242results about How to "Improve the effect of obstacle avoidance" patented technology

The invention discloses a picking method and picking robot device aiming at fruits which are in size of an apple and is similar to a sphere. The picking robot device comprises a mechanical actuating device, control system hardware and control system software. The mechanical actuating device comprises a picking mechanical arm, an underactuated manipulator, an electric sliding table and an intelligent mobile platform, wherein the control system hardware comprises an IPC (industrial personal computer), a motion control card, a data acquisition card, an AHRS (attitude and heading reference system), a coder, a monocular camera, a binocular camera, a force sensor, a slipping sensor and the like. During operation, the IPC fuses information of the coder, the AHRS, monocular camera components and an ultrasonic sensor to enable the mobile platform to independently navigate and avoid obstacles. A binocular vision system collects images of mature fruits and obstacles and extracts the characteristics of the images so as to realize obstacle avoidance of the mechanical arm and fruit positioning. Finally, the IPC fuses the information of the force sensor, the slipping sensor and the position sensor, thereby further reliably gripping the mature fruits and separating the fruits from fruit branches.

The invention discloses an automatic-navigation crawler-type mobile fruit picking robot which comprises a mechanical execution system and a control system and is characterized in that the mechanical execution system comprises an intelligent movable platform, a fruit picking mechanical arm and a two-finger type manipulator, wherein the intelligent movable platform comprises two crawler assemblies, an experimental facility fixing rack, a supporting stand column, a cross beam, a speed reducer and the like; and the control system comprises an industrial personal computer, a motion control card, a data collecting card, an image collecting card, an encoder, a GPS (global position system), a monocular zooming camera assembly, a binocular camera, a laser ranging sensor, a control circuit and the like. The automatic-navigation crawler-type mobile fruit picking robot integrates the fruit picking mechanical arm, the two-finger type manipulator, the intelligent movable platform and the sensor system, integrates multiple key technologies such as fruit identification, motion of the picking mechanical arm, grabbing of a tail-end executer, automatic navigation and obstacle avoidance of the movable platform, and the like, and really realizes automatic and humanized fruit picking.

The invention relates to a method for planning a path for a mobile robot based on environmental modeling and a self-adapting window, which relates to a method for planning a real-time path for the mobile robot. The method comprises the following steps of: performing modeling and analysis on a multiple constraint local environment; performing passable analysis; performing safety analysis; performing motion smoothness analysis; performing goal-directed analysis; and performing path planning by adopting the self-adapting window. Because the method has better environmental suitability and obstacle avoiding capacity, the method obtains good safety and reachability, has high calculation real-time property, so the method solves the problem that the mobile robot generates an obstacle avoidance path in real time in an uncertain complex environment, provides a path selection method with optimized integration, better meets the requirements on obstacle avoidance for the mobile robot, realizes the real-time path planning and control of the robot, and provides an effective collision-less path planning method for the navigation application of the mobile robot.

The invention discloses a map construction and navigation method, a device, and a system. The map construction and navigation method is used for identification of detected barriers, determining the types of the barriers in a plurality of types based on identification results, constructing a map to mark the barriers, and recoding the types of the barriers. In navigation, when new barriers are detected on a current path, obstacle avoidance treatment is carried out based on the types of the new barriers. The invention also provides the corresponding device and the system. According to the map construction and navigation method, constructed maps are provided with type meanings used for describing barrier characteristics, different composition strategies and avoiding strategies can be adopted for barriers of different types, and better practicality and flexibility are achieved.

The invention provides an intelligent automatic following method based on a visual sensor. The method comprises the steps that the visual sensor collects the environment information of a suitcase relative to the owner of the suitcase, and sends the environment information to a data processing module; the data processing module identifies the suitcase owner to acquire the coordinate position of the suitcase relative to the owner of the suitcase; the data processing module sends an instruction to a drive module to drive the motor of left and right rear wheels of the suitcase to run; the suitcase and the suitcase owner are kept in a set range through a PID controller; and a main controller enables the suitcase and the suitcase owner to keep synchronization by predicting the next step of the suitcase owner. The invention further discloses a system and the suitcase, wherein the system and the suitcase use the method. According to the invention, the position of an obstacle is determined by directly using depth information acquired by the visual sensor to avoid the obstacle; the method has the advantages of high recognition accuracy and good obstacle avoiding effect, and is less susceptible to an external environment; and especially a variety of obstacle avoiding ways such as ultrasonic are combined to further improve the recognition accuracy and obstacle avoiding effect.

