79 results about "Car following" patented technology

The invention discloses an intelligent automobile longitudinal driving assistance system based on driving characteristics. The intelligent automobile longitudinal driving assistance system comprises a driver state and environment sensing module, a driver characteristic real-time identification module, an intelligent decision-making and mode switching module and a style self-adaption longitudinal control module. The driver state and environment perception module analyzes environment information and driving behavior characteristics by constructing an extended intelligent driver model, and defines acceleration deviation to perform driving style clustering. And the driver feature real-time identification module deploys the BP neural network model in an online system to realize real-time identification of the driving style. The intelligent decision-making and mode switching module intelligently assesses risks in combination with driving styles and environment information, and dynamically switches four modes of cruise control, car following, early warning and emergency braking. And the style self-adaptive longitudinal control module adaptively adjusts a control strategy according to the driving style and the expected acceleration, and converts the expected acceleration into driving torque or braking pressure through a dynamic weight mechanism, so that personalized longitudinal control is realized.

The invention relates to a personalized automatic lane changing and speed control driving collaborative decision-making method. The method comprises the following steps: S1, constructing a personalized decision-making hierarchical framework; s2, building a lane change decision training network, determining an optimization target of a lane change decision, introducing an action shielding mechanism to eliminate potential safety hazards of dangerous actions, setting an upper-layer state space, an action space and a lane change reward function required by training, and endowing the lane change reward function with personalized weights; s3, building a car-following decision training network, determining an optimization target of a car-following decision, quantizing the optimization target into a reward coefficient, setting a lower-layer state space, an action space and a car-following reward function required by training, and endowing the car-following reward function with personalized weights; and S4, a collaborative decision method is adopted, coupling training of the lane changing decision training network and the car following decision training network is carried out, and style reward priority experience playback is established to enrich experience playback priority measurement. Compared with the prior art, the method has the advantages of improving the safety and the driving efficiency of the vehicle and the like.

The invention discloses a vehicle following model and acceleration optimization method considering a front vehicle lateral offset effect in an Internet of Vehicles environment, and belongs to the field of intelligent traffic, and the method comprises the steps: introducing a rearview effect, the front vehicle lateral offset effect and multi-front vehicle speed information on the basis of a full-speed-difference following model, establishing a car-following model considering the lateral deviation effect of the front car in an Internet of Vehicles environment; performing linear stability analysis and nonlinear analysis on the car-following model to obtain a neutral stability condition and a coexistence condition; the simulation verification can describe the car following behavior considering the lateral deviation in the car networking environment, and reveal the operation mechanism of the networked vehicle in the traffic system. Besides, whether a driving safety gain factor and a motion synchronization gain factor are introduced to update the car-following model or not is judged based on driving safety identification and motion state synchronization identification conditions of the car-following vehicle, the acceleration of the car-following vehicle at the next moment is optimized, and the car-following vehicle can run in a safer and more efficient car-following mode on the road.

The invention discloses a variable curvature complex road condition mixed traffic flow-oriented CAVs car-following queue forming method. The method comprises the steps of obtaining state information of confluence CAVs and a confluence center of an initial CAVs queue; performing confluence scene division according to the state information of the confluence CAVs; for the collaborative lane-changing confluence scene, establishing a collaborative lane-changing game model considering the compromise degree of a human driver based on the confluence CAVs, the confluence center and the position state of HVs in the confluence direction, and generating a collaborative lane-changing confluence decision; for an overtaking lane-merging confluence scene, generating an initial confluence track based on road surface information by using a dynamic programming algorithm; constraining the initial confluence trajectory through a double-layer quadratic programming algorithm to generate an overtaking lane-merging confluence decision; and the confluence CAVs complete confluence through a collaborative lane changing confluence decision or an overtaking lane changing confluence decision, and join the confluence into the initial CAVs queue to form a CAVs car following queue. According to the method, the influence of HVs and road conditions (environmental information) on the formation of the CAVs car-following queue in a mixed traffic scene is considered.

