113 results about "Global planning" patented technology

The invention discloses an intelligent path planning method for a mobile robot, and the method comprises the steps: building a static two-dimensional grid map, and carrying out the global path planning through an improved ant colony algorithm; enabling the mobile robot sensor module to detect unknown obstacle information, calculating an obstacle motion trail and a robot motion trail, adopts an optimized dynamic window method to carry out local dynamic obstacle avoidance, and taking the current position of the robot as a starting point and a closest key node on a global planning path as a temporary target point to carry out dynamic obstacle avoidance; and enabling the robot to travel along the planned path and safely reach the destination. According to the method, the actual problems of static obstacles and dynamic obstacles in the map environment are comprehensively considered, the heuristic function of the ant colony algorithm is improved, pheromone updating rules are adjusted for global path planning, the optimized dynamic window method is adopted for obstacle avoidance when the robot encounters the dynamic obstacles in the running process, and local path planning is completed; and the robot has higher practicability and research value in actual map operation.

The invention provides an autonomous underwater vehicle (AUV) vertical plane under-actuated motion control method, which comprises the steps that: (1) initialization setting is performed on the AUV; (2) a top-layer control computer transmits a mission and finishes the global planning; (3) a motion control computer receives the feedback information of a sensor, performs control calculation by using a self-adaptive neuro-fuzzy inference system-based auto-disturbance rejection controller, and outputs a control command, namely an elevator angle delta s of the stern; (4) a steering engine executes the control command, finishes the coordination control of AUV depth and pitch attitude, and realizes the motion control under the AUV vertical plane under-actuated constraint; and (5) whether the mission is finished is judged, if the mission is finished, the data is saved and the voyage is ended, and if the mission is not finished, the control command is continuously calculated by the motion control computer. The AUV vertical plane under-actuated motion control method is suitable for the under-actuated, strong-coupling and complex motion relationship of the AUV in the vertical plane motion process, and can realize precise motion control.

The invention discloses an unmanned aerial vehicle three-dimensional track multi-target particle swarm global planning method, which comprises the following steps: (1) establishing an environment model according to a flight environment, and adopting a digital map technology when the flight environment of an unmanned aerial vehicle is processed; (2) establishing a flight path planning model according to the environment model established in the step (1); and (3) applying a particle swarm optimization technology to the flight path planning model in the step (2), and giving an improved multi-target backbone particle swarm global flight path planning algorithm with few control parameters. The method has the advantages that the three-dimensional global multi-target flight path planning model ofthe unmanned aerial vehicle is established, three index functions of flight path length cost, threat cost and concealment cost and corresponding constraint requirements are given, a multi-target particle swarm global planning method with few control parameters is provided, and the practicability of path planning is enhanced.

The invention discloses an unmanned vehicle semantic map modeling and application constructing method based on perception and location monitoring and relates to the technical field of unmanned driving. According to the method in the invention, two concept modules, namely entity and attribute, are included in unmanned vehicle semantic map modeling, wherein the entity comprises a vehicle entity, a road network entity and an obstacle entity; the road network entity comprises region entity and point entity; the attribute comprises point coordinate, area coverage and constraint; and the semantic relation is divided into two parts, namely object attribute and data attribute. According to the method disclosed by the invention, a set of map element data hierarchy structure applicable to the unmanned vehicle is constructed, and by designing the sufficient semantic relationship among map elements, the semantic map is conveniently generated; and semantic reasoning is performed on the semantic map, global planning path, the current posture of the unmanned vehicle and surrounding real-time obstacle information so as to obtain local scene information of the unmanned vehicle, the unmanned vehicleis assisted in performing behavior decision, understanding of the unmanned vehicle on driving scene elements is efficiently completed, and the associated search efficiency of the map elements is improved.

The invention relates to a plane track planning method of an unmanned underwater vehicle (UUV) formation, and belongs to the technical fields of unmanned underwater vehicles and track planning. The method includes: constructing a mission space model according to an environment information database or environment information of sensor detection; using an improved and fused algorithm of an APF algorithm and an RRT algorithm for global track planning on the basis of static environment information; and using global planning path points as sub-target-points, and carrying out local planning in sections on the basis of dynamic environment information. According to the method, the unreachable-target and local-optimization problems of APF are solved through a certain improvement scheme in a globalplanning algorithm, the three major characteristics of RRT non-determination, non-optimization and slow convergence are mitigated, deterministic and stochastic track planning methods are combined, static planning and dynamic planning are combined, location planning and speed planning are combined, a track reduction algorithm achieves an effect of further optimizing a track, and meeting of missionrequirements of safety, optimality and real-time performance of track planning of multiple unmanned underwater vehicles is guaranteed.

