274 results about "Road junction" patented technology

The invention belongs to the field of visual tracking, and relates to a multi-target visual tracking method based on cooperation of a dynamic neural field and a neural network, which takes a cross-modal cooperation architecture as a core and comprises a dynamic neural field module based on multi-target trajectory maintenance and shielding matching and an improved MoESDQ neural network module. Meanwhile, a collaborative decision-making mechanism is designed, when the activation peak value of the dynamic neural field is attenuated to a preset threshold value, neural network feature matching is triggered, and disappearance target reproduction correlation is achieved based on cosine similarity. The objective of the invention is to solve the visual tracking capability under the condition of scene and target motion change in a monitoring range, for example, under an intelligent traffic intersection scene. The problems of high ID switching rate, multi-target misassociation and low tracking precision under a real-time tracking background caused by scene change or frequent shielding of vehicles and pedestrians, similar target appearances, transient disappearance and reproduction of the targets and sudden illumination change are solved.

The invention discloses an automatic driving decision-making method and system for a port mixed traffic intersection based on deep reinforcement learning, and relates to the technical field of automatic driving. Comprising the following steps: acquiring real-time state information of automatic driving transportation equipment in a port mixed traffic intersection environment, and fusing the real-time state information into an automatic driving transportation equipment state vector in a heterogeneous manner; constructing a reinforcement learning decision model based on the DDPG; building a port traffic environment simulation platform; the reinforcement learning decision model based on the DDPG is trained; and solidifying and deploying the trained reinforcement learning decision model based on the DDPG in a vehicle-mounted calculation unit of the automatic driving transportation equipment, and controlling the driving of the automatic driving transportation equipment. The traffic efficiency, stability and safety of the automatic driving transportation equipment at the port intersection can be improved, the unmanned transportation process of the port mixed traffic scene is promoted, and the wharf transformation and operation cost is reduced.

The invention relates to a method for operating a motor vehicle (2), wherein the motor vehicle (2) is automatically guided longitudinally. An intersection (6) arranged in the direction of travel (X) in front of the motor vehicle (2) is detected, at which the traffic rule "right before left" applies and at which there is a road (8) from the right. Furthermore, visibility (E) is ensured. a , E b ) of the intersection (6) is determined, and a first velocity (v a , v b ) for at least partial passage of the intersection (6), in particular only depending on the certain visibility (E a , E b ) is determined. The speed of the motor vehicle (v KFZ ) is adjusted to the first speed (v a , v b ) set.

Provided is a vehicle control device capable of preventing unnecessary operations in a driving assistance function for avoiding a collision between an own vehicle and a pedestrian at an intersection, for example. There is provided an operation-suppression determination unit adapted to determine whether to change the result of collision determination (whether to suppress an unnecessary operation), based on the change (temporal change) of the lap rate between a target object and an own vehicle, and based on the change (temporal change) of the lateral speed generated in the target object with respect to the own vehicle, if a collision determination unit determines a collision. Further, there is provided a control-intervention determination unit adapted to determine control intervention in the own vehicle, based on results from the collision determination unit and the operation-suppression determination unit.

Techniques are provided which may be implemented using various methods and / or apparatuses in a vehicle to utilize vehicle external sensor data, vehicle internal sensor data, vehicle capabilities and external CV2X input to determine, send, receive and utilize data elements to determine inter-vehicle spacing, intersection priority, lane change behavior and spacing and other autonomous vehicle behavior.

The invention provides an intelligent traffic scheduling method and system based on multi-modal fusion and space-time prediction, and relates to the technical field of intelligent traffic scheduling, and the method comprises the steps: collecting traffic-related multi-modal data; performing preprocessing and data-level and feature-level fusion processing on the multi-modal data to generate a fusion feature matrix; constructing an STGCN-LSTM space-time prediction model according to the fusion feature matrix, and predicting the traffic flow and queuing length of each entrance lane of the current scene to obtain a prediction result; and dynamically optimizing a signal lamp timing scheme according to the prediction result and the real-time traffic state. By accurately sensing a real-time traffic state, predicting a traffic flow change trend in a short time in the future and dynamically adjusting an intersection signal lamp timing scheme, on-demand timing is realized, the average waiting time of vehicles is shortened, the queuing length at an intersection is reduced, the traffic efficiency at the intersection is improved, and meanwhile, the traffic demands of pedestrians and non-motor vehicles are considered; and the safety and smoothness of traffic operation are ensured.