The invention discloses a car following control method and a related product. According to the scheme, multi-source data are acquired, and the multi-source data are fused to obtain a fusion result; based on the fusion result, performing multi-modal trajectory prediction on the driving behavior of the preceding vehicle to obtain a prediction result of the driving behavior of the preceding vehicle; the multi-modal trajectory prediction comprises longitudinal motion prediction and transverse motion prediction; quantifying a car following risk by using a multi-dimensional risk index to obtain a risk level; constructing a multi-target cost function based on the fusion result, the front vehicle driving behavior prediction result and a control vector, and solving the multi-target cost function by using a preset constraint condition to obtain an initial control parameter of the vehicle; and on the basis of the risk level, initial control parameters of the vehicle are adjusted, and target control parameters of the vehicle are obtained. Compared with the problem of response lag in adaptive cruise control in the prior art, the adaptive cruise control method has obvious advantages.

The invention relates to the technical field of automobile control, in particular to a car following control method and system and a medium, and the car following control method comprises the steps that a target car which can be followed by a current car is recognized according to the real-time car state, the surrounding environment state and the traffic participant state; presenting the following state of each target vehicle based on the information of the target vehicle which can be followed by the current vehicle; configuring a following mode responding to the user instruction; and when the following mode of the user instruction is responded, the vehicle is planned and controlled to follow the target vehicle to realize the driving behavior, and the driving behavior at least comprises the following target trajectory tracking and the vehicle trajectory planning. The user can be assisted in controlling the vehicle to follow the dynamic target vehicle designated by the user to dynamically drive, and the experience of the user in the using process of the intelligent driving assistance function is improved.

The invention provides a vehicle sliding energy recovery method and device, equipment and a storage medium, and the method comprises the steps: obtaining vehicle following parameters of a target vehicle when it is detected that the target vehicle enters a sliding state; the car following parameters are input into a strategy network model used for determining the target regenerative braking torque of a target vehicle motor, so that the target regenerative braking torque output by the strategy network model is obtained; and controlling the target vehicle motor to output the target regenerative braking torque so as to recover the vehicle sliding energy. By adopting the technical scheme provided by the invention, collaborative optimization of the sliding energy recovery efficiency and the driving smoothness is realized.

The invention provides an intelligent vehicle following method and system, and the method comprises the following steps: obtaining the driving environment information of a vehicle in real time, carrying out the visual display, and recognizing a driving region and a vehicle which can be followed in the displayed driving environment information of the vehicle; receiving a trigger instruction, and taking the selected vehicle capable of being followed as a target following vehicle; automatically generating a vehicle-following strategy according to the position information of the lane where the target vehicle-following vehicle is located, the vehicle on the lane, the traffic marker and the obstacle information; and a corresponding control instruction is generated based on the vehicle following strategy to automatically control the vehicle to execute acceleration and deceleration, lane changing and overtaking processing, and vehicle following driving of the vehicle relative to the target vehicle following vehicle is completed. According to the method, the travelable area and the vehicle which can be followed are divided for the user to select, in the process, the user only needs to give the vehicle selection instruction which can be followed, the vehicle which needs to be followed is selected, the system follows the generated moving track to automatically complete vehicle following, and the vehicle following mode is more flexible.

The invention discloses an automatic driving vehicle path planning method based on a remote sensing image, and relates to the technical field of image recognition. The method comprises the following steps: an edge server pre-processes an original remote sensing image collected by an unmanned aerial vehicle and received in real time; analyzing the preprocessed remote sensing image, identifying roads and vehicles in the remote sensing image, and marking the vehicles as CAV vehicles and HDV vehicles; constructing a vehicle kinetic equation, analyzing the traffic flow, and selecting a car-following model or a lane changing model; after the lane changing model is selected, the automatic driving vehicle carries out rasterizing processing on the road ahead, and the optimal path of migration to a target grid is calculated. According to the method, through cooperative processing of the unmanned aerial vehicle remote sensing image and edge calculation, the global view of the autonomous vehicle is improved, the unmanned aerial vehicle can accurately obtain a long-distance road topological structure and dynamic obstacle distribution, and planning lag or decision errors caused by a local view blind area are avoided.

