140 results about "Autonomous robot" patented technology

A method for greatly reducing data storage requirements of autonomous robots capable of product inventory is described. Instead using high resolution images for label identification and position tracking, a lower resolution map can be searched. Human or machines can identify position of labels, and via a reverse mapping, the corresponding position of a label on the high resolution image can be identified. Except for those portions of the high resolution image showing a label, most of the high resolution image can be discarded. Further processing on the limited image subset can be used to read the labels.

The invention discloses a robot automatic obstacle avoidance target recognition system and method, and relates to the technical field of autonomous navigation, and the method comprises the steps: obtaining and fusing an obstacle boundary map, a passable region mask and a dynamic target hot area map, and outputting an environment feature map; inputting the environment feature map into a pre-trained deep reinforcement learning model, and generating an obstacle avoidance instruction set according to the real-time state of the robot and a global path planning result; and acquiring actual path data of the robot, comparing the actual path data with an expected path point by point, and if the continuous deviation feature exceeds a preset continuous deviation feature threshold, inputting the environment feature map, the obstacle avoidance instruction set and the continuous deviation feature into the deep reinforcement learning model for updating. According to the invention, the obstacle avoidance capability of the autonomous robot in a dynamic complex environment is improved through multi-modal sensing fusion and a closed-loop dynamic optimization mechanism.

The invention provides a robot operation method and system based on a visual language model and reinforcement learning, and relates to the technical field of robot operation, a mechanical arm of a robot operates a target object according to task description, and the robot operation method comprises the steps that to-be-executed task description, a real-time task observation image and a real-time environment observation image are acquired; based on the task description and the environment observation image, decomposing the task description into executable subtask sequences represented by semantic key points by utilizing a visual language model; performing space mapping on the executable subtask sequence; and generating a reference trajectory by taking the mapped coordinates and directions as targets, and finely adjusting the reference trajectory by using the task observation image to obtain a final task operation trajectory. According to the method, robustness is shown in a long sequence task, diversified objects can be flexibly operated, the potential of combination of multi-modal reasoning and self-adaptive control learning is fully excavated, and a new path is developed for constructing an autonomous robot system with a higher capability level.

Thus, there is disclosed an autonomous robotic construction system comprising at least one frame comprising at least one substantially horizontal track and at least one set of substantially vertical track; at least one nozzle; at least one movable device coupled to the frame and configured to move said nozzle around said frame; at least one pump configured to pump building materials through said at least one nozzle; and at least one computer system comprising at least one microprocessor configured to control said at least one nozzle, said at least one movable device and said at least one pump to control deposition of any building materials on a site.

The invention relates to the field of robot technology and artificial intelligence, and discloses a robot fine operation method and system based on a visual language model and semantic key point characterization, a closed-loop multi-body Agent system is constructed, GPT-4o and Ground DINO are combined to accurately understand and disambiguate a natural language instruction of a user, an innovative bridging layer is introduced, and the robot fine operation method and system based on visual language model and semantic key point characterization are obtained. Abstract decision information is converted into bottom execution parameters represented by three-dimensional semantic key points, the problem of decision transfer distortion is solved, meanwhile, a KMP algorithm is improved, and the stiffness and contact force of trajectory tracking are dynamically optimized by introducing a learning-based time-varying hybrid impedance / force control strategy, so that the accuracy of trajectory tracking is improved. According to the method, the generalization success rate of fine operation tasks of the robot and the stability of physical interaction are remarkably improved, seamless connection from high-level semantic understanding to low-level action generation is achieved, and an efficient and reliable technical scheme is provided for autonomous operation of the robot in a complex scene.

Robots, systems, methods, and computer program products for training and operating (semi-)autonomous robots to complete work objectives are described. A robot accesses a library of reusable work primitives from a catalog of libraries of reusable work primitives, each reusable work primitive corresponding to a respective basic sub-action that the robot is trained to autonomously perform. A work objective is analyzed to determine a sequence of reusable work primitives that complete the work objective, and the robot executes the sequence to complete the work objective. A robot can be deployed with access to an appropriate library of reusable work primitives, based on expectations for the robot. The robot is trained to perform reusable work primitives in multiple libraries, by generating control instructions which cause the robot to perform each reusable work primitive. Training is performed by real-world robots performing reusable work primitives, or simulated robot instances performing the reusable work primitives.

The present application relates to a kind of self-robot multi-task operation planning method and system driven by embodied cognitive large model, wherein the method comprises: S1, based on the real-time acquisition RGB diagram and depth diagram are encoded to obtain embodied visual representation;S2, obtain natural language instruction and and embodied visual representation are fused across modalities, obtain fusion feature, and based on fusion feature multi-task decomposition scheme;S3, based on multi-task decomposition scheme, utilize diffusion strategy to generate the continuous action trajectory of robot end effector;S4, obtain the second RGB image and second depth diagram after robot executes according to continuous action trajectory, and it is used as closed loop feedback signal, system is used to realize the above-mentioned method.Compared with prior art, the present application is based on embodied cognitive large model, and the depth of visual and language modalities is deeply fused, and combined with diffusion strategy action decision module, accurate action trajectory is predicted, and the multi-task autonomous planning and accurate execution capability of robot in dynamic complex environment is significantly improved.

