97 results about "Real-time path planning" patented technology

A path planning system and method for an object, such as a vehicle, provides a randomized adaptive path planning that handles real-time path planning for a vehicle operating under kinodynamic constraints in dynamically changing and uncertain environments with probabilistic knowledge of vehicle and obstacle movement.

The invention relates to a method for planning a path for a mobile robot based on environmental modeling and a self-adapting window, which relates to a method for planning a real-time path for the mobile robot. The method comprises the following steps of: performing modeling and analysis on a multiple constraint local environment; performing passable analysis; performing safety analysis; performing motion smoothness analysis; performing goal-directed analysis; and performing path planning by adopting the self-adapting window. Because the method has better environmental suitability and obstacle avoiding capacity, the method obtains good safety and reachability, has high calculation real-time property, so the method solves the problem that the mobile robot generates an obstacle avoidance path in real time in an uncertain complex environment, provides a path selection method with optimized integration, better meets the requirements on obstacle avoidance for the mobile robot, realizes the real-time path planning and control of the robot, and provides an effective collision-less path planning method for the navigation application of the mobile robot.

A path planning system and method for an object, such as a vehicle, provides a randomized adaptive path planning that handles real-time path planning for a vehicle operating under kinodynamic constraints in dynamically changing and uncertain environments with probabilistic knowledge of vehicle and obstacle movement.

A joint search method for UAV multiobjective path planning in an urban low altitude environment first constructs a static safety index map based on static known obstacles. Meanwhile, based on proactively detected obstacles that are not marked on a geographic map by a UAV, the method constructs online a dynamic safety index map. Second, a multiobjective path planning problem is solved using a joint offline and online search method. Moreover, this method first plans offline the least cost path from a starting point to an end point and then invokes the online search scheme to replan online a changed path when the UAV detects unknown obstacles. Thus, the UAV can avoid dynamic obstacles effectively. The online search scheme has a small search space and can quickly replan a safe path for the UAV, thus satisfying the requirement of UAV on the real-time path planning.

Relating to the technical field of intelligent traffic, the invention provides a real-time path planning method and system. The method includes: when a current client drives according to an initial path, collecting the destinations, sampling locations and sampling time of other clients in real time; planning the navigation paths of the other clients according to the destinations, sampling locations and sampling time respectively, and extracting all sections containing the initial path and target sections of relevant sections associated with all the sections from the navigation paths respectively; and carrying out statistical analysis on the target sections and the sampling locations and sampling time of the other clients, and forecasting the traffic information of each section in the initial path in a future period of time. The method and system provided by the invention have the characteristics of wide data range and even sample, improve the accuracy of the path planning result, especially for traffic variation without obvious regularity, and improve the accuracy of path planning.

The invention relates to a vehicle comprehensive information system based on the third-generation (3G) mobile communication, comprising a server and a vehicle-loaded terminal communicating with each other via a 3G network. The vehicle-loaded terminal comprises a vehicle bus interface module, a 3G mobile communication modem module and an embedded-type control module, and the server comprises an information receiving module, an information storage module, a function module and an information issuing module. The vehicle bus interface module is accessed to an inside control bus of a vehicle through an OBD interface, obtains the vehicle running information and transmits the information to the embedded-type control module; the embedded-type control module obtains and processes the vehicle running information and communicates interactively with the server through the 3G mobile communication modem module connected with the embedded-type control module; the information reception module receives the information of the vehicle-loaded terminal transmitted by the 3G network; the information storage module stores the information of the information receiving module and the application information; the function module is used for realizing the application functions of vehicle positioning, map navigation, real-time path plan, theft prevention of vehicles and the like; and the information issuing module is used for transmitting information provided by the server to the vehicle-loaded terminal.

The invention relates to a mobile robot real-time layered path planning method based on a grid map. The method, which is used in a grid map, comprises the following steps: carrying out binary classification according to external environment information, and establishing a grid map; planning an outer path according to a speed-based artificial potential field method; and when the path is about to fall into local minimum and oscillation, planning an inner path according to an A star algorithm. The problem that the traditional artificial potential field method may fall into local minimum and planned path oscillation and the problem that the A star algorithm is not applicable to real-time path planning are solved. Real-time, safe and stable operation of mobile robots is ensured.