The invention discloses an implementation method from 3D sparse point cloud to a 2D raster image based on VSLAM, and the method comprises the steps: visual SLAM processes image information obtained bya camera, and 3D sparse point cloud is generated; secondly, the image is divided into a plane area and a height area through visual segmentation based on colors, the plane area is used for map pointmapping, a Bresenham straight line drawing algorithm is adopted for all received key frames and map points, and a counter is added for optimizing a mapping unit; the height area is used for obstacle detection, and a gradient threshold value and a Canny edge detection algorithm are adopted; and finally, autonomous navigation is performed on the 2D grid map which is obtained after conversion and canbe used for navigation and obstacle avoidance, a Dijkstra global planning algorithm and a DWA local path planning algorithm are adopted, and a low-cost visual sensor is adopted to acquire environmental information, so that indoor operation of the robot is realized.

The invention discloses an autonomous driving network under multi-scale perception and global planning, mainly focuses on deeper exploration of perception capability and effective improvement of obstacle avoidance planning, network interpretation and other capabilities, and provides an effective solution for the three weak core problems. Firstly, the network is structured and layered to improve the interpretation capability of each part of the network; secondly, the multi-scale perception capability of the network is improved by pre-training an FPN network [15], an obstacle avoidance module isadded to optimize the vehicle planning capability, and finally, the flow direction is controlled by perceiving obstacle avoidance features and planning a navigation instruction, so that effective feedback of the vehicle to global intention and local features is realized.

The invention discloses an improved unmanned aerial vehicle track real-time planning method, which is used for solving the technical problem that the existing unmanned aerial vehicle target tracking track planning method is poor in moving target tracking real-time performance. According to the technical scheme, a flight route is planned in advance according to state information of an unmanned aerial vehicle and a tracked target, and the unmanned aerial vehicle is guided to fly along the preset route. As the tracking target is a maneuvering target, different from global planning flying from thepoint A to the point B, airway planning cannot be completed offline at a time and must be carried out online in real time according to the unmanned aerial vehicle, the position of the target and thelike, flight and planning are carried out at the same time, and a planned airway responds to maneuvering of the target in time. Model prediction control is adopted to replace global optimization withlocal optimization, so that route planning of the unmanned aerial vehicle can respond to dynamic changes of the battlefield environment in time. Due to the fact that local optimization needs to be calculated, near-real-time solving can be achieved, the target is predicted in real time, the position of the target is updated in time, and the real-time performance of route planning is better.

The invention discloses a satellite cluster configuration adjustment planning method for space target collaborative observation. According to the method, each satellite is regarded as an intelligent Agent with autonomous planning and decision-making capability, a coordination graph based on a cluster communication structure is established, and tasks optimized by a global optimal configuration adjustment strategy are decomposed to local learning of each satellite based on the communication coordination graph. According to the method, the top-layer planning of configuration adjustment and bottom-layer control are comprehensively considered; solving is carried out from the perspective of cluster cooperation planning; the global planning learning task is divided into the paired Agents according to the communication relationship, so that the autonomy and intelligence of the satellite cluster are enhanced, the on-orbit viability and the task execution level of the satellite cluster are improved, and a new idea and method are provided for on-orbit autonomous operation and management of the satellite cluster.

The invention relates to a pedestrian evacuation simulation method and system adopting an artificial neural network-based Q-Learning algorithm. The method comprises the steps that to-be-evacuated pedestrians are divided into a plurality of groups according to initial related parameters, a leader is selected in each group, and the rest of the to-be-evacuated pedestrians are taken as followers; in each group, the leader preferentially learns and selects an optimal path obtained by performing global planning on evacuation paths through the artificial neural network-based Q-Learning algorithm, and the followers calculate a resultant force of the followers, the pedestrians in the group, the pedestrians between the groups, and environments according to a social force model, avoid barriers and follow the leader; and the to-be-evacuated pedestrians are all evacuated. According to the method and the system, global path planning is carried out in combination with the advantages of reinforcement learning and an artificial neural network; the deficiencies of pure reinforcement learning are made up for; a bottom layer matches with the social force model to guide a movement; and quick and effective way finding and relatively real evacuation of crowds can be realized.

The invention belongs to the technical field of distribution and relates to a distribution route planning method and a device. The method comprises the following steps: obtaining the locations of alluser orders to be delivered and the initial positioning of the delivery personnel; According to the location of all orders and the initial location of the distribution personnel, the global planning of all orders to be distributed is carried out by using the reverse multi-objective heuristic search method, and the optimal route set for distribution is obtained; For a new order in which a distribution location occurring in the distribution process is not included in the current location to be distributed, The distribution route selected and executed from the optimal route set is matched according to the location of the new order, the remaining undistributed locations of the distribution route are incrementally reprogrammed relative to the location of the new order and the current positioning of the distribution personnel, and the optimal route set is updated. It aims at irregular insertion of new orders, provides optimized routes for the distribution personnel and pushes to the distribution personnel, and saves the time spent by the distribution personnel on the way.