The disclosed techniques provide an elevator car with a passenger compartment and a robot-dedicated compartment that includes a charging interface, a containment structure with fire suppression, and an access control assembly with a multi -panel door to admit and release an autonomous robotic device without exposing the passenger compartment. A control unit monitors sensors and interlocks to verify car-to-landing alignment and safe transfer, operates the door system, and coordinates car travel and deployment of the autonomous device to designated locations. The techniques include staging and recharging the autonomous device in the robot-dedicated compartment, monitoring environmental and battery conditions using the containment structure, commanding verified transfer through the access control assembly, coordinating movement of the car and the autonomous device, and recording status and exceptions while transporting the device to a designated location.

A system for receiving and delivering packages to a building having a package receiving station, a delivery robot and a control system. The package receiving station having a display, an input device, a package receiving area, a robot loading area, at least one package manipulation devices, and a computing device, and the delivery robot capable of interacting with the package receiving station to receive packages to be delivered, such that the package receiving station is capable of receiving a package at the package receiving area, moving it to the robot loading area and loading the package onto the delivery robot and the control system is capable of notifying a recipient of the arrival of the package, coordinating a delivery time, and initiating a package delivery whereby the package is loaded onto the delivery robot and delivered to a location within the building and delivers the package.

Multiple workpiece transfer holders for autonomous robots can be stacked and stored, and the stacked workpiece transfer holders for autonomous robots can be automatically unloaded. [Solution] By inserting the lowest ends of the four support columns of the upper work transport holder 10 into the openings at the uppermost ends of the four support columns of the lower work transport holder, it becomes possible to stack, for example, eight work transport holders, each with a pallet on it. An autonomous mobile robot (AGV) enters the work transport holder magazine 20 in the direction indicated by the solid arrow, raises the eight stacked work transport holders at once, and transports them from the work transport holder magazine in the direction indicated by the dashed arrow to a predetermined stock position.

An autonomous collaborative robotic system for automatically detecting, locating, and mapping underground assets is provided. The collaborative robotic system includes two autonomous robots, each robot including a housing with extendable legs, a camera module, a laser module designed to project a structure light pattern on a pipe interior, a sensor module designed to collect images from the camera module, and a processing module designed to process and stitch data to generate a network of underground assets and identify one or more features within the asset network.

An autonomous robot localization system for managing a plurality of autonomous robots is disclosed. The autonomous robot localization system includes a plurality of rail paths including a plurality of markers, a plurality of autonomous robots, and a system controller. The plurality of rail paths is used for guiding the plurality of autonomous robots. The plurality of autonomous robots include a plurality of readers, and a plurality of robot controllers. The plurality of readers include a plurality of sensors The plurality of robot controllers generate a plurality of marker patterns for corresponding marker based on assigned presence and absence status of the plurality of marker bits. The system controller manages movements of the plurality of autonomous robots based on a plurality of commands sent to the plurality of robot controllers.

This invention discloses a method for autonomous robot operation in industrial assembly, relating to the field of robot control technology. The method is applied to a system containing multiple RGB-D cameras, a robotic arm, and an edge computing platform. It simultaneously acquires images and depth information from multiple perspectives, unifying them to a base coordinate system through coordinate reconstruction. Based on dual-view deviation and a fusion threshold, it determines whether to merge point clouds or downgrade single-view images, and performs PCA-OBB solving to obtain target geometric parameters and generate a grasping pose. It receives natural language commands, generates voxel operation code from a large language model to construct a 3D voxel cost map, and plans the path using a weighted A* algorithm. During robotic arm operation, it calculates pose error in real time and achieves closed-loop control through judgment, PID correction, or local replanning. This invention solves problems such as poor robustness of multi-view perception, poor real-time performance of large models, and large assembly errors, improving the efficiency and stability of autonomous operation in industrial assembly, and is suitable for complex assembly scenarios.

A system for removing trash items from a space includes employing an autonomous robot to detect trash within the space, to approach the trash item upon detection and to remove the trash item from the space. The autonomous robot may have two or more trash bins with each trash bin being designated to be filled with a particular category of trash. The categories of trash may be different from one another. The autonomous robot is configured to detect the trash category of the trash item that will be picked up and, after picking up the trash item, to insert it in the appropriate trash bin. This way, the autonomous robot can collect and sort trash items according to their kind. A pan with sweeper arms can be used by the robot for collecting a trash item. In another approach, a trash item can be suctioned by the robot using vacuum.