A vehicle driving assistance apparatus notifies an operator of a vehicle of a moving body when recognizing the moving body based on wireless communication information. The moving body moves toward an intersection ahead of the vehicle. The moving body satisfies a predetermined condition. The predetermined condition includes a first condition that a moving speed of the moving body is equal to or lower than a first speed and an intersection arrival margin time is within a range equal to or shorter than a first time and equal to or longer than a second time shorter than the first time. The intersection arrival margin time is the time remaining until the moving body arrives at the intersection. The apparatus notifies the operator of the presence of the moving body when recognizing the presence of the moving body satisfying the first condition.

The invention discloses an automatic generation method of an intelligent unmanned system city simulation test scene, and relates to the field of simulation scene construction and intelligent unmanned system test.The method comprises the steps that based on terrain boundary parameters, a plurality of rectangular areas with function labels are generated through Poisson disc sampling and a distance gradient algorithm; constructing a navigation grid representing the passable area; arranging a plurality of road intersections by adopting a constrained Poisson sampling algorithm; calculating the heart weight based on each intersection, and calculating the connection strength between the intersections through a gravity model; generating a global road network topology structure by adopting an improved minimum spanning tree algorithm; performing path search by adopting an algorithm A to obtain an optimal path, and automatically generating a road model and ancillary facilities; and extracting road network, road parameters and subsidiary facility information in the generated urban scene, and generating a standardized scene description file according to an OpenDRIVE standard format. And the construction efficiency of the simulation test scene, the test effectiveness and the cross-platform compatibility are improved.

The invention discloses a security and protection monitoring data sharing and analysis platform and method based on cloud computing, and relates to the technical field of cloud computing. The security and protection monitoring data sharing and analysis platform and method based on cloud computing comprises the following steps: S1, collecting monitoring data in real time, performing data preprocessing, and optimizing visual images and video streams; s2, a distributed computing architecture is designed, uploading and synchronous data sharing of monitoring data are carried out, and edge device computing is optimized; s3, target vehicle detection and state initialization are carried out, multi-target vehicle tracking is realized, the vehicle position and state are predicted, target matching is carried out, error correction is carried out, and real-time updating and feedback are carried out; and S4, identifying a traffic event, analyzing and predicting a traffic state, evaluating a prediction result in real time, and carrying out event feedback and optimization decision response. The problem that accurate real-time detection and tracking cannot be achieved due to shielding, misrecognition and loss of targets when a vehicle moves at a complex urban intersection is solved.

In examples, autonomous vehicles are enabled to negotiate yield scenarios in a safe and predictable manner. In response to detecting a yield scenario, a wait element data structure is generated that encodes geometries of an ego path, a contender path that includes at least one contention point with the ego path, as well as a state of contention associated with the at least on contention point. Geometry of yield scenario context may also be encoded, such as inside ground of an intersection, entry or exit lines, etc. The wait element data structure is passed to a yield planner of the autonomous vehicle. The yield planner determines a yielding behavior for the autonomous vehicle based at least on the wait element data structure. A control system of the autonomous vehicle may operate the autonomous vehicle in accordance with the yield behavior, such that the autonomous vehicle safely negotiates the yield scenario.

Techniques are described herein for evaluating and tuning parameters for controlling the behavior of an autonomous vehicle in or near intersections controlled by traffic signals. A planning component of an autonomous vehicle may use a set of traffic signal parameters to compute trajectory costs for the vehicle associated with traversing an intersection controlled by a traffic signal in a non-permissible state (e.g., a red light). A parameter tuning system may execute driving simulations using the planning component and a candidate set of parameters to control the behavior of a simulation vehicle within a training data set of traffic signal intersections. The parameter tuning system may determine performance metrics based on the behaviors of the simulated vehicle and may execute a search algorithm to determine modified (e.g., optimal) parameter sets for controlling vehicles during real-world driving scenarios having intersections controlled by traffic signals.

A system designed to avoid a rear-end cross-traffic collision, wherein the system features: an obstacle detection unit (20) which detects the position of an obstacle (B) by receiving electromagnetic waves reflected from a reflection point of the obstacle (B); a direction estimation unit (30) which estimates the direction of travel of the obstacle (B) based on the position of the obstacle (B) detected by the obstacle detection unit (10); and a collision determination unit (B) which determines the possibility of a collision with the obstacle (B) on the basis of the direction of travel of the obstacle (B) estimated by the direction estimation unit (30), characterized by a reliability evaluation unit (50) which collects the multiple directions of travel of the obstacle (B) estimated by the direction estimation unit (30) and evaluates an estimated reliability degree for the direction of travel of the obstacle (B) by using the number of directions of travel collected and a variance or standard deviation between the directions of travel collected, wherein, if the reliability level estimated by the reliability evaluation unit (50) is equal to or greater than a preset reliability level, the collision determination unit (40) determines the possibility of a collision with the obstacle (B) on the basis of the direction of travel of the obstacle (B).