The invention relates to a planning method for a simulated path of a robot under a complex dynamic scene and a robot motion planning simulation platform for achieving the method. According to the method, path security evaluation criteria are established according to a collision possibility and an arrival possibility, an algorithm framework for planning two layers of interactive paths is adopted, motion planning is divided into an environment exploration layer and a partial path planning layer, the two layers perform information interaction by means of a self-adaptive path buffering area, and a security update search tree is taken as a top planner and applied to the environment exploration layer in the two-layer interactive framework. The simulation platform comprises a problem module, a planning module and an execution module. A safe and real-time path planning scheme is provided according to a path planning strategy selected by simulating a human path, the defect that only the feasibility of the path is considered but the continuity of the path is not concerned in the prior art is overcome, and the motion planning of the robot in a complex dynamic environment is realized.

The invention discloses a cooperative real-time path planning method for multiple unmanned aerial vehicles (UAVs) in case of communication latency. UAV data, obstacle data and target point data are firstly set to generate a digital map; then a simultaneous arrival constraint is executed, and the flight speed of each UAV is obtained; a communication latency constraint is executed, and the spacing range of the UAVs is obtained; an A-* algorithm is executed, and the next path of each UAV is obtained; and whether conditions of a collision avoidance constraint and a communication distance restriction are satisfied or not is judged, and whether the UAVs arrive a target point or not is finally judged. By adopting the cooperative real-time path planning method, the multiple UAVs can take off from different places and simultaneously arrive at the same target point under the condition of communication latency and can avoid obstacles on the way; the collision among the UAVs is avoided; and meanwhile, the communication among the UAVs can be kept.

The invention relates to a real-time path planning method of AUV (Autonomous Underwater Vehicle), in particular to a method for carrying out online, real-time local path planning according to an online map in an AUV real-time collision preventation process. The method comprises the steps of: setting the quantity of small populations according to the quantity of path points of the AUV, initializing; carrying out immune selection on each small population to obtain subgroups; carrying out genetic manipulation on one subgroup, carrying out cell cloning on the other subgroup; then clustering through a vaccination and an antibody to form the next generation of small population, judging whether the next generation of small population meets the conditions or not; if yes, selecting optimal individuals of the small populations; and selecting the optimal individuals from the set consisting of all optimal individuals to be used as a planning path. According to the invention, the diversity of the population is maintained by using an antibody clustering principle, the premature convergence of an algorithm is avoided, and the global optimization is facilitated. The established immune genetic algorithm is used for clustering and analyzing generated filial generations by adopting a self-regulating mechanism, and the diversity of the population is ensured.

The invention provides a method and a device for automatically planning an unmanned aerial vehicle formation path. The method comprises steps: each unmanned aerial vehicle in the unmanned aerial vehicle formation is loaded with fleet path planning data and fleet formation description data of the whole formation, wherein the fleet path planning data of the whole formation are advance trajectory data planned for a predetermined point in the formation formed the unmanned aerial vehicle formation as a whole, and the fleet formation description data at least comprise the number of unmanned aerial vehicles in the formation and position coordinate data of each unmanned aerial vehicle relative to the predetermined point; and according to the fleet path planning data and the fleet formation description data of the whole formation, each unmanned aerial vehicle adopts a swarm intelligence algorithm based on a repulsion-attraction model for real-time self path planning. Distributed design is carried out on the self real-time path planning of the unmanned aerial vehicle, central computing resources are saved, and the algorithm complexity is not increased along with increasing of the number of the formation members.

