164 results about "Ground vehicles" patented technology

The invention discloses an aerial unmanned aerial vehicle configuration number prediction method based on ground vehicle trajectory data, and belongs to the technical field of unmanned aerial vehicle control. In order to solve the problem of predicting the configuration number of aerial unmanned aerial vehicles based on a ground traffic state, the method comprises the steps of constructing a vehicle trajectory set; constructing a traffic density thermal field; constructing an average speed trend vector field; constructing a direction consistency index; a traffic density thermal field is used as a basic load, the modulus length of an average speed trend vector field represents mobility, a direction consistency index represents a traffic order, weighted combination is carried out to construct distribution pressure intensity, the distribution pressure intensity is converted into the demand intensity of air resources, and a space vector from a vehicle position to a nearest unmanned aerial vehicle take-off and landing point and a terrain complexity factor are considered. Constructing a preliminary unmanned aerial vehicle demand estimation field; and introducing a task urgency weighting function, the current task backlog amount and the weather flight risk to construct a final unmanned aerial vehicle deployment suggestion function, and completing prediction of the air unmanned aerial vehicle configuration number based on the ground vehicle trajectory data.

The invention relates to the technical field of artificial intelligence security, in particular to a physical domain robust adversarial attack method oriented to unmanned aerial vehicle aerial photography target detection, and aims at challenges of various environmental factors, the method comprises the following steps: initializing a learnable pixel tensor to generate an adversarial patch; inputting the training samples, the adversarial patches and label files of the adversarial patches into a patch conversion module to generate adversarial samples, inputting the adversarial samples into a YOLO target detector, performing weighted summation on each loss item based on the performance of the adversarial patches on each target detection network, constructing a unified optimization target, solving the overall loss for a detection model, and constructing an optimal target; according to the method, the adversarial patch is installed on the top of the vehicle or around the vehicle, so that the ground vehicle can avoid the unmanned aerial vehicle target detection system, and therefore, robustness detection of the aerial photography target detection neural network can be realized.

The invention discloses an air-ground task intersection prediction method for emergency rescue, and belongs to the technical field of unmanned aerial vehicle control. In order to solve the problem of accurately predicting an air-ground task intersection with reachability and energy efficiency requirements, the method comprises the following steps: predicting an unmanned aerial vehicle path; predicting a ground vehicle path; generating candidate intersection points; calculating the time cost of the rescue task, the energy consumption cost of flight and the environmental risk cost; constructing a comprehensive cost function; constructing a confidence factor through the terrain height difference, the path node complexity and the communication shielding score, and carrying out risk correction on the comprehensive cost function to obtain a corrected comprehensive cost function; and introducing factors such as a ground slope angle, a wind speed value, a ground trafficability score and an unmanned aerial vehicle flight distance to carry out punishment correction, and extracting an optimal air-ground task intersection point coordinate for emergency rescue. The method is suitable for various emergency rescue, multi-platform cooperation and intelligent task scheduling, and has wide application prospect and popularization value.

Systems and methods for causing a first autonomous vehicle (e.g., a drone or other aerial vehicle) to utilize a LIDAR pattern being emitted by a LIDAR device of a second autonomous vehicle (e.g., a ground vehicle) to determine one or more characteristics of the second vehicle. The one or more characteristics may comprise, for example, (i) a make and / or model of a manufacturer of the LIDAR device and / or the second vehicle; and (ii) a particular unit of the LIDAR device and / or the second vehicle. The first vehicle may further utilize the LIDAR pattern of the second vehicle to perform other operations, such as mapping a 3-D model of the environment being traversed by the second vehicle.