The invention provides a following driving method, system and equipment for a heavy commercial child-mother vehicle based on inter-vehicle communication, and belongs to the technical field of commercial child-mother vehicles, the mother vehicle starts a predictive self-adaptive cruise function, and the child vehicle starts a following mode. The mother vehicle obtains speed limit and curvature information through a map and carries out dynamic planning in combination with the state of the mother vehicle. The child car receives the operation information of the mother car in real time through the DSRC technology and corrects the air resistance coefficient of the child car according to the distance between the cars. The child car determines a safe car-following distance according to the car speed, the load difference and the ramp, and the torque demand of the child car is calculated through an inverse dynamics model based on the mother car state. The sensor is kept coincident with the longitudinal center line of the mother vehicle, and the steering angle is calculated when transverse deviation occurs. And the child vehicle also performs smooth processing on the deceleration of the mother vehicle, and sends torque, steering and deceleration requests to the execution unit. According to the invention, the driving safety is improved, the fatigue strength of a driver is reduced, and safe exit during communication interruption is ensured.

The utility model relates to the technical field of cable hanging devices, and discloses a cable hanging device for car following of a tunneling roadheader, which comprises a sliding rail, an adjusting and locking device is arranged on the surface of the sliding rail, a hanging and mounting device is arranged on the surface of the adjusting and locking device, and a cable hanging device is arranged on the hanging and mounting device. The adjusting and locking device comprises a sliding plate, a magnetic attraction limiting U-shaped frame, an inner magnet sliding block, a bearing, a rotating shaft rod, an inner end sliding plate, a bearing plate, a top end positioning plate, a holding block, an inserting block, a butt joint inserting groove and a connecting plate. According to the cable hanging device for car following of the tunneling fully-mechanized coal winning machine, by arranging an adjusting locking device, a penetrating groove in an inner end sliding plate is aligned with a butt-joint inserting groove, a holding block is held to insert an inserting block into the corresponding butt-joint inserting groove and the penetrating groove for limiting connection, and the purposes of positioning and fixing are achieved after adjustment; and during adjustment, the magnetic attraction assembly is arranged to increase the limiting strength, sliding stability is ensured, a positioning and fixing structure is arranged after adjustment, and use is convenient.

The invention discloses suspension bridge steel box girder bridge floor dismantling equipment and method based on fine planing and milling, the equipment comprises a vehicle body, the bottom of the vehicle body is connected with a crawler belt through a hydraulic cylinder, a hydraulic rod is arranged at the bottom of the vehicle body, and a slag conveying device is arranged on the advancing side of the vehicle body; the milling mechanism comprises a fixed frame, a lifting plate and a milling device; the monitoring mechanism comprises a sliding frame, a protection frame, a hardened steel wheel, a first rack and a second gear; the marking mechanism comprises a sliding sleeve, a fixed block, a second rack and a sixth gear; and the lifting motion of the sliding sleeve is controlled by the lifting of the hardened steel wheel through the meshing of the second rack and the sixth gear. The conical head is used for knocking the ground to form a hole, marking liquid flows into the hole, a car following person can conveniently find and stop milling operation in time, the damage condition of the tool bit is found in time, the situation that the damaged tool bit is continuously used for milling is avoided, the milling quality is greatly improved, and the service life of equipment is greatly prolonged.

The application discloses a kind of driver real-time state perception's car-following behavior intelligent modeling method and system, specifically including the following steps: (1) data acquisition, the driving data of vehicle in actual road is collected, the data needed to be acquired include the speed of current vehicle and front vehicle, position change information and the change information of relative distance;(2) data screening and processing, the data obtained in step (1) are screened, and the vehicle historical data with following characteristics on a road are selected;(3) the corresponding simulation environment is constructed in Matlab by method;(4) by the following state transformation method, the real driving situation of driver is simulated by constantly changing state in Matlab simulation environment.The method considers human factors in car-following model, so as to ensure the accuracy of car-following.

The invention provides a car following control method, a computer program product and electronic equipment, according to the car following control method provided by the invention, target related information of a current car following target of a car can be acquired; if the current car-following target of the car and the historical car-following target of the car belong to the same object and the preset comfortable braking condition of the car is met, smoothing processing can be carried out on the original longitudinal distance between the current car-following target and the car in the target related information; the target longitudinal distance between the current car following target and the car is obtained.

