60 results about "Ring road" patented technology

An intelligent traffic management device for optimizing traffic flow at one or more intersections using reinforcement learning, comprising: a central control unit housed in a weatherproof enclosure and mounted on a structural support near an intersection; a sensor interface operatively connected to a variety of multimodal sensors, including at least radar-based vehicle detectors, inductive loop sensors embedded in the road surface, infrared pedestrian detection detectors, and high-resolution optical imaging modules; a powerful embedded computing unit consisting of a multi-core processor and a GPU configured for on-device inference; a reinforcement learning engine embedded in the computing unit, comprising a deep reinforcement learning model trained to map environmental states defined by traffic-related sensor inputs to optimized action policies for traffic light control; a signal actuation module electrically connected to traffic signal controllers, with action policies outputting signal phase durations and transitions in real time; a communications module supporting wireless connectivity and configured for device-to-device communication and cloud synchronization; a policy synchronization module configured to perform federated learning-based updates of model parameters by exchanging gradient weights or distilled traffic state vectors with neighboring intelligent traffic management devices deployed in a traffic network; where the reinforcement learning engine continuously observes traffic state vectors consisting of vehicle counts, average speeds, queue lengths, and pedestrian activity, and dynamically updates the policy to maximize cumulative traffic throughput and minimize average delay.

The invention provides a phase jump compensation method and device of a network-forming converter, a terminal and a medium. The method comprises the following steps: calculating an instantaneous power angle compensation amount based on the voltage of a grid-connected point of the grid-forming converter; if the instantaneous power angle compensation amount is greater than a preset threshold value, determining a weighted full feed-forward compensation amount based on a capacitor voltage of the network-constructing converter, and determining a cross decoupling compensation amount based on a bridge arm current of the network-constructing converter; and adding the instantaneous power angle compensation amount, the weighted feed-forward compensation amount and the cross decoupling compensation amount into a voltage control loop of the network-forming converter to obtain a control signal added with phase jump compensation. According to the method, the influence of internal virtual inertia on the output response of the grid-forming converter can be reduced, the change of the power grid is quickly responded, the power grid adaptability of the grid-forming converter is improved, the power grid adaptability comprises the phase angle jump adaptability and the power grid strength SCR adaptability, and an overcurrent fault during phase jump is avoided.

The invention provides an agent dynamic scheduling method and device based on deadlock prediction, and the method comprises the steps: determining a loop-free target driving path formed between a task starting point and a task ending point indicated by a to-be-executed transportation task corresponding to each agent for each agent; according to the occupied resources, the to-be-applied occupied resources and the target driving path corresponding to each agent, whether deadlock conflict occurs to each agent is determined, the occupied resources describe path nodes and road sections occupied by the agent, and the to-be-applied occupied resources describe path nodes and road sections to be applied by the agent; and for the impending deadlock conflict, unlocking of the deadlock conflict is completed by using a preset unlocking strategy. According to the method, the impending deadlock phenomenon is accurately predicted and solved, so that map resources can be reasonably scheduled in an uncertain dynamic environment, and the stability of an intelligent logistics system is improved.

The invention provides a multi-path main road signal cooperative control method considering speed fluctuation, and the method comprises the steps: firstly collecting traffic data, including road network geometric data, traffic flow data and signal control data, and determining a plurality of main paths according to the traffic flow data; then, based on the running speed of each vehicle on each main path, the vehicle running average speed and the speed fluctuation quantity on each main path are calculated; and finally, constructing a signal control optimization model: constructing a target function by taking weighted green wave bandwidth maximization of all paths as a target, adding a loop integer constraint, an interference constraint, a speed fluctuation space-time constraint, a highest speed fluctuation constraint and a lowest speed fluctuation constraint, solving the signal control optimization model, and obtaining an optimized signal period and green wave bandwidth. And outputting the optimized signal timing strategy. The signal timing generated by the method has a good prospect in the aspect of reducing travel delay and parking times, and a better multi-path collaborative effect can be realized.