The application provides a kind of intersection unmanned mine car cooperative control method and system without signal light, comprising: based on conflict point model, the internal area of intersection is constructed;Based on the internal area of intersection, an optimization area is constructed;Mine car enters optimization area, sends the car state information and pass request to intersection manager;Based on conflict table, intersection manager judges whether there is potential conflict between mine car;According to first-in first-out and first-in first-out principle, the priority of mine car is judged;Based on priority analysis result, intersection manager sends the pass instruction and pass priority information to the mine car that has sent pass request;A deep reinforcement learning model is constructed, a deep learning network is trained based on DDPG algorithm and parameters are updated, and the acceleration of each mine car in intersection is adjusted.The application realizes safe passage of unmanned mine car in irregular intersection scene without signal light, and effectively improves the passage efficiency.

The invention provides an intersection MAP message acquisition and generation method and system based on intelligent network connection. The method comprises the following steps: S1, acquiring original sensing data acquired by various sensing devices such as a roadside camera and a laser radar; s2, taking a road side unit RSU as a GNSS clock synchronization source, performing clock synchronization on the sensing equipment and the edge computing unit, and providing a unified time reference for data; s3, in an edge calculation unit, performing cross-modal fusion on visual semantic information of the image and geometric information of the laser point cloud, and reconstructing a semantic octree map model coded with a road environment three-dimensional semantic topological structure; and S4, extracting road topology information from the model, and generating and broadcasting an MAP message through V2X protocol stack coding of the RSU. According to the invention, the existing roadside facilities can be efficiently utilized, and the real-time acquisition and generation of the MAP message can be realized.

The present application relates to a kind of layered reinforcement learning driven car-road cooperation automatic driving longitudinal following control method and system, belong to the field of automatic driving vehicle control.For the problem that the generalization ability of existing following control method is insufficient, strategy update is easy to lose stability, easy to fall into local optimum, adopt layered architecture, upper layer adapts intersection, high-speed straight road and ramp multiple typical traffic scenes, based on real-time car-road cooperation communication information dynamic planning follow target, after normalizing processing to multi-source heterogeneous traffic characteristics, generate environment state vector;Lower layer uses proximal policy optimization algorithm, outputs continuous accelerator or brake command through actor-critic double network, and updates network parameters by combining strategy entropy with pruning loss with Jacobian correction.The method improves the cross-scene generalization ability and perception robustness, effectively guarantees the stability and monotonicity of strategy update, avoids instruction step mutation, breaks the exploration deadlock, and balances driving safety, traffic efficiency and driving comfort.

Disclosed herein a vehicle and a method of controlling the same. When the vehicle enters a junction on a navigation map, the vehicle selects a nearby route from a plurality of nearby routes as a final traveling route to be guided by a navigation system based on a curvature radius of each of the plurality of nearby routes split at the junction and a curvature radius of a current lane on which the vehicle is traveling.

The invention discloses a road traffic flow state adaptive control method based on edge node sensing, and relates to the technical field of intelligent traffic control. Comprising the following steps: S1, acquiring traffic flow data of each intersection through a set sensor network, and acquiring a local utility value of each intersection; s2, according to the traffic flow data of the intelligent agent arranged at each intersection, determining marginal external cost, and combining the marginal external cost with a local utility value to construct a comprehensive decision function; and S3, according to the comprehensive decision function, setting a maximized comprehensive decision function corresponding to each agent, and according to a set signal timing physical constraint condition, obtaining an optimal signal timing scheme of each intersection through a distributed optimization algorithm. Autonomous cooperative control independent of a central server is realized, and overall optimization of regional traffic flow is realized while autonomy of the intersection is guaranteed.

The invention relates to a method for controlling a vehicle (14, 16) in a special situation where an escape route (32) is to be provided for an emergency vehicle (30) in a traffic area (10), in particular an intersection area, with a traffic system (22), wherein the traffic system (22) comprises at least one sensor (26) for monitoring the traffic area (10), a communication device (28) for establishing a communication link (30) with the vehicle (14, 16), and a controller (24) for generating driving instructions for the vehicle (14, 16), wherein the driving instructions can be sent to the vehicle via the communication link (30), wherein the road users (12, 14, 16, 18) and their movements in the traffic area (10) are detected by the traffic system (22), wherein the method comprises the following steps: e) Identifying a special situation in which an escape route (34) for an emergency vehicle (32) is to be provided, f) Creating a prediction of the driving behavior of road users (12, 18) taking into account a behavior prediction provided to the controller (22), in particular stored in the controller (22), for the road users (12, 18) present in the traffic area, g) Creating a driving instruction for the vehicle (14, 16) to provide the escape route (34) taking into account the created prediction of the driving behavior of the road users (12, 18) and sending the driving instruction to the vehicle (14, 16). The invention further relates to a traffic system (22) which can carry out such a method.

