132 results about "Obstacle avoidance algorithm" patented technology

The invention discloses a mobile robot path planning and obstacle avoidance method and system. The mobile robot path planning method comprises the following steps: establishing a two-dimensional grid map by utilizing known obstacle environment information; in the two-dimensional grid map, establishing a global coordinate system at the place of a mobile robot, and setting a starting point and a terminal point of the mobile robot; determining the shortest path between the starting point and the terminal point through a jump point search algorithm, wherein the shortest path comprises a plurality of local target points connected in sequence; and in the process of controlling the mobile robot to move to each of the local target points, utilizing a local obstacle avoidance algorithm to avoid a dynamic obstacle. The mobile robot path planning and obstacle avoidance method adopts the jump point search algorithm to obtain the shortest path quickly, so that path search efficiency can be improved, and storage space is saved; and through the local obstacle avoidance algorithm, accuracy and real-time performance of mobile robot path planning and obstacle avoidance can be ensured, and autonomous navigation of the mobile robot is realized.

The invention relates to an unmanned ship dynamic obstacle avoidance algorithm based on a speed obstacle method and a dynamic window method. On the basis of the speed obstacle method, the unmanned ship dynamic obstacle avoidance algorithm considers the characteristic of the ship's large length-width ratio, uses the ellipses to represent the unmanned ship and the obstacle, and gives a method for solving the ellipse tangents; considering the kinematic performance of the unmanned ship, only the speed and direction that the unmanned ship can reach in a given time is used to calculate obstacle avoidance; the starting time of obstacle avoidance is determined by comparing the time of collision with the time required for the unmanned ship to avoid the obstacle, and the obstacle avoidance is endedby determining that the unmanned ship is safely moving in the desired direction of the navigation and moving in the direction of the target point; and the virtual obstacle is added according to the speed and movement direction error of the obstacle to reduce the influence of the obstacle motion information error. The unmanned ship dynamic obstacle avoidance algorithm can ensure that the unmanned ship can effectively avoid the static and dynamic obstacles encountered during the autonomous navigation on the sea surface.

The invention discloses a system and method for allowing a robot to follow a target person according to fused measuring information of multiple sensors. The system comprises a sensor detection part, a detection fusion part, a motion executing part and a host main control computer, wherein the sensor detection part is used for acquiring the positions of all similar persons in a visual field and transmitting all measuring information to the host main control computer; the detection fusion part is used for updating the position of a target person with a sampling-based joint probability filtering algorithm by using the host main control computer; and the motion executing part is used for generating a motion target according to current target person information and obstacle information and executing tracking and following. In the invention, measuring information of multiple sensors is fused, and collisionless following is performed on the target person in combination with the sampling-based joint probability filtering algorithm and an obstacle avoidance algorithm, so that self-following of the robot can be realized under the condition that interfering persons exist in a room, and the following robustness and tracking accuracy are increased simultaneously.

The invention discloses a target recognition and tracking system for an unmanned ship and a working method thereof. The system comprises a data acquisition unit, a sensing unit, a data processing unitand a main control unit; the data acquisition unit comprises a 3D laser radar, a transmitting transducer, a pair of hydrophones and an integrated navigation system, the sensing unit includes a 3D laser radar and two wide-angle cameras; the data processing unit is a quad-core industrial control computer, and the main control unit uses an STM32F4 processor and is in communication with a shore-basedupper computer through a wireless data transmission and image transmission module. The 3D laser radar and the vector hydrophone are adopted to scan obstacles on the water surface and below the watersurface, the industrial control computer analyzes the water surface obstacle position, and the hydrophone processor determines the position of the underwater obstacles. According to the position of the acquired obstacle, the industrial control computer adopts an obstacle avoidance algorithm to perform obstacle avoidance of the obstacles, the unmanned ship can avoid obstacles on and below the watersurface, and the goal of operation in water areas with complex underwater conditions is achieved.