The invention relates to the field of intelligent transportation, and discloses an intelligent monitoring and management system and method for an expressway and electronic equipment, and the system collects global spatial-temporal data of the expressway to construct digital twins synchronized with the physical world; in the twinborn body, performing prediction and deduction based on a space-time causal map to identify potential risks; responding to the risk, generating an optimal intervention strategy through anti-fact deduction and executing the optimal intervention strategy, and recording a predicted intervention effect of the optimal intervention strategy; and after intervention, comparing a real traffic state with a prediction effect, calculating an anti-fact error, and carrying out dynamic self-correction on the space-time causal map according to the anti-fact error. According to the invention, links of perception, prediction, decision making, execution and feedback are fused into a self-adaptive control loop, and a self-correction mechanism based on an anti-fact error is introduced, so that the system can continuously learn and self-evolve from interaction with the physical world, and the problems of model solidification and poor adaptability of a traditional traffic management system are solved.

The invention discloses a multi-agent path planning method and related equipment, and relates to the technical field of artificial intelligence, and the method comprises the steps: responding to a multi-agent path planning instruction, determining a plurality of agents of a to-be-planned path, determining the priority of each agent of a current planning node, and based on the priority, determining the path of the current planning node; and determining a first grid map corresponding to the current planning node, and planning a grid where each multi-agent is located at the next planning node based on the one-way traffic constraint state of each loop in the first grid map and the priority. According to the method, the corresponding one-way passing constraint state of each loop in the current planning node is determined based on the priority, the motion direction of each agent in each loop corresponding to the current planning node is ensured to be uniform, then narrow channel conflicts are avoided, and the task completion efficiency of multiple agents is improved.

The invention discloses an efficient processing line for automobile pistons, including a first turning and drilling compound machine tool, a second turning and drilling compound machine tool, a compound boring machine and a compound lathe arranged in an arrangement. The first turning and drilling compound machine tool is used for processing the pin seat oil return hole, the ring segment straight oil hole, the rough and fine stopper, the rough turning of the first three ring grooves, and the rough turning of the outer circle skirt process of the piston. The second turning and drilling compound machine tool is used for the piston ring segment oblique oil hole or the ring segment straight oil hole, the rough and fine combustion chamber process, the compound boring machine is used for processing the rough boring hole, the snap ring groove, the inner and outer chamfers, and the fine boring process of the pin holes on both sides of the piston, and the compound lathe is used for processing the piston special-shaped outer circle and the fine turning of the first three ring grooves. The invention integrates more than a dozen processes on the production line formed by four devices, reduces equipment occupancy, reduces operators, reduces the time consumed by processing multiple clamping, coordinates the processing time between each process, saves time, reduces labor intensity, and improves production efficiency.

The application relates to the technical field of vehicles, in particular to a long-time-domain driving behavior decision method suitable for high-speed and loop traffic scenes, which comprises the following steps: acquiring a global planning path of a vehicle, a current motion state of the vehicle and current motion states of all surrounding vehicles in a region; generating an optimal driving behavior sequence of the vehicle according to the global planning path, the current motion state of the vehicle and the current motion states of all surrounding vehicles in the region; planning a driving track of the vehicle based on a first driving behavior of the optimal driving behavior sequence, and regenerating the optimal driving behavior sequence after the vehicle executes the first driving behavior based on the driving track, until the global planning path is completed. Therefore, the embodiment of the application can realize multi-step decision of driving behaviors such as lane-changing gap selection and lane-changing overtaking, has foresight, and simultaneously gives an optimal solution to long-time-domain driving behavior sequence planning based on feasibility discrimination, considers safety and high efficiency, and meets the needs of general driving.

Aspects of the disclosure provide for determining whether a vehicle is in a loop for an autonomous vehicle. For instance, a route from a current location of the vehicle to a destination for a trip may be generated. Locations traversed by the vehicle during the trip may be tracked. Locations of the route may be compared to the tracked locations to determine an overlap value. Whether the vehicle is in a loop may be determined based on the overlap value.

The utility model discloses a well ring reinforcing structure of a drainage system inspection well, which is characterized in that a well ring beam is arranged on a brick shaft and filled with C30 reinforced concrete, a well ring used for installing a well lid is arranged on the well ring beam through expansion bolts, and a gap between the well ring beam and an original concrete road layer is filled with concrete mixture. Leveling by using a ruler and a scraper blade; a plurality of notches are formed in the well ring, a plurality of protruding groove strips are arranged on the well lid and used for being clamped on the well ring, the well lid is prevented from rotating in the using process and fixed in the notches, leveling layers are adopted on the outer side of the well ring and the top of the well ring beam and used for leveling the road surface around the well lid, and a gasket is arranged at the bottom of the well ring. The well lid is flush with the surrounding road surface after being mounted; in the well ring pavement cutting and digging process, the periphery of the well ring is cut and dug into a whole hexagonal structure for construction, so that the installation and construction stress of the well ring beam, the well ring and the well lid is balanced, and the structural stability is ensured.

