54 results about "Local planning" patented technology

The invention discloses a mixed robot dynamic path planning method which is capable of being applied on the condition that a part of environment information is known, and unknown dynamic and static obstacles exist at the same time. Aiming at the conditions, the mixed robot dynamic path planning method comprises the following steps: utilizing a genetic algorithm (GA) as a global planning method to obtain global paths, and then conducting local planning by means of an improved artificial potential field method. According to the mixed robot dynamic path planning method, in local planning, speed and acceleration information of a robot and a barrier is considered, and therefore the mixed robot dynamic path planning method has better effects on processing dynamic path planning. In addition, effects of global planning path for local planning are also considered. The mixed robot dynamic path planning method is ease to achieve, robot paths obtained are more optimized, and meanwhile good flexibility is shown in the application.

The invention provides a local obstacle avoidance considering UUV moving object sliding mode tracking control method, which comprises the steps of detecting position information of a UUV, a moving object and an obstacle in real time, acquiring state estimation of the moving object at the moment k, building a relative motion model of the UUV, the moving object and the obstacle, autonomously switching between a tracking strategy and an obstacle avoidance strategy according to the relative positions of the UUV, the moving object and the obstacle based on the size of the object tracking radius and the obstacle avoidance safety radius, acquiring tracking control deviation according to the measurement feedback of the instruction speed, the course, the UUV navigation speed and the course changing angular speed, and carrying out calculation based on a horizontal plane non-singular terminal sliding mode controller so as to acquire thrust of a UUV propeller and course changing torque of a rudder at the moment k, and executing the above steps in a cyclic manner so as to realize tracking control for the moving object at the next moment. According to the invention, a local planning strategy in the complex environment is combined with a UUV dynamics model, and the tracking accuracy of the moving object is ensured under the premise the UUV navigation safety.

Systems and methods providing adaptive path planning techniques utilizing localized learning with global planning are described. The adaptive path planning of embodiments provides global guidance and performs local planning based on localized learning, wherein the global guidance provides a planned path through the dynamic environment from a start location to a selected destination while the local planning provides for dynamic interaction within the environment in reaching the destination, such as in response to obstacles entering the planned path. Global guidance may combine an initial global path with history information for providing a global path configured to avoid points of frequent traffic conflicts. Local planning may utilize localized deep reinforcement learning to direct interactions of an automated vehicle traversing the global path in a dynamic environment, such as in response to obstacles entering the global path. Sequential localized maps may be generated for deep learning models utilized by localized training techniques.

The invention discloses a ridge-regression-extreme-learning-machine-based local path planning method for an outdoor robot. The method comprises the following steps: step one, collecting environment information and extracting a region of interest by using a laser radar; step two, constructing a composite map of multi-frame laser radar data by using a robot track calculation method; step three, carrying out data point clustering and logic identification of the laser radar, extracting a dynamic obstacle and road boundary, and identifying a passable area in a laser radar map; and step four, planning a hyperplane by using ridge regression extreme learning machine (RRELM) and integrating initial point and target point constraints of path planning, thereby obtaining a local planning path of a robot. With the method, the generalization performance of path planning learning by the machine is improved in an outdoor non-specific scene, so that the local path of the outdoor robot becomes smooth and thus convenient tracking can be realized.

The invention provides an intelligent vehicle local path planning method in a structured environment. The method comprises the following steps of positioning and map loading, obstacle information processing, coordinate system conversion and analysis, decision and replanning method, speed planning and local planning updating. Firstly, a corresponding local reference path is loaded by using a high-precision map and self-vehicle positioning information, then obstacle information is detected, coordinate system conversion is performed on the local reference path and the obstacle information, whether replanning is required is judged, and a local optimal path is obtained through a decision and replanning method. And finally, safe and stable driving is realized through speed planning and updatingof a local planning result. According to the invention, path planning, lane changing decision and speed planning are integrated, and the time performance of the intelligent vehicle local path planningmethod in the structured environment can be improved while the unmanned driving safety is guaranteed.