The invention discloses an unmanned aerial vehicle assisted Internet of Vehicles trajectory planning method and system based on traffic flow prediction, and the method comprises the steps: S1, employing multi-source historical traffic data collected by a distributed sensor network as input, and building a traffic flow space-time prediction model based on a deep learning algorithm; s2, a vehicle networking model composed of a plurality of vehicles and a plurality of unmanned aerial vehicles is constructed, the unmanned aerial vehicles fly at a fixed height and serve as air base stations to provide services for ground vehicles, and only one unmanned aerial vehicle provides services for each vehicle; and S3, constructing a multi-unmanned aerial vehicle assisted Internet of Vehicles communication system model, clustering ground vehicles by using a clustering algorithm in combination with traffic flow prediction data, and further jointly optimizing trajectory planning and resource allocation strategies of the unmanned aerial vehicles by taking a clustering center as a pre-deployment position of the unmanned aerial vehicles for each vehicle cluster. The corresponding system comprises the sensor network, the cloud platform and the unmanned aerial vehicle cluster carrying the base station, and the communication quality and the energy efficiency of the Internet of Vehicles can be effectively improved.

The invention relates to the field of multi-mode collaborative transportation and logistics, in particular to a collaborative distribution optimization method and system for taking off, landing and synchronous recovery of a vehicle-mounted unmanned aerial vehicle on the way (in the advancing process). According to the method, a layered decoupling framework is adopted; in the first layer, subsection division is performed on a road network, taking-off and landing positions are continuously optimized in candidate taking-off and landing subsection pairs based on a Lagrange multiplier method and geometric synchronization constraint, and a client cluster candidate set is formed; the second layer performs joint optimization on selection of a single take-off and landing sub-segment pair in each client cluster and a global path of a ground vehicle to construct a generalized traveling salesman variant, and designs a sub-segment distance measurement and an overlapping deduction strategy to deal with any continuous take-off and landing distance calculation and multi-unmanned aerial vehicle cooperation problem. Experiments show that compared with a fixed stop point or discretization in-transit strategy, the method can significantly reduce the total delivery cost and the completion time, and has robustness and expandability for customer scale, distribution, unmanned aerial vehicle speed and road network density change.

The application provides a method and system for detecting camouflaged targets by unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs). The system ensures the synchronization of UAVs and UGVs through the global positioning system (GPS), and uses the infrared cameras, binocular cameras, and radar sensors carried by both to efficiently collect data in the target area. The system further preprocesses and analyzes the collected data, and uses improved SSD algorithms and pattern recognition techniques to identify potential camouflaged targets, and performs pattern matching and information fusion to improve the accuracy of the identification results. The SE attention module is introduced innovatively, which optimizes the feature fusion process, enhances the network's spatial correlation capture ability, and enables the system to use global information more effectively, improving the detection accuracy of camouflaged targets. The application solves the problem of poor reliability in traditional methods for detecting camouflaged targets, improves the real-time performance and effectiveness of the cooperative operation of UAVs and UGVs, and significantly improves the accuracy and response speed of camouflaged target identification in battlefield environments. It has important theoretical value and application prospect in various military crisis response.

Provided is an antenna integrated structure in which an antenna is inserted into ground vehicle, marine ship and aircraft structure, and more particularly, a sandwich panel type antenna integrated latticecore having a structure for improving communication performance of an antenna module.

The application discloses a method for predicting the number of air unmanned aerial vehicles (UAVs) based on ground vehicle trajectory data, and belongs to the technical field of UAV control. In order to solve the problem of predicting the number of air unmanned aerial vehicles based on ground traffic state, the application comprises the following steps: constructing a vehicle trajectory set; constructing a traffic density thermal field; constructing an average speed trend vector field; constructing a direction consistency index; taking the traffic density thermal field as a basic load, the modulus of the average speed trend vector field representing fluidity, and the direction consistency index representing traffic order, and performing weighted combination to construct a demand intensity of air resources converted from a distribution pressure intensity; considering a spatial vector from a vehicle position to a nearest UAV take-off point and a terrain complexity factor, and constructing a preliminary UAV demand estimation field; introducing a task urgency weighting function, a current task backlog and a weather flight risk to construct a final UAV deployment suggestion function, and completing the prediction of the number of air unmanned aerial vehicles based on ground vehicle trajectory data.