The invention provides a floor sweeping robot, an obstacle avoidance method, and a readable storage medium. The floor sweeping robot includes a camera, a processor and a driver. The obstacle avoidance method includes the steps: utilizing the camera to take images of the ground in the driving direction of the floor sweeping robot, performing line detection on the images after zooming and grey processing, identifying obstacles, determining the world coordinates of the obstacles to perform predetermination according to the world coordinates of the obstacles, calculating the driving direction and speed of the floor sweeping robot at the next moment, and driving the floor sweeping robot to avoid the obstacles. The floor sweeping robot has the advantages of relatively more accurate obstacle avoidance targets and better obstacle avoidance effect.

The invention discloses a hospital service robot based on a cloud platform and a method. The robot is provided with a plurality of cabinets for containing different medicine materials, updates a planned walking route in real time according to a designated walking route and in combination with the data of a ultrasonic sensor, delivers the medicine materials to designated destinations, receives acquired information of a fingerprint recognition device, identifies the acquired information and then transmits the acquired information to the cloud platform via a wireless communication module, receives information transmitted from the cloud platform, and opens a corresponding cabinet after determining the information a corresponding medical care worker in order to automatically dispense the medicine materials. The hospital service robot and the method can greatly reduce the labor intensity of nurses.

The invention discloses a snakelike mechanical arm, wherein a rigid rod is taken as a central strut, a flexible rope is adopted for driving, a power supply and a driver are arranged on a snakelike arm base, and the snakelike mechanical arm has the advantages of compact structure, strong flexibility and large rigidity. Different actuators or sensors are arranged on a tail end of the snakelike mechanical arm so as to complete different operation tasks, such as detection of non-structural narrow spaces of cabins, carriages and the like, as well as gluing, detection, chip removal, redundancy pickup and the like of inner cavities of airplanes.

The invention discloses an automatic parallel parking path planning method based on two sections of second-order Bezier curves. The method comprises the steps of obtaining target parking space information to determine a parking target position and establishing a global coordinate system by taking the parking target position as an original point; constructing a parking trajectory segmentation judgment model to determine the number of planned trajectory segments, planning the end position range of the first section of trajectory, determining the start point, the end point and the control point of each section of planned trajectory, performing path planning by using a second-order Bezier curve, performing monitoring at set intervals, and adjusting the planned trajectory by using a dynamic adjustment planning trajectory method. According to the method, the requirement for the initial pose of the to-be-parked vehicle is lowered, and the environmental adaptability of the path planning methodis improved; the vehicle can be driven into the planned area manually through simple adjustment, so that the cost is reduced, and the method can be applied to medium and low-grade vehicles; control points of parking trajectory planning are easy to determine, a trajectory generation algorithm is simple, and the path curvature is continuous. The correction difficulty of the track error is reduced,and the obstacle avoidance performance and parking efficiency of the vehicle are improved.

The invention provides a fleet formation control device and a formation control method based on an information physical network, wherein a fleet comprises navigation vehicles (Ri) and following vehicles (Rj); a fleet intelligent obstacle avoiding device arranged on each vehicle of the fleet comprises a vehicle external sensor module (1), a GPS positioning module (2), a wireless communication module (3) and a central processing unit module (4); the central processing unit module (4) used for realizing communication and application protocols receives speed and position information of the vehicle through the GPS positioning module (2) and processes the speed and position information; and when an infrared sensor (5) senses that an obstacle object exist in the front, the central processing unit module (4) obtains linear speeds and angular speeds of the navigation vehicles (Ri) and the following vehicles (Rj) by means of formula calculation, and the navigation vehicles (Ri) and the following vehicles (Rj) send the obtained linear speeds (vj) and angular speeds (wj) to a vehicle controller (7) through a CAN bus so as to ensure the fleet to advance in a formation manner.