The invention discloses a path planning method based on multi-agent enhanced learning, and belongs to the technical field of aircrafts. Firstly, a global state division model of an air flight environment is established, and a global state transfer table Q-Table 1 is initialized, and the global state of a certain line is randomly selected to be used as the initial state s1; in all columns of the current sate s1, an epsilon-greedy algorithm is adopted to select a certain column to be recorded as a behavior a1; based on the selected behavior a1, the next state, a formula which is as shown in thespecification, of the current state s1 is obtained in the global state transfer table Q-Table 1; the specific element values corresponding to the current state s1 and the behavior a1 are updated in the global state transfer table Q-Table 1 according to a transfer rule of a Q-Learning algorithm; a formula which is as shown in the specification is updated to enter an inner layer cycle; and a local planning path corresponding to the updated state s1 is obtained by adopting the Q-Learning algorithm. The number of iterations of the outer-layer cycle is increased by 1 until N1, and global path planning of the aircraft in the air is completed. The aircraft can meet requirements of different environments, so that the survival rate and the task completion rate of the aircraft are improved, and theconvergence speed of the enhanced learning is improved.

The invention discloses a path planning method for a foot-type robot. An improved A* algorithm and a self-adaptive DWA algorithm are utilized to plan a reasonable path of robot motion, one characteristic of the improved A * algorithm is as follows, as long as a passable path from a starting point to a target point exists in the environment, the method can always be successfully searched. Comparedwith other local path algorithms, the method has very outstanding advantages, the thought of the fusion algorithm adopted by the method is to perform global path planning by using the characteristic,and then perform real-time local planning in combination with the adaptive DWA, so a final path is close to global optimum and has better dynamic adaptive capacity at the same time.

The invention relates to a motion planning method based on driving habit learning. The method comprises the following steps: step 1, a cloud processing terminal collects manual driving trajectories, and through an image processing, extracts preview points with road traffic attributes; step 2, the cloud processing terminal delivers the preview points in front of a vehicle in real time according tothe state of a self-driving vehicle; step 3, the self-driving vehicle generates an algorithm based on a set path, generates an alternate trajectory cluster between the vehicle and each preview point,and selects an optimal path according to a cost function. Compared to the prior art, the motion planning method based on driving habit learning has the following advantages: using artificial driving trajectories to generate local planning paths and getting rid of dependence on high-precision maps; new attributes are added to the preview points, and the way of generating is changed, so that the path of the local planning is more in line with the driving habits of people.

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 present disclosure provides distributed domain network planning systems and methods. The network planning systems and methods include a distributed domain network planning system that adapts planning concepts to networks operated by modern distributed control planes, such as ASON / ASTN, GMPLS, etc. The network planning systems and methods operate on a multi-domain network utilizing a control plane and local planning systems associated with each individual domain in the multi-domain network. The network planning systems and methods also operate on a single domain network utilizing a control plane and local planning systems associated with the single domain network. The network planning systems and methods build on a distributed control plane philosophy that the network is the database of record. There is significant operational value to distributing the planning function of a large network using the systems and methods disclosed herein.

The invention relates to a realization method of capacity expansion operation of 220-500kV lines. The transmission capacity of the lines can be improved by allowing the maximum permissible operation temperature of a lead wire to achieve 80 DEG C under the condition that the existing power grid resource is fully used; in addition, the transmission capacity of the lines is controlled by monitoring conditions such as different ambient temperatures where the lines are located and the real-time operation temperature of the lead wire, so that operation scheduling personnel can grasp operation conditions of the lines in real time; the transmission capacity of each unit line is improved under lower investment increase; and the method has good reference significance in improving the transmission capacity of the built-up line, lowering the investment of the newly-built line, and solving the problems of line corridor shortage, electric power construction and local planning contradiction, as well as frequent heavy load and overload of a residual section when certain areas or a certain section has N-1 failures.

The invention discloses a dynamic obstacle avoidance path planning and calculation method for an unmanned motorcycle. The method comprises following steps: establishing an equilibrium kinetics model and a kinematic model of the unmanned motorcycle; acquiring a passage for connecting an initial node and a target node on a grid map with an A* algorithm of adaptive resolution; acquiring real-time control quantity with a cone-based dynamic obstacle avoidance algorithm through combination of the equilibrium kinetics model and the kinematic model to avoid obstacles. With the adoption of a low-precision map in the method, the environment is shown in a multi-level manner, operating time of the algorithm is greatly shortened, the demand for real-time capability in path planning is met, besides, sensitivity to the obstacles is modulated to be stable with the cone-based local planning mode, and crossing of multiple obstacles is facilitated.