The invention discloses a dynamic path planning method of a robot by combining an A* algorithm and a VFH obstacle avoiding algorithm. The method comprises steps of representing the environment where the robot is located into a grid map and searching a global initial path in a grid map by use of the A* algorithm; when the robot moves towards a target point along the initial path, judging whether the robot comes across an obstacle, if yes, using the VFH algorithm to carry out obstacle avoidance, or else allowing the robot to move towards the target point; during obstacle avoidance, firstly, setting a stage target point in the initial path, generating an obstacle avoiding path between the current position and the stage target point, moving for one step forwards, updating the current position,judging whether the space between the current position of the robot and the stage target point is shielded, if yes, re-calculating the obstacle avoiding path, or else, allowing the robot to move forone step forwards towards the stage target point along the obstacle avoiding path; and carrying out circulation until the robot reaches the stage target point, returns back to the initial path and continues to move towards a destination. By combining the two algorithms, efficiency of path planning of the robot is improved; and the autonomous navigation ability of the robot in the indoor dynamic environment is ensured.

The invention provides a Dubins path based obstacle avoidance control device and method for a driverless car. The device comprises a camera arranged outside the left A pillar of the driverless car, acamera arranged outside the right A pillar of the driverless car as well as a laser radar arranged on the roof of the driverless car. The method comprises the following steps: the radar performs positioning and speed measurement on obstacles entering a camera monitoring range; a sequence of an obstacle to collide with the smart car is determined with an obstacle avoidance algorithm; the smart carreplans the current obstacle avoidance path according to the new obstacle sequence to finish the obstacle avoidance operation. By arranging the cameras in the middles of the two A pillars of the driverless car, the problem about bind area of the driverless car is solved effectively, and perfect and accurate degree of information acquisition is increased; different obstacle avoidance judgment algorithms are adopted for different obstacles in driverless operation, and obstacle avoidance accuracy and precision of the driverless car are improved.

The invention discloses a path tracking obstacle avoidance and guidance method which comprises the following steps: (1) starting a guidance mode and executing a path plan to obtain a time sequence signal of a GVS (ground vehicle system) motion state variable; (2) executing a path tracking guidance algorithm, so as to obtain psidp and udp of DVSs; (3) monitoring a minimum distance lmin from the DVSs to the border of a safety circle family of an obstacle in real time and determining psid of the DVSs according to lmin; (4) calculating ud and rd of the DVSs; (5) judging a distance between the DVSs, wherein the GVS motion state keeps unchanged if the distance between the DVSs is equal to or greater than a threshold distance, otherwise, information of the GVS motion state moves downwards according to a time sequence; (6) substituting DVS guidance information into a control loop and updating DVS position information at a next time point; (7) measuring a position of an actual ship, judging whether the ship arrives at a destination, ending sailing if 'yes' and updating the time to enter into the step (2) if 'no'. According to the method, the guidance algorithm and an obstacle avoidance algorithm are combined with each other in a ship sailing process, so that a ship can be more accurately controlled to realize guidance and obstacle avoidance.

The invention discloses an AUV obstacle avoidance method in a dense obstacle environment, belonging to the technical field of intelligent control of autonomous underwater vehicles (AUVs). According tothe scheme of the invention, obstacle data detected by the sonar is processed by a contour convex algorithm and Bessel interpolation, the boundary of obstacles is simplified, and an obstacle avoidance track in a dense obstacle environment is designed by using a predicted guidance obstacle avoidance algorithm. Considering the complexity and diversity of the dense obstacles, the method combines obstacle avoidance parameters and obstacle avoidance rules to formulate an obstacle avoidance weight function to further obtain the global optimal predicted obstacle avoidance parameters, and finally, the corresponding obstacle avoidance guidance track points are formulated to enable the AUVs to achieve the goal of obstacle avoidance. Experimental data can show that the algorithm provided by the invention has better adaptability and obstacle avoidance execution efficiency for complex and dense obstacle environments, and can be better utilized in the underwater obstacle avoidance process of the autonomous underwater vehicles (AUVs).

