicle subsystem; the vehicle subsystem includes a collaborative control module, an in-vehicle monitoring module and an automatic driving control module; The collaborative control module is used to send a data acquisition request for the target operation route to the cloud subsystem when it is determined that the intelligent public transport vehicle enters the target operation route; The cloud subsystem is used to respond to the data acquisition request and feed back to the collaborative control module a control parameter data packet of the intelligent public transport vehicle on the target operation route; wherein the control parameter data packet is determined by the cloud subsystem based on the vehicle parameters of the intelligent public transport vehicle and the road condition information of the target operation route; the control parameter data packet includes a reference comfort threshold value of the intelligent public transport vehicle under a plurality of preset working conditions, and the reference comfort threshold value represents a vehicle motion parameter that satisfies the comfort of passengers; The collaborative control module is further configured to send a passenger data acquisition instruction to the in-vehicle monitoring module when it is determined that the intelligent public transport vehicle enters any target operating condition among the multiple preset operating conditions; The in-vehicle monitoring module is used to obtain passenger image data of passengers in the intelligent public transport vehicle in response to the passenger data acquisition instruction, and send the passenger image data to the collaborative control module; The collaborative control module is further configured to correct the reference comfort threshold under the target operating condition based on the passenger image data to obtain a target comfort threshold under the target operating condition, and send the target comfort threshold to the automatic driving control module; The automatic driving control module is used to control the intelligent public transport vehicle to travel based on the target comfort threshold when the intelligent public transport vehicle is in the target operating condition; The road condition information includes the road type and road image data of the target running route; the vehicle parameters include the spring stiffness coefficient, the shock absorber damping coefficient and / or the suspension geometry parameters of the suspension system; The cloud subsystem includes a vehicle performance determination module, a benchmark threshold acquisition module and a reference threshold determination module; The vehicle performance determination module is used to determine the ride comfort of the intelligent public transport vehicle based on the spring stiffness coefficient, the shock absorber damping coefficient and / or the suspension geometric parameter; The reference threshold acquisition module is used to determine the reference comfort threshold of the intelligent public transport vehicle under multiple preset working conditions based on the road type and the riding comfort; The reference threshold determination module is used to correct the benchmark comfort threshold based on the road image data to obtain the reference comfort threshold of the intelligent public transport vehicle under multiple preset working conditions.

2. The automatic driving and control system of an intelligent public transportation vehicle according to claim 1, characterized in that: The reference threshold determination module includes a road image recognition submodule and a reference threshold correction submodule; The road image recognition submodule is used to determine the aging factor of the target running route based on the road image data; The aging factor represents the aging degree of the target operation route; The reference threshold correction submodule is used to correct the reference comfort threshold based on the aging factor to obtain a reference comfort threshold of the intelligent public transport vehicle under a variety of preset working conditions.

3. The automatic driving and control system of an intelligent public transportation vehicle according to claim 2, characterized in that: The road image recognition submodule includes a road feature extraction unit and a first model recognition unit; The road feature extraction unit is used to extract features from the road image data to obtain multi-dimensional wear feature data; the multi-dimensional wear feature data includes road surface wear feature data and road marking wear feature data; The first model recognition unit is used to input the multi-dimensional wear feature data into a pre-trained road aging recognition model, and output an aging factor of the target running route; the road aging recognition model is trained based on the multi-dimensional wear feature data of sample road image data.

4. The automatic driving and control system of an intelligent public transportation vehicle according to claim 1, characterized in that: The multiple preset operating conditions include acceleration operating condition, deceleration operating condition, lane changing operating condition and turning operating condition; The automatic driving control module is used to determine the running track of the intelligent public transport vehicle and send the running track to the collaborative control module; The collaborative control module is further used to determine the target operating condition of the intelligent public transport vehicle among the multiple preset operating conditions based on the operating trajectory and the driving status data of the intelligent public transport vehicle.