The invention discloses a method for optimizing a charging path of an electric automobile based on user travel rules. The method comprises the following steps: (1) counting the owner travel characteristic; (2) performing data acquisition, wherein the data comprises data related to the electric automobile travel characteristic as well as data of charging stations and road congestion conditions; (3)establishing a traffic network, namely establishing a regional traffic network comprising nodes and two-way edges; (4) performing data analysis and processing, namely counting habitual charging stations and charging time of the owner, generating corresponding travel links, and correcting the analytical result according to the survey results in the (1); (5) establishing an electric automobile charging path optimization model; and (6) selecting the optimal charging requirement guided traveling path integrating the charging time, traveling path and cost for owner preference from the multiple travel links by utilizing the electric automobile charging path optimization model. According to the method disclosed by the invention, the travel path corresponding to the travel requirements is provided for the user by fully considering the regional historical circumstances and user charging habits, the defect that the real-time path planning system has harsh requirements on communication hardwarefacilities is overcome, and the charging path is personalized.

The invention provides a multi-UAV (unmanned aerial vehicle) cooperative searching method and system based on path planning and information fusion, and the method comprises a step of the real-time path planning: enabling each UAV to determine the movement and an observation object at a next moment according to current map information and an algorithm; a step of search map updating: updating a probability map and a certainty degree map according to an observation result; a step of information fusion: enabling each UAV to broadcast its own map information and receive the map information of otherUAVs, and calculating the real-time search map information; and a step of decision making: judging whether a target is located at a current position of the UAV or not according to the updated map information, and assisting the making of a decision according to the certainty degree map. The method can remarkably improve the search time, reduces the flight cost of task execution, improves the search accuracy, achieves the innovative fusion of real-time path planning and the information fusion, and enables a search mechanism to be more complete, efficient and reliable.

The invention provides an aircraft surface trajectory prediction method based on a long-short term memory (LSTM) neural network. The LSTM neural network and a polynomial fitting method are combined toimplement the trajectory prediction technology. By setting an incremental sampling period, the position at any moment with in a long period of 60 seconds is theoretically predictable. However, when the position within an excessively long period is predicted, the training data generated by preprocessing has low quality so as to result in low prediction precision and has no practical effect on thedetection of surface taxiing conflicts. Thus, it is relatively appropriate to predict the position at any moment with in a middle-long period of 30 seconds. The method, by means of the historical memory of the LSTM neural network, can implicitly simulate the surface motion state of an aircraft according to the context of a trajectory sequence, can be used for predicting the position of the aircraft on the taxiway and the runway of an airport in the future, avoids the surface taxiing conflicts of the aircrafts, paves the way for real-time path planning, ensures the safe and efficient operationfor the airport.

The invention discloses a real-time route planning method. The method comprises the following steps: defining route cost according to the route condition in a route net, generating pheromone according to the route where vehicles are positioned, reporting the pheromone to a server, calling the ant colony algorithm, calculating the concentration of the pheromone of the route at the next moment according to the pheromones of all vehicles, and finally selecting the next route for the vehicle by the server according to the traffic flow information of all routes, so as to avoid congestion, realize accurate prediction of the traffic flow condition, keep away from road congestion, ensure the traffic flow maximization of the optimal route, prevent wide fluctuation of the road condition wholly, and generate a reasonable optimized route, wherein the concentration of the pheromone is traffic flow estimated parameter; and besides, compared with the traditional route planning method, the real-time route planning method has the technical effects of simplicity, flexibility and difficulty in falling into local solution.

The invention discloses a method for real-time path planning based on dynamic feedback. The method comprises the following steps: 1, transmitting information of a starting point and a destination to a navigation server by using a navigation client; 2, planning a first optimal path from the starting point to the destination by the navigation server, and setting the first optimal path as a current navigation path to be transmitted to the navigation client; 3, judging whether the destination is reached or not, if so, ending navigation, and otherwise, transmitting the current position information to the navigation server; 4, judging whether a path updating condition is met or not, if the path updating condition is not met, turning to the step 3, and otherwise, planning a second optimal path from the current position to the destination; and 5, if the second optimal path is superior to the current navigation path, setting the second optimal path as a new navigation path, transmitting the new navigation path to the navigation client and turning to the step 3, otherwise, turning to the step 3 directly. By adopting the method disclosed by the invention, the navigation path is planed dynamically, and the method is adaptable to topological changes of a whole road network and can be used for significantly improving the driving efficiency.