Autonomous and manually operated vehicles are integrated into a cohesive, interactive environment, with communications to each other and to their surroundings, to improve traffic flow while reducing accidents and other incidents. All vehicles send / receive messages to / from each other, and from infrastructure devices, enabling the vehicles to determine their status, traffic conditions and infrastructure. The vehicles store and operate in accordance with a common set of rules based upon the messages received and other inputs from sensors, databases, and so forth, to avoid obstacles and collisions based upon current and, in some cases, future or predicted behavior. Shared vehicle control interfaces enable the AVs to conform to driving activities that are legal, safe, and allowable on roadways. Such activities enable each AV to drive within safety margins, speed limits, on allowed or legal driving lanes and through allowed turns, intersections, mergers, lane changes, stops / starts, and so forth.

A method for adaptive and predictive speed management of a motor vehicle, the vehicle traveling on a route determined by a navigator, comprises: detection (21) that the motor vehicle is approaching at least two successive intersections on the same side of the lane; determination (23) that following the route involves taking the intersection furthest from the motor vehicle; and detection (25) of the activation of a turn signal by the driver of the motor vehicle; then, if the nearest intersection to the vehicle is (27) less than a predetermined distance from the furthest intersection, adjustment (29) of the vehicle's speed to take the furthest intersection, otherwise adjustment (31) of the vehicle's speed to take the nearest intersection. Figure to be published with the abbreviation: Fig 2

According to one aspect, the present description relates to a system for controlling road traffic, the system comprising an intersection controller (110) configured to transmit electrical signals to optical units (21A, 22A, 23A) of traffic lights at the intersection, the electrical signals resulting from control signals, a transmitter (120) configured to transmit, to connected vehicles, messages configured to inform of an assumed state of at least one optical unit, and a safety module (130). The safety module comprises a receiver (135) configured to receive, via wireless link, each message transmitted by the transmitter (120); a measurement unit configured to determine, simultaneously on receiving the message, an actual state of the at least one optical unit; and a processing unit configured to generate an inconsistency signal in the event of a difference between the assumed state and the actual state of the at least one optical unit.

According to the present invention, a digital rear-view mirror installed in a vehicle receives navigation information from a navigation device also installed in the vehicle, and an operation of the digital rear-view mirror is controlled using the navigation information, whereby convenience of a driver can be increased. Specifically, the rear-view mirror according to a preferred embodiment of the present invention: when a vehicle enters within a first threshold distance from a main point (branch point, intersection, or entry / exit lamp) where the direction of the vehicle needs to be changed from navigation information, switches to a wide-angle display mode and displays a rear-view image to a driver at a wide angle on a display included in the rear-view mirror; and when the driver turns on a turn signal lamp, identifies whether a vehicle is detected behind in a corresponding direction and displays the detected vehicle on the display, so that even though the driver does not manually switch the display mode one by one in a situation where a lane change is required by approaching the main point, a display screen is automatically and dynamically switched according to the situation, thereby enabling the driver to more conveniently identify a rear situation of the vehicle and an approaching rear vehicle.

Monitoring system for intersection areas, comprehensive - a hemispherical mirror (1) for optical all-round vision, - at least one motion sensor (2) for detecting vehicles or pedestrians, and - at least one optical signaling device (3), wherein the optical signaling device (3) is coupled with the motion sensor (2) and switches to a warning color when motion is detected.

The invention relates to path prediction for autonomous or semi-autonomous systems and applications. In various examples, probability-based techniques may be used to predict an intent path of a machine through an environment. For example, various input data from perceptual systems, localization systems, map systems, and / or other data sources may be used to determine occupant intent and calculate scores associated with road segments in an environment. These scores may indicate the probability that certain road segments are part of the path of the machine intended by the occupant, and may be aggregated for each road segment across multiple instances of receiving and analyzing the input data. In some cases, the highest-score road segment may be selected as part of the predicted path of the machine. For example, at an intersection where a plurality of road sections intersect, the road section with the highest score can be selected as a predicted path.

An autonomous driving device according to the present invention comprises: a light-emitting unit including a left light-emitting module and a right light-emitting module; and a control unit for controlling the autonomous driving device so that the autonomous driving device passes through an intersection according to predetermined traffic rules, wherein the control unit controls the operation states of the left light-emitting module and the right light-emitting module to indicate the traveling direction of the autonomous driving device at the intersection.

