10results about How to "Realize autonomous navigation" patented technology

The invention relates to a shoreline identification and course keeping method, system and device based on vision. The method comprises the following steps: acquiring an image of a water area in front of a ship in real time through a shipborne camera; processing the image by using an improved Spatial CNN model to extract a left shoreline and a right shoreline, fitting the left shoreline and the right shoreline into straight lines, and calculating an intersection point of the two fitted straight lines; taking the intersection point as a far-end piloting target point, and calculating a heading adjustment value according to the field angle of the shipborne camera and the position relation of the ship relative to the piloting target point; and inputting the heading adjustment value into a PID controller for PID adjustment so as to generate a steering engine control instruction, and driving the ship to automatically adjust the heading according to the steering engine control instruction. The method is suitable for a complex river environment without map and support of positioning equipment, and autonomous navigation and course control of the ship are realized.

The utility model discloses a tray type cargo carrying four-way shuttle vehicle, which belongs to the technical field of cargo carrying, and is characterized in that the tray type cargo carrying four-way shuttle vehicle comprises a base, a shell is arranged at the top of the base, an adjustable tray assembly is arranged in the shell, and a telescopic rotary detection assembly is arranged on the front side of the shell; the adjustable tray assembly comprises a main tray fixedly connected to the top of the shell, and the problems that an existing tray type cargo carrying four-way shuttle vehicle is generally fixed in tray size and inconvenient to adapt to carrying of cargos of different specifications, so that trays need to be replaced when the cargos of different sizes are carried or the carrying efficiency is low due to the fact that the trays cannot adapt to the cargos can be solved. The problems that the existing tray type cargo carrying four-way shuttle vehicle generally has a fixed detection range and is inconvenient to comprehensively sense long-distance and short-distance obstacles in a complex storage environment, so that the obstacle avoidance is not timely or a detection blind area exists, and the running safety of the shuttle vehicle is influenced are solved in order to solve the problems that the existing tray type cargo carrying four-way shuttle vehicle is inconvenient to comprehensively sense the long-distance and short-distance obstacles in the complex storage environment.

The visual navigation unmanned dining car comprises a dining car body and a visual navigation mechanism, access doors are hinged to the front side and the right side of the dining car body through hinges, and a mounting base is arranged in the middle of the front side of the lower end of the dining car body; the visual navigation mechanism comprises a protective cover, a two-dimensional code scanner, limiting grooves, limiting columns, a scraping strip, a cross scraping strip and a visual navigation assembly, the movable protective cover is arranged at the lower end of the outer surface of the mounting base, the two-dimensional code scanner is slidably connected to the middle of the interior of the mounting base through a fixing frame, and the limiting grooves are formed in the middles of the left side wall and the right side wall of the protective cover correspondingly; according to the unmanned dining car with the visual navigation function, linkage of opening and closing of the protective cover and lifting of the two-dimensional code scanner can be achieved through movement of the protective cover, self-cleaning of the scraping strip and the cross-shaped scraping strip is matched, and precise and reliable operation of the unmanned dining car is achieved in combination with multi-source visual navigation.

The application discloses a parking path planning method and device, a vehicle and a storage medium. The method comprises the following steps: after determining that the vehicle enters a target parking lot, acquiring environmental data of the vehicle, wherein the environmental data of the vehicle comprises spatial position information of a sensing target and spatial position information of an obstacle; acquiring an electronic map of a ramp region in the target parking lot based on the spatial position information of the sensing target, and acquiring an electronic map of a flat region in the target parking lot based on the spatial position information of the sensing target; and performing path planning based on the electronic map of the ramp region, the electronic map of the flat region and the spatial position information of the obstacle, so as to obtain a planned parking path of the vehicle. The technical scheme provided in the application embodiment can realize autonomous navigation and automatic parking in the target parking lot with the ramp region, and the intelligence of automatic driving is improved.

The invention relates to the technical field of unmanned aerial vehicles, in particular to an air-ground dual-purpose multi-rotor self-walking unmanned aerial vehicle which comprises a lower chassis, steering wheels are arranged on the four sides of the lower chassis, the four steering wheels are distributed in a rectangular array mode, a driving mechanism is installed in the lower chassis, the four steering wheels are all installed on the driving mechanism, a controller is installed on one side of the lower chassis, and the controller is connected with the controller. The upper end of the lower chassis is fixedly connected with an upper chassis, one side of the upper chassis is provided with a pan-tilt camera, and the upper end of the pan-tilt camera is provided with a laser radar. Through cooperation of the laser radar and the pan-tilt camera, the equipment realizes autonomous navigation and real-time obstacle avoidance, and meanwhile, real-time image data collected by the pan-tilt camera is transmitted to an unmanned aerial vehicle management platform; remote monitoring of the operation state and the working environment of the unmanned aerial vehicle is realized; in a scene with limited airspace, the controller can remotely issue a control instruction to drive the unmanned aerial vehicle to be automatically switched to a ground running mode, and accurate tail end delivery of goods is completed by means of the ground moving mechanism.