An automated cruise control system is disclosed. Sensors detect driving parameters associated with the ground vehicle as the ground vehicle maneuvers along a segment of the roadway. A ground vehicle control detector detects ground vehicle control inputs associated with an operation of the ground vehicle. The ground vehicle control inputs are generated from a longitudinal operation of the ground vehicle. A energy consumption cruise controller automatically adjusts the operation of the ground vehicle as the ground vehicle maneuvers along the segment of the roadway to maintain the operation of the ground vehicle within an operation threshold based on the detected driving parameters and ground vehicle control inputs. The operation threshold is the operation of the ground vehicle that decreases an amount of overall energy consumed by the ground vehicle and maintains a longitudinal speed of the ground vehicle within a longitudinal speed threshold.

The invention belongs to the technical field of automobiles, and particularly relates to a ground vehicle low-calculation-power path tracking control method considering a coupling gradient. The method comprises the following steps: firstly, establishing a vehicle dynamics model and a kinematics model considering the coupling gradient through coordinate transformation and dynamics analysis, and ensuring the path tracking precision of an unmanned ground vehicle on the coupling gradient; secondly, an unmanned ground vehicle path tracking system considering actuator time lag is constructed, and state space equation discretization is carried out, so that the system can be used for model prediction control; and finally, a path tracking control method is constructed, Laguerre function fitting is utilized to replace a link of solving an optimal control sequence through quadratic programming in traditional model prediction control, and the computing power demand of the control method is remarkably reduced. Through simulation verification, the provided control method can effectively reduce the computing power of the control method on the premise of ensuring the path tracking accuracy of the unmanned ground vehicle.

Wheels are arranged on the lower portion of a ground carrier in a bilateral symmetry mode, a power system and a communication and automatic driving control system are arranged in a vehicle head on the front portion of the ground carrier, and a connecting clamping groove is formed in a floor of the ground carrier. Electromagnetic spring buckles are arranged on the lower portion of the flight cabin and correspond to the four connecting clamping grooves formed in the ground carrier floor in position. Wings with upward inverted inner sections and straight outer sections are respectively arranged on the left and right sides of the upper part of the flight cabin; the inner section and the outer section of each wing are averagely divided into two sections; when the hydraulic mechanism is opened and closed, the inner section and the outer section can be folded or unfolded around the hinge connecting mechanism, and after folding, the spring positioning pins are inserted into the positioning holes. Oblique empennages are arranged on the left side and the right side of the tail portion of the upper portion of the flight cabin respectively, and deflection rudders are arranged on the rear edges of the outer ends of the oblique empennages. The hovercar can run on the ground, can take off and land vertically, can hover in the air or fly horizontally and can sail underwater; the safety and reliability are high, and the use efficiency is high.

The application discloses a kind of vehicle-mounted mechanical arm auxiliary aircraft take-off system, belong to aviation equipment technical field.System includes aircraft, vehicle-mounted mechanical arm device, vehicle-mounted power battery pack and carrying truck;The vehicle-mounted mechanical arm device is fixedly installed on truck frame, and the end of mechanical arm can be separated with the bottom of aircraft It realizes detachable docking, relies on vehicle-mounted power battery pack to provide power drive mechanical arm to stretch and lift up.In the aircraft take-off stage, mechanical arm exerts upward and forward boost force to aircraft, and the maximum energy consumption of vertical take-off is transferred to ground vehicle system in the flat flight stage, which greatly reduces the battery consumption of aircraft itself.The system is suitable for various types of vertical take-off and landing aircraft, especially for logistics distribution unmanned aerial vehicle, manned aircraft and other scenarios, effectively prolongs the aircraft range, improves the effective payload, the overall structure is flexible and convenient to deploy, with high engineering application value.