The embodiment of the invention provides a vehicle door control system and a rail train, and the vehicle door control system comprises a vehicle door state detection device; each door in the train is provided with a door state detection device; when the vehicle door is normally closed, an effective vehicle door closing output signal is generated, and the vehicle door closing output signal is accessed to the safety loop; a gating station; a door control station is arranged beside at least one vehicle door and used for opening or closing the corresponding vehicle door. When the door control station is activated, the corresponding vehicle door can be opened through the door control station, and the vehicle door closing signal of the corresponding vehicle door is bypassed, so that the opened vehicle door does not affect a train safety loop. According to the vehicle door control system and the rail train provided by the embodiment of the invention, the vehicle door opened by the door control station does not influence a safety loop, and the other vehicle door states are still interlocked with the traction, so that a trainman can open the vehicle door to observe surrounding conditions in the running process of the train, and the running safety of the train is improved.

The invention discloses a coiled material hot melting paving device for ground construction, and relates to the technical field of building construction equipment, and the coiled material hot melting paving device comprises a driving mechanism and a paving mechanism; the paving mechanism comprises a main body box, a group of bearing main bodies, an electric telescopic frame and a fixed circuit loop; and a set of electric telescopic frames are fixedly mounted at the top of the main body box, and an air roller is rotationally connected between the interiors of the set of electric telescopic frames. When the coiled material is unfolded, a preheating plate and a combustor on the equipment are used for synchronously heating the back surface of the coiled material, so that the bottom of the waterproof coiled material is in a molten state, then the equipment is in a forward moving state, and pressure is directly applied by using rolling friction generated by a compaction roller and the dead weight of the equipment; air between the coiled material and a base layer is discharged through rolling of the pressing rollers, the coiled material and the base layer are firmly bonded, the edge pressing rollers on the two sides conduct directional compaction on the edge of the coiled material, edge warping or leakage is prevented, it is ensured that full-width bonding is uniform, and the efficient and stable paving process is achieved.

The invention provides a reservoir basin flood inverted siphon storage structure of a pumped storage power station, and relates to the technical field of water-power engineering pumped storage power stations, and the reservoir basin flood inverted siphon storage structure comprises an inlet control device which is connected with a reservoir surrounding highway interception and drainage ditch and comprises a flood storage water inlet and a trash rack, and the trash rack is arranged between a water and sediment diversion structure and an inverted siphon channel; the water-sediment diversion structure comprises a desilting basin communicated with the flood storage water inlet; the inverted siphon channel comprises a vertical shaft and an adit, the vertical shaft is connected with the desilting basin, the bottom end of the vertical shaft is connected with an inlet of the adit, and an outlet of the adit extends into the pumped storage basin. The problem that catchment water on the periphery of a traditional pumping storage basin can only be drained and cannot be utilized, and water source waste is caused is solved, considerable rainfall can be reasonably utilized, the water storage time is shortened, and evaporation leakage loss is supplemented.

The invention relates to a business district division method and system based on vector data and a graph theory, and belongs to the technical field of big data analysis. The business district division method based on the vector data and the graph theory comprises the steps that urban road network data and POI data in a vector format are loaded, the urban road network information is preprocessed, and the POI data comprise geographic coordinates and classification information; traversing the preprocessed urban road network data so as to convert the geographic road network graph into a road network topological graph according to the traversed node set, the traversed edge set and the connection relation of the traversed node set and the traversed edge set; traversing each edge in the road network topological graph to identify a minimum closed loop enclosed by the edges as a business district; and performing spatial matching on points of interest POIs in the point of interest POI data and the business districts to determine which business district each point of interest POI belongs to. By constructing a road network topological graph, a high-consumption image conversion and processing process is completely avoided, and efficient operation can be realized on common hardware.

The utility model belongs to the technical field of positioning machinery, and relates to the detection of a bearing inner ring raceway, in particular to a double-row ball bearing inner ring raceway detection device, which comprises a support frame, and the support frame comprises a first workbench, a second workbench, a side plate and a base, the structure of the device is partially similar to that of a double-row ball bearing outer ring raceway detection device. The main points are as follows: the same workbench is provided; the same workpiece lifting mechanism; the same detection propulsion mechanism is mainly different in structure and installation position of the first detection module, the second detection module, the first detection steel ball positioning sleeve and the second detection steel ball positioning sleeve. According to the utility model, the double rows of detection steel balls, the double detection dies and the standard cushion block are used for simultaneously detecting the double raceways of the inner ring; the detection precision is more accurate, the clearance dispersion difference is smaller after the outer ring is automatically selected and matched and the steel ball is sleeved, and the clearance better meets the requirement.

