48 results about "Bidirectional search" patented technology

The invention relates to the technical field of unmanned aerial vehicle trajectory planning, in particular to a bidirectional tree random search method based on a complex environment node cost function, which comprises the steps of surveying obstacle data in a flight area and modeling, then introducing a target deviation strategy and a bidirectional search tree mechanism, and combining with an improved minimum cost method to obtain a random search result. Alternately expanding the two trees to generate an initial path, and integrating the path length, the obstacle distance and the flight height energy consumption by a cost function; and finally, pruning the initial path, removing redundant nodes, smoothing the trajectory by adopting a cubic spline interpolation method, ensuring curvature continuity, and generating an optimal path meeting the flight performance of the unmanned aerial vehicle. According to the invention, through an improved bidirectional minimum cost fast expansion random tree algorithm, dynamic association of obstacle constraint, target deviation and path cost in unmanned aerial vehicle path planning in a complex environment is represented, and a more efficient search convergence speed and better path quality are obtained. And rapid convergence and global optimization of the track of the unmanned aerial vehicle in a high-dynamic environment are realized.

The invention discloses a global path planning method for a power converter valve inspection operation robot, and the method comprises the steps: obtaining the spatial point cloud data of a converter valve region through a three-dimensional structured light camera, and constructing a two-dimensional environment map containing obstacle expansion information through projection and rasterization; generating a snakelike or spiral full-coverage global theoretical path according to the scanning step length of the camera; in the inspection execution process, the feasibility of the path section is judged through discrete sampling and continuous collision detection; local obstacle avoidance adopts an improved A * algorithm, forward and backward bidirectional search is simultaneously executed in a limited local search area, and a dynamic heuristic function of a coverage potential item and a safety score item is introduced. And finally, splicing the local path and the theoretical path to form a global feasible inspection path. The method effectively solves the problem that the coverage rate and the obstacle avoidance efficiency are difficult to consider in a complex converter valve hall environment in a traditional method, and is particularly suitable for automatic inspection of equipment-intensive scenes such as an electric power converter valve hall.

The invention relates to the technical field of artificial intelligence, in particular to an operator fusion method, device and equipment and a computer readable storage medium, and the method comprises the steps: determining whether a to-be-split current node and an upstream node which are different in data arrangement type and are directly connected exist in a computational graph or not; if yes, performing downstream one-way search by taking the current node as a starting point to construct a first sub-graph containing a first associated node, and performing two-way search by taking the upstream node as a starting point to construct a second sub-graph containing a second associated node; taking the first sub-graph and the second sub-graph as a new calculation graph, and performing iterative detection until no direct connection node with different data arrangement exists; and if a plurality of first sub-graphs exist, combining the first sub-graphs with the same graph attributes to obtain a third sub-graph so as to realize operator fusion. The invention aims to improve the efficiency of operator fusion.

The application belongs to the technical field of mechanical arm motion planning, and provides a kind of adaptive sampling and multi-channel expansion mechanical arm path planning method, first, the environment obstacle set is constructed, the point to obstacle distance, the clearance configuration and the segment level minimum clearance are established, and the unified safety criterion is constructed;Subsequently, according to the approximation state of bidirectional search tree, the sampling window is adaptively updated, and the random reference sample is generated in combination with the stagnation detection mechanism;On this basis, the hierarchical multi-channel expansion mechanism of direct pointing expansion, bypass expansion, potential field wall expansion and global bottom expansion is used to generate candidate new nodes;When a feasible new node is generated, it is connected to the current search tree and real meeting detection is carried out, if the double trees are successfully connected, path backtracking, splicing, simplification and full path safety review are further executed, and the final executable path is output.The application can improve the safety, search efficiency and environmental adaptability of the path planning of the mechanical arm in the complex limited environment.

The application discloses a kind of global path planning methods for power converter valve inspection operation robot, obtains the spatial point cloud data of converter valve area using three-dimensional structured light camera, constructs two-dimensional environment map containing obstacle inflation information by projection and rasterization;According to the snake shape or spiral shape global theoretical path of full coverage generated by camera scanning step;During inspection execution, the feasibility of path segment is judged by discrete sampling and continuous collision detection;Local obstacle avoidance uses improved A* algorithm, simultaneously executes forward and backward bidirectional search in the limited local search area, and introduces the dynamic heuristic function of coverage potential item and safety score item.Finally, the local path and theoretical path are spliced, and the global feasible inspection path is formed.The application effectively solves the problem that the coverage rate and obstacle avoidance efficiency of traditional method are difficult to consider under complex converter valve hall environment, and is especially suitable for automatic inspection in equipment-intensive scenes such as power converter valve hall.

