13 results about "Rapidly exploring random tree" patented technology

The invention relates to the technical field of unmanned aerial vehicle flight attitude control, in particular to an unmanned aerial vehicle flight attitude adjustment method and system based on reinforcement learning. Comprising the following steps: constructing a dynamic environment grid map based on a digital map and a real-time semantic segmentation result, and generating an initial track by introducing a space-time constraint fast search random tree algorithm; collecting flight state information, environment perception information and image definition indexes of the unmanned aerial vehicle, inputting the flight state information, the environment perception information and the image definition indexes into a space-time attention encoder, and generating a semantic-fused state tensor; performing importance distribution on the state tensor through an information entropy weighting mechanism to obtain a weighted state vector; inputting into a Meta-SAC model with meta-learning ability, and outputting a target flight reference pose and an LQR controller dynamic gain coefficient; the control module drives the LQR controller to generate a flight control instruction based on the information; and a reward function is constructed based on the image quality and the energy consumption efficiency, and a reinforcement learning strategy is fed back in real time.

The invention discloses a UUV path planning method based on an improved fast search random tree. The method is suitable for the fields of autonomous navigation, task execution, obstacle avoidance, safety guarantee and the like of UUVs. The method comprises the following steps: S1, determining an initial step length; dynamically adjusting the initial step length according to the scale of the task space and the complexity of the environment; and S2, carrying out target bias sampling. In the sampling process, according to a set bias threshold value, an algorithm biases a sampling point to a target area according to a certain probability, so that the target guidance quality of search is enhanced; and S3, removing redundant points. A Dijkstra algorithm is adopted to simplify a path, unnecessary turning points are removed, and more nodes are inserted into the path to improve the intensity of the path, so that the optimization space is increased. Then, redundant point removal is executed again, so that the path is further simplified; and S4, smoothing the path. Through the maximum curvature constraint, it is ensured that the turning angle of the path does not exceed the preset limit, meanwhile, in combination with a polynomial fitting method, abrupt turning in the path is reduced, and the smoothness of the path is improved.

The invention discloses a path determination method and device of a mechanical arm, a robot, a storage medium and a computer program product. The method comprises the steps that the working space of the mechanical arm and the starting point and the target point of the path of the mechanical arm are obtained; estimating a path cost and determining a path cost threshold according to the starting point and the target point of the path; a fast search random tree is constructed bidirectionally from the starting point and the target point of the path, and an initial path meeting a path cost threshold value is obtained; and key points of the initial path are extracted, the extracted key points of the initial path are updated, and an optimized path of the initial path is obtained and serves as the path of the mechanical arm, so that the path of the mechanical arm is determined. According to the scheme, the path cost is estimated, the path cost threshold value is determined, the bidirectional fast search random tree is constructed to determine the initial path, the key points of the initial path are extracted and updated to optimize the initial path, the path with the low cost can be fast obtained, and the flexibility and the real-time performance of path planning of the mechanical arm can be improved.

A method and control arrangement (10) for providing a path of an autonomous vehicle (1) in a defined environment, the autonomous vehicle (1) having certain dynamics and kinematics. The method comprises obtaining (S1) a starting configuration and a goal configuration for the autonomous vehicle and searching (S7) the defined environment using a Rapidly Exploring Random Tree, RRT, algorithm to find a feasible path from the starting configuration to the goal configuration. The searching comprises generating random configurations in the defined environment using a random sampler taking into account driving constraints implied by the dynamics and kinematics of the autonomous vehicle, generating one or more new goal configurations in the vicinity of the goal configuration using a goal random sampler, and using the one or more new goal configuration for finding the feasible path with the RRT algorithm. The method further comprises providing (S8) a path for the autonomous vehicle using a result of the searching (S7). The disclosure also relates to a vehicle (1) comprising the control arrangement (10).

The invention relates to a redundant snakelike mechanical arm path planning method based on an AC-RRT (Angle Constraint Rapidly-Exploring Random Tree) algorithm, and provides an AC-RRT (Angle Constraint Rapidly-Exploring Random Tree) algorithm. A step length and target offset probability determination method is provided according to the obstacle distribution relation in the space, and the adaptive capacity of the algorithm is improved; a random tree extension angle constraint model is provided according to the mechanical structure of the snakelike mechanical arm, so that a planned path better conforms to the spatial motion characteristics of the mechanical arm; and finally, a target point greedy query method is introduced, the path search time is shortened, and redundant nodes are reduced. Matlab simulation is carried out, performance differences between RRT and RRT-connect algorithms are compared, V-REP software is combined with a mechanical arm model to carry out analog simulation on the algorithms, and the feasibility of the algorithms is verified.

The global path planning method based on potential energy guidance fast search random tree algorithm belongs to the technical field of intelligent vehicle path planning, and solves the technical problem that the traditional fast search random tree algorithm can cause the planned trajectory to travel close to the obstacles. First, the position of the obstacles and the start and end positions are determined through the two-dimensional space map planned by the vehicle. For any point in the map, the potential energy value thereof is calculated, and the potential energy values of all the obstacles are superimposed to obtain the potential energy value of the arbitrary point. The potential energy values of all the arbitrary points in the two-dimensional space map are obtained in the same way. Then, the potential energy values of each point of the whole map are normalized to obtain a potential energy map matrix. The potential energy map matrix is introduced into the fast search random tree algorithm, a potential energy threshold is set, and the randomly generated points are screened. After screening, the potential energy values are introduced into the cost function of the fast search random tree algorithm, and rewiring optimization is performed, so as to perform vehicle path planning.

