95results about How to "In line with driving habits" patented technology

The invention relates to an anthropomorphic reference track planning method for unmanned driving, including the following steps: building a vehicle steering model, and generating dynamic constraints of vehicle steering according to the basic parameters of vehicles; acquiring map information of roads according to a vehicle top decision, and getting start and end point constraint information of a reference track according to the map information; according to the dynamic constraints of vehicle steering and the start and end point constraint information of the reference track, generating a plurality of turning track curves which basically meet the geometric and dynamic constraints of vehicle steering and accord with people's driving habits and steering law, and forming a basic feasible track cluster; and with the integral of lateral acceleration over time as an index, selecting a most comfortable track as a finally generated optimal reference driving track within the intersection from the basic feasible track cluster. As the driving characteristic of people is considered and the driving law of people is simulated, the reference driving track generated is in accordance with the driving habits of people.

The invention relates to a preceding vehicle following method based on a deep convolutional neutral network and solves the problems that a self-adaptive cruise system in the prior art has tedious visual ranging and controller design processes, cannot fine adjust control parameters according to driving habits of drivers and cannot meet different personal driving habits. Driving behavior data are trained, and under the condition of given visual sensing input, accurate control of vehicle accelerators and automatic pedals under multiple work conditions is realized by imitating human drivers according to feature description of the surroundings by the deep convolutional neutral network. All that is required is to fine adjust the deep neutral network parameters with different work condition training samples instead of designing the controller structure and adjusting the controller gain under different work conditions. The tedious visual ranging and controller design processes are avoided, and the vehicle following behavior of the drivers is simulated by adjusting the deep neutral network parameters.

The invention discloses an adaptive vehicle anti-collision method. A plurality of vehicle speed parameters, vehicle distance parameters and braking distance parameters at different driving types are pre-established by a control system of a vehicle, longer vehicle distances are set when the vehicle speeds are higher, the vehicle distances are increased or decreased appropriately according to different road conditions, sensors on the vehicle obtain dynamic information, such as the vehicle speeds or accelerations, analysis is performed by combining driving behaviors, a driver is classified into a certain driving type through statistical analysis and an artificial neural network, control parameters of the vehicle are adjusted by referring to the driving type of the vehicle driver, and thus an electronic control unit of the vehicle can perform warning or control to brake in an appropriate time in accordance with the driving habits of the driver. By adopting the adaptive vehicle anti-collision method, the problem that the safety vehicle distance and a brake device cannot be adjusted by an anti-collision system of the existing vehicle by aiming at different vehicle speeds, road conditions, habits of the driver or vehicle conditions is solved.

The invention discloses an ACC / AEB system based on human-imitating driving. The system comprises an environment sensing module, a data fusion module, a decision control module, a human-imitating driving module and an execution module. By means of the technical scheme, an enhanced neural network is utilized, the learning of driving behavior parameters of a driver can be achieved in the driving process, the driving behavior parameters are compared with the parameters obtained through the calculation of the decision control module and corrected, the situation that in the decision control process,acceleration, deceleration, braking force, acceleration rate and deceleration rate are over high or over low, and accordingly the comfort and the safety of the driving are affected is avoided, so that the ACC / AEB system is more suitable for the driving characteristics of the driver, the drive is made to have the same feeling as his / her own driving, the human-imitating driving in the ACC / AEB process is achieved, and the system better meets the driving requirements of the driver.

The invention discloses an angry driving behavior monitoring and intervening device capable of automatically adapting to driver characteristics. The device comprises a vehicle whistling monitoring system, a steering wheel operation monitoring system, an acceleration changing monitoring system, a sound monitoring system, a vehicle-mounted system, a self-adaptation detection system, a driving anger feeling recognition system and an early warning reminding system. Common behaviors expressed during angry driving of a driver can be monitored in real time from multiple aspects, influences of driver individual differences on anger monitoring and recognition are eliminated, the precision is high, and the accuracy is better. Meanwhile, when the driver has the angry driving behavior, the device performs real-time intervention on the driver in recorded individualized sound early-warning modes at different levels, and therefore the intervention problem that the universality is low and consumed time is long when mental training is adopted as the main means is solved, and potential safety hazards brought by angry driving are greatly reduced.

