67 results about "Carriageway" patented technology

This specification provides a method for training a lane detection model. The method includes: determining lane line image samples and sample labels, wherein the sample labels are target lane lines in the lane line image samples; extracting features from the lane line image samples to obtain a first feature image and a second feature image; determining lane line clustering information and initial lane line key points based on the first feature image and the second feature image; performing clustering based on the lane line clustering information and the initial lane line key points to obtain predicted lane lines; and training a lane line detection model based on the predicted lane lines and the target lane lines. By integrating the clustering process of lane line key points into the entire lane line detection model training process, lane line key point clustering is performed simultaneously with network training, thereby improving the overall performance of the lane line detection model.

The utility model provides a kind of TBM lane anti-collision device, it is characterized in that, including: first support and second support of left and right interval arrangement, are used for being mounted on TBM rear matched trailer;Protective frame, one end is transversely rotatable with first support connection, the back of other end and second support abut;The upper portion and the lower portion of the front of protective frame are respectively detachably provided with several composite anti-collision buffer strips, and the middle portion of the front of protective frame is detachably provided with several composite rubber spring buffer blocks.The utility model can effectively improve buffering performance, avoid to cause harm to TBM machine head and worker, can effectively shorten the replacement construction period, reduce the influence to construction progress, effectively facilitate maintenance;And when not need to use, protective frame can be rotated around first support to avoid operator or equipment, effectively facilitate use.

This utility model discloses a safety warning system for underground parking garage ramps, applied to the curves of ramps in underground parking garages, including an uphill lane and a downhill lane. Sensors are installed on the road surface to detect whether vehicles are passing the current location; these sensors are divided into uphill and downhill sensors. The uphill sensor is located at a certain distance from the uphill curve before the uphill section, and the downhill sensor is located at a certain distance from the downhill curve before the downhill section. Warning devices are divided into uphill and downhill warning devices. The downhill warning device is connected to the uphill sensor and located at the beginning of the downhill section to warn downhill vehicles; the uphill warning device is connected to the downhill sensor and located at the beginning of the uphill section to warn uphill vehicles. Based on these measures, the system can detect oncoming vehicles on the underground parking garage ramp in real time and improve the safety of the ramp curve by warning drivers.

The invention relates to a vehicle headlamp (1) comprising a low beam module (2) for generating a low beam distribution, wherein the low beam module (2) for this comprises at least one light source (2a), and a high beam module (3) for generating a high beam distribution, wherein the high beam module (3) for this comprises at least one light source (3a), a projection lens (4), and a ray shield (5), wherein the two light modules (2, 3) are associated with the projection lens (4) as a common projection lens (4) and with the ray shield (3) as a common ray shield (3) in such a way that the light sources (2a, 3a) are arranged respectively such that the common ray shield (5) is in the light path from the respective light source towards the common projection lens (4) in order to delimit the light distribution respectively radiated into the common projection lens (4), and the common projection lens (4) is arranged in the light path of the two light modules (2, 3) such that the light rays radiated by the light modules (2, 3) that pass through the common ray shield (5) can be imaged by the common projection lens (4) in the form of an additive light distribution onto the carriageway, wherein the common projection lens (4) has an optical axis (z), wherein the common projection lens (4) at its exit side (4') has a first deflection section (4a) extending upwards and downwards along the periphery of the projection lens transversely to the optical axis (z), which is arranged at the surface of the projection lens (4), wherein in this first deflection section (4a) the exit side (4') of the common projection lens (4) is configured by juxtaposed projections (6a, 6b, 6c, 6d, 6e, 6f, 6g, 6h), which are respectively delimited by the connection of a first side face (6a') facing the optical axis (z) and a second side face (6a") facing away from the optical axis (z), wherein the totality of the projections comprises at least projections (6a, 6b, 6e, 6f, 6g, 6h) of a first type in which these side faces are configured substantially asymmetrically with respect to one another.

The utility model belongs to the field of tunnel especially, it is an intensive composite evacuation passageway structure of single hole double -deck open cut tunnel, including upper layer traffic layer, lower layer traffic layer, vehicle access and ground evacuation stair, lower layer traffic layer is located below upper layer traffic layer, and vehicle access is located in the front side of upper layer traffic layer and lower layer traffic layer, and ground evacuation stair is set up in the right side of vehicle access, the upper layer traffic layer and vehicle access mouth of vehicle access of upper layer traffic layer are set up on the middle wall of upper layer traffic layer and vehicle access, the lower layer traffic layer and vehicle access mouth of vehicle access of lower layer traffic layer are set up on the middle wall of lower layer traffic layer and vehicle access, and the vehicle in double -deck tunnel's upper layer traffic layer and lower layer traffic layer is realized in vehicle access vehicle access lane board through vehicle access in vehicle access, the utility model discloses the rational design, through the intensive overall design to personnel evacuation, vehicle evacuation and equipment room layout, formed a kind of composite evacuation passageway structure, improves evacuation efficiency and the utilization of urban space.