The invention discloses a global path planning method based on a potential energy guided fast search random tree algorithm. The method belongs to the technical field of intelligent automobile path planning. The technical problem that a traditional fast search random tree algorithm causes a planned track to run close to an obstacle is solved. The method comprises the following steps of: determining the positions of obstacles and the starting point and terminal point positions through a two-dimensional space map planned by a vehicle, calculating the potential energy value of any point in the map, superposing the potential energy values of all the obstacles to obtain the potential energy value of any point, and obtaining the potential energy values of all the points in the two-dimensional space map according to the same method; normalizing the potential energy value of each point of the whole map to obtain a potential energy map matrix; and introducing the potential energy map matrix into a fast search random tree algorithm, setting a potential energy threshold, screening random generation points, introducing the potential energy value into a cost function of the fast search random tree algorithm after screening, and performing rewiring optimization, thereby performing vehicle path planning.

The invention relates to a robot path planning method and device, robot equipment and a medium, and belongs to the technical field of robot motion control path planning, and the method comprises the steps: 1, exploring a motion path of a robot in a constructed target map space based on a preset rapid search random tree, obtaining an offset sampling point in the target map space based on a fixed direction offset strategy; 2, taking the direction vector of the bias sampling point as a reference direction, and adopting a four-direction discretization strategy to determine an exploration direction; 3, decomposing the exploration direction by adopting a layered exploration strategy, and expanding the random tree based on the decomposed exploration direction; and 4, when the random tree is not expanded to the connectable range of the target point of the robot, repeating the steps 1 to 3 until the random tree is expanded to the connectable range of the target point, and obtaining a path planning solution of the robot, thereby improving the path planning efficiency in the narrow scene.

A method, an apparatus for continuous path planning, a computer device, and a storage medium. The method designs the optimization function based on the rapidly exploring random tree to plan path, and the optimal path is screened out from the random tree according to target function including the reconstruction completeness optimization function, the path effectiveness optimization function, and the path smoothness optimization function when the reconstruction degree of the preset sampling points is determined to meet the preset requirement.

A kind of seven degrees of freedom manipulator motion planning method based on hybrid multi-policy RRT, adaptive step growth strategy is introduced to fast search random tree, the node growth step length of fast search random tree in different subspace in the process of generating path is obtained;Subspace incremental sampling strategy is introduced to fast search random tree, so that fast search random tree tends to sample in unexplored area;The breadth-first search strategy is introduced to fast search random tree, the search result is refined, and invalid nodes are removed.The present application can generate different length of node growth step length according to the different obstacle density in the environment, quickly cover unknown area and get the effective motion path between initial point and target point by introducing three strategies.The present application significantly improves the motion planning efficiency of manipulator in unstructured environment, can meet the high efficiency, fast response demand in the process of precision operation, and provides convenience for subsequent speed planning and control of manipulator.

The application discloses an improved fast search random tree path planning method based on energy consumption constraint, and the algorithm is as follows: modeling according to actual geographic information, drawing a digital elevation model of a required map, determining a sampling mode of sampling points according to whether an initial feasible path can be found from a starting point to an ending point, determining a node expansion step length according to a dynamic step length strategy, generating a new expansion node, introducing a slope proportion coefficient by using a dimension reduction idea, adding an energy consumption constraint condition to a heuristic function, generating a logical path length as an optimal path judgment standard, reconnecting and rewriting a node parent node, and reaching the target point when a distance from the new node to the target node is less than a threshold value. The application effectively reduces randomness and blindness of the sampling points, reduces a search space and a range of a search tree, considers an energy consumption influence of an elevation slope on a robot driving process, makes a planned path have the characteristics of being relatively flat and low in energy consumption, and improves a working efficiency of the robot.

This application relates to a parking space search method, apparatus, and vehicle, belonging to the field of vehicle technology. The method includes: constructing a global map based on perception information within the vehicle's perception range when the vehicle's location is not covered by a high-precision map; determining a target exploration point; wherein the target exploration point is the optimal exploration point selected from the perception boundary points in the global map; planning a target path from the vehicle's location to the target exploration point on the global map based on a fast search random tree algorithm, using a first preset condition; wherein the first preset condition is used to make the tree nodes sampled by the fast search random tree algorithm tend to fall within the neighborhood of the target exploration point; and controlling the vehicle to cruise along the target planning path to search for available parking spaces. Thus, parking space search can be achieved efficiently, accurately, and intelligently even without high-precision map coverage.

The invention relates to a parking space searching method and device and a vehicle, and relates to the technical field of vehicles, and the method comprises the steps: building a global map based on the sensing information in a vehicle sensing range corresponding to a vehicle position under the condition that the vehicle position is not in a coverage area of a high-precision map; determining a target exploration point; wherein the target exploration point is an optimal exploration point selected from sensing boundary points in a global map; based on a first preset condition, adopting a fast search random tree algorithm to plan a target planning path from the vehicle position to the target exploration point on the global map; wherein the first preset condition is used for enabling tree nodes sampled by the fast search random tree algorithm to tend to fall into a neighborhood of the target exploration point; and controlling the vehicle to cruise along the target planned path to search for available parking spaces. Therefore, parking space exploration can be efficiently, accurately and intelligently realized under the condition of no high-precision map coverage.