The invention relates to a large transport vehicle safety protection system and an early warning method. The early warning method comprises the steps that S1, the system conducts power-on self-test; S2, a millimeter wave radar assembly transmits obstacle target information detected in real time to a system processing terminal, and a camera assembly transmits road image information recorded in realtime to the system processing terminal; S3, the system processing terminal gives a radar confidence factor and a camera confidence factor to each target in real time; S4, the total confidence of eachtarget is calculated in real time, and whether the target is a real target or not is judged in real time according to the total confidence; and S5, according to the current vehicle speed and the realtarget, early warning is carried out on a right ahead target during starting, or a right ahead target during driving, or a side target during steering, or a side target during lane changing, or a rear target during lane changing. According to the invention, radar, camera and vehicle driving parameter information are combined, the detection range is expanded, and the method is used for vehicle front dead zone detection, lateral anti-collision and rear dead zone detection.

The invention discloses a lane departure warning method and system for preventing repeated warning of one-side lane departure. The method comprises the following steps of acquiring a road image in front of a vehicle; identifying a lane line of a lane in which the vehicle is located from the road image; and because a warning line, a warning end line and an external recount line are arranged at a one-side lane line, when the outer side surface of a tire on one side of the vehicle is beyond the warning line but a driver is unconscious, performing lane departure warning. The lane departure warning method and system for preventing repeated warning of one-side lane departure disclosed by the invention can judge whether the tire on one side of the vehicle is beyond the external recount line, and if not, another lane departure warning is prohibited to execute, so that the problem that the left wheel and the right wheel respectively trigger the lane departure warning is effectively solved; and if yes, a situation whether the tire on one side of the vehicle is beyond the warning end line is judged, and if yes, another lane departure warning is allowed to execute, so that the situation that the warning is missed out cannot occur.

The invention provides a method, device and equipment for planning a lane changing path of a vehicle and a readable storage medium, which can be used for intelligent driving and comprise the followingsteps: acquiring a current first motion state of the vehicle and lane center line information of a lane where the vehicle is located; mapping the first motion state from a vehicle coordinate system of the vehicle to a reference coordinate system taking a lane center line as a reference line to obtain a second motion state; determining a reference lane changing path in a reference coordinate system according to the second motion state; and mapping the reference lane changing path into a vehicle coordinate system to obtain a target lane changing path. According to the method, the device, the equipment and the readable storage medium provided by the embodiment of the invention, the reference lane changing path is determined in the reference coordinate system, so that the reference lane changing path is more convenient to solve. And the reference coordinate system is constructed based on the center line of the lane where the vehicle is located, and the curve situation is naturally considered, so that the planned lane changing path conforms to the change trend of the curved road and more conforms to the driving habit of human beings.

The invention provides a navigation route processing method, device and equipment. The method comprises the steps: determining an entrance shape point and an exit shape point of a navigation route atan intersection under the condition of moving to the intersection; carrying out smooth curve connection on the entrance shape point and the exit shape point to obtain a driving path corresponding to the intersection; and displaying the driving path on the topographic map of the intersection. According to the method, the entrance shape point and the exit shape point of the navigation route at the intersection are determined under the condition of moving to the intersection, the smooth curve connection is performed on the entrance shape point and the exit shape point to obtain the driving path corresponding to the intersection, and the driving path is displayed on the topographic map of the intersection. Since the driving-in road section and the driving-out road section of the navigation route at the intersection are connected directly by the smooth curve in the driving path and the driving path conforms to the actual driving route of the user to conform to the driving habit of the user,so that the user can quite easily recognize the driving way at the intersection.

The invention relates to a vehicle overtaking auxiliary control method applied to a two-way two-lane road and an overtaking auxiliary system of the vehicle overtaking auxiliary control method appliedto the two-way two-lane road. The method comprises the following steps that main vehicle state information, surrounding vehicle state information and road information are acquired; whether the main vehicle driver has the intention of overtaking by the road is judged and the process goes to the next step if the judgment result is yes; whether the main vehicle can perform overtaking is judged by overtaking auxiliary control before overtaking, and the process goes to the next step if the judgment result is yes, or alarming is performed and the process goes to the next step; whether the main vehicle enters the opposite lane is judged, and the process goes to the next step if the judgment result is yes; whether the main vehicle can complete overtaking is judged by overtaking auxiliary control in the overtaking process, and the main vehicle driver is assisted to perform overtaking or alarming is performed according to the judgment result; and whether the main vehicle returns to the originallane is judged. Compared with the methods and the systems in the prior art, the vehicle overtaking safety on the two-way two-lane road can be enhanced, and the method and the system have the advantages of high practicality, high reliability and great real-time performance and the stress and the fatigue of the driver can also be reduced.

