44 results about "Rapidly exploring random tree" patented technology

A path planning apparatus of a robot smoothes a motion path while satisfying a constraint. In a configuration space where a manipulator of a robot performs a task, a Rapidly-exploring Random Tree (RRT) path which extends from a start point and reaches a goal point may be smoothed while satisfying a constraint to generate a stable motion path. Accordingly, path planning performance is improved and an optimal path satisfying a kinematic constraint may be rapidly obtained.

An apparatus for mine avoidance that enables a battle group commander to rapidly detect, classify, and identify mines, and form a tactical picture of mined areas. The system is enabled by a graphical user interface which generates a display of the minefield and an avoidance path which is calculated by a rapidly-explored random trees algorithm interacting with algorithms defining avoidance object spaces inserted by an operator in two or three dimensions and transit vehicle characteristics. The apparatus enables a method which establishes the parameters of an area representing a minefield. The area is then populated with obstacle spaces whose areas are functions of the probability of the existence of a mine and through which an avoidance route through the minefield may not pass. The start and end points of the avoidance route are entered on a graphic display of the minefield and an avoidance path there between is calculated and presented as an avoidance route.

The invention discloses a method and a system for planning a sea path of an unmanned ship based on an RRT (rapidly-exploring random tree) algorithm. The method comprises the following steps of obtaining data of a sea map, so as to obtain complete information of the sea map; according to the definition of a polygon of the sea map, displaying the conditions of the sea surface, and rasterizing the original vector data, so as to obtain a complete interface of the sea map; enabling a user to set passing points on the interface of the sea map, and planning the path within the preset time threshold value by an improved RRT algorithm, so as to obtain the final asymptotically optimal effective path; converting the final effective path into the practical longitudinal and altitude information, outputting the longitudinal and altitude information of turning points on the path, and providing for a power control system of the unmanned ship to use. The method has the advantages that the RRT algorithmis further improved, the path passing the multiple preset passing points is planned, and a path compression algorithm is applied so as to effectively reduce the path distance.

The invention relates to an unmanned plane locus planning method based on random sampling in a narrow space, which belongs to the unmanned plane locus planning field. The method comprises the steps of obtaining unmanned plane flight environment information; taking an original state of an unmanned plane, an object state and a 3D model of a flight environment as initial parameters of a locus plan; conducting road sign points sampling based on the 3D model of the flight environment; storing the road sign points in road sign point lists corresponding to a narrow space N and an open area U respectively; employing multiple rapidly-exploring random trees and connecting multiple RRT locus trees in pairs to form a fused RRT locus tree; then connecting the fused RRT locus tree with the original state and the object state of the unmanned plane, thereby generating a complete locus that connects the original state and the object state of the unmanned plane. According to the invention, the calculating efficiency of the unmanned plane locus planning in a narrow space can be effectively raised.

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.

A path planning apparatus of a robot smoothes a motion path while satisfying a constraint. In a configuration space where a manipulator of a robot performs a task, a Rapidly-exploring Random Tree (RRT) path which extends from a start point and reaches a goal point may be smoothed while satisfying a constraint to generate a stable motion path. Accordingly, path planning performance is improved and an optimal path satisfying a kinematic constraint may be rapidly obtained.

The invention belongs to the technical field of application of unmanned aerial vehicles, and discloses an RRT (rapidly-exploring random tree) route optimizing method of an unmanned aerial vehicle based on a greedy algorithm. The RRT route optimizing method comprises the following steps of using qinit as the current point qi, and initializing n to be 0; performing collision detection on a Q focus point qm-n since qi (n is [0,1,2 until to (m-i-1)]), and uniformly selecting points on the connecting line of qi and qm-n at certain intervals; judging whether the existence point is positioned on theobstacle or outside a map; when the existence point exists, turning to step 4; or else, turning to step 5; when the obstacle exists, namely that the connecting line passes through the fly-prohibitingarea, and n is equal to n+1, judging whether qi is qm-n-1 or not; when qi is qm-n-1, enabling i to be equal to i+1; or else, returning back; when the obstacle does not exist, connecting qi and qm-n, enabling qi to be equal to qm-n, and turning to step 6; judging whether i is equal to m or not; when i equal to m, finishing the program. The RRT route optimizing method has the advantages that when the RRT algorithm route of the unmanned aerial vehicle is planned, the route is reduced, the greedy concept is utilized, the result is the current optimum result, the number of route points is reduced,and the route is greatly optimized; the certain engineering value is realized on the application of route planning of the unmanned aerial vehicle or other robots.