The application provides a Chinese-oriented named entity recognition method and system, and belongs to the technical field of natural language processing; comprising: an encoding stage step, context encoding of input Chinese text; a feature extraction stage, a double-branch structure of global semantic branch and local boundary branch in parallel is adopted, wherein the local boundary branch carries out boundary feature enhancement through multi-granularity convolution combined with a learnable Gaussian Laplacian operator; a feature fusion and prediction stage step, global and local features are fused through a gating mechanism, and multi-label classification prediction is carried out based on a preset six-tuple grid label system; a decoding stage step, named entities are obtained through bidirectional search strategy decoding according to predicted relationship probability; through boundary perception feature extraction and enhanced label system, the recognition accuracy and recall rate of nested entities and discontinuous entities in Chinese text are significantly improved.

The invention provides an aero-engine strong non-stationary cross frequency signal time-frequency analysis method and system, and relates to the technical field of aero-engine signal processing and fault diagnosis, and the method comprises the steps: obtaining a vibration signal, and obtaining initial time-frequency distribution; performing adaptive ridge line extraction on the initial time-frequency distribution, and determining a time-frequency block range of an intersection region; carrying out local sub-blocking on the time frequency distribution in the intersection area to obtain optimized time frequency distribution; performing component reconstruction on the vibration signal by adopting Vold-Kalman order filtering to obtain final time frequency distribution; according to the method, the ridge line fracture time-frequency block is determined through bidirectional retrieval repair, the intersection area and the hierarchical cascade reconstruction component are optimized through comprehensive evaluation indexes, the ridge line continuity and instantaneous frequency extraction precision of the intersection area are remarkably improved, and high-resolution representation and accurate separation of strong non-stationary intersection frequency signals are achieved.

This invention provides a path planning method for industrial robotic arms based on potential field perception and experience-based adaptation, relating to the fields of robot motion planning and intelligent manufacturing technology. Based on the path planning framework of the RRT-Connect algorithm, this method constructs a bidirectional search tree within the search space. It uses the calculated safety margin of the direction-aware space as the initial environmental safety margin for nodes, employs an artificial potential field lateral deflection direction guidance strategy to determine the expansion direction, and uses a parameter adaptive adjustment method with a clearly bounded mapping relationship to adaptively determine the node expansion parameters based on the environmental safety margin of the parent node. This achieves efficient and stable collision-free path planning in complex assembly environments. This method is applicable to path planning problems for multi-degree-of-freedom industrial robotic arms and can significantly improve path planning efficiency and path quality in complex assembly environments.

The invention relates to the technical field of data storage and processing, and discloses an equity penetration method based on bidirectional search, a terminal and a storage medium. The method comprises the following steps: constructing an equity graph structure: constructing a directed graph based on original stock holding data; the vertex set represents an institution entity, and the edge set represents a stock holding relationship between institutions; the weight of the edge in the stock right graph represents the stock holding proportion between the institutions, and timestamp information is added to the edge to record the timeliness of the stock holding relation; image structure cleaning: deleting unweighted edges in the stock right image, and detecting and eliminating cyclic stock holding; for any given starting point and end point in the stock right graph, initiating forward search from the starting point to obtain a forward path, initiating reverse search from the end point to obtain a reverse path, and when the forward search and the reverse search intersect at one vertex, merging the reverse paths of the forward path and the reverse path to obtain a forward path and a reverse path; and thus, a complete strand-holding link is obtained. According to the invention, stock right penetration between institutions can be effectively realized.

This invention discloses a collaborative operation system and method for a drone and a robotic dog in a mining scenario. The system includes a drone, a robotic dog, and a wireless communication module. The drone and the robotic dog transmit data through the wireless communication module. The drone includes a laser terrain scanner, and the robotic dog is equipped with a high-definition camera and an infrared sensor. The laser terrain scanner is used to perform a global terrain scan of the mining blasting area to obtain laser point cloud data. The high-definition camera is used to identify obstacle elevation values, and the external sensors are used to collect road slope data. This invention utilizes a bidirectional BFS search algorithm combined with adjacent grid selection weights and priorities to generate multiple planned paths. The drone sends the planned paths to the robotic dog in advance, and the robotic dog only needs to select the optimal path based on the actual road conditions. The lightweight MobileNet model improves the robotic dog's computation speed and time, and the selection of the optimal path based on actual road conditions requires low hardware computing power.