This invention relates to the field of template joint reinforcement technology, and more particularly to a template joint reinforcement device for underground ring road construction. The device includes multiple templates, a sealing component, a reinforcement component, and a support component. The sealing component includes insert iron plates installed between the multiple templates. These insert iron plates are used to grind the sidewalls of the templates and fill the gaps between them. One end of each insert iron plate is fixedly fitted with a reinforcement iron plate to prevent cement leakage, and the reinforcement iron plate and the insert iron plate form a T-shape. This invention, by installing insert iron plates between the templates, grinds the splicing surfaces between the templates, making the mating surfaces smoother and improving the splicing effect. The reinforcement iron plates prevent cement leakage from the splicing joints, and the sealant and sealing strips further enhance the sealing effect of the templates. The interaction between the components reinforces the position of the templates layer by layer, improving their stability. This eliminates the need for additional bolts or other components, saving engineering materials.

The invention discloses a test background vehicle-like man interaction behavior lightweight generation method in an unprotected left-turn scene, and the method comprises the steps: 1, setting two closed loops as a route 1 and a route 2, and enabling the route 1 and the route 2 to have crossed road sections; 2, a test background vehicle is arranged on the route 1, and an automatic driving main vehicle is arranged on the route 2; 3, simulation is carried out, the background vehicle is tested before simulation is started, and the automatic driving main vehicle is still; after simulation is started, each test background vehicle is controlled in an IDM following mode when not driving to an intersection area, and is switched to a human-like interaction mode when driving to the intersection area, so that the performance reliability of an automatic driving main vehicle algorithm is tested; 4, after passing through the intersection area, the test background vehicle is switched to the initial IDM vehicle following mode for the second time; and 5, repeating the steps 3 and 4, and circularly and continuously monitoring the performance reliability of the automatic driving main vehicle algorithm. According to the invention, the safety and credibility of the automatic driving algorithm can be tested.

The application provides a kind of multi-path arterial signal coordination control method considering speed fluctuation, comprising first collecting traffic data, including road network geometry data, traffic flow data and signal control data, determine a plurality of main paths according to traffic flow data.Then based on the driving speed of each vehicle on each main path, the average speed and speed fluctuation of the vehicle on each main path are calculated.Finally, a signal control optimization model is constructed: the maximum weighted green wave bandwidth of all paths is taken as the target, the objective function is constructed, and loop integer constraint, interference constraint, speed fluctuation space-time constraint, maximum speed fluctuation constraint and minimum speed fluctuation constraint are added, the signal control optimization model is solved, the optimized signal cycle and green wave bandwidth are obtained, and the optimized signal timing strategy is output.The signal timing generated by the method has good prospects in reducing travel delay and parking frequency, and can achieve better multi-path coordination effect.

The invention discloses a method for establishing an independent coordinate system of segmented projection engineering of an annular road, and relates to the technical field of road management.The method comprises the steps that firstly, on the basis that a coordinate system of a user-defined central meridian and an elevation compensation plane is established, segmentation operation and projection plane setting operation are conducted on the annular road, and a road section corresponding to the annular road is obtained; secondly, obtaining a segmentation weight coefficient corresponding to each road section in the annular road, and obtaining a Lagrange multiplier according to all the segmentation weight coefficients; then obtaining a terrain curvature correction factor corresponding to each road section in the annular road, and obtaining a comprehensive allocation weight according to the terrain curvature correction factors and the segmentation weight coefficients; and finally, on the basis of the comprehensive distribution weight, obtaining the coordinate correction value of the control point of each road section, and revising the control point of each road section according to the coordinate correction value of the control point of each road section, so that the problem of cracks existing in the annular road constructed in the prior art can be effectively solved.