The invention provides a group task scheduling method for an automatic parking robot. The group task scheduling method comprises the following steps: (1) triggering task scheduling; (2) extracting application information of each task application, obtaining the position of a pickup node of each task application, and generating the position of a placement node of the pickup node; Acquiring the positions of all the current free automatic parking robots; (3) searching the shortest access path applied by each task; Generating a cost topological graph among the nodes so as to generate a node cost matrix; (4) carrying out global path planning on each current automatic parking robot, and providing expected arrival time for a client; And (5) adopting a multi-objective cost function in combination with the node cost matrix, evulating the passing cost and the operation cost, carrying out local planning on all the automatic parking robots with the minimum comprehensive cost for completing the batch of tasks as the target, and acquiring the task sequence of each parking robot. According to the method, the calculation speed of the whole plan can be improved to the maximum extent, and the operation cost is reduced.

The invention relates to the technical field of power systems, in particular to a multi-source data fusion-oriented power distribution network intelligent planning system, which comprises a data acquisition module, a region division module, a current situation analysis module, a load prediction module, a power balance module, a unit system planning module, a scheme comparison and selection moduleand a planning project library module; the advanced information communication technology is fully utilized, a power distribution network intelligent planning system which integrates drawing and data,interacts on line, is intelligent and efficient is built; intelligent area statistics, intelligent diagnosis analysis, intelligent scheme checking and intelligent scheme recommendation are achieved; visualized, on-line and intelligent operation of a power distribution network unit system planning full-service process is promoted to be achieved, and the efficiency and the quality of planning work are improved; through a planning algorithm, information such as power grid resources, geographic topography, gallery resources, environmental specialty, local planning and urban layout is widely fused,comprehensively considered and comprehensively calculated by taking a power distribution network power supply unit as an aperture, so that the scientificity and the reasonability of power distribution network planning are improved.

The invention discloses a path planning method and device and a computer readable storage medium and relates to the path planning field. The path planning method comprises the following steps of according to a distance between storage position nodes in an access task, generating a preliminary planning path with a shortest driving distance, wherein the preliminary planning path includes an access sequence of necessary nodes of a car; dividing the preliminary planning path into multiple segments by using the necessary nodes of the car in the preliminary planning path, wherein a starting point and an end point of each segment are the necessary nodes; and determining a local planning path with the smallest total access cost of each segment according to an access situation of each node so that the car completes an access task involved in the segment according to the local planning path. Under a condition that the car does not carry out large detour, the path of each segment is selected according to a current situation, task access efficiency of the car is improved, and task completion efficiency is further increased.

The invention provides a local dynamic obstacle avoidance path planning method for an unmanned vehicle, which solves the problems of target inaccessibility and local optimum under partial working conditions of a traditional artificial potential field method by improving the artificial potential field method, and enables the unmanned vehicle to overcome local oscillation, thereby being capable of planning a local planning path meeting obstacle avoidance requirements. According to the method, in the path planning process, vehicle kinematics and dynamics performance requirements are added, the collision safety priority is set, the smoothness of the planned path is guaranteed, and the tracking requirement of a lower-layer vehicle tracker is met; by analyzing the working conditions of complex dynamic obstacles in the road environment, obstacle avoidance planning can be performed for lateral dynamic obstacles and same-direction obstacles, and the two working conditions are combined, so that the planning algorithm meets obstacle avoidance under the working conditions of multiple dynamic obstacles, and the applicability and effectiveness of the planning algorithm are improved.

The invention provides a data-driven path planning method for an unmanned underwater vehicle, and is mainly applied to path planning of an underwater region traversal task. The method comprises the following steps: firstly, for a task area, carrying out environment modeling by utilizing a grid method, reading priori knowledge to update a modeling map, and generating an initial global path by utilizing initial map information; during execution of the task, detecting and receiving observation data in real time, carrying out online path planning analysis, deciding a global planning mode and a local planning mode based on a planning mode decision evaluation function F, if the global planning mode and the local planning mode are switched to the local planning mode, carrying out local planning according to a heuristic rule set, and returning to an initial global planning path after traversal of a local feature dense area is completed; according to the scheme, online guidance decision makingis carried out according to underwater real-time high-dimensional space observation data, global and local planning decision making is carried out on the basis of real-time detection conditions, an adaptive planning strategy is selected through planning mode switching, the method can be suitable for more complex environments, and the time efficiency is remarkably improved.