The application discloses a substation secondary circuit path identification method, device, equipment and medium, and belongs to the field of power systems, the method is: obtaining the first connection relationship of each screen cabinet and each element to construct the first connection relationship matrix, determining the simplified judgment result according to the element quantity and the connection density corresponding to the screen cabinet and simplifying the first connection relationship matrix to obtain the second connection relationship matrix, and then performing bidirectional search in the second connection relationship matrix according to the positive power supply node and the negative power supply node by using a bidirectional depth-first search algorithm to obtain the secondary circuit path, so that the problem of low path identification efficiency of the substation secondary circuit in the prior art can be solved by implementing the application.

The invention provides a path planning method and system for personnel evacuation and obstacle avoidance, and belongs to the technical field of personnel evacuation dynamic obstacle avoidance path planning. The invention provides a Bi-RRT *-based personnel evacuation path planning algorithm with self-adaptive bias and a new improved self-adaptive extended step length. On the basis of the standard Bi-RRT * algorithm, an adaptive bias strategy which is jointly influenced by search experience and obstacles is added, so that the convergence speed of the algorithm is effectively improved, the path search efficiency is improved, and the ability of passing through narrow terrains is improved; based on a self-adaptive step length search strategy combining the repulsion size and the direction included angle, the obstacle avoidance capability is improved; in combination with improved adaptive bias, adaptive step length and bidirectional search capability, the adaptive capability to a complex evacuation space search path and the search efficiency of a multi-obstacle region algorithm are effectively improved. The method has remarkable advantages in the aspects of path planning efficiency, path quality, convergence speed, complex environment adaptability and the like.

The invention relates to the technical field of three-dimensional laser point cloud data processing, in particular to a building contour extraction method based on point cloud hierarchical projection and geometric constraint, which comprises the following steps: slicing a single building point cloud in the vertical direction to obtain a sliced point cloud; projecting the slice point cloud to a plane; performing straight line fitting and segmentation on the slice point cloud projected to the plane to obtain a plurality of line segments; wherein straight line fitting and segmentation are carried out, rough fitting is carried out firstly, then segmentation is carried out, and fine fitting is carried out on the segmented point cloud; screening line segments perpendicular to or parallel to the main line through geometric constraint; according to the screened line segments, removing parallel line segments of the same edge to obtain a non-redundancy line segment set; and connecting the line segments in the line segment set through a bidirectional search connection mechanism and a differentiated closing strategy, and performing closing, smoothing and regularization processing to obtain the building contour. According to the scheme, the building contour line can be efficiently and accurately extracted, and the method is suitable for practical engineering application.

The application discloses a kind of uterine myoelectricity signal classification method based on multivariate empirical mode decomposition, comprising: 1, using multichannel surface electrode acquisition a period of uterine contraction within uterine myoelectricity signal and carries out denoising pretreatment;2, using multivariate empirical mode decomposition to extend the uterine myoelectricity signal after denoising pretreatment to time-frequency domain, obtain the intrinsic mode component containing different time scale of uterine myoelectricity signal, according to variance contribution and correlation coefficient select effective component therein;3, to the intrinsic mode component after screening, sliding window is carried out, and six characteristic values are calculated;4, using chi-square test pre-screening and sequence bidirectional search combination feature selection algorithm, select optimal feature subset;5, based on support vector machine model, classify normal and abnormal activity in uterine myoelectricity signal.The application can utilize the local information of uterine myoelectricity signal in time-frequency domain, filter out irrelevant noise and redundant features, to complete the abnormal activity identification in uterine myoelectricity signal.

The invention provides a path planning method and system for operation of a transformer substation oil sample collection robot, and relates to the technical field of robot path planning. The method comprises the following steps: firstly, constructing an elliptical state subset space based on an initial point, a target point and a current optimal path cost in a free space of a configuration space, sampling to obtain a random point, and generating a new node meeting a constraint condition by using nearest neighbor search and a Steer function; a neighborhood point set is constructed through a Near function, a father node is reselected by adopting a ChoseParen function and taking the minimum path cost as a criterion, a bidirectional search tree is constructed by combining a reverse extension strategy starting from an initial point and a target point at the same time, and a work path is output when the node distance in the two search trees is smaller than a set value. The method can improve path planning search efficiency and path generation quality, and is suitable for transformer substation oil sample collection robot operation path planning.