The invention relates to a vehicle ad hoc network post-disaster emergency data transmission method based on unmanned aerial vehicle assistance, and the method comprises the steps: obtaining the driving information of nodes in an unmanned aerial vehicle-vehicle ad hoc network and the state information of emergency data to be transmitted, and calculating a reference trajectory path according to preset network topology information and a data transmission destination; on the basis of the moving track path of the neighbor node of the node, screening the neighbor node meeting a preset condition, and constructing a candidate relay node set of the ground vehicle and air unmanned aerial vehicle ad hoc network; calculating evaluation parameters of the candidate relay node set, and evaluating the data transmission capability; and determining a target relay node based on the data priority and the data transmission capability, and transmitting the post-disaster emergency data. Therefore, the problems that in the related technology, it is assumed that network connection is continuous or semi-continuous, it is difficult to deal with high intermittency of a post-disaster network and rapid changes of a topological structure, relay selection depends on geographic information and the moving direction, and multi-dimensional parameter evaluation of node transmission capacity is lacked are solved.

This invention discloses a universal mobile carrier navigation control method that integrates safety zone and pedestrian density, belonging to the field of intelligent navigation and safety control technology. This method constructs a multi-layered digital navigation map under a unified coordinate system; it acquires real-time pedestrian density and environmental data around the carrier through a sensor network and cloud interface; in normal mode, it plans conventional paths to avoid high-density pedestrian traffic based on a safety-first principle; when the carrier malfunctions or triggers an emergency signal, the system automatically switches to an emergency avoidance mode, selects the nearest avoidance area that meets safe stopping conditions, and controls the carrier to move along the avoidance path and complete a precise stop. This invention has strong versatility and is applicable to various carriers such as aircraft, ground vehicles, robots, and ships, significantly reducing the safety risks in the operation of urban mobile carriers.

The invention is notably directed to an aircraft carrier ground vehicle (10), which comprises a chassis (102), a landing platform (104), a coupling mechanism (106), and an actuation mechanism (108). The landing platform is designed to accommodate an aircraft (20). The coupling mechanism connects the landing platform to the chassis to form a kinematic pair, in which the landing platform is rotatably mounted on the chassis. The actuation mechanism is adapted to rotate the landing platform relative to the chassis, to allow an aircraft to land on the landing platform as the vehicle moves along a landing direction of the aircraft and compensate for an inclination angle of the aircraft on landing, in operation. The aircraft carrier ground vehicles may further be designed to allow taxiing and take-off of the aircraft. The invention is further directed to related aircraft carrier ground vehicle systems, which include several vehicles that are swarmed for landing an aircraft, as well as aircraft landing and take-off methods.

A method, system, storage medium, and computer program product for correcting deviations in a ground vehicle are disclosed. The ground vehicle is configured to access and retrieve goods at a target storage location. The deviation control method includes: acquiring ground markings corresponding to the target storage location; identifying angular and positional deviations; causing a second positioning coordinate axis to deviate from a preset angle value relative to a second direction in a first clockwise direction; moving the ground vehicle towards a second reference coordinate axis in a direction parallel to the positioning coordinate system; responding to the ground vehicle moving to a position where the positioning origin falls on the second reference coordinate axis, rotating the ground vehicle around the positioning origin in a second clockwise direction by a preset angle value, wherein the second clockwise direction is opposite to the first clockwise direction; and moving the ground vehicle towards the first reference axis in a direction parallel to the second direction, so that the positioning origin coincides with the reference origin. This disclosure can improve inbound and outbound efficiency.

The present disclosure provides an autonomous ground vehicle system configured to be deployed in and coordinate with a multi-agent swarm of autonomous ground vehicles. The system includes one or more processors, one or more memories, one or more wireless communication modules, one or more motors, and one or more sensors configured to observe an environment through which the autonomous ground vehicle system navigates. The system is configured to receive a multi-agent behavior request requiring multiple agents to be performed, translate the request into one or more tasks each configured to be performed by a single agent, assign at least a first task to the autonomous ground vehicle system based on a cost function indicating efficiency, and autonomously execute the first task causing the system to navigate through the environment using the sensors and motor.