5. The automatic driving and control system of an intelligent public transportation vehicle according to claim 4, characterized in that: The driving state data includes vehicle speed change rate, longitudinal acceleration, lateral acceleration, steering wheel angle and steering wheel angle change rate; The collaborative control module includes an acceleration condition determination submodule, a deceleration condition determination submodule, a lane change condition determination submodule and a turning condition determination submodule; The acceleration operating condition determination submodule is used to determine that the target operating condition is the acceleration operating condition when the vehicle speed change rate is greater than an upper threshold value and the longitudinal acceleration is a positive value; The deceleration operating condition determination submodule is used to determine that the target operating condition is the deceleration operating condition when the vehicle speed change rate is less than a lower threshold value and the longitudinal acceleration is a negative value; The lane-changing operating condition determination submodule is used to determine that the target operating condition is the lane-changing operating condition when the lateral acceleration is greater than an acceleration threshold, the steering wheel angle change rate is greater than an angle change rate threshold, and the running trajectory indicates that the intelligent public transport vehicle crosses the lane; The turning condition determination submodule is used to determine that the target condition is the turning condition when the steering wheel angle is greater than an angle threshold and the trajectory curvature of the running trajectory is greater than a curvature threshold.

6. The automatic driving and control system of an intelligent public transportation vehicle according to claim 5, characterized in that: The collaborative control module further includes a first reference threshold determination submodule, a second reference threshold determination submodule, a third reference threshold determination submodule and a fourth reference threshold determination submodule; The first reference threshold determination submodule is used to determine, when the target operating condition is determined to be the acceleration operating condition, that the reference comfort threshold under the acceleration operating condition includes a longitudinal acceleration threshold and a longitudinal jerk threshold; The second reference threshold determination submodule is used to determine, when it is determined that the target operating condition is the deceleration operating condition, that the reference comfort threshold under the deceleration operating condition includes a braking deceleration threshold and a braking jerk threshold; The third reference threshold determination submodule is used to determine, when the target operating condition is determined to be the lane changing operating condition, that the reference comfort thresholds under the lane changing operating condition include a lane changing acceleration threshold, a centering acceleration threshold, a lateral acceleration threshold, and a lateral jerk threshold; The fourth reference threshold determination submodule is used to determine, when it is determined that the target operating condition is the turning operating condition, that the reference comfort thresholds under the turning operating condition include a lateral acceleration threshold when entering a turn, a longitudinal acceleration threshold when exiting a turn, a lateral acceleration threshold, and a longitudinal jerk threshold.

7. The automatic driving and control system of an intelligent public transportation vehicle according to claim 1, characterized in that: The collaborative control module includes a passenger image recognition submodule and a reference threshold correction submodule; The passenger image recognition submodule is used to determine the passenger risk factor based on the passenger image data; The passenger risk factor represents the passenger's riding safety level; The reference threshold correction submodule is used to correct the reference comfort threshold under the target operating condition based on the passenger risk factor to obtain the target comfort threshold under the target operating condition.

8. The automatic driving and control system of an intelligent public transportation vehicle according to claim 7, characterized in that: The passenger image recognition submodule includes a passenger feature extraction unit and a second model recognition unit; The passenger feature extraction unit is used to extract features from the passenger image data to obtain multi-dimensional passenger feature data; The multi-dimensional passenger characteristic data includes age characteristic data, gender characteristic data and standing passenger density data; The second model recognition unit is used to input the multi-dimensional passenger feature data into a pre-trained passenger risk recognition model and output the passenger risk factor; the passenger risk recognition model is trained based on the multi-dimensional passenger feature data of sample passenger image data.

9. The automatic driving and control system of an intelligent public transportation vehicle according to claim 1, characterized in that: The vehicle terminal system also includes a voice prompt module; The automatic driving control module is further configured to send the preset working condition to the collaborative control module when it is determined that the predicted motion parameter of the intelligent public transport vehicle under any of the preset working conditions exceeds the target comfort threshold under the preset working condition; The collaborative control module is further used to determine a target voice prompt instruction corresponding to the preset working condition, and send the target voice prompt instruction to the voice prompt module; The voice prompt module is used to output the target voice prompt information corresponding to the target voice prompt instruction in response to the target voice prompt instruction; The target voice prompt information is used to prompt passengers that the intelligent public transport vehicle is about to enter the preset operating condition.

Images