The invention discloses an automatic driving test method and system. Belongs to the technical field of automatic driving testing. According to the method, a high-fidelity virtual environment is constructed by collecting real scene data, and a virtual sensor is configured; mapping the real track to a virtual space, and generating a dynamic traffic flow in combination with a car following and lane changing model; after the real vehicle and the virtual intelligent agent are synchronously initialized, the real vehicle runs in the physical field and periodically updates the state; the virtual traffic flow is dynamically evolved according to the state of the main vehicle, and the virtual sensor senses the target in the field of view and generates a virtual sensing result; real sensor data is used as a reference, and virtual and real perception information is fused to form unified input; and circularly executing until the task is completed, wherein each virtual agent only participates in one test. According to the scheme, high-reality and high-efficiency closed-loop testing is achieved, the defects of a traditional method in the aspects of scene richness and testing safety are overcome, and the reliability and repeatability of verification of the automatic driving system are improved.

The invention provides a vehicle-following target determination method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of intelligent driving, and the method comprises the steps: obtaining a lane changing behavior of a first vehicle under the condition that the first vehicle has a lane changing direction, determining a lane changing state of the first vehicle and a target lane into which the first vehicle needs to be driven, determining a position relation of a second vehicle in front of the first vehicle relative to the target lane; and determining a target tracking vehicle of the first vehicle from the second vehicles according to the lane changing behavior, the lane changing state and the position relationship. According to the invention, the accuracy and smoothness of vehicle following target switching can be improved during automatic driving of the vehicle.

The invention discloses a car following track generation method and device, and the method comprises the steps: obtaining a first predicted driving track of a current car and a second predicted driving track of a target front car in an automatic driving mode; performing near-end point taking processing on the first predicted driving track to obtain position information of a plurality of near-end control points; performing far-end point taking processing on the second predicted driving track to obtain position information of a plurality of far-end control points; and according to the position information of each near-end control point and the position information of each far-end control point, determining a Bezier curve equation for predicting the following track of the vehicle in the future target duration. Therefore, the high-order Bezier curve is combined with a control point dynamic adjustment mechanism, and the vehicle following robustness can be improved. Meanwhile, part of control points are generated through the high-order Bezier curve and the predicted driving track of the vehicle, the smoothness of the vehicle following track under the complex road condition is improved, and the carsickness of passengers is reduced.

The invention belongs to the technical field of heterogeneous traffic flow modeling and intelligent traffic management, and relates to a heterogeneous traffic flow macroscopic fundamental diagram experimental modeling method considering takeover behaviors, which comprises the following steps of: firstly, performing stage division on driving behaviors of L3-level man-machine co-driving vehicles, and selecting a car-following model; integrating TOV permeability and takeover rate, four typical car-following modes in heterogeneous traffic flow and a function degradation mechanism of cooperative adaptive cruise control to deduce theoretical scale models of vehicles of various models in the traffic flow. A joint simulation platform is built to restore a heterogeneous traffic flow scene, and a two-stage multi-cycle experiment process is designed to collect comprehensive traffic flow data under different density levels. Whether the experimental vehicle model proportion is matched with the theoretical vehicle model proportion or not is checked, and if yes, the improved Underwood model is used for fitting experimental data to obtain an experimental model of the macroscopic fundamental diagram. The method has the advantage that an accurate model basis is provided for heterogeneous traffic flow characteristic analysis and CAV cooperative control strategy formulation.

The application discloses a kind of net link environment under the bend traffic safety discrimination and regulation method, comprising:1, calculate the following car follow path;2, calculate the collision time of two cars;3, calculate the collision time change rate;4, traffic safety discrimination is carried out in combination with collision time and collision time change rate;5, consider front and rear car safety risk and regulate;6, the above steps are recycled until the control duration ends.The application can accurately carry out traffic safety discrimination when vehicle runs on curved road section, real-time explore potential traffic accident, so as to reduce the driving risk of vehicle when driving on curve, and can improve the operation efficiency and safety of vehicle on curve.