The invention relates to a torque control method for artificial refueling before creeping speed of an electric automobile. The torque control method specifically includes the steps that under the conditions that a braking pedal and an accelerator pedal of the electric automobile are not treaded and the gear of a gearbox is engaged to the forward gear or the reversing gear, the electric automobileis accelerated to approach a target creeping speed according to a preset creeping control scheme, and at the moment, if the accelerator pedal is manually treaded, the torque of a driving motor is controlled as follows: 1, the currently required torque of the driving motor is calculated by checking a torque table under the normal driving condition of the electric automobile; and 2, the calculated torque and the driving motor torque corresponding to the creeping control scheme at the moment are compared, and the larger torque is selected as the actual torque of the driving motor. The torque control method can avoid the automobile weak feeling generated by reduced required torque when a driver treads an accelerator, so that driving stability and comfort are good.

The invention provides an autonomous driving vehicle lane selection method and system and a vehicle. The autonomous driving vehicle lane selection method comprises the steps of obtaining road information ahead of the vehicle; judging whether the road ahead of the vehicle is a ramp narrowing road according to the road information; if so, before the vehicle drives into the ramp narrowing road, selecting a target lane from the ramp narrowing road according to a driving rule; and controlling the vehicle to change lanes to the target lane. According to the autonomous driving vehicle lane selectionmethod provided by the invention, the priority driving target lane of the autonomous driving vehicle can be planned when the autonomous driving vehicle drives on the expressway ramp, thereby avoidingthe danger of collision with other vehicles caused by a large lateral deviation of the autonomous driving vehicle driving on the ramp due to inaccurate positioning of a map; and the target lane selection planning mode conforms to the driving habit of people.

The invention discloses a shared automatic driving automobile system. The shared automatic driving automobile system comprises a vehicle side, a cloud side, a sensor, a data collecting system and an automatic driving system. The vehicle side and the cloud side are connected through data uploading and model downloading. The vehicle side comprises a driver identity identifying module. The driver identity identifying module is connected with a driving mode selector. The driving mode selector is connected with a manual driving mode and an automatic driving mode. The manual driving mode and the automatic driving mode are connected with the data collecting system and the automatic driving system. The cloud side comprises a scene rebuilder, a machine learner and an automatic driving model. The scene rebuilder is connected to the machine learner. The machine learner is connected to the automatic driving model. The shared automatic driving automobile system is capable of saving energy consumption, improving travelling efficiency of people, saving cost of automobile maintenance, effectively increasing safety guarantee of a driver, conveniently driving by the driver, and meeting using requirements of more users.

The invention provides a throttle opening adjusting method and device. The throttle opening adjusting method is applied to an ECU in a vehicle; and the ECU has a self-learning mode; in the self-learning mode, the vehicle is in a static state. The throttle opening adjusting method comprises the steps of obtaining an actual throttle opening when a driver performs at least one stepping action on an accelerator pedal on the basis of at least one expected throttle opening when entering the self-learning mode, wherein the expected throttle opening is a throttle opening in an accelerator pedal contour map; and on the basis of the actual throttle opening and the expected throttle opening, updating a throttle opening in the accelerator pedal contour map so that the updated accelerator pedal contourmap is adaptive to a driving behavior of the driver. According to the throttle opening adjusting method, the accelerator pedal can automatically adapt to the driver without the driver to passively adapt to the accelerator pedal; and therefore, the user experience is better.

The invention provides a vehicle following control system and method for an intelligent driving vehicle. The corresponding vehicle following time interval and the safe parking distance are obtained according to the real-time vehicle speed of the intelligent driving vehicle and the real-time traffic state of the road where the intelligent driving vehicle is located, and then the vehicle following speed and the distance with the front vehicle are automatically adjusted. The real-time traffic state of the road, the real-time vehicle speed of the vehicle, the consistent vehicle following time interval and the safe parking distance are adopted, and compared with the existing fixed time interval control strategy, the behavior of the intelligent driving vehicle is enabled to better accord with the driving habit of human beings. Furthermore, the real-time traffic state of the road where the intelligent driving vehicle is located is calculated through the speed information of the vehicle in front of the intelligent driving vehicle, and compared with a traditional fixed-point traffic state monitoring method, the method is low in cost and good in real-time performance.