The invention provides an automatic parking method and device and electronic equipment. The method comprises the steps of: generating a global planning path according to a relative position relation of a target garage and an intelligent container truck, generating a local planning path corresponding to the global planning path, determining the front wheel rotation angle of the intelligent container truck according to the local planning path, and controlling the intelligent container truck to drive according to the front wheel rotation angle. By means of the automatic parking method and device,automatic parking of the intelligent container truck can be achieved.

The invention discloses a method and a device for determining a local planning path. The method and the device are used for solving a problem that the local planning path of automatic driving is not smooth in the prior art. The method comprises the following steps: firstly, taking the current position of a target vehicle as a start point, and according to coordinates information of a plurality ofpreset position points in preset distance on a preset planning path, determining the coordinates information of at least one other position point, except for the preset position points, on the presetplanning path; further determining planning point coordinates information corresponding to the preset position point according to the coordinates information of the preset position point and positionoffset corresponding to the preset position point; according to the coordinates information of the other position points and the position offset corresponding to the other position points, determiningthe planning point coordinates information corresponding to the other position points; and finally, fitting the planning point coordinates information to form the local planning path. Since the planning point coordinates corresponding to the plurality of preset position points ant at least one other position point are fitted to form the local planning path, the local planning path is more smooth.

The invention provides a multi-satellite situation awareness system distributed task planning method based on a contract net. The contract net comprises a global planning layer, an emergency planning layer and a local planning layer. The method comprises the following steps: step 1, a global supervisory satellite assigns a local supervisory satellite; 2, the global supervisory satellite carries out bidding on the sensing task, and the local supervisory satellite carries out task bidding; 3, after the global supervisor satellite receives the bidding result, matching between the sensing target cluster and the satellite cluster is carried out; 4, the local supervisor satellite carries out bidding on the sensing task, and the subordinate satellite carries out bidding; 5, after the local supervisor satellite receives the bidding result, the local perception target is distributed to the local satellite; 6, when an emergency task occurs, the emergency task supervisor satellite allocates the emergency task to each local planning layer; and 7, the local planning layer allocates the task to a satellite executing the task; According to the method, the problem of task allocation with multiple satellites, multiple tasks and multiple burstiness can be solved.

The invention discloses a mixed robot dynamic path planning method which is capable of being applied on the condition that a part of environment information is known, and unknown dynamic and static obstacles exist at the same time. Aiming at the conditions, the mixed robot dynamic path planning method comprises the following steps: utilizing a genetic algorithm (GA) as a global planning method to obtain global paths, and then conducting local planning by means of an improved artificial potential field method. According to the mixed robot dynamic path planning method, in local planning, speed and acceleration information of a robot and a barrier is considered, and therefore the mixed robot dynamic path planning method has better effects on processing dynamic path planning. In addition, effects of global planning path for local planning are also considered. The mixed robot dynamic path planning method is ease to achieve, robot paths obtained are more optimized, and meanwhile good flexibility is shown in the application.

The embodiment of the invention discloses a navigation method and device, a storage medium and equipment. The method comprises the following steps: determining a global planning path in a target map according to a current position of a robot and a final position in a navigation request; determining a corresponding initial local path in the global planning path based on the local planning range, wherein the local planning range corresponds to the boundary of a local cost map, and the local cost map comprises obstacle information in the local planning range; generating a corresponding local planning path according to the initial local path and a local cost map; and generating a navigation control instruction of the robot according to the local planning path and a preset robot model corresponding to the robot. By the adoption of the technical scheme, the generated navigation control instruction better conforms to the characteristics of the robot, the situation that the robot is stuck or vibrated in the process of moving according to the navigation control instruction can be avoided, and the smoothness of autonomous movement of the robot is improved.