The invention discloses an obstacle dodging method of UAV based on the velocity obstacle arc method. The obstacle dodging method mainly comprises the following steps: establishing a 2-dimensional barrier cone; establishing the velocity obstacle arc; defining the ranking of known obstacle threats and implementing the judgment for dodging activity; solving the arc parameters of the velocity obstacle; solving the dodging direction. And the known obstacles are classified into three levels of obstacle threats, the level I obstacle threat must be dodged; the level II obstacle shall receive the analysis as to the impact incurred from the UAV dodging process; the level III obstacle doesn't need to be dodged at all. The method can effectively avoid the negative influences brought by the negligence of 'potential dangers' characterized by the prior art of obstacle dodging algorithms, and can solve the complex tasks of dodging multiple obstacles, the method can hugely upgrade the self dodging capability of UAV under complex environment.

The invention discloses a tele-operation mechanical arm three-dimensional obstacle avoidance method based on virtual thrust. When obstacles exist on the tail end track of a tele-operation mechanical arm, the tail end track is traced according to an obstacle avoidance algorithm with the improved task priority. While the tail end of the mechanical arm gets closer to the obstacles, the virtual thrustis started to participate in the obstacle avoidance task. Under the condition that the task track tracing error of a tail end executor of the tele-operation mechanical arm is extremely small, the avoidance action of the mechanical arm for the obstacles is completed. After obstacle avoidance is achieved, while the tail end of the mechanical arm gets away from the obstacles, strength of the virtualthrust is gradually reduced, the tail end track continues to be traced, and the given work task is completed. By means of the algorithm, the tail end of the tele-operation mechanical arm can completethe given task in a three-dimensional complex environment, and meanwhile collision between rod pieces and the obstacles and collision between all joints and the obstacles are ensured. Under infusionof the virtual thrust, the defect that the task conversion algorithm is caught in the local obstacle avoidance dead zone is overcome.

The invention discloses a material carrying and moving composite robot. The robot comprises the following modules of a visual grabbing module, a Mecanum wheel-based moving control module, a laser navigation module and a laser and sonar obstacle avoidance module, wherein the visual grabbing module is used for grabbing information data of a target material, processing the information data, comparingthe information data with key characteristic information of the target material, and carrying out visual grabbing on the target material during the material carrying and moving process; the Mecanum wheel-based moving control module is used for controlling walking poses of the composite robot; the laser navigation module is used for conducting navigation and optimal path planning according to a global map and a local map, and conducting rough positioning of the position of a target station; and the laser and sonar obstacle avoidance module integrates a laser obstacle avoidance algorithm and asonar obstacle avoidance algorithm, and is used for obstacle avoidance during walking. The robot has the beneficial effects of being high in target material grabbing success rate, accurate in positioning and capable of automatically walking.

The invention discloses a fuzzy neural network control method for an omni-directional intelligent wheelchair to avoid an obstacle. An obstacle avoidance algorithm on the basis of an improved fuzzy neural network is combined with a strategy transforming mechanism and a state control variable is added to solve the problem of an obstacle avoidance condition with the motion direction out of an angle of a view field. The state control variable is adopted to record a motion state of a user in the moving process; a path planning result is guaranteed to be close to an original motion direction of the user as far as possible; automatic obstacle avoidance navigation of the omni-directional intelligent wheelchair is implemented. Compared with a conventional obstacle avoidance algorithm, when facing the same obstacle, the fuzzy neural network control method can well forecast the moving direction and the moving speed of the dynamic obstacle so as to rapidly plan an obstacle avoidance path; the obstacle avoidance method provided by the invention enables the wheelchair to carry out obstacle avoidance path planning according to the intention of the user to the greatest degree and not only optimizes the obstacle avoidance path, but also shows humanistic care for the user.