A system described herein may efficiently perform a multi-destination backward search, which may be a part of performing a bidirectional search in a node map that implements contraction hierarchy techniques. Lowest cost paths to each node reachable to each destination node of a set of destination nodes may be computed. A queue may be initialized with the set of destination nodes. For each particular node in the queue, the system may add higher priority neighbors of the particular node to the queue, identify costs of outgoing links from the particular node to the higher priority neighbors, compute lowest cost paths associated with the set of destination nodes based on the identified costs of outgoing links from the particular node to the higher priority neighbors and any previously computed lowest cost paths associated with the set of destination nodes, and increment to a next node in the queue.

The invention relates to path planning, in particular to an autonomous search path planning method and system for a rescue robot, and specifically, the method comprises the following steps: obtaining a grid map of a rescue environment, and calculating a weighted extension distance fusing a geometric distance, terrain trafficability and environment risk cost for adjacent nodes; a forward open list starting from a starting point and a reverse open list starting from a target are established, and in bidirectional search, environmental risks are included in a forward evaluation function, and the environmental risks are not included in a reverse evaluation function; when a node accessed in the other direction is searched in a certain direction, recording the node as an initial intersection, and continuing bidirectional expansion by taking the total expansion distance of the current path as an upper bound to search a better intersection; in all the intersection points, selecting a point which enables the total extension distance to be minimum after the forward path and the reverse path are spliced as an optimal intersection point, and generating an initial path; and smoothing the initial path to ensure that the terrain trafficability and the environmental risk value of each point on the smoothed path are within a safety threshold, and obtaining a feasible path.

The invention discloses an abnormal transaction recognition method and system based on deep learning, and relates to the technical field of automatic tasks, and the method comprises the steps: firstly obtaining historical transaction data, a data label and a target deep learning model designated by a user, and achieving the collection of a data recognition task; then diversified coding individuals are generated by adopting a vertical and horizontal reverse chaos strategy, and the task processing efficiency is improved; according to historical transaction data and data labels, a triangular walk strategy, a multi-strategy oscillation learning strategy and a bidirectional search strategy are adopted to carry out collaborative optimization on coding individuals, and the task identification accuracy is improved; and finally, deploying the target deep learning model to a cloud end through the target coding individual obtained through optimization, so as to identify to-be-identified transaction data uploaded by the user and realize an automatic data processing task for the user. Through the clustering collaborative optimization strategy, the global exploration and local development capabilities of the algorithm are balanced, and the optimization efficiency of hyper-parameters and the recognition precision and generalization capability of a final model are remarkably improved.

The invention relates to an unmanned high-speed service area robot global path planning method and device and a robot. The method comprises the steps that 1, a path grid map is constructed; step 2, improving the Runyanlong optimization algorithm, including: generating an initial population; random key coding; judging the priority; introducing an affinity function; embedding a concentration adjusting mechanism; carrying out a double-variation strategy; step 3, bidirectional beetle antennae parallel search: taking a starting point and a target point corresponding to the initial path sequence generated after optimization in the step 2 as double search initial points, and synchronously executing the improved Rhouyanlong optimization algorithm; if the two-way search meets at the middle path points, directly butting to form an optimal path sequence; if not, selecting an optimal path sequence through a distance strategy and a time strategy; the distance strategy is to select a sequence with shorter path length, the time strategy is to select a sequence with shorter walking time consumption, and random selection is carried out when the length or time consumption is equal. The problem that the convergence speed is not high enough is solved.

The invention discloses a rapid optimal path planning method for a mobile robot based on IBIPF-RRT. The rapid optimal path planning method comprises the following steps: step S1, a sampling stage; the path between the two target points in the walking process of the robot is limited in an oval area, and the average value of the paths obtained through multiple times of operation of the RRT * algorithm is taken as the long axis of an oval; s3, a parent node and child node updating stage: a step S3 of performing expansion by using a predefined IPsteer function to obtain an expansion point qnew; checking whether the qnew and the qnew collide with each other or not, and restarting sampling if the collision occurs; and S4, searching a set Qnew of adjacent points in a certain range by taking the extension point qnew as a center if the collision does not exist, and S4, optimizing the connection stage. The invention provides a bidirectional search strategy of the shortest path, path recombination is carried out after the path is planned, and the problem of local optimization caused by a dual-tree search strategy can be solved, so that the overall optimization after connection is ensured.