The invention discloses an unmanned boat obstacle avoidance method based on collision hazardous area prediction. The method comprises according to the position and speed of the unmanned boat at the current moment and the position and speed of an obstacle, determining a collision risk, calculating a possible collision area, and then projecting the area onto a grid map to achieve an obstacle avoidance purpose by enabling the unmanned boat to avoid the area (hazardous area). The method combines an obstacle avoidance rule of sea vessels, uses a Theta* search algorithm to carry out path planning, and finally obtains the unmanned boat driving path in order not to collide with the obstacle and to meet the obstacle avoidance rule at sea. A simulation experiment proves that the method has a good obstacle avoidance effect.

An embodiment of the invention provides an automatic driving method, an automatic driving device, equipment and a storage medium. The automatic driving method comprises the steps of acquiring a radarpoint cloud and images of the same scene acquired by means of radar equipment and photographic equipment which are carried on automatic driving equipment; and detecting the radar point cloud and the images based on a preset obstacle detection model to obtain information of an obstacle in the scene, and executing a corresponding automatic driving strategy based on the information of the obstacle, so that a moving trajectory of the automatic driving equipment avoids the obstacle. The automatic driving method and the automatic driving device can realize the obstacle avoidance operation in the automatic driving scene, particularly can reduce the workload of manually labeling training samples of the obstacle detection model, improves the labeling efficiency, improves the precision of the obstacle detection model, and enhances the obstacle avoidance ability of automatic driving.

The invention discloses a soft landing relay obstacle avoiding method which is used for completing soft landing of a celestial body through two matched stages, namely a rough obstacle avoiding stage and a fine obstacle avoiding stage, wherein in the rough obstacle avoiding stage, a visible-light camera is used for carrying out rough detection on a larger range and larger obstacles to remove largeobstacles which directly threaten landing safety; and then the surface of the celestial body is subjected to accurate three-dimensional obstacle detection by utilizing laser scanning in a safe area selected in the rough obstacle avoiding stage so as to obtain and remove obstacles with smaller dimensions and ensure landing safety to the maximum extent. The soft landing relay obstacle avoiding method disclosed by the invention has good autonomy and high reliability, can be used for soft landing detection of the celestial body with more complicated terrain, and is especially applicable to soft landing of deep-space unmanned celestial bodies in a longer distance; the soft landing relay obstacle avoiding method greatly improves the obstacle avoiding capacity and lengthens the obstacle avoidingdistance, and improves the landing safety; and the soft landing relay obstacle avoiding method reduces the technical index requirement on sensors, reduces the difficulty in research of visible-light/laser imaging sensors, and is beneficial to engineering application.

The invention relates to a humanoid robot, which is a movable mechanical device consisting of a head, a body part, arms and legs, and is matched with a circuit control system and a sensing system to realize humanoid movement. Each moving joint of the humanoid robot is realized by closely matching a motor output torque with each movable member. The humanoid robot can be used for finishing various types of operation instead of people and expanding the capabilities of human beings on multiple aspects, and can be widely applied to a plurality of fields such as service, medical treatment, education, entertainment and the like.

Provided is an autonomous driving vehicle, and an infrastructure for supporting autonomous driving thereof. The autonomous driving vehicle of the present invention receives information obtained by converging sensor information (for example, infrastructure sensor information and traffic information) based on an infrastructure and vehicle sensor information selected by the infrastructure from the infrastructure positioned at the outside. Accordingly, the autonomous driving vehicle of the present invention may overcome a limitation of vehicle-based autonomous driving, thereby improving obstacle avoidance performance, solving inaccuracy of a sensor, and decreasing frequent setting of a path.

The invention relates to the field of mechanical arm kinematics control and planning, and discloses a collision detection mechanical arm path planning method based on an improved ant colony algorithm.The improved mechanical arm path planning method comprises the following steps of: performing kinematics analysis of a mechanical arm according to an established mechanical arm model, and completinga space mechanical arm kinematics inversion solution by correcting a Schmidt QR decomposition inversion method; considering the distribution condition of obstacles around selectable nodes, and improving the state transition probability of the ant colony algorithm; performing collision detection between the mechanical arm and the obstacle and between the mechanical arm and the mechanical arm connecting rod by adopting a cuboid envelope method; and searching an optimal path in the working space by the mechanical arm end executor, carrying out joint corner solving and collision detection, and finally realizing mechanical arm path planning. According to the method, a traditional mechanical arm path planning ant colony algorithm is improved for the mechanical arm path planning problem, the improved algorithm has a high convergence speed, the obtained path track is reasonable, and the obstacle avoidance effect is good.