The invention provides a land leveling method based on GNSS (Global Navigation Satellite System). The method comprises the following steps: determining the general trend of a planned path through analyzing the terrain of the global planning of a target land parcel according to acquired terrain information and a terrain environment model of the target land parcel; then, carrying out local adjustment for avoiding the empty load and full load of ground leveling equipment through the calculation of excavation and filling earth volume based on the terrain environment model and the terrain information, namely, determining the target planned path of the traversing target parcel through the combination of the setting rule based on the calculation of the excavation and filling earth volume and thejudgment of empty/full load; and finally, guiding the ground leveling equipment to carry out target land parcel leveling operation according to the planned path. According to the method provided by the invention, through reasonable ground leveling path planning, the empty load, full load, repeated leveling and omissive leveling of the ground leveling equipment can be effectively avoided or reduced, the land leveling can be effectively guided, and thus the land leveling efficiency is improved.

The invention discloses a network connection automatic driving system and method for a scenic spot sightseeing vehicle. The system comprises: an environment sensing module; a man-machine interaction module; a vehicle-road-cloud interaction module; and a decision and control module which carries out the global planning of a tourist route according to the man-machine interaction information and the Internet of Vehicles information, and provides an optimal tourist route for tourists. If the tourists select a route recommended by the system, an upper-layer planning sub-module directly reads a pre-stored tourist route and optimizes the route according to the actual tourist distribution condition of the scenic spot; and if the tourist selects a custom scenic spot sightseeing point, the upper-layer planning sub-module performs on-line tourist route planning according to the tourist demand and the current tourist distribution condition of the scenic spot.

The invention relates to an unmanned ship hybrid sensing autonomous obstacle avoidance method and system based on reinforcement learning. The method comprises the following steps: 1) building a marineenvironment; 2) setting an action space according to the condition of an unmanned ship propeller, and performing learning according to global planning information provided by a static chart and obstacle information in a radar system detection radius range to obtain a reinforcement learning state code; 3) setting a reward target weight to obtain a comprehensive reward function; 4) establishing andtraining an evaluation network and a strategy network; and 5) respectively inputting the reinforcement learning state codes into the evaluation network and the strategy network, inputting the comprehensive reward function into the evaluation network, and determining the output of the controller according to the action corresponding to the learned average value of the strategy network. Compared with the prior art, the method and sysem have high self-learning capability, can adapt to different large-scale complex environments through simple deployment training, and further realize autonomous perception, autonomous navigation and autonomous obstacle avoidance.

The invention discloses an autonomous mobile robot and a path navigation and path planning method and system thereof. The method comprises a global planning process and a local planning process. The method specifically comprises the following steps: acquiring positioning information and sensing information; generating a cost map according to the positioning information and the sensing information,wherein the cost map is used for A-satellite path searching to obtain an initial navigation path; optimizing the initial navigation path, sampling vertexes of the optimized path, and taking out key points from the vertexes for interpolation to obtain a global navigation path; generating a to-be-selected path group according to positioning information and the global navigation path; evaluating each to-be-selected path according to the real-time perception information to obtain an optimal path, and outputting the optimal path; according to the method, the near-optimal navigation path can be quickly searched in a large range, a series of points describing the global navigation path are obtained, the points of the global navigation path are adjusted and selected, and the global navigation path capable of meeting the requirements of continuous curvature and no collision is obtained.

The invention relates to a system for planning a dynamic path of a robot based on a cloud terminal, and the system employs a method which comprises the steps: building preset maps at a robot side, anduploading the preset maps to a server side; marking barrier points of the preset maps at the server side, connecting a passable path, setting a weight value of the passable path at the server side according to a first preset algorithm, carrying out the configuration of the same barrier point on a plurality of preset maps to generate a barrier point path, setting the weight value of the barrier point path according to a second preset algorithm and then connecting the plurality of preset maps to generate a dynamic map, transmitting the dynamic map to the robot side, storing the dynamic map in adatabase of the server side, calculating the optimal dynamic path according to a third preset algorithm and transmitting the optimal dynamic path to the robot for execution. The invention also discloses a method for planning the dynamic path of the robot based on the cloud terminal, and the method can solve a problem of robot dispatching automatic path planning across regions, can achieve the dynamic global planning, and improves the operation efficiency.