The invention provides a vehicle following control method, a computer program product and electronic equipment, according to the vehicle following control method provided by the invention, a target overlapping rate between a target object existing in front of a vehicle and a lane where the vehicle is located can be determined in combination with a vehicle surrounding environment image of the vehicle; and according to the bending degree of the road in front of the vehicle, a preset threshold positively correlated with the bending degree is determined, so that the vehicle following target of the vehicle is determined from the target objects with the target overlapping rate reaching the preset threshold.

The invention discloses a predictive self-adaptive cruise control method for a vehicle. The method comprises the following steps of: 1, positioning the position of the vehicle through a GPS (Global Positioning System) or positioning equipment assembled on the vehicle; 2, solving an economic optimal driving speed; step 3, entering a predictive self-adaptive cruise car following mode; fourthly, P-THW is calculated according to the predicted vehicle speeds vp1, vp2... vpn of the vehicle; fifthly, the vehicle is controlled to run with vp1 as the slope entering speed; if vp1lt; vtv, and v1gt; when vtv, enabling v1 to be equal to vtv, and re-planning vp1; 6, driving according to the planned vehicle speed; when vp1lt; vtv, and v1gt; when vtv, taking vtv as a new v1 for re-planning; and 7, calculating the safe turning speed vsafety of the vehicle, wherein the vsafety is the rollover prevention speed. The method has the advantages that vehicle speed is reduced, vehicle safety is guaranteed, and fuel economy is improved; the situation that the vehicle speed is too high in the downhill process after follow-up acceleration is avoided, and fuel consumption is reduced. Unnecessary acceleration behaviors are avoided, the situation that speed reduction is still needed during turning after acceleration is prevented, and energy waste is avoided.

The invention relates to the technical field of video monitoring processing, and particularly discloses a video monitoring method and system for barrier gate car following prevention, and the method comprises the following steps: extracting a foreground target in a video frame; extracting a target residual area based on the mirror surface highlight area of the foreground target; generating a complete contour model of the foreground target based on the target residual region; determining a position point of the complete contour model in each video frame, and connecting the position points to form a motion track of the foreground target; and sorting the foreground targets according to the sequence of the foreground targets appearing in the monitoring area, obtaining motion tracks A1 and A2 of two adjacent foreground targets in the sorting, and judging whether a car following behavior exists or not based on the motion tracks A1 and A2. According to the invention, the accuracy of car following judgment is improved.

The invention provides a vehicle, a vehicle following control method thereof and a storage medium in the field of vehicles. The vehicle following control method comprises the steps that the current cruise type and the current slip rate of the vehicle and the current rainfall level state of the position where the vehicle is located are determined; determining a target car following control strategy according to the current cruise type; determining a target expected acceleration according to the current slip rate and the current rainfall level state based on the target vehicle following control strategy; and performing vehicle following control on the vehicle according to the target expected acceleration. Therefore, the problems that the vehicle following distance control is inaccurate, the vehicle following distance is insufficient when the rainfall is large and the like due to the fact that the road condition cannot be accurately reflected in rainy days and the influence of different rainfall on driving cannot be distinguished in rainy days can be effectively solved, and the driving safety in rainy days is remarkably improved; therefore, the car following safety, the driving stability and the driving adaptability are synchronously improved under the complex weather condition.

The utility model relates to the technical field of vehicle brake devices, in particular to a safety linkage device for an auxiliary brake air brake signal switch of a learner-driven vehicle, which comprises a fixed base, a fulcrum rotating shaft, a transmission lever and a reset spring. The fulcrum rotating shaft is rotatably clamped in one set of adjusting clamping grooves, the rear portion of the transmission lever penetrates through the middle of the fulcrum rotating shaft in a swinging mode and is inserted into the fixed base, the front portion of the transmission lever is warped upwards and abuts against the lower surface of the auxiliary brake pedal in a sliding mode, and the electrical signal switch is installed in the fixed base. The rear end of the transmission lever is provided with a touch piece used for touching the electrical signal switch, and the reset spring is connected between the rear portion of the transmission lever and the front side wall of the box body of the fixed base. According to the device, through linkage arrangement, the brake lamp of the vehicle can be triggered to be lightened no matter the main brake or the auxiliary brake is stepped down, a brake prompt is sent to a following vehicle behind, and rear-end collision accidents of the vehicle are reduced.