The application relates to a ground vehicle tracking control method and system, which comprises the following steps: dividing each image of a shooting picture into an ROI region and a background region, dividing the background region into a plurality of grids, and assigning corresponding feature points to the ROI region and the plurality of grids; calculating the optical flow residual of the feature points in the ROI region, judging the real-time position of a tracked vehicle on the image based on the optical flow residual; predicting the state of the tracked vehicle, obtaining the latest state of the tracked vehicle, calculating the real-time longitude and latitude corresponding to the tracked vehicle based on the latest state and the latest position, and issuing a flight point for a UAV based on the real-time longitude and latitude of the tracked vehicle to realize real-time tracking. Through the application, the interference of UAV self-vibration on image recognition can be overcome, and the tracking can be quickly recovered after the tracked vehicle is temporarily blocked.

The invention discloses a deviation correction control method and system for a ground carrier, a storage medium and a computer program product. The ground carrier is configured to take down goods on a target storage position or store the goods carried by the ground carrier into the target storage position; the deviation correction control method comprises the following steps: acquiring a ground identifier corresponding to a target storage position; identifying an angle deviation and a position deviation; enabling the second positioning coordinate axis to deviate a preset angle value relative to the second direction along the first hour hand direction; moving the ground carrier towards a second reference coordinate axis of the reference coordinate system along a direction parallel to a second positioning coordinate axis of the positioning coordinate system; in response to movement of the ground carrier to a position where the positioning original point falls on a second reference coordinate axis, the ground carrier rotates around the positioning original point by a preset angle value along a second hour hand direction, and the second hour hand direction is opposite to the first hour hand direction; the ground carrier moves towards the first reference coordinate axis in the direction parallel to the second direction, so that the positioning original point coincides with the reference original point.

The invention is entitled Route planning for ground vehicles through unfamiliar terrain. A method is provided for supporting one or more ground vehicles in performing a mission that includes traversing a ground area. The method includes accessing geospatial data generated from an aerial survey of the ground area and performing an analysis of the geospatial data to produce terrain data that describes the ground area. The terrain data is weighted based on constraints of the one or more ground vehicles and a priority order of mission criteria. A map is constructed in which the ground area is represented as a geospatial mapping array of the weighted terrain data, and a path is searched on the map that satisfies the mission criteria. The path is described by a series of waypoints that define a route through the ground area, and the route indication is output for use by the one or more ground vehicles in traversing during the mission.

The invention belongs to the technical field of automobiles, and particularly relates to a ground vehicle four-wheel cornering stiffness estimation method considering cross-country environment disturbance. The method comprises the following steps: firstly, establishing a vehicle dynamics model and a kinematics model considering a coupling gradient through coordinate transformation and dynamics analysis, and ensuring the precision of the established unmanned ground vehicle model in a complex cross-country environment; secondly, constructing an unmanned ground vehicle path tracking system and performing state space equation discretization so that the unmanned ground vehicle path tracking system can be used for four-wheel independent cornering stiffness estimation; finally, a four-wheel cornering stiffness estimation method based on adaptive forgetting least square is provided, and accurate and reliable estimation of the tire cornering stiffness in the off-road environment can be ensured.

The invention relates to a method for identifying objects in a warehouse by means of a ground vehicle, comprising the following steps: emitting an identification signal by means of a transmitting device of the ground vehicle; detecting, by means of a receiving device of the ground vehicle, the identification signal reflected by objects in the surroundings as signal echoes; assigning a spatial angle and a reception time to each of the signal echoes; checking whether a plurality of the signal echoes is assigned to the same spatial angle; if a spatial angle is assigned to a plurality of signal echoes, evaluating the signal echo which last arrives in the receiving device for this spatial angle depending on the reception time for the identification of the object; identifying the object on the basis of the signal echoes.

A synthetic aperture radar target identification method based on incremental learning comprises the following steps: training a basic model by using samples of an existing category, then when a new training sample arrives, keeping a topological structure of a feature space of an old category to relieve disastrous forgetting, and is suitable for synthetic aperture radar target identification in a dynamic scene. According to the method, a new ground vehicle target and a sea surface ship target can be effectively identified, a Swindow-Transform is used as a feature extractor, local and global information of a synthetic aperture radar image is captured at the same time, a space structure of a sample is maintained by using an elastic Hertz diagram, the correlation between samples is fully utilized, the training efficiency is improved, and a deviation calibration layer is used, so that the training efficiency is improved. And the influence of new and old sample deviation on incremental learning performance is relieved.