The utility model discloses a road cone with high stability, which comprises a base, a detachable road cone body is arranged at the top of the base, integrally formed support legs are arranged on the outer walls of four corners of the bottom of the base, the interiors of the base and the support legs are of hollow structures communicated with each other, and a filling nozzle is arranged on the outer wall of one side of the top of the base. A hollow ring is arranged in the base, a bottom plate is fixedly mounted on the outer wall of the bottom of the road cone body, a plurality of lug plates which are annularly distributed at equal intervals are fixedly arranged on the inner wall of the hollow ring, a plurality of via holes are formed in the edge of the bottom plate, and clamping grooves are formed in the positions, close to the via holes, of the bottom plate. According to the road cone, the base and the supporting legs which are of hollow structures are adopted, water can be added into the road cone through the filling nozzle, so that the weight of the base is increased, then the road cone body is fixedly connected with the base, the stability of the gravity center of the road cone is guaranteed, and the phenomenon that the road cone easily inclines is avoided.

The invention discloses an ultra-efficient energy-saving road and method for reducing air resistance of vehicles, trains, ships and the like to be close to zero. According to the principle that a ball and air pushed by the ball run at a high speed in the same system and in the same direction almost without friction in a sealed ring, a channel is divided into a left channel 1 and a right channel 3 which are closed, the left channel 1 and the right channel 3 are connected end to end to form a long-strip-shaped ring channel, and the connecting positions of channel bodies are communicated. High-pressure gas in front of a vehicle and a ship on the left road 1 can be directly pressed into and sucked into the right road 3, particularly sucked into a negative-pressure area behind the vehicle and the ship on the right road 3, and vice versa, so that the high-pressure gas at the head of the vehicle and the ship can automatically pass through the opposite side road to reach a low-pressure area at the tail of the vehicle and the ship, the air resistance is close to zero, the same system circulation in the shortest distance is realized, and the service life of the vehicle and the ship is prolonged. The head channel opening and the tail channel opening of the channel are open, and air cannot flow out. The defects that when vehicles, ships and the like run, air in the places where the vehicles and the ships arrive is pushed to be scattered to the outside, the tails are pulled by negative pressure, and a huge amount of energy is wasted are overcome, and therefore the huge amount of energy is saved.

The invention discloses an unpowered carbon dioxide spiral loop heat pipe shallow geothermal road snow melting system which comprises a carbon dioxide spiral loop heat pipe arranged below a road surface, and the carbon dioxide spiral loop heat pipe comprises a spiral pipe evaporation section, an ascending air pipe, a descending liquid pipe, a multi-U-shaped pipe condensation section and a backflow suppressor which are communicated with one another; the spiral pipe evaporation section, the ascending air pipe, the descending liquid pipe and the backflow suppressor are vertically buried in a drill hole of a rock-soil body below a roadbed, and the multi-U-shaped pipe condensation section is horizontally buried in the roadbed. A spiral pipe evaporation section of the system absorbs terrestrial heat and vaporizes a working medium, an ascending gas pipe penetrates through a variable temperature layer to convey a gas phase to a multi-U-shaped pipe condensation section located below a pavement structure layer, and the working medium releases heat to the pavement and condenses; and the condensate flows to the reflux suppressor through the down liquid pipe and then returns to the evaporation section of the spiral pipe to form closed circulation. The whole system is compact in structure, high in heat transfer efficiency, flexible in arrangement and suitable for freezing prevention and snow melting of complex scenes such as ramps, sidewalks and bridge floors.

The application discloses a kind of anti-leakage circulating fans in ring road type high-pressure gas flow calibration device, magnetic coupling shaft coupling includes outer rotor, inner rotor, high-pressure isolation cover and first flange plate;The end of outer rotor is provided with accommodating groove, the end of inner rotor is placed in the accommodating groove of outer rotor, and the inner wall of accommodating groove and the outer periphery of inner rotor are respectively circumferentially evenly provided with multiple N-pole and S-pole interval arrangement magnet, so that the number of magnet on outer rotor and inner rotor is equal, and the magnetic pole is opposite at diametral opposite position;High-pressure isolation cover is the thin-walled shell with closed top, is placed between outer rotor and inner rotor, and does not contact with outer rotor and inner rotor.This application changes transmission form and sealing form, not only significantly improves the safety of system, but also effectively reduces maintenance difficulty and cost, improves work efficiency, and has important significance for promoting the development of clean energy technology.