The invention discloses a mobile robot autonomous exploration method fusing path information richness, and the method comprises the following steps of: acquiring environmental information in a sensingrange by a robot and changing an environment from an unknown state to a known state; generating a quick search random tree in an idle area of the known state, clustering boundary points of the quicksearch random tree by adopting a clustering algorithm to obtain centroid points, and meanwhile, detecting a grid state of the boundary points and removing invalid points; combining the information gain, the path cost, the path information richness and the boundary point information richness to construct a revenue function, and calculating a revenue value of the revenue function at each centroid point; selecting the centroid point with the maximum income value as a target point, and guiding the robot to move to the target point; and repeating the above steps until the whole environment is explored to obtain a grid map. According to the method, the path information richness and the boundary point information richness are added when the revenue function is constructed, consideration factors in the boundary point selection process are enriched, the perception uncertainty of the robot is reduced, and the exploration efficiency is improved.

A means for mine avoidance that enables a battle group commander to rapidly detect, classify, and identify mines, and form a tactical picture of mined areas. The system is enabled by a graphical user interface which generates a display of the minefield and an avoidance path which is calculated by a rapidly-explored random trees algorithm interacting with algorithms defining avoidance object spaces inserted by an operator in two or three dimensions and transit vehicle characteristics. The apparatus enables a method which establishes the parameters of an area representing a minefield. The area is then populated with obstacle spaces whose areas are functions of the probability of the existence of a mine and through which an avoidance route through the minefield may not pass. The start and end points of the avoidance route are entered on a graphic display of the minefield and an avoidance path there between is calculated and presented as an avoidance route.

The invention discloses a parafoil combined type flight path planning method in a complex environment. The method comprises: dividing a parafoil air-drop area into an obstacle area with obstacles andan open and flat circular landing area with a target point as the circle center; quickly searching a feasible track in the obstacle area by adopting a quick search random tree path planning algorithm,and only considering an obstacle avoidance task in the obstacle area under the search termination condition that the horizontal distance between the position to which the path extends and the targetlanding point is less than or equal to the radius of the circular landing area; and taking the termination state of track search in the obstacle area as the initial state of track planning in the circular landing area, and completing parafoil height control and headwind alignment tasks in the circular landing area by adopting the planning design of segmented homing. Obstacle avoidance and other requirements needing to be met by parafoil route planning in a complex environment are divided into two stages to be processed, meanwhile, smooth connection of the two route planning stages can be met,and parafoil route planning in the complex environment is achieved.

The invention discloses an articulated engineering vehicle path planning method based on a support vector machine, and the method comprises the following steps: 1, searching a proper path in an experiment scene through employing a target-oriented quick search random tree algorithm, and respectively marking real obstacles at two sides of the path as two different classification labels; 2, respectively adding a group of virtual obstacles near the starting point and the ending point of the vehicle, marking the virtual obstacles as two different classification labels, and obtaining a two-dimensional optimal zero potential curve and a maximum interval of the marked real obstacles and virtual obstacles through a support vector machine theory; 3, obtaining a plurality of key inflection points onthe two-dimensional optimal zero potential curve by utilizing a 'farthest reachable distance method '; 4, obtaining a planned path. In consideration of the interference of obstacles in reality and thespecial steering characteristics of the articulated engineering vehicle, a path capable of enabling the articulated engineering vehicle to directly track is designed.

The invention discloses a parafoil combined track planning method in a complex environment, which divides the parafoil airdrop area into an obstacle area with obstacles and an open and flat circular landing area with the target point as the center; In the area, the fast search random tree path planning algorithm is used to quickly search for feasible trajectories. The termination condition of the search is that the horizontal distance between the location where the path extends and the target landing point is less than or equal to the radius of the circular landing area. In the obstacle area, only Obstacle avoidance task: take the termination state of the track search in the obstacle area as the initial state of the track planning in the circular landing area, and use the segmented homing planning and design in the circular landing area to complete parafoil height control and headwind countermeasures. quasi-task. The invention divides the obstacle avoidance and other requirements that need to be met by parafoil track planning in complex environments into two stages, and at the same time can meet the smooth connection of the two track planning stages, and realizes parafoil navigation in complex environments. trail planning.