This utility model provides a delivery robot, including a chassis with a front and rear side on both sides along its length, and wheels mounted on opposite sides along its width. The wheels are driven by motors installed inside the chassis, and the motors are configured to drive the wheels on both sides of the chassis to rotate in opposite directions along its width. The chassis contains a driver, a power module, an embedded computing module, and a main control board, which is connected to the driver, the power module, and the embedded computing module. This delivery robot uses a depth camera to sense road conditions ahead, avoiding collisions. The motor-controlled wheel steering enables the depth camera to capture images horizontally. Since the depth camera has a large field of view in the vertical direction, the combination of the depth camera and wheel steering allows for comprehensive, blind-spot-free imaging.

This utility model provides a delivery robot. Wheels driven by motors are mounted on opposite sides of the chassis in the width direction. The motors are configured to drive the wheels on both sides of the chassis to rotate in opposite directions. An openable takeout box frame is located at the upper end of the chassis. An inner takeout box frame is located inside the outer frame and extends through the opening. A touch screen is located on the outer side of the movable takeout box. This delivery robot uses a fusion of depth camera and LiDAR to sense the surrounding road conditions. The depth camera, combined with wheel steering, enables omnidirectional shooting. Navigation and positioning are achieved through a BeiDou positioning module for precise location. Users can retrieve their takeout by inputting a pickup code via a voice interaction module and the touch screen, meeting the needs of different users. After receiving the correct pickup code, the inner takeout box frame rises, allowing the user to easily retrieve the takeout.

The application discloses a kind of full-automatic carrying robot of potted flower flowerpot, including walking and moving mechanism, flowerpot clamping mechanism, sensing and positioning system, navigation system and flowerpot placing system;Walking and moving mechanism is used to drive robot to move and adapt to topography fluctuation;Flowerpot clamping mechanism includes mechanical arm and clamping device, for performing the grabbing, lifting and releasing operation to flowerpot;Sensing and positioning system includes camera and laser radar, for identifying and positioning target flowerpot;Flowerpot placing system is electrically connected with walking and moving mechanism, flowerpot clamping mechanism and sensing and positioning system respectively, for controlling walking and moving mechanism and flowerpot clamping mechanism according to the information of sensing and positioning system, complete the autonomous grabbing and placing of flowerpot;Navigation system combines boundary line identification to carry out path planning and decision-making, realize the autonomous navigation of robot.The application realizes the full autonomous identification, grabbing, transport and placing of potted flower flowerpot by multi-sensor fusion and visual navigation technology.

This invention discloses a vision-based agricultural robot control system and navigation path extraction method, comprising: a vision processing module, a controller, a power supply module, a motor drive module, an infrared reflection sensor, an ultrasonic sensor, and a peristaltic pump module. Crop information is collected by a camera and transmitted to the vision processing module. The vision processing module processes the data to obtain the navigation centerline and transmits the required navigation parameters to the controller, thereby controlling the motor speed and achieving motion control of the agricultural robot. Simultaneously, the infrared reflection sensor detects crops, and the detected parameters are transmitted to the controller. The controller then controls the peristaltic pump module to spray pesticides, and the ultrasonic sensor performs obstacle avoidance to ensure the safety of the agricultural robot. This invention exhibits high accuracy, low processing time, good adaptability, and robustness in various crop environments.

The invention relates to the technical field of agricultural automation, in particular to an orchard-oriented graph-free autonomous navigation method based on laser radar, a plant protection method and a robot. By designing a navigation method based on laser radar point cloud and GNSS positioning attitude information, a vehicle can stably run along fruit trees without a global map and global path planning. Plant protection operation variable spraying control based on point cloud information: performing preprocessing and pre-segmentation on point cloud data acquired by a laser radar in combination with an autonomous navigation system, performing identification and segmentation on crops based on a three-dimensional semantic segmentation model, extracting crop canopy structure data, and further generating variable spraying control parameters, and precise pesticide application control in the plant protection operation process is realized.