The invention provides a subtropical city charging station layout optimization method and system based on climate adaptive clustering, and belongs to the technical field of city charging infrastructure planning. The problems that in existing planning, climate adaptability is insufficient, analysis of a driving mechanism is not accurate, and strategy pertinence is not high are solved. The method comprises the following steps: collecting data of a city-surrounding high-speed enclosed area of a subtropical city, and constructing an equal-area hexagonal grid with the side length of 1000m after data cleaning and coordinate conversion; a kernel density estimation method is adopted to analyze the aggregation degree of the charging stations, and adaptive features are obtained in combination with a climate adaptive DBSCAN clustering algorithm; constructing a multi-scale geographically weighted regression model by taking the density of the charging station as a dependent variable, and quantifying the influence of spatial heterogeneity; and according to clustering and regression results, providing a charging station layout scheme from driving factor guidance, a climate adaptive hierarchical strategy and a climate adaptation dimension. The method is mainly used in the subtropical city charging network construction field.

The application relates to the field of intelligent transportation, and discloses an expressway intelligent monitoring and management system, method and electronic equipment. The system collects expressway global space-time data to construct a digital twin body synchronized with the physical world. In the twin body, potential risks are identified through prediction and deduction based on a space-time causal graph. In response to the risks, an optimal intervention strategy is generated through counterfactual deduction and executed, and the prediction intervention effect is recorded. After the intervention, the real traffic state and the prediction effect are compared, the counterfactual error is calculated, and the space-time causal graph is dynamically self-corrected accordingly. The application integrates perception, prediction, decision-making, execution and feedback into an adaptive control loop, introduces a self-correction mechanism based on counterfactual error, enables the system to continuously learn and evolve from interaction with the physical world, and solves the problems of model solidification and poor adaptability of traditional traffic management systems.

The invention relates to the technical field of bus protection, and provides a bus operation state identification method and a brake coefficient identification method and system based on bus correlation, and the method comprises the steps: determining a bus correlation matrix according to the connection state of a circuit breaker and a disconnecting link in a bus topological structure; determining the correlation between the sections of buses by using the correlation coefficient of each section of bus and each interval in the bus correlation matrix, and constructing a bus correlation coefficient matrix; performing path search by using the bus correlation coefficient matrix, and identifying the running state of each section of bus; if no correlation exists between one bus section and other bus sections, the bus section is in split operation; if the correlation between the bus sections forms a loop, the bus sections forming the loop are all in closed-loop operation; and if the bus sections have correlation but do not form a loop, the bus sections which do not form the loop run in parallel. The method is simple in calculation process and can quickly judge the running state of each section of bus.

The present application relates to a kind of mixed vehicle space domain deep reinforcement learning collaborative control method for mountain ring road scene, belong to intelligent network connection traffic technical field, including the following steps: S1: establishing mountain ring road mixed vehicle fleet scene and coordinate system;Vehicle time domain horizontal and longitudinal coupling dynamics are constructed and equivalent control input is introduced, arc length variable is introduced and time inverse function is defined, and horizontal and longitudinal coupling dynamics model in space domain is constructed;S2: the slope and its confidence are calculated;The HDV trajectory of pilot vehicle is predicted;Space domain delay collaborative error is constructed;S3: space domain PPO controller is constructed, and comprehensive reward function is defined, and horizontal and longitudinal joint control action is output;S4: multiple constraint fusion compensation and action saturation projection execution are carried out.

The invention relates to the technical field of image processing, and provides a flyover crossing road disease identification method and system based on unmanned aerial vehicle inspection, and the method comprises the steps: collecting flyover crossing road images at a plurality of moments; obtaining a plurality of road edge sections, and screening a plurality of suspected annular road sections; obtaining a plurality of continuous road edges to obtain a plurality of suspected annular road edges; longitudinal coordinate changes of two adjacent road edge sections in the suspected annular road edge in the flyover crossing road image are analyzed, and the initial three-dimensional degree of each suspected annular road edge in the flyover crossing road image is obtained; correcting to obtain a corrected three-dimensional degree of each suspected annular road edge; and constructing a disease identification model based on the flyover crossing road image, constructing an attention mechanism in combination with the correction three-dimensional degree of the suspected annular road edge, and learning three-dimensional information of the model to realize disease identification of the flyover crossing road. The invention aims to solve the problem of three-dimensional information loss of the cross road under aerial photography of the unmanned aerial vehicle.

Aspects of the disclosure provide for determining whether a vehicle is in a loop for an autonomous vehicle. For instance, a route from a current location of the vehicle to a destination for a trip may be generated. Locations traversed by the vehicle during the trip may be tracked. Locations of the route may be compared to the tracked locations to determine an overlap value. Whether the vehicle is in a loop may be determined based on the overlap value.