The invention relates to a fire-fighting UAV flight path planning method based an obstacle avoiding system. Ultrasonic distance-measurement sensors are arranged before, behind, on the left side and onthe right side of an UAV. When the measured distance is not less than a safety distance, an original control signal is output and the UAV will fly normally as planned. When an obstacle is found in one direction of the UAV, it is judged that collision is about to occur. A flying control system will take actions such as throttling back and tilting and flying towards the direction opposite to the obstacle according to the measured distance to avoid the obstacle. According to the invention, the obstacle avoidance algorithm designed in the invention has the advantages of good compatibility and high implementation efficiency compared with the traditional local obstacle avoidance planning algorithms (the artificial potential field method and the grid method). Based on the ultrasonic obstacle avoidance system, the adopted A* search algorithm can effectively reduce the computational load of an airborne controller, and can ensure that the UAV can quickly avoid obstacles in emergencies and planout new flight paths in time.

The invention discloses an intelligent bird expelling robot and relates to the field of robots. The intelligent bird expelling robot comprises a main body, and a detection device, a control device and a bird expelling device which are arranged on the main body, wherein the detection device is used for obtaining the position information of the main body and the information of obstacles on the advancing route of the main body and transmitting the position information of the main body and the information of the obstacles to the control device; the control device is used for conducting calculation and analysis according to the position information of the main body and the information of the obstacles in combination with a built-in angle potential field method obstacle avoidance algorithm, controlling the main body to operate according to analysis results and transmitting control information to the bird expelling device; and the bird expelling device is used for executing bird expelling actions according to the control information. The intelligent bird expelling robot has the advantages that the robot is mobile and flexile, two bird expelling operation modes, i.e. an autonomous patrol mode and a remote control mode are supported, the expenses in expelling birds and the labor intensity of working personnel are effectively reduced and the bird expelling effect is long-lasting.

The invention discloses an unmanned ship real-time obstacle avoidance algorithm based on deep reinforcement learning, and relates to the technical field of unmanned ships. According to the invention,a deep learning method is adopted to obtain image information, on the basis of an A3C algorithm, a network structure is optimized, obstacle avoidance information is enriched, and according to three requirements of path planning, obstacle avoidance and environment exploration and adaptation, the action space of an intelligent agent is re-standardized, and three kinds of environments are selected for training; and in combination with a GPU platform, the pre-training data is integrated into the deep neural network, so that the training efficiency is improved, and the real-time performance of thealgorithm is ensured. The result shows that the method shortens the training time by 59.3% and improves the efficiency by more than 71.7% while meeting the single processing speed requirement, and theperformance of the algorithm model in an unknown environment is effectively improved and is superior to the existing scheme.

The invention discloses an anti-dropping method and a device for a robot. The method comprises steps: a first distance between the robot and an obstacle detected by a sensor is acquired; whether the first distance meets a first condition is judged, wherein the first condition is used for indicating the robot to be in a determined falling distance range; when the first distance meets the first condition, a stop command is sent to the robot, wherein the stop command is used for indicating the robot to stop moving; and when the first distance does not meet the first condition, the robot is controlled to execute an obstacle avoidance algorithm, wherein the obstacle avoidance algorithm is used for controlling the robot to avoid the obstacle. The technical problem of a long braking distance of the robot is solved.

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 discloses a motion planning system and method of an industrial robot for smoothly grabbing a moving object. The motion planning system of the industrial robot for smoothly grabbing the moving object comprises a smooth grab model building module, an obstacle avoidance algorithm module and a smooth grab algorithm module. The smooth grab model building module is used for describing the relative relationship between the target position and an end actuator and the relationship between an obstacle and the arm plane of the industrial robot so as to generate an attraction vector and a rejection vector. The obstacle avoidance algorithm module is used for generating the motion for avoiding the obstacle so as to avoid the moving obstacle. The smooth grab algorithm module is used for generating the smooth grab motion according to a smooth grab algorithm in the mode of using the attraction vector and the speed of the moving object as the input under the condition that the obstacle leaves from a collision-free region, so that the smooth grab operation is achieved. By the adoption of the motion planning system and method of the industrial robot for smoothly grabbing the moving object, the purpose that the industrial robot smoothly grabs the moving object in the working space in the complex industrial environment can be achieved, and therefore the damage to the object to be grabbed is avoided.