The invention relates to the technologies of image processing, real-time mapping, path planning, robots and the like, and provides a collaborative search blocking platform of a ground robot. The collaborative searching and blocking method based on the ground robot uses a ground robot carrying a camera and a processor to carry out target searching; one robot additionally carries a laser radar; therobot carrying the laser radar establishes an environment map by using the laser radar, and the map is transmitted to other robots, all the robots acquire image information of the surrounding environment through cameras, the image information is processed, an appointed target object is identified in a plurality of objects by utilizing a pre-trained detection and tracking algorithm, the appointed target object is tracked for a long time, and data transmission among the robots is performed through a wireless network; when a certain robot detects a target, the robot can track the target and sendthe position information of the target to other ground robots in real time, and real-time path planning and encircling are carried out. The method is mainly applied to robot design occasions.

The invention discloses a real-time path planning method based on a vehicular ad-hoc network. The technical scheme is characterized in that the method comprises the following steps: 1) obtaining map data and extracting information; 2) collecting real-time traffic information by utilizing the vehicular ad-hoc network technology; 3) setting road weight based on the real-time traffic information and carrying out path finding; and 4) updating the real-time traffic information in the driving process and carrying out path finding again. The real-time path planning method solves the problem that an existing path planning system lacks of real-time performance and accuracy, and provides more convenient and faster driving paths for users to cope with different degrees of road congestion information and ever-changing road traffic states.

The invention discloses a binocular-vision blind guiding instrument based on reinforcement learning. The binocular-vision blind guiding instrument based on reinforcement learning comprises a binocular-vision module, a voice module, a state set generating module, a reinforcement learning module and a GPS navigation module, wherein the binocular-vision module is used for processing images of a firstimage collecting module and a second image collecting module, generating a real-time depth map and establishing a three-dimensional scene; the voice module comprises a voice input module and a voiceoutput module, the voice input module comprises a voice recognition module, the voice recognition module is used for carrying out voice recognition, and the voice output module is used for outputtingbehavior instructions, positioning information and path navigation information of the reinforcement learning module in a voice manner; the state set generating module extracts environment characteristics of the three-dimensional scene through a convolution neural network, and a state set is generated; the reinforcement learning module comprises a reinforcement learning network, and the reinforcement learning network is used for learning the state conversion strategy with the state set as input to obtain output action instructions; the GPS navigation module is used for positioning and generating path planning according to voice recognition information. Real-time path planning signals of blind persons can be provided, and the action strategy of the blind persons is conveniently guided in real time.

The invention relates to an intelligent fire alarming method. The intelligent fire alarming method includes the steps: when receiving a fire alarm command, acquiring sensing information of a pluralityof sensors, wherein the sensing information includes: a combustion value of a combustible material, a wind direction value, a smoke concentration value, a temperature value and a flame value at a fire site, and a heartbeat value, a blood pressure value and a respiratory rate of a user; when determining that the fire alarm command is valid according to the sensing information, acquiring a fire video of the fire site, and transmitting the fire alarm command to an alarm terminal; acquiring the time that the fire alarm command is sent to the alarm terminal; if the transmission occurs in the daytime, acquiring the road condition information and sending the optimal path planning to the alarm terminal, and if the transmission occurs at night, acquiring street light information and sending the optimal path planning to the alarm terminal; and when determining that the fire alarm command is invalid, outputting the prompt of fire self-rescue measure to guide the user to carry out self-rescue. The invention also provides an intelligent fire alarm terminal and a storage medium. The intelligent fire alarming method, the terminal and the storage medium can solve the difficulties of the user foralarming, can provide more comprehensive fire information for rescue staff, and can perform real-time path planning at the same time so as to enable the rescue staff to arrive at the fire site as soonas possible.