The invention relates to a system comprising at least one autonomous mobile robot (service robot) and at least one mobile terminal for operating the robot. According to an embodiment of the invention, the robot and the mobile terminal are configured to communicate via at least one first wireless connection. The robot is configured to detect information about a stay position of a user (e.g. based on a stay position of the terminal) and, depending on the detected information about the stay position, to decide whether to send information to the mobile terminal and, if so, which information, and / or to decide whether to execute, interrupt, continue or terminate activities by the robot and, if so, which activities.

The invention discloses an SVG valve hall autonomous inspection robot control method and system, and the method and system achieve the intelligent inspection of an SVG valve hall through an autonomous robot carrying a depth camera, a panoramic camera, a vibration sensor and an infrared camera. The robot scans an environment by using a depth camera, matches a preset three-dimensional template to accurately position equipment coordinates, and dynamically plans a full-coverage inspection path. And then, the robot runs along an inspection path and synchronously acquires common images, vibration data and infrared temperature data to form a multi-dimensional information set, and a fault position is identified through parameter comparison. For the fault position, the robot continuously monitors the image sequence, the temperature fluctuation and the vibration change trend, predicts possibly-affected associated equipment in combination with the topological relation of the equipment, and outputs the name and the coordinate of the associated equipment. According to the method, three-dimensional positioning, multi-sensor cooperation and dynamic trend analysis are fused, the limitation of traditional single-point detection is broken through, fault spreading prediction is achieved, and the intelligent level of inspection diagnosis is improved.

Methods and systems for autonomous robot motion planning are disclosed. The method and system using the method includes obtaining, by an electronic processor, robot configuration training data, the robot configuration training data including a start configuration and a target configuration; applying, by the electronic processor, the start configuration and the target configuration to the neural network model to obtain a time field; determining, by the electronic processor, a predicted velocity indication based on the start configuration, the target configuration, and the time field; obtaining, by the electronic processor, a reference true speed indication; and training, by the electronic processor, a neural network model based on a loss between the predicted velocity indication and the reference truth velocity indication. Other aspects, embodiments, and features are also claimed and described.

Autonomous robotic systems for ultrasound examination are provided. The robotic systems include a robotic arm having an end effector for connecting an ultrasound tool. The arm is connected to a base station having a computing and control assembly disposed therein configured to process inputs from a vision module and control the robotic arm to position the tool to perform an ultrasound procedure on a patient. The end effector can include a load cell for measuring forces and torques experienced by the tool. A haptic device can be used to control articulation of the robotic arm to position the tool and provide force feedback to an operator. The robotic system can be configured to generate a 3D model of the patient, receive input of a feature region, and control the robotic arm to position the tool to perform an ultrasound procedure on the feature region. Various cleaning devices for cleaning the ultrasound tool are described.

This invention belongs to the field of special robots and intelligent control, and discloses a method for autonomous robot operation in the space environment. This method addresses the challenge of high-precision and stable autonomous operation of robots in the complex lighting, communication-restricted, and microgravity environment of space. It achieves high-precision acquisition of the pose and motion state of non-cooperative targets by constructing a multi-sensor fusion stable perception mechanism adapted to the extreme space environment; it employs an edge computing-driven task autonomous planning strategy to achieve efficient autonomous decision-making and rapid response in space-based operations under communication-restricted conditions; and it proposes a force-position cooperative control method based on learning perturbation compensation to ensure high-precision and stable execution of space-based operations in a microgravity environment. The method proposed in this invention effectively improves the success rate of space robot operations and contributes to promoting the large-scale application of space manufacturing.

The utility model belongs to the technical field of automatic driving, and particularly relates to an automatic driving robot which is composed of a fixing support and a head structure, the head structure is movably connected with the fixing support, the fixing support is fixed on a seat of a cockpit, and a scene collecting mechanism and a view range moving mechanism are arranged in the head structure. The scene acquisition mechanism comprises a simulation left eye and a simulation right eye, and the visual field range moving mechanism comprises a head rotating structure and an eyeball rotating structure. According to the utility model, the infrared emitter and the dynamic camera in the simulation eye are used for collecting scenes in the driving process of an automobile, the rotation of eyeballs is realized through the reciprocating structure connected with the simulation eye, the sight range of the simulation eye is increased, and the visual field activity range mechanism is also arranged in the simulation eye, so that the visual field of the automobile can be simulated. And the view collection range is increased through the view activity range mechanism.