This application discloses a method, apparatus, and electronic device for calibrating camera extrinsic parameters. The method includes: acquiring road perception information transmitted by roadside equipment, the road perception information including first angle information of an autonomous vehicle relative to lane lines, and the roadside equipment being at least one from a preset set of roadside equipment; acquiring a first road image captured by the camera of the autonomous vehicle, and performing lane line detection on the first road image to obtain a first lane line detection result, the first lane line detection result including first lane line edge detection results; determining a first camera extrinsic parameter correction value for the autonomous vehicle based on the road perception information and the first lane line detection result; and determining a calibration result for the camera extrinsic parameters based on the first camera extrinsic parameter correction value. This application corrects the camera extrinsic parameters of the autonomous vehicle by using a pre-established and regularly maintained set of roadside equipment, eliminating the need for calibration in a fixed calibration workshop or external calibration site, thus improving calibration efficiency and accuracy.

The application discloses a traffic scheduling method and device, electronic equipment and a readable storage medium. The method comprises the following steps: reconstructing a lane of a road based on real-time road conditions to obtain a reconstructed lane topology; grouping traffic tools based on the destination and / or driving path of the traffic tools to obtain at least one fish school team; determining a target fish school team corresponding to the reconstructed lane topology based on the reconstructed lane topology and the at least one fish school team; and scheduling traffic of the target fish school team based on the reconstructed lane topology.

This invention discloses a lane line reconstruction method, device, vehicle, and medium for autonomous vehicles, relating to the field of intelligent driving vehicle technology. The method includes: collecting environmental perception data corresponding to the target vehicle based on intelligent driving sensors installed on the target vehicle; generating a lane line attribute dataset corresponding to the driving road based on the environmental perception data; determining the lane line type corresponding to each lane line of the driving road based on the lane line attribute dataset; and reconstructing the target lane lines based on the lane line types and the lane line attribute dataset. This technical solution can improve the accuracy and completeness of lane line data, avoid path deviation problems caused by lane line data defects, and ensure the stability of the vehicle's driving trajectory.

The utility model discloses a kind of upper ditch lower culvert road drainage devices, it includes drainage gallery, box culvert, overflow pipe and water collecting pipe, drainage gallery is located between non-motor vehicle lane and motor vehicle lane, vegetation shallow ditch is formed under the concave of drainage gallery, and the highest of drainage gallery is lower than the height of non-motor vehicle lane and motor vehicle lane, box culvert is located below drainage gallery;One end of overflow pipe extends into box culvert, overflow pipe passes through drainage gallery to make the other end of overflow pipe extend into vegetation shallow ditch;Water collecting pipe is buried in drainage gallery, water collecting pipe has water collecting mouth, and water collecting pipe is communicated with overflow pipe.The utility model uses road median strip space arrangement drainage gallery, construction only needs shallow layer excavation, avoid affecting carriageway structure.Box culvert, overflow pipe, water collecting pipe combination form three-dimensional drainage network to replace traditional deep buried pipe network, when maintaining, can be directly operated through gallery area, without interrupting traffic.

This application provides a lane line display method, apparatus, electronic device, vehicle, and medium. The method includes: acquiring vehicle information corresponding to a vehicle-mounted system (V2S), and determining a first moment when the V2S information is received, the V2S information including multiple location points collected centered on the vehicle; determining a target map image to be rendered within a time period corresponding to the first moment and a second moment when the V2S information is received next; performing lane line shifting processing using the multiple location points to obtain lane line prediction points corresponding to the target map image; and performing lane line fitting based on the lane line prediction points corresponding to the target map image to obtain target lane lines, thereby rendering the target lane lines at the corresponding positions in the target map image and displaying them on the V2S. In this method, the lane lines change with the image, achieving synchronous and continuous display changes between the lane lines and the map image, improving display continuity.