The invention belongs to the technical field of artificial intelligence and robot navigation, and particularly relates to a hybrid path planning method for an indoor mobile robot. According to the method, using a grid method for modeling the environment; searching a global path by using a bat algorithm as a global path planning method; optimizing the obtained global path, namely deleting redundantpath nodes, and reducing the length of the path and turning points of the path; designing an evaluation function of a dynamic window method, and bringing the global path into the evaluation functionof the dynamic window method to realize the combination of local planning and global planning; introducing an adaptive idea to dynamically adjust the coefficient of the evaluation function, and improving the dynamic obstacle avoidance capability of the fusion algorithm. The method can be applied to path planning of the indoor mobile robot, path planning and robot control are combined, and dynamicobstacle avoidance is considered under the condition that the global optimal path is guaranteed.

The invention belongs to the technical field of space cleaning, and relates to a sweeping robot region division system and a sweeping robot region division method. As for existing sweeping robots, walking modes, which are adopted during cleaning, are generally subjected to global planning, two-dimensional space obstacles are taken into consideration only, and all ground regions in maps are coveredin one time. For such large space regions as supermarkets, malls, hotel lobbies and the like, three-dimensional space obstacles need to be considered by robots for the large public spaces, and the walking modes of the conventional domestic robots cannot meet requirements. The sweeping robot region division system provided by the invention comprises an obstacle isolating region and cleaning regions, wherein the cleaning regions include at least one block-shaped structural region which is sequentially arranged; and according to the method, obstacles in the cleaning region are isolated, and thenthe cleaning regions are ordered in accordance with the block-shaped structures. With the application of the system and the method provided by the invention, various obstacles in a three-dimensionalspace can be effectively avoided, so that the sweeping robot can conduct autonomous moving in a complex and variable three-dimensional environment better, and subsequently, large space grounds can becleaned.

The invention provides a driving planning method and device for an automatic driving vehicle and the automatic driving vehicle, and relates to the technical field of automatic driving. The driving planning method comprises the steps of obtaining a global planning path of the automatic driving vehicle; segmenting the global planning path to obtain a plurality of segmented planning paths; controlling the automatic driving vehicle to travel according to each segmented planning path in sequence, and monitoring deviation condition data of the automatic driving vehicle at the end point of each segmented planning path; and re-planning the global planning path of the automatic driving vehicle according to the deviation condition data of the automatic driving vehicle. Therefore, the driving condition of the automatic driving vehicle can be considered in real time, the automatic driving vehicle is prevented from seriously deviating from the originally planned path, and the driving accuracy of the automatic driving vehicle can be ensured.

The invention discloses a method and a device for determining a traveling strategy of a mobile robot, a storage medium and the mobile robot. The method comprises the steps of: when a slip early warning signal is received, controlling the mobile robot to stop moving, and storing a real-time position and a driving path map when the mobile robot stops moving; determining a planning path that has beenexecuted by the mobile robot in a global planning path according to the real-time position and the driving path map when the mobile robot stops moving; and finally, determining the traveling strategyof the mobile robot according to the planning path that has been executed by the mobile robot in the global planning path and the real-time position when the mobile robot stops moving. By controllingthe slip mobile robot to stop moving, storing the position when the mobile robot stops moving, and determining the planning path that has been executed by the mobile robot in combination with the position thereof, the accuracy of the driving path map can be effectively improved, thereby being conducive to determining the correct traveling strategy by the robot.

The invention belongs to the technical field of visual SLAM processing technology and mobile chassis navigation path planning, and particularly relates to an active visual SLAM system based on a panorama camera, which comprises an intelligent chassis module, a panorama camera module, a camera dynamic bracket, a monocular camera module and a processor; the processor comprises an evaluation module, a visual SLAM processing module, a global planning module, a local path planning module and a dynamic support planning control module. By adding the intelligent chassis module capable of doing curvilinear motion at any radius, the monocular camera module installed on the multi-degree-of-freedom camera dynamic support and the panoramic camera module used for evaluating the whole environment, the problem that traditional visual SLAM mapping scanning is not purposeful is solved. According to the invention, visual mapping and positioning are more purposeful, the mapping and positioning speed is increased, the mapping and positioning quality is improved, and the mapping and positioning reliability and flexibility are enhanced.

The invention discloses a mixed reality electronic sand table system and a simulation method. The system comprises a display device (1), a sand table console (2), a main control computer (3), a head-mounted display (4), an operation handle (5), a camera switch (6), and a camera module (7). The display device is embedded into a sand table top, and the sand table content is displayed by the display device. The sand table content can be directly operated by touch, supplemented by detailed description and explanation. A pair of head-mounted mixed reality glasses is used as a virtual scene observation device to carry out simulated marching in a local virtual scene, wherein the operation is performed by gestures. Global planning can be carried out based on a global view, and local visibility test can be carried out. Moreover, marching can be simulated. The system is of higher practicability in route planning and time checking.