The application discloses a kind of intelligent driving car path planning methods based on multi-algorithm cooperation, belong to intelligent driving technical field, including: by the improved Bi-RRT* algorithm initialization two respectively from start point and target point growth search tree and carry out bidirectional search;Dynamic detection two search tree node distance, when meeting condition, trigger the strategy of opposite bias, and carry out global path generation;In global path generation, improved artificial potential field method is used to carry out local path planning, and new node is expanded;When expansion failure, trigger ray projection navigation mechanism, detect the feasible path in front through sector area, select optimal intersection and expand, when the node of two search trees meets connection condition and path has no collision, realize bidirectional connection, generate initial complete path;The initial complete path generated is handled with path cooperation optimization and smoothing, generates final path, and the path planning ability of intelligent driving vehicle in complex environment is improved by the method.

The invention discloses a mechanical arm obstacle avoidance control method fusing point cloud data and an improved algorithm, and the method comprises the steps: collecting the point cloud data of a working space of a mechanical arm in real time through a laser radar, achieving the alignment of a point cloud and a mechanical arm coordinate system through coordinate system correction, and obtaining an effective obstacle point cloud through specific preprocessing; converting the point cloud data into an octree structure for constructing an environment obstacle model; an obstacle avoidance path is planned based on an improved BI-APF-Informed-RRT algorithm, the algorithm fuses a bidirectional search mechanism and an artificial potential field method, the path length is shortened through dynamic elliptical sampling and a multi-objective optimization strategy, and the number of nodes is reduced; a modular integrated framework is constructed, combination of point cloud data, an obstacle avoidance algorithm and mechanical arm control is achieved, and track synchronization of a digital mechanical arm and a physical mechanical arm is achieved through ROS and Unity communication; according to the method, the obstacle avoidance capacity of the mechanical arm in a complex environment can be effectively improved, the path planning efficiency and safety are improved, and high practicability and stability are achieved.

The present application relates to a kind of port ship unloading area analysis method based on AIS data, comprising the following steps: first, AIS data preprocessing-washing and screening of original data and attribute supplementing;Second, ship stay voyage section extraction-define stay voyage section using motion characteristics and express using Geohash grid;Third, port destination text matching-irregular destination is matched with standard port name;Fourth, destination bidirectional search-accurately destination is analyzed using ship trajectory, and the attribution port of stay grid is determined;Fifth, grid integration and route cutting-integrate grid of different port attribution to obtain unloading area and cut ship full cycle route.The present application solves the problem that unloading mode is complex around port, and route is complex, utilizes the complementary advantage of space-time information and destination text in AIS data, and provides reliable technical support for the trade monitoring of bulk energy goods such as crude oil.

This invention discloses a bidirectional heuristic path planning method and system based on fixed-period switching, belonging to the field of path planning technology. The method includes the following steps: initializing forward and reverse searches, starting from the beginning and end points of the path planning respectively; controlling the search direction to alternately switch between the forward and reverse searches based on a preset fixed period N; evaluating and expanding nodes based on a consistency heuristic function in each search step; and merging the two paths to generate the final planned path when the paths of the forward and reverse searches intersect at a node. This invention employs a fixed-period switching strategy, completely avoiding the computational overhead of dynamic judgment and eliminating the resulting uncertainty. The balanced bidirectional search effectively controls the depth and breadth of the search tree, reducing the number of nodes simultaneously existing in memory.

The invention discloses a parking path planning method and system based on bidirectional multi-level search, and relates to the technical field of intelligent vehicle planning, and the method comprises the steps: starting to search from a parking starting point to obtain a forward search node set, and starting to search from a parking target point to obtain a reverse search node set; if the total number of the search nodes or the search levels do not meet the requirement, multi-level bidirectional search is started; searching nodes in the two sets are traversed to determine a collision-free curve with the continuous curvature, forward searching nodes and reverse searching nodes of the collision-free curve with the continuous curvature are connected with a parking starting point and a parking target point respectively, and the two obtained parking geometric curves are combined with the current collision-free curve with the continuous curvature; a parking path curve is obtained; and selecting an optimal path meeting a preset condition from all the parking path curves as a final parking path. The problems that an existing scheme is single in parking path and unreasonable in parking path are solved, and the parking success rate is increased.