This invention discloses a vehicle lane correction system based on real-time fusion of video stream and satellite positioning. The system includes a processor, an Ethernet switch, a low-latency camera, a GNSS satellite antenna, and a receiver connected in sequence. The low-latency camera collects real-time video stream data of the ground lane lines and transmits it to the processor via the Ethernet switch. The GNSS satellite antenna receives satellite positioning signals, and the receiver decodes the received satellite signals. The processor preprocesses the video stream data and uses a lightweight deep learning segmentation model to segment the lane lines. Combining this with GNSS positioning information, a dynamic confidence-weighted fusion algorithm is used to fuse multi-source information, outputting the vehicle's lateral offset status and lane correction control signals to the vehicle control system. This invention is easy to install and maintain, has a low system failure rate, and can balance visual and GNSS output results, effectively improving the accuracy of the lane correction results.

The application discloses a kind of different types tunnel construction clearance automatic generation method, step (1), establish standard database, tunnel road grade, design speed, lane number and left side maintenance road width, right side maintenance road width, left side lateral width, right side lateral width, driving lane width, residual value one-to-one corresponding storage;Step (2), obtain the tunnel road grade, design speed, lane number input by user, and generate standard construction clearance basic parameters by matching with standard database;Step (3), receive the individualized parameter input by user, including left side widening value, right side widening value, emergency parking width, emergency parking lane cross slope value, maintenance road height;Step (4), set reference point three-dimensional coordinates, based on basic parameters and individualized parameters, the three-dimensional coordinates of each feature point of construction clearance are calculated by trigonometric function;Step (5), according to the feature point coordinates, tunnel construction clearance graphics are automatically drawn and layer, line type and color identification are completed, and the automation and intelligent level of tunnel engineering design is significantly improved.

Provided is a system for identifying lanes in which vehicles are traveling. The system includes one or more processors programmed to identify vehicles traveled on a curved road including lanes; estimate radiuses of curvature for trajectories of the vehicles traveling on the curved road; cluster the radiuses of curvature using a clustering algorithm; and determine lane ID information for each of the vehicles on the curved road based on the clustered radiuses of curvature.

This invention provides a method for evaluating the instantaneous operating efficiency of vehicles, comprising: constructing an ideal catch-up process for each feasible lane based on acquired instantaneous data; calculating the average speed of the vehicle to be evaluated under the ideal catch-up process as the expected achievable average speed of each feasible lane in the current scenario, and calculating the duration of the catch-up process; using the maximum duration among all feasible lanes as a benchmark, unifying the evaluation time domain through a time alignment mechanism, recalculating the average speed of the vehicle to be evaluated in each feasible lane within the aligned time window, and taking the maximum value as the global theoretical reference speed; calculating the currently available acceleration space based on the reference speed and the current speed of the vehicle to be evaluated; calculating the change in the available acceleration space based on multiple consecutive moments, thereby correcting the original available acceleration space to obtain the instantaneous operating efficiency index of the vehicle to be evaluated. This invention possesses the ability to perceive the instantaneous operating efficiency of vehicles under different scenarios.

The present application relates to a device for identifying a signaling unit at a lane traveled by a vehicle. The device is configured to determine an arrangement of one or more signal signs of the signaling unit based on environmental data of one or more environmental sensors of the vehicle. The device is further configured to associate the one or more signal signs with one or more corresponding grid cells of a signal sign grid by means of an association logic.

This invention relates to the fields of autonomous driving and intelligent transportation technology, specifically to a Transformer-based method for predicting highway train trajectories. The method includes: acquiring the historical trajectories of each highway train and the lane centerlines of each lane in the current environment; acquiring historical trajectory vector sequences and lane centerline vector sequences; performing feature encoding and cross-attention mechanism processing on the historical trajectory vector sequences and lane centerline vector sequences respectively to obtain a first trajectory feature code and a lane feature code; performing lane feature code concatenation, self-attention mechanism, and position encoding processing on the first trajectory feature code to obtain a second trajectory feature code; performing feature fusion based on the second trajectory feature code and the lane feature code to obtain fused features; and performing classification and regression processing respectively to obtain multiple predicted trajectories and the probability of each predicted trajectory, which serve as the trajectory prediction result. This invention can improve the accuracy of highway train trajectory prediction.

This system prevents drivers from mistakenly identifying multiple parallel lane markings as parking lines on public roads. [Solution] A parking determination device comprising: a parking line acquisition unit that detects parking spaces and / or other vehicles around the vehicle based on image data acquired by photographing the area around the vehicle, and acquires a predetermined number or more of the detected parking spaces and / or other vehicles adjacent to each other in a predetermined direction; and a parking determination unit that determines whether the vehicle is in a parking lot with a parking line, wherein if it is detected that another vehicle has passed a parking space included in a parking line detected in front of the vehicle's direction of travel at a predetermined speed or higher, it is determined that the parking line is not a parking line.