The invention discloses a vehicle omni-directional following method based on UWB and a laser radar sensor. The method comprises the following steps: firstly, establishing a vehicle coordinate system,a laser radar coordinate system and a UWB sensor coordinate system, establishing a world coordinate system, and performing coordinate mapping between the world coordinate system and the vehicle coordinate system; then, enabling the vehicle to sense the position and posture of the vehicle in a world coordinate system with an artificial origin in real time; acquiring obstacle information by using the laser radar sensor, converting coordinates of an obstacle in a laser radar coordinate system into coordinates in the vehicle coordinate system, and constructing an occupied grid map by using a binary Bayesian filtering algorithm; and finally, enabling the vehicle to realize real-time following in any direction based on an occupied grid map and an automatic following and obstacle avoidance algorithm based on a parallel genetic algorithm. The method is simple in algorithm and high in positioning precision, and can realize omnibearing real-time following of the autonomous vehicle around the user.

The invention discloses a tour guide robot with an automatic navigation system. The tour guide robot comprises a base, anticollision radar, a robot main body, a heat bracket, a camera, a GPS positioning instrument, a voice broadcast, a display screen and a storage tank. A central processing unit, a human-machine interaction module, an intelligent navigation module, an obstacle detection module, awalk driving module, a wireless communication module and a working module are arranged in the robot main body. The human-machine interaction module comprises a voice recognition unit and an intelligent semantic analyzing unit. The intelligent navigation module comprises the GPS positioning instrument and the voice broadcast. The obstacle detection module comprises a 3d vision imaging sensor, an ultrasonic distance measuring sensor and an obstacle avoidance algorithm unit. The walk driving module comprises a driving motor and a walk driving mechanism. The working module comprises an image recognition processing unit and an explaining unit. The storage module comprises an electronic map and a database. The tour guide robot disclosed by the invention is convenient to use and can provide interesting and accurate tour guide services to tourists.

The invention discloses a humanoid intelligent robot system. The humanoid intelligent robot system is characterized in that the system comprises a robot body and a control system; the control system comprises a visual image acquiring module, a central processing module, a drive module and a sensing module; and a pre-planed real-time gait control algorithm and a binocular vision based obstacle avoidance algorithm are established in the central processing module to control motion of a robot. The gait of the humanoid robot can be accurately controlled through combined usage of the two algorithms,so that the humanoid robot better achieves the functions of obstacle avoidance and gait adjustment and the adaptability of the humanoid robot to a pavement is improved.

The invention discloses a three-dimensional obstacle avoidance method based on a preset route for a ground surface close-range autonomous exploration unmanned aerial vehicle. The method comprises thesteps of: when the unmanned aerial vehicle performs a ground surface close-range autonomous exploration task, according to demands of the task, selecting an artificial potential field method as an obstacle avoidance algorithm; presetting the route of the unmanned aerial vehicle, and establishing a coordinate system in a direction from a departure point in the preset route to a target point; improving the artificial potential field method and providing an obstacle avoidance principle, which is introducing a line potential field, so that the unmanned aerial vehicle can return to the preset routeafter the obstacle is effectively avoided; improving a repulsive potential field so that the unmanned aerial vehicle can autonomously escape a local minima; constructing an obstacle avoidance scene of the unmanned aerial vehicle performing the task according to a post-disaster scene, approximating the obstacle as a spherical shape, and constructing an obstacle scene; and in the obstacle avoidancescene, performing three-dimensional simulation and analysis on the trajectory and the speed of the unmanned aerial vehicle performing the task, and verifying the feasibility of the method. Accordingto the three-dimensional obstacle avoidance method based on the preset route for the ground surface close-range autonomous exploration unmanned aerial vehicle, the three-dimensional obstacle avoidanceof the unmanned aerial vehicle based on the preset route is realized, the trajectory of the obstacle avoidance process is smooth, and the speed of the unmanned aerial vehicle is stable.