Exemplary embodiments of the present disclosure are directed towards an autonomous robotic system for tracking, capturing, and eliminating insects and method employed thereof. The system comprising an autonomous robotic device is configured to enable communication between a server, and a computing device over a network, whereby the computing device comprises a remote-control module configured to allow the user to remotely control the robotic device. The autonomous robotic device comprising a processor in communication with a capturing unit, whereby the capturing unit is configured to capture insects in an enclosed chamber, and the processor is configured to detect and track images of insects in the space and identify the target insect based on this tracking. The processor configured to receive the data of the insect detection to the navigation unit, wherein the navigation unit configured to navigate towards detected insect locations using simultaneous localization and mapping (SLAM) algorithms, AI-based tracking, and machine learning models to monitor common insect hotspots over time.

An autonomous robotic cart includes a chassis, sensors coupled with the chassis, visible light cameras, and a handlebar unit coupled with the chassis. The handlebar unit includes a handlebar and a force sensor configured to detect a translational force and a rotational force exerted on the handlebar. The autonomous robotic cart also includes a holonomic and omnidirectional mechanical drive unit coupled with the chassis. The autonomous robotic cart is configured to autonomously navigate a physical environment to execute one or more navigation goals determined based on communication with a remote computing system configured to manage a fleet of robots including the autonomous robotic cart and also to cause the autonomous robotic cart to move translationally and rotationally in a direction corresponding to a output force vector determined based on sensor data.

The invention relates to the technical field of robots, and discloses a divergent decision-making method and system for accompanying behaviors of an autonomous robot, and the method comprises the steps: predicting an optimal path, making a decision, executing the decision, obtaining execution data, and optimizing the execution efficiency of the robot in an industrial control system, an industrial control system or an industrial master controller. Meanwhile, accurate path planning and execution feedback are provided for a factory control system, and the overall operation process is optimized. Through combination of quantum annealing random exploration and GCN topology matching degree evaluation, the path selection process is optimized, field potential energy is corrected through adaptive Kalman filtering, the feasibility score of the path is further optimized, and meanwhile, through dynamic weighted scoring and path quality quantification, the robot can realize efficient and safe path planning in a complex environment, and the path selection efficiency is improved. The decision-making performance and adaptability of the robot in a complex dynamic environment are improved, and powerful technical support is provided for autonomous robot application in a factory control system.

A method for inventory monitoring and an autonomous robot for inventory monitoring are provided. The method includes detecting one or more shelf labels from one or more images, where the one or more images are captured by one or more cameras on an autonomous robot. The method further includes obtaining one or more bounding boxes based on the one or more shelf labels detected from the one or more images, where each bounding box encloses one or more facings of a same product, and associating the one or more bounding boxes with the one or more shelf labels detected from the one or more images.

Provided is an edge-based intelligence support method for performing a complex task of an autonomous behavior robot. Provided is a method for performing a task of an autonomous behavior robot, according to an embodiment of the present invention, in which the autonomous behavior robot performs the task by using an ultra-lightweighted artificial intelligence model, an edge server supports the task performance of the autonomous behavior robot by using a lightweighted artificial intelligence model, and a cloud server supports the task performance of the robot by using a huge artificial intelligence model. Accordingly, in addition to distributing and updating, through edge computing, an artificial intelligence model required when the autonomous behavior robot performs various tasks, the task performance itself is supported through an edge or cloud, thereby increasing the task performance efficiency of the autonomous behavior robot to improve service quality.

An autonomous robot guidance system and related methods are disclosed. An exemplary autonomous robot includes a processor circuit that detects a first reference based on image data collected while the robot is in a first driving mode, wherein the first driving mode corresponds to an autonomous driving mode, and in response to the detection of the first reference, switches the robot from the first driving mode to a second driving mode, moving the robot in the second driving mode in a direction corresponding to the position of the first reference relative to the robot; generates navigation data for the robot, wherein the navigation data indicates the position of the robot in the environment, switches the robot from the second driving mode to the first driving mode, and after switching from the second driving mode, drives the robot in the first driving mode based on the navigation data.

This product is an autonomous robot capable of two-way communication with the user.

An autonomous robotic system and methods for transporting patient stretchers, hospital beds, gurneys, and other patient transport apparatuses are provided. The autonomous robotic system includes a mobile robot module including extendable arms configured to interface with wheels of patient apparatuses; a wheel engagement module configured for capturing, lifting, guiding, caging, steering, or pulling the wheels of the patient apparatuses; and a navigation module including LiDAR, computer vision, and / or other sensors to autonomously guide the mobile robot module within hospital environments.

A control method of an autonomous working system, a map acquisition method, a control method of an autonomous robot, and an autonomous working system wherein the control method of the autonomous working system comprises: acquiring environmental information collected over a target area (S901), the environmental information comprising image data and position data; generating a map of the target area based on the environmental information (S902), the map comprising at least one type of attribute information, the attribute information being associated with a specific area in the map; and generating a working strategy of the autonomous robot in the target area based on the attribute information (S903). By adopting the mode, the accurate and comprehensive map can be quickly obtained, so that the complete work of the working area is realized.