The application relates to a multi-scale adaptive cooperative traffic signal control method, and relates to the technical field of traffic signal control.The application is aimed at the problem that the existing red light time is too long, leading to low traffic efficiency.The application first utilizes an SAC module and combines real-time traffic conditions to obtain the green light time of each phase, thereby realizing real-time control of the signal light.Then, the application utilizes a DQN module and combines the intention (the intention includes straight driving, left turning and right turning, in the application, only left turning and straight driving involve route changing) of the vehicle in each entrance to judge whether the vehicle is to change the route, wherein the route changing includes that the vehicle with the straight driving intention changes the route to right turn, makes a U-turn, and then right turns to enter the opposite straight driving lane; the vehicle with the left turning intention changes the route to right turn, makes a U-turn, and then straight drives to enter the opposite straight driving lane.Through the technical scheme of the application, the green light time of the signal light can be dynamically adjusted, and the traffic efficiency is greatly improved through the route changing operation.

This application relates to a method, apparatus, computer device, and storage medium for determining a passable lane area. The method includes: determining at least one candidate lane segment corresponding to a target road segment covered by a navigation path in the current navigation scenario; for each candidate lane segment, determining its corresponding entry endpoint and exit endpoint; determining the earliest possible entry position of the candidate lane segment based on the allowed entry status of its corresponding entry endpoint in the current navigation scenario; and determining the latest possible exit position of the candidate lane segment based on the allowed exit status of its corresponding exit endpoint in the current navigation scenario; and determining the passable lane area corresponding to the target road segment based on the earliest possible entry position and the corresponding latest possible exit position of each candidate lane segment. This method can accurately reflect the topological relationship between each candidate lane segment and other lane segments, improving the accuracy of passable lane area determination.

An autonomous commercial vehicle transporting oversized loads is controlled based on sensor data determined by environment sensors of the commercial vehicle and / or data of a digital map. Navigable areas including lanes in the direction of and against the direction of travel and hard shoulders are determined in the form of respective polygons, in which the autonomous commercial vehicle may be present. The behavior of the autonomous commercial vehicle is determined depending on the navigable areas, objects identified on the basis of the sensor data, and an intrinsic movement estimation. At least one corridor command is transmitted to a movement planning module, which plans a trajectory and / or a path of the commercial vehicle with avoidance of a collision with identified objects. The planned trajectory and / or the planned path are / is fed to a movement control module, which controls the autonomous commercial vehicle such that it follows the planned trajectory and / or the planned path.

The application relates to a simulation test method and device for vehicle lane centering control, a computer device, a storage medium and a computer program product. Vehicle state parameters of a controlled vehicle are obtained according to real vehicle test experiments, and vehicle position structure information of the controlled vehicle in a simulation lane is determined according to the vehicle state parameters of the controlled vehicle at a current time; two-side lane line information including two-side lane line fitting parameters is determined according to the vehicle position structure information; lane center line target fitting parameters are determined according to the two-side lane line fitting parameters; lane centering control is performed on the controlled vehicle based on the lane center line target fitting parameters, and a target error of the controlled vehicle after control deviating from the center line is calculated. According to the scheme, simulation tests are performed on the vehicle again after real vehicle test experiments, response errors of different steering systems between different vehicle individuals on the lane centering control software are avoided, and the test precision of the lane centering control software is improved.

This application discloses an assisted driving method, related devices, and a vehicle, relating to the field of intelligent driving. The method includes: acquiring surrounding information of the vehicle, and then determining whether a lane-keeping event to be executed by the vehicle exists based on the surrounding information and the vehicle's operating status information. When the existence of the lane-keeping event is determined, and the vehicle's emergency lane-keeping function is simultaneously activated, the emergency lane-keeping function is controlled to intervene and maintain the vehicle's lane. This assisted driving method, by detecting the vehicle's surrounding environment and combining it with the vehicle's operating status information, determines whether there is a risk of collision with an object, thereby triggering a lane-keeping event. Based on this, when the vehicle's emergency lane-keeping function is activated, it can be controlled to intervene and maintain the vehicle's lane, effectively avoiding the risk of collision with objects around the vehicle, thus ensuring driving safety.