The present invention provides an ultra-wideband-based automatic following fast positioning method. The method mainly comprises the following steps of: calculating a relative distance between two basestations and a tag by measuring timestamps of transmitting and receiving data packets between the tag and the base stations, estimating an optical value of the distance through multiple filtering, rapidly calculating a distance from a platform equipped with the base stations to the tag and a relative angle, locating the position of the tag, and calculating the distance and the relative angle. Theultra-wideband-based automatic following fast positioning method achieves a fast and efficient positioning mode and reduces the calculation amount.

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 discloses a bionic snake-like robot and a method, and belongs to the field of bionic robots. The snake-like robot comprises two parts including a drive box (1) and a multi-joint snake-like arm (2), wherein the drive box (1) is composed of drive motors, winches and supporting plates, and the multi-joint snake-like arm (2) is composed of joint units, universal joins and steel wire ropes. The series-connection structure design of the universal joints (9) is adopted in various joint units (8) of the bionic snake-like robot, and the joint units (8) are driven through the steel wire ropes (10) evenly distributed along the circumference; and the structure design that steel wire rope through holes are evenly distributed in a parse manner in the sector direction along the circumference, and wiring is conducted is adopted in the joint units (8). The bionic snake-like robot has the characteristics that the structure is simple, the redundancy freedom degree is high, flexibility is good, and the narrow space obstacle avoiding capability is high.

The invention provides a road identification and path optimization AGV (automatic guided vehicle) based on machine vision and a control system of the AGV. By the aid of machine vision, a speed-adjustable motor, an ultrasonic module and the like, automatic road identification and optimal path selection of the AGV are realized. A camera is used for acquiring road images, a main control system is used for identifying features points simply built on a movement path by PA (polyamide) adhesive paper, the path is automatically identified, the optimal path is selected by a Dijkstra algorithm, task signals in the driving process are transmitted by a remote control module, obstacles are detected by the ultrasonic module to trigger audible and visual alarm, and emergency brake is realized.

The invention discloses an implementation method for the rapid great pitch angle change motion of a pectoral fin paddling type robotic fish, which includes the following steps: (Step 1) a rapid pitch kinematics model is created; (Step 2) a phase oscillator model with the characteristic of time and spatial asymmetry is created; (Step 3) a CPG (Central Pattern Generator) control network structure is created; (Step 4) a rapid pitch motion control system is created. The implementation method adopts multi-drive coordinated pectoral fin and tail motion, the robotic fish can generate pitch moment far greater than moment generated by the deflection of a swimming bladder or a single tail fin by means of the kinetic characteristic of spatial and time asymmetry, consequently, the implementation method can realize the rapid pitch (pitch angle change is greater than 60 degrees) motion of the pectoral fin paddling type robotic fish, and the obstacle-crossing and obstacle-avoiding ability of the robotic fish facing vertical wall type obstacles underwater is greatly enhanced.

The invention discloses an intelligent networked four-wheel independent steering and independent driving electric vehicle emergency obstacle avoidance system, and aims to improve the obstacle avoidance capability of the electric vehicle by utilizing a vehicle-to-vehicle interaction technology. According to the obstacle avoidance system, different obstacle avoidance modes can be switched according to the risk degree of collision between the vehicle and a front obstacle under three conditions, namely normal functions, partial function obstacles and function failure, of the vehicle-to-vehicle interaction module carried by the vehicle. The vehicle can receive motion information of other vehicles through the vehicle-to-vehicle interaction module so as to make a more reasonable obstacle avoidance decision; other vehicles can also receive warning information sent by the vehicle, and favorable conditions are created for obstacle avoidance of the vehicle. Particularly, under the emergency condition that the vehicle cannot avoid collision through braking measures, the emergency obstacle avoidance system receives path planning information of other vehicles through the vehicle-to-vehicle interaction module, and judges whether the possibility of lane changing obstacle avoidance exists through a decision module, so that the collision risk is further reduced.