The invention relates to a creep torque control method in the starting stage of an electric vehicle. The creep torque control method specifically comprises the steps that under the situations that theelectric vehicle is static and a brake pedal and an accumulator pedal are not stepped, a gear position of a gearbox is engaged to a forward gear or a reverse gear, and the torque of a driving motor is controlled through the following steps that 1, the torque of the driving motor is increased from zero to the first torque at the first acceleration; 2, the torque of the driving motor is kept unchanged; 3, when the travelling speed of the electric vehicle reaches the first speed, the torque of the driving motor is decreased at the second acceleration; 4, when the travelling speed of the electricvehicle reaches the second speed, decreasing of the torque of the driving motor is stopped; and 5, the torque of the driving motor is subjected to PI adjustment through the difference value between the actual traveling speed of the electric vehicle and the target creep speed, and thus the traveling speed of the electric vehicle is stabilized at the target creep speed. The creep function of the electric vehicle in the starting stage is achieved, control is precise and reliable, and the control process is scientific and reasonable.

The invention discloses a method, a device and equipment for detecting vehicle yaw based on trajectory data and a medium. The method comprises the following steps of acquiring a starting place and a destination of a to-be-navigated route, querying historical driving routes which are the same as the starting place and the destination, and forming a navigation route database by using the queried historical driving routes, matching the vehicle with the historical driving route in the navigation route database to obtain the historical driving route matched with the vehicle, navigating the vehicle based on the historical driving route matched with the vehicle, and according to the current position of the vehicle, setting an electronic fence in a preset range of the navigation route, and if the vehicle leaves the electronic fence and cannot be matched with all historical driving routes in the navigation route database, determining that the vehicle is yawed. According to the method, navigation of the vehicle can be realized only according to the trajectory data reported by the vehicle machine, whether the vehicle is yawed or not can be detected, additional equipment does not need to be additionally arranged, and the yaw judgment accuracy is greatly improved.

The invention provides a horizontal autonomous parking control method. The horizontal autonomous parking control method comprises the steps of acquiring position coordinates of a target garage position, position coordinates of an obstacle vehicle and initial pose information of a to-be-parked vehicle; determining a parking reference track of the to-be-parked vehicle; based on the initial pose information and the first arc trajectory of the vehicle, generating a first target trajectory by adopting a forward-looking window tracking algorithm; based on the first target point and the tangent trajectory, generating a second target trajectory by adopting a foresight window tracking algorithm; based on the second target point and the second arc trajectory, generating a third target trajectory byadopting a foresight window tracking algorithm; and according to the first target track, the second target track and the third target track, controlling the vehicle to be parked into the target storage location. The invention further provides a horizontal autonomous parking control device, a vehicle and a storage medium. According to the method, automatic parking can better accord with driving habits, and the driving experience is improved.

The invention discloses a brake system having a small turn radius, belonging to the automobile field. According to the invention, the brake system comprises a normally open solenoid valve and a small turn switch which are arranged in left and right rear wheel brake circuits, wherein the normally open solenoid valve is used for realizing that the normally open solenoid valve in the turning inner-side rear wheel brake circuit is in an energized cutoff state so as to cut off the turning inner-side rear wheel brake circuit, maintain the brake pressure or the semi-brake pressure of the rear wheel brake and maintain the brake or the semi-brake of the rear wheel when the automobile is subject to a process of small turning or small-turning U turn; and the small turn switch is used for controllingthe normally open solenoid valve directly or indirectly by an electric control unit. The invention is beneficial to reducing the turn radius of the automobile.