This application provides a map construction method, apparatus, device, storage medium, and program product. The method includes: determining initial trajectory data and performing road matching processing on the initial trajectory data to obtain target trajectory data; determining lane information of the drivable road where the target trajectory data is located based on the trajectory data distribution in a first direction; wherein the lane information is used to indicate at least one lane; determining the lane centerline of each lane in a second direction based on the target trajectory data, and determining the lane width of each lane based on the lane centerlines of adjacent lanes; acquiring trajectory image data and performing lane line recognition processing on the trajectory image data to obtain lane line information; determining road attribute information based on the lane information, lane centerline, lane width, and lane line information; wherein the road attribute information is used to construct a high-precision map. This method can achieve low-cost, low-consumption, and high-efficiency map construction.

This invention relates to a method for operating a lane-keeping assist system (2) for a motor vehicle (1) that is at least partially assisted in its operation. The method involves detecting the surrounding environment (8) of the motor vehicle with a potential driving lane (4) using an optical detection device (5) of the lane-keeping assist system, analyzing the surrounding environment using an electronic computing device of the lane-keeping assist system, and performing at least partially assisted lane-keeping movements (9) using a lateral adjustment device (10) of the lane-keeping assist system based on the analyzed surrounding environment. When analyzing the surrounding environment, group data (12) provided by an electronic computing device (11) outside the motor vehicle is considered. Based on the group data analysis, future drivable road segments (13) outside the detection area (7) of the optical detection device are identified, and future partially assisted lane-keeping movements are determined for the lateral adjustment device. The invention also relates to computer program products and lane-keeping assist systems.

This invention relates to driving assistance devices, driving assistance methods, and non-transitory computer-readable storage media. The driving assistance device for a vehicle includes: a display device disposed in the passenger compartment of the vehicle and extending along a predetermined direction, the display device having a plurality of display areas divided along the extending direction; and a control device that controls the display device. The control device is configured to: acquire, on a merging lane merging with a main lane, the position of the vehicle relative to a merging start point where a lane change from the merging lane to the main lane is possible; and cause at least one of the plurality of display areas to emit light based on the position of the vehicle relative to the merging start point, such that as the vehicle's position approaches the merging start point, the at least one illuminated display area shifts in the extending direction.

The application provides a lane-changing back-to-normal auxiliary control method and device and a storage medium, and relates to the technical field of vehicle control. The method comprises the following steps: after detecting that the vehicle speed is greater than a preset speed, activating a back-to-normal auxiliary function, obtaining driving state information of the vehicle, obtaining a lateral movement distance of the vehicle when changing lanes according to the driving state information when the driver operates the vehicle to change lanes, obtaining back-to-normal auxiliary torque information according to the driving state information if the lateral movement distance is large, and inputting the back-to-normal auxiliary torque information to the motor end of the steering system, so that the steering system outputs a corresponding back-to-normal auxiliary torque, and the driver is reminded to control the vehicle to return to normal in time when the driver operates the vehicle to change lanes at high speed, so as to avoid collision or scratching with other vehicles on the adjacent lane.

A multi-lane device moving apparatus and a usage method. The multi-lane device moving apparatus comprises a moving unit, which comprises a moving plate and an operation slot provided at the center of the moving plate; a mounting unit, which comprises a mounting plate disposed in the operation slot, a pressure reduction assembly disposed between the mounting plate and the moving plate, and linear assemblies disposed on two sides of the mounting plate; and adjustment units, which are disposed on two sides of the moving plate. In the present invention, by mounting an operating device on the mounting plate, the mounting plate moves linearly in the direction perpendicular to a lane, so as to drive the operating device to move, enabling the operating device to change lanes, and thereby solving the problem of high costs caused by the need to provide multiple lanes in a station with corresponding devices.

The application discloses a lane departure suppression method, system, vehicle and equipment of a vehicle. The lane departure suppression method of the vehicle comprises the following steps: acquiring the vehicle speed, lane curvature and lateral position deviation of the vehicle relative to the lane center; judging whether the lane departure is caused unconsciously according to the lateral position deviation; if yes, generating a reference trajectory for returning the vehicle to the lane center according to the vehicle speed and the lane curvature; calculating the lateral control amount and the longitudinal control amount of the vehicle according to the reference trajectory and the vehicle state data in combination with a preset dynamic prediction model; and performing lane departure suppression control on the vehicle according to the lateral control amount and the longitudinal control amount. According to the application, the reference trajectory for returning the vehicle to the lane center can be generated after the lane departure caused unconsciously is judged, and the optimal lateral control amount and the longitudinal control amount can be solved in combination with the dynamic prediction model, so that the lane departure suppression control can be performed on the vehicle while the driving stability of the vehicle is ensured.