The invention belongs to the technical field of drone operation and discloses a drone real-time path planning method based on an improved RRT (Rapidly-exploring Random Tree). The drone real-time pathplanning method comprises the following steps: constructing a local rolling window; setting local sub-goal points; carrying out random sampling and planning by adopting a local RRT algorithm; and carrying out an algorithm termination principle. According to the drone real-time path planning method, an original algorithm, which is only applicable to global planning, is improved and fused; the window is constructed according to local known environment information; and the sub-goal points are determined through a certain method and a global planning algorithm is used for exploring in the environment. In a process of rolling and frontward moving the window, the environment information in the window is continuously updated and planning mapping and feedback are realized; finally, a goal point isrealized. With regard to the RRT algorithm, the improvement method based on the rolling window does not need to carry out random exploring on a whole space when being compared with global planning; however, planning is limited in numerous windows which are continuously updated; a random exploring range is reduced and the calculation amount is reduced; and online planning can be realized.

The present invention relates to a rescue path planning method based on multiple starting points, multiple to-be-rescued points, and multiple destinations. Three components: a wireless sensor, a mobile terminal and a remote server end which are pre-deployed inside the building are involved in the method. The rescue path planning method comprises the following steps: obtaining environment information through a wireless sensor network deployed inside the building, and establishing an environment model by using a grid method; and according to the environment model established by using the grid method, establishing a combined optimization model by improving the ant colony algorithm, thereby finding the shortest rescue route. According to the combined emergency rescue real-time path planning method for multiple starting points, multiple to-be-rescued points, and multiple exits provided by the present invention, a multi-objective combination optimization model for the post-disaster emergencyrescue is established, an improved ant colony algorithm is designed, model solving is performed, requirements for rapid decision-making in the post-disaster emergency rescue route planning can be better satisfied, a safe and fast rescue route can be found, and the efficiency of disaster rescue can be improved.

The invention relates to a point, line and plane obstacle model construction-based station real-time emergency response path planning method. With the method adopted, it can be ensured that an algorithm can calculate a three-dimensional optimal path in real time after a station emergency event without losing the position information of fixed obstacles in indoor environments. According to the coreidea of the method, before path planning, data processing is performed on the overall architectural design planar graph of a station in advance; obstacle map construction work in an entire area is completed; information is recorded in a server, so that system operation time can be shortened; with special conditions such as a condition that some escalators inside the station move upwards and downwards, and a condition that some escalators from a waiting room to a platform can only go downwards, and passengers can only go upwards through stairs, are considered, upward movement and downward movement attribute information and other attribute information are added to path cost, and therefore, a planed path can be in line with actual and situations; and by means of accurate and real-time path planning, station security personnel are guided to complete handling work in an emergency efficiently.

The invention discloses a cooperative control system and a cooperative control method based on an unmanned surface vehicle and multiple underwater robots. The cooperative control system comprises theunmanned surface vehicle and the multiple robots. The unmanned surface vehicle generates underwater exploration search targets and path planning information corresponding to all the robots based on obtained geographical positions of all the underwater exploration search targets, the underwater topographic information and the real-time geographical positions of all the robots; each robot receives the underwater exploration search target and the path planning information sent by the unmanned surface vehicle; and the search targets are investigated according to the path planning information, andimage information of a underwater suspicious target is acquired and compared with the received underwater exploration search targets until image video shooting and data acquisition of the suspicious target and the search targets are completed in the process of executing search target exploration when the underwater suspicious target is close to the underwater suspicious target. According to the cooperative control system, the SOM network is adopted to solve the problems of multi-machine cooperation, information sharing, multi-task allocation and real-time path planning of the unmanned surfacevehicle and multiple underwater robots.

A real-time route planning method based on travel time prediction is characterized by based on the similarity of historical data, training a BP neural network prediction model by using the historical data of road vehicle travel time to obtain predicted data with relatively small errors; using the predicted data as the data for route navigation planning and dynamically planning a route in real time by using a Dijkstra shortest path algorithm; and improving the defect that many traditional navigation systems calculate the total travel time based on the driving speed of a vehicle on the road, and do not take account of other factors in the vehicle driving process. The method, based on the similarity of historical data, predicts the vehicle travel time by the BP neural network algorithm, can relatively accurately predict the travel time of the vehicle and plans a route.