The invention discloses an automatic driving vehicle driving method with a backup path. The automatic driving vehicle driving method comprises the following steps of pre-storing the backup path of a vehicle traveling under specific road scenes in an automatic driving control system of the vehicle; whether the vehicle travels under the specific road scenes or not is judged in real time; if yes, combining a path planned through sensing by the control system with the backup path for driving; and if not, performing driving according to the path planned through sensing by the control system. The specific road scenes refer to a shunting turnout and a ramp. By means of the automatic driving vehicle driving method with the backup path, under specific rod scenes such as the shunting turnout, the pre-stored backup path can be used to instruct vehicle driving, so that the driving of an autonomous vehicle conforms to human driving habit, and meanwhile, the safety of automatic driving is improved.

The invention relates to a vehicle front collision avoidance method and system. The method comprises the steps of determining the current speed of a vehicle and the current speed of a front obstacle;determining a collision avoidance mode which is about to be adopted by the vehicle, wherein the collision avoidance mode comprises single braking collision avoidance, single steering collision avoidance or combination of braking collision avoidance and steering collision avoidance; calculating a collision avoidance distance corresponding to the determined collision avoidance mode through a set operation formula according to the current speed and the determined collision avoidance mode; determining a current distance between the vehicle and a front obstacle; judging whether the current distancereaches the collision avoidance distance or not, and if yes, it is judged that the collision avoidance condition is met. Braking and steering collision avoidance are comprehensively considered, the collision avoidance frequency can be effectively reduced, interference to a driver is reduced, and driving habits are better met.

The invention discloses an interactive thinking based intelligent engine automatic-start-stop triggering system. Automatic start-stop of an engine is judged according to the road condition whether a vehicle needs to start a start-stop system, and accordingly an unnecessary engine automatic-start-stop phenomenon is avoided. The system consists of a traffic intersection interaction mechanism, a road congestion section interaction mechanism and an automobile circuit control mechanism which are connected in a wireless communication mode. The system saves energy, reduces emissions, can decrease severe road congestion situations, can avoid frequent engine start and stop, is suitable for information interaction between automobiles and road situations, and accordingly avoids application in unnecessary automatic-start-stop by judging whether vehicles are under the road situation needing automatic engine start and stop or not.

A self-learning method, apparatus (160), device (170) and storage medium for an automatic driving system are provided. The method comprises: acquiring driving data (S201); removing abnormal data in the driving data to obtain data to be processed (S202); and selecting a to-be-learned driving parameter according to the to-be-processed data, and calculating the to-be-processed data according to a calculation rule corresponding to the driving parameter to obtain a learning result of the driving parameter (S203), the learning result being used for instructing the automatic driving system to set the driving parameter according to the learning result in the automatic driving journey. The method is applied to an intelligent vehicle, a network connection vehicle and an automatic driving vehicle, and can ensure that the self-learning data of the automatic driving system accords with the design operation domain, the traffic rule and the safe driving rule of the vehicle, so that the automatic driving system parameters obtained by self-learning can not only accord with the driving habit of a user, but also can also accord with the driving habit of the user. Meanwhile, the safety and the user experience are also improved.

The invention discloses an automobile outside rear-view mirror with a blind area prompt function. The automobile outside rear-view mirror comprises a left rear-view mirror and a right rear-view mirror. The left rear-view mirror and the right rear-view mirror each comprise a shell and a mirror body embedded to the shell. Each mirror body comprises a mirror bracket and a lens, wherein the lens is embedded to the opening of the corresponding shell through the mirror bracket. The right rear-view mirror further comprises a right blind area prompt lamp assembly installed in the shell of the right rear-view mirror. A first transparent window is arranged at the upper right corner of the lens of the right rear-view mirror. The right blind area prompt lamp assembly is located at the position, corresponding to the first transparent window, in the shell of the right rear-view mirror. The left rear-view mirror further comprises a left blind area prompt lamp assembly installed in the shell of the left rear-view mirror. A second transparent window through which a light source of the left blind area prompt lamp assembly is emitted out is arranged at the upper left corner of the lens of the left rear-view mirror, the left blind area prompt lamp assembly is located at the position, corresponding to the second transparent window, in the shell of the left rear-view mirror, and therefore the light source of the left blind area prompt lamp assembly can penetrate through the lens of the left rear-view mirror conveniently to be emitted outwards.