The application is suitable for the field of smart community, and provides a smart community ground vehicle management method and system based on artificial intelligence. The method comprises the following steps: binding and associating an outside visitor vehicle and a visited household in a bidirectional manner, so as to uniquely correspond the visitor vehicle information and the household account; managing the visitor vehicle entering process by adopting a reservation system, and performing compliance auditing on the reservation information; constructing a mechanism for identifying illegal parking behaviors and tracing responsibilities, and if the visitor vehicle violates the parking management rules, deducting the integral of the associated visited household account; establishing a ladder type management model of the integral of the visited household, and opening the management authority of the visitor vehicle according to the integral level and different welfare treatment; the method and system can clearly define the illegal responsibility subject through bidirectional binding and responsibility tracing, improve the passing efficiency through the reservation system and intelligent auditing, and stimulate the enthusiasm of the household in participating in the management through the integral ladder management. The parking order of the community is optimized, and the management cost is reduced.

The present invention relates to a computer-implemented method for determining a position to be reached by at least one drone (Dk) in a fleet of drones following a ground vehicle (V) and controlled by a control device, the method comprising: - determining, by a processor of the control device, a current reference position of the fleet of drones; - determining, by the processor of the control device, the position to be reached by the at least one drone (Dk) on the basis of the current reference position, an arrangement of the drones and an arrangement width, the position to be reached by the at least one drone (Dk) being calculated by adding a periodic deviation vector to a position of the vertex of the polyline corresponding to the at least one drone.

The application provides a kind of multi-unmanned aerial vehicle collaborative reasoning optimization method based on DAG topology generation and dynamic DNN model partition, comprising when receiving the task request of ground vehicle, dynamically adjusting the position of unmanned aerial vehicle based on potential field method, and constructing topological network in combination with greedy clustering and DAG topology generation strategy;Dynamic DNN model partition is carried out based on non-continuous layer distribution mechanism and dynamic programming algorithm DPA, and the non-continuous layer of DNN is dynamically distributed to different unmanned aerial vehicles;DNN reasoning is carried out according to topological network and partition scheme;Cache update is carried out based on priority and energy-aware strategy;Delay and overhead are calculated.The application can intelligently allocate tasks and balance loads according to the complexity of the task and the computing power of each unmanned aerial vehicle, thereby improving the overall efficiency of the system and reducing the processing delay;The allocation strategy of task and data can be flexibly adjusted according to the network state and environmental change, to ensure the real-time performance and efficiency of the task.

The invention relates to systems for controlling road vehicles using reflection or re-emission of electromagnetic waves, for example, lidar systems, for warning or preventing collisions of ground vehicles.The traffic participant alert complex for preventing their collisions consists of a driver information system, a road situation recognition and fixation system, a data radio exchange system, a power supply system, a data processing processor, a GSM module, a control processor, and a remote server.The use of the claimed traffic participant alert complex for preventing their collisions expands the functionality of road infrastructure elements, improves road safety, and creates potential for further use of road situation data.

The invention discloses a highway accident rescue scheduling method and device based on air-ground cooperation, and a medium. The method comprises the following steps: extracting accident features corresponding to highway accidents; according to the accident features, constructing an accident feature set including a plurality of accident feature parameters, and determining material response scores corresponding to the emergency materials through response intensity of various emergency materials to the accident feature parameters; for the specified emergency materials whose material response scores are not less than a preset activation threshold value, determining material demands to be scheduled for the highway accident through a scheduling quantity function; according to the material requirements, a scheduling model with the minimum rescue response time as a target function is constructed, and marshalling schemes corresponding to the ground vehicles and the unmanned aerial vehicles are determined through the scheduling model; and based on the marshalling scheme, constructing a target function used for minimizing the total length of the scheduling resource path, so as to carry out rescue path planning on the ground vehicle and the unmanned aerial vehicle, and obtaining a rescue path corresponding to the highway accident.