The invention discloses a mobile robot path planning method capable of adaptively adjusting path point tolerance, which comprises the following steps of: performing global path planning according to atarget point, a current position of a robot and an environment map to obtain a global planning path of a global planning path point set; starting a local planner according to the global planning pathpoint set, and controlling the robot to move to the target point; calculating the positioning quality of the robot, and judging whether global planning path point tolerance adjustment is started or not; when global planning path point tolerance adjustment is started, calculating global planning path point tolerance according to the robot positioning quality, and inputting the global planning pathpoint tolerance into a local planner; and calculating, by the local planner, a local planning path to the next global planning path point according to the obtained global planning path point tolerance, and controlling the robot to move to the next global planning path point. The invention further discloses a mobile robot path planning device for self-adaptively adjusting path point tolerance. According to the invention, the path planning efficiency is improved on the whole.

The invention discloses a path planning method and device for a robot, and the method comprises the steps: carrying out the global path planning based on a path map in a moving range of the robot, and obtaining a global path of the robot from a current position to a target position; performing local path planning based on the global path and the current position of the robot to obtain a local path; recording information of a local path on a path map; and performing global path planning based on the path map with the recorded information so as to update the global path. The problem that the matching degree of the global planning path and the local planning path is too small in the prior art can be solved.

The invention discloses a driverless vehicle path planning method based on a three-layer architecture, which comprises the following steps: step 1, mapping: abstracting and mathematically describing aroad of an application scene, and representing and storing the road; and step 2, application: realizing path planning on the road network map by utilizing the established road network map of the specific scene according to task requirements. The invention has the beneficial effects that (1) global path planning and local path planning are comprehensively considered by utilizing a three-layer architecture, so that the global path planning and the local path planning are closely connected with a physical platform, more useful information is provided for the local path planning of the road, andthe planning performance is improved; an improved A-satellite search method based on a guide line is introduced into a third planning execution layer, and the guide line and key points are utilized, so that a local planning path meeting expectation is reserved to the greatest extent, and the characteristic of flexible obstacle avoidance is also kept.

The invention discloses a control method for an intelligent electronic control unit of a hybrid electric vehicle engine. The method belongs to the technical field of engine control. The control method for the intelligent electronic control unit of the engine comprises the steps that power-on initialization is carried out, and information is collected and interacted; a response module acts, and emergency processing is implemented; a cooperation module acts, and expected torque and an expected rotation speed are decided; and a local planning module acts, and corresponding torque and a corresponding rotation speed are obtained. The method disclosed by the invention is characterized in that an engine intelligent body kernel is disposed based on an original ECU of the engine; the method aims to grant an engine intelligent body with a capability of interaction and cooperation and enhance intelligence of the engine intelligent body; and optimized solution and calculation are carried out to the demanded torque and the demanded rotation speed of the engine by an internal control algorithm, so that performance of the engine is optimized.

The present disclosure provides distributed domain network planning systems and methods. The network planning systems and methods include a distributed domain network planning system that adapts planning concepts to networks operated by modern distributed control planes, such as ASON / ASTN, GMPLS, etc. The network planning systems and methods operate on a multi-domain network utilizing a control plane and local planning systems associated with each individual domain in the multi-domain network. The network planning systems and methods also operate on a single domain network utilizing a control plane and local planning systems associated with the single domain network. The network planning systems and methods build on a distributed control plane philosophy that the network is the database of record. There is significant operational value to distributing the planning function of a large network using the systems and methods disclosed herein.

The invention relates to a multi-layer global perception map construction method and system universal for structural and non-structural environments, and belongs to the technical field of map construction. According to the universal multilayer global sensing map construction method for the structural and non-structural environments, after a global topological map is constructed according to multi-source sensing information or an initial map, single-frame sensing maps are respectively established based on different sensing information in the multi-source sensing information, then, based on the global topological map, the single-frame sensing maps are fused to obtain multilayer sensing sub-maps, and the multilayer sensing sub-maps are constructed according to the obtained multilayer sensing sub-maps. And finally, the multi-layer perception sub-map and the global topological map are associated and stored to obtain an accurate global map, so that the complexity of local environment information in the map can be improved, and the problem that enough environment information cannot be provided for local planning of the unmanned vehicle in the prior art is solved.