This invention relates to an intelligent signal control method and system for asymmetric intersections, belonging to the field of intelligent traffic control technology. The method dynamically adjusts traffic light timings by collecting real-time traffic flow data from main roads and side roads, utilizing data processing and analysis techniques. Specifically, if there are no vehicles waiting on side roads before the main road's green light ends, the main road's green light time is automatically extended to improve intersection efficiency. The system includes a data detection unit, a data processing unit, a signal control unit, and a data storage unit, capable of real-time monitoring of traffic flow and vehicle queuing, and adjusting signal timings based on real-time data. This invention effectively reduces vehicle waiting time, increases traffic flow, reduces congestion, and improves traffic safety and efficiency.

The invention relates to an information processing apparatus and an information processing method. On the basis of position information of a plurality of vehicles, the information processing device detects the presence of a fleet in which a number of vehicles greater than or equal to a first threshold value are traveling or stopped continuously at a speed lower than a first speed on a first lane of a road including a plurality of lanes. When the fleet is within a predetermined range from a first facility located on the first lane side of the road, and no matter how the lighting color of a signal lamp arranged at a first intersection is, the number of vehicles which are about to turn to the first facility side is greater than or equal to a second threshold value within the predetermined range. The information processing device determines that the fleet is a first fleet caused by entry into the first facility. The information processing device causes a first vehicle traveling in front of a first fleet on a first lane to display a first object related to the first fleet on a display device so as to overlap with a real space.

Method (400) for implementing sensor fusion to determine a collision potential for a vehicle (100), the method comprising: Identifying (410) a specific intersection (200) that the vehicle (100) is approaching, using a processor; Identify, using the processor, collision potential scenarios associated with one or more paths through the specified intersection (200), wherein each collision potential scenario defines a risk of collision between the vehicle (100) and an object in a specified area; Setting (430), using the processor, a weighting with which one or more information sources of the vehicle (100) are taken into account for each collision potential scenario, such that one or more of the one or more information sources that provide the most relevant and reliable information about the specific area corresponding to the collision potential scenario is given the highest weighting; Implement (440), using the processor, a sensor fusion based on setting the weighting of one or more information sources and performing a detection based on the sensor fusion; Providing (450), using the processor, a warning or implementing actions according to the detection, Identifying and storing the collision potential scenarios associated with the one or more paths through each intersection (200) on a map, wherein identifying the collision potential scenarios associated with the one or more paths through the particular intersection (200) includes retrieving the collision potential scenarios from a memory in real time and updating the weighting with which the one or more information sources of the vehicle (100) are considered for each upcoming collision potential scenario in real time based on real-time conditions, wherein the real-time conditions include a quality of data from the one or more information sources or ambient light conditions.

A vehicle driving support device includes a surrounding environment recognition unit, a travel control unit, and a collision avoidance controller. The collision avoidance controller is configured to estimate a position of a vehicle and generate a forecast traveling path thereof when turning across an opposite lane at an intersection, recognize an oncoming vehicle traveling on each of lanes of the opposite lane, based on surrounding environment information acquired by the surrounding environment recognition unit, detect, for each lane, a collision forecast position at which the forecast traveling path intersects with a traveling path of the oncoming vehicle, and forecast a collision of the vehicle with the oncoming vehicle, determine whether to execute collision avoidance control in which the travel control unit operates a brake driver, for the collision forecast position, and dispose the collision avoidance control at a collision avoidance position on the forecast traveling path.

The invention belongs to the technical field of road traffic management, and provides a comprehensive traffic management system and method.The system comprises a dispatching platform, a plurality of unmanned aerial vehicles, intelligent street lamps, relay transmission equipment, a controller and traffic signal lamps; the unmanned aerial vehicle is connected with the scheduling platform to execute the instruction; the intelligent street lamps are arranged along the road, connected with the relay equipment, and used for collecting and analyzing road data and interacting; the relay equipment is connected with the scheduling platform and the controller to realize data transmission; the controller is connected with the traffic lights and controls operation of the lights according to platform instructions. The traffic lights are arranged at intersections to adjust traffic order. According to the invention, through cooperation of the scheduling platform and the relay transmission device, the intelligent street lamp, the unmanned aerial vehicle and the traffic signal lamp are connected to realize multi-device data closed-loop circulation; the intelligent street lamp has a data preprocessing capability, and does not need to upload all original data to a centralized platform, so that the processing pressure that data interaction depends on the centralized platform in the background technology is relieved.