The invention discloses a target real-time path planning method for a target generator. The real-time calculation of a virtual target operation parameter is realized by adopting a fuzzy rule, meanwhile, a target dynamically detects a dynamic barrier in an environment, a new path is planned according to the threat degree and position information of the barrier, so that the barrier is dynamically avoided, and the intelligence of the target generator is greatly improved; when the barrier is little in threat for the target, the complexity of a path planning algorithm is effectively reduced by adopting a geometric algorithm, the virtual scene rendering speed is increased, and the continuity of a virtual target movement picture is improved; and when the barrier is larger in threat for the target, the target is controlled by adopting a fuzzy algorithm for rapidly avoiding the barrier, the phenomenon of frame skip or inconsequent movement caused by desynchrony of pose position and orientation calculation updating and frame frequency is effectively avoided, and the picture quality of the target generator is improved.

The invention relates to a throughput flexible intelligent assembly logistics path planning platform comprising a sensor system, a production line system, a real-time logistics path intelligent control system and a communication facility, wherein the sensor system is used for real-time recording and delivery of parameters of product parts by corresponding sensors; the production line system is used for the implementation of the production of product parts and the assembly of the product; and the real-time path planning intelligent control system comprises an intelligent control system processing unit using an autonomous decision-making algorithm, wherein the intelligent control system processing unit is connected to the sensor system and used for increasing or reducing the number of production line according to the production requirements of parts, dynamically adjusting the ratio between parts production and product assembly lines in real time according to production requirements, andadjusting the number and sequence of parts on the assembly line according to assembly requirements.

The invention discloses an AGV (automated guided vehicle) real-time path planning method based on modified quantum ant colony algorithm, comprising the sequential steps of S1, initializing environmental and algorithm parameters; S2, receiving an AGV path planning task; S3, constructing AGV path solutions; S4, evaluating a current solution, and recording an optimal solution; S5, using a quantum rotation gate; S6, allowing quantum mutation; S7, updating pheromone; S8 judging after computing is ended, and providing in time an AGV path that meets the comprehensive requirements, such as global search, computing time, iteration early quick convergence, and iteration late solution diversity. Manpower and time costs are saved, goods transport efficiency is improved, and production efficiency can be improved.

The invention discloses an indoor fire alarm and evacuation method. The method comprises the steps of receiving an alarm triggering command sent by an alarm node; sending a wake-up command to all alarm nodes to make all the alarm nodes immediately send detection information to a server in real time; obtaining real-time weight information of all indoor routes according to the real-time detection information; receiving real-time location information of a mobile end; generating a real-time optimal evacuation route from a real-time location to any entrance according to normal-state weight information and the real-time weight information, namely an indoor route with the real-time maximal sum of normal-state weight and real-time weight from the real-time location to any entrance; sending the optimal evacuation route to the mobile end in real time according to ID information of the mobile end. Thus, through the adoption of the indoor fire alarm and evacuation method, the provided evacuation route is not only shortest but also safest; compared with local algorithms used in existing evacuation methods, an algorithm of real-time path planning is adopted, complex and changeable fire conditions can be adapted, the practicability is higher, and the efficiency of fire evacuation can be improved.

The invention discloses a UAV path planning method for an electromagnetic interference environment, and the method can be used to obtain a globally optimal path rapidly. Update of information elements of an ant colony algorithm serves as a point of penetration, the global and searching capabilities of the ant colony algorithm are improved by updating the global and local information elements in the ant colony optimization searching process, the searching speed for the globally optimal path of the algorithm is improved, a new path can be generated rapidly according to new work nodes, real-time path planning of a UAV can be realized, and it is proved that when the method is used to resolve a given object point, generation of an initial track needs 353ms, generation of a new track by changing track points needs 261ms, and rapid track searching and computing are suitable for real-time UAV line-patrol path planning in the real environment. The UAV path planning method can be popularized and applied in the technical field of UAV.