The invention discloses a divider based on shift multiplication and power reduction, relates to the field of digital logic circuits and embedded computing, and completes operation through three steps of symbol preprocessing, power shift multiplication power locking and cross-magnitude bit-by-bit weight coefficient reduction. Dynamic precision pre-scaling and median prejudgment bidirectional search is introduced, a quotient coefficient is tested from a cardinal number intermediate value, up-down search is performed according to a residual error, and iteration is greatly reduced. Compared with the prior art, the method does not need a hardware multiplier and a huge lookup table, only depends on displacement, addition and subtraction and small-amount comparison, is suitable for a small MCU with limited resources, solves the problems that a traditional software division method is low in efficiency and an SRT algorithm is large in resource consumption, and achieves high cost-performance balance.

The invention provides a hydrofoil craft cargo transportation path planning method and device and a storage medium, and relates to the field of marine ship cargo transportation path planning, and the method comprises the steps: constructing a rasterized work map according to an actual marine operation environment of hydrofoil craft cargo transportation; constructing a forward search set and a backward search set based on a bidirectional A search architecture; performing forward search and backward search synchronously, and performing adaptive cutting on a node neighborhood according to the position of the current node in each search process; calculating a dynamic weight based on the coordinate dispersion of the current node and the neighborhood node, and substituting the dynamic weight into a heuristic function to adjust the comprehensive cost value; when it is detected that nodes of the forward search and the backward search coincide, the search is terminated, a forward search path and a backward search path are spliced, and the optimal cargo transportation path of the hydrofoil craft is obtained. According to the method, the time and efficiency of hydrofoil craft cargo transportation path planning are improved, and the path planning precision is also improved.

This invention relates to the field of artificial intelligence, and more particularly to a method for automatic parking path planning using a short-time bidirectional search algorithm. The method includes the following steps: incorporating a hybrid A* algorithm with a bidirectional search algorithm; using a grid method to optimize the bidirectional search algorithm to address the problem of overlapping nodes in the forward and reverse searches during bidirectional search; optimizing the node search process of the hybrid A* algorithm; and integrating the bidirectional search algorithm to accelerate the search time of the hybrid A* algorithm in the automatic parking path planning process. This effectively reduces the number of invalid nodes in the later stages of unidirectional search and reduces the number of searches. Simultaneously, the use of a grid method to divide the map effectively avoids the possibility of repeated searches within the same area. Furthermore, the combination of the grid method and the bidirectional search algorithm greatly increases the probability of intersection during the forward and reverse search processes.

The invention provides a route planning method and device for an optical fiber communication network, electronic equipment and a medium. The method comprises the following steps: acquiring a route request of the optical fiber communication network; analyzing the routing request, and determining a source node, a target node and a path constraint condition; the method comprises the following steps: under a path constraint condition, carrying out path search simultaneously from a source node and a target node by adopting a bidirectional search strategy based on a pre-constructed multi-level resource topological graph, recording searched nodes by adopting an adaptive Bloom filter, carrying out priority ranking on nodes to be searched, and searching the nodes to be searched according to a priority ranking result, an optimal path planning scheme is obtained; wherein the multi-level resource topological graph comprises a multi-level grid structure, and the multi-level resource topological graph takes a plurality of physical resources of the optical fiber communication network as nodes and takes an incidence relation among the plurality of physical resources as edges. According to the method, the efficiency and the accuracy of route planning are improved by performing bidirectional search on the multi-level resource topological graph.

This invention relates to a method for scheduling coke pushing plans in a disordered state in a coke oven based on a bidirectional Dijkstra algorithm. The method includes constructing initial and target state nodes, constructing forward and backward state transition graphs, calculating the edge weights of each directed edge, initializing the forward and backward search starting nodes, performing a bidirectional Dijkstra search and identifying candidate meeting nodes, calculating the total cumulative penalty value and selecting the final meeting node, and concatenating the forward and backward state sequences to obtain a coke pushing plan that restores the current disordered state to a normal sequence state. This method for scheduling coke pushing plans in a disordered state in a coke oven, based on a bidirectional Dijkstra algorithm, solves the problems of existing scheduling methods being easily affected by differences in operator experience, having long solution times, and being unfavorable for timely handling of disordered conditions on the production floor.