The invention provides a vehicle speed limiting auxiliary control method and system in order to reduce the probability that the torque output of a driving motor is zero or high pressure occurs in therunning process of a vehicle and improve the running safety. The method comprises the following steps: obtaining a current vehicle speed of a vehicle; comparing the current vehicle speed with a presetfirst threshold value, a preset second threshold value and a preset third threshold value, wherein the second threshold value is larger than the first threshold value, and the third threshold value is larger than the second threshold value; if the current vehicle speed is not greater than the first threshold value, executing a slope-free control step; if the current vehicle speed is greater thanthe first threshold value and not greater than the second threshold value, executing a pedal control step; if the current vehicle speed is larger than the second threshold value and not larger than the third threshold value, executing a braking control step; and if the current vehicle speed is greater than the third threshold, executing a protection control step. The probability that the torque output of the driving motor is zero or high pressure exists during driving can be reduced, and the driving safety is improved.

The invention discloses a path planning and vehicle speed optimization apparatus based on vehicle monitoring and internet-of-vehicles technology, comprising a vehicle monitoring integrated index determining module, and a culture index determining module, a driving skill index determining module, a fuel saving index determining module, a stability index determining module, a performance index determining module, an interior ambient index determining module, an internet-of-vehicles information-index determining module, a path planning method module, and a speed optimization module. Vehicle information is monitored through a sensor, a vehicle is analyzed and estimated so as to determine vehicle monitoring integrated index in real-time vehicle operating state; real-time road network information is acquired through the internet of vehicles; traffic condition is determined and analyzed to determine a real-time road traffic state index for traffic in front of the vehicle, and reasonable pathplanning suggestions and speed optimizing recommendations can be provided for a driver.

The invention discloses a mistaken ignition preventing device for an automobile, which comprises an ignition loop, a clutch pedal, a clutch master cylinder, a clutch support, a clutch switch and a pressing sheet, wherein the root of the clutch pedal is hinged with the clutch support by a bolt; the clutch master cylinder is fixed on the clutch support; a push rod of the clutch master cylinder is hinged with the clutch pedal; the clutch switch is arranged on the clutch support; the clutch switch is a normally contacted switch and is connected in series to the ignition loop; the pressing sheet is arranged at the position of the clutch pedal adjacent to the root; and when the clutch pedal is in the natural state, the pressing sheet presses a contact of the clutch switch all the time to switch off the ignition loop. In the mistaken ignition preventing device, the misoperation of igniting without stepping on the clutch pedal can be prevented on the premise of no change in the driving habit, so vehicles are prevented from moving suddenly during starting, and potential safety hazards are eliminated; and the mistaken ignition preventing device has the characteristics of skillful design, low reforming cost, safety, reliability and the like, is easy to reform, and can be used on various automobiles with manual transmission.

The invention provides an expressway unmanned vehicle formation method based on multi-agent reinforcement learning, the method regards a vehicle formation problem as a multi-agent cooperation problem, and each vehicle has an independent decision-making capability. The method can achieve flexible formation on the premise of safe and rapid driving, namely, safe obstacle avoidance is achieved when the traffic flow is large while the formation does not need to be kept, and the formation is recovered when the traffic flow is small; an end-to-end mode of directly mapping image input to vehicle control quantity is large in training difficulty due to large action search space, so that a lane changing strategy is learned only by using a multi-agent reinforcement learning method, the accurate control quantity is calculated in combination with an S-T graph trajectory optimization method, so that control constraints are increased, the kinematics principle is respected, safety guarantee is achieved, and human driving habits are met.

The invention discloses a vehicle traveling system, a control method thereof and an environmental sanitation vehicle. A throttle pedal of the vehicle traveling system is connected with a chassis controller, a mode conversion switch is connected with the chassis controller and used for selecting a connecting mode between the chassis controller and the traveling unit, the traveling unit executes a first traveling mode when the mode conversion switch controls the chassis controller to be directly connected with the traveling unit, the traveling unit executes a second traveling mode when the modeconversion switch controls the chassis controller to be connected with the traveling unit through a communication connection unit and a controller which are sequentially connected, and a brake pedal is connected with the chassis controller and the traveling unit and used for controlling the traveling unit to reduce speed or stop. By the aid of the vehicle traveling system, a driver only needs to operate the mode conversion switch, switching between two traveling modes can be achieved, the driver can control two traveling drive modes by the aid of the throttle pedal, the vehicle traveling system meets driving habits, false operations are decreased, and driving safety is ensured.