A system for identifying autonomous vehicles includes at least one sensor that may be configured to provide sensor data associated with at least two vehicles. A pre-processing module may be coupled to the at least one sensor and may be configured to determine a set of data including at least car following data based on the sensor data. An autonomous vehicle (AV) / human-driven vehicle (HV) identification neural network may be coupled to the pre-processing module and configured to generate an AV / HV identifier for at least one of the at least two vehicles based on at least the car following data during a predetermined time period.

The invention provides a heterogeneous driving behavior feature extraction and online identification method in a man-machine cooperation scene, and the method comprises the steps: obtaining traffic data in multiple man-machine cooperation driving scenes, and carrying out the research based on a data set; carrying out preprocessing methods such as target detection, multi-target tracking and acceleration smoothing on the data set, and extracting characteristic parameters in a car following process; a clustering index is calculated from the characteristic parameters, clustering analysis is carried out on the car following behaviors based on a K-Means clustering algorithm, and the car following behaviors are divided into three types according to driving behavior differences; on the basis of a factor analysis method, common factors are extracted from the characteristic parameters, and heterogeneous driving behavior car-following characteristic parameter extraction is achieved; according to the extracted common factors, an online identification model is constructed through an artificial neural network (ANN), three types of heterogeneous driving behaviors are classified in real time, and the problem that ACC cannot accurately identify the car following characteristics of the heterogeneous driving behaviors under man-machine cooperative driving can be solved.

The invention discloses a method for determining a longitudinal vehicle-following target, electronic equipment, a storage medium and a vehicle. The method for determining the longitudinal vehicle-following target comprises the steps of obtaining a first overlapping rate of a target object and a vehicle according to detection data of the target object; and when a plurality of first overlapping rates obtained according to the continuous multi-frame detection data of the target object meet a selected overlapping rate condition, determining that the target object is a longitudinal car following target. According to the method, consideration can be carried out in the time dimension, the longitudinal car-following target is determined through continuous multi-frame detection data of the target object, the problems of discontinuity, instability and the like when the longitudinal car-following target is determined are avoided, the car-following experience is improved, and the accuracy of selecting the longitudinal car-following target is improved.

The application relates to a ship traffic flow basic map drawing method based on a microscopic car following theory, which comprises the following steps: S1, acquiring AIS data in a selected area, carrying out AIS data pretreatment, and establishing a rectangular coordinate system on the area; S2, segmenting a single channel according to a division standard, and preliminarily screening the pretreated AIS data; S3, drawing a ship trajectory map according to conversion information, and screening effective ship car following data pairs from the preliminarily screened AIS data; S4, drawing a speed-car following distance basic map; S5, drawing a speed-density basic map; S6, drawing a speed-traffic volume basic map; and S7, drawing a traffic volume-density basic map. The application screens effective ship car following data by processing AIS data in a selected area, draws a complete maritime traffic flow basic map according to the relationship among traffic flow characteristic parameters, and provides a reference basis for traffic characteristics and traffic conditions of the water area.

The invention specifically discloses a vehicle following time interval control method and system based on a cloud platform. The method comprises the steps that vehicle positioning information of a vehicle, the speed of a front vehicle and the distance between the vehicle and the front vehicle are obtained; calculating a TTC value of a car following time interval under manual driving according to the speed of the front car and the distance of the front car; uploading the own vehicle positioning information and TTC data of the vehicle to a cloud platform in real time; the cloud platform records personal positioning data and TTC data corresponding to a plurality of vehicles in real time, and performs data processing to obtain a safe time interval of a corresponding road section; and when the vehicle performs automatic vehicle following driving, the safe time interval is adopted to perform vehicle following control on the front vehicle. According to the invention, the safety and intelligence of automatic car-following driving can be improved, and the comfort of driving experience is improved.