143 results about "Mobile robot system" patented technology

The invention belongs to the field of robot control, and particularly relates to a reinforcement learning tracking control method of a mobile robot based on event triggering, and the method employs an Actor-Critic synchronous learning algorithm to solve an optimal control strategy, employs interaction data to carry out strategy iteration updating, and introduces an event triggering mechanism. The controller updates the control signal only when the trigger threshold value is met; based on the optimal control theory, the consistent final bounded stability of the four-Mecanum-wheel mobile robot system is analyzed, and the reinforcement learning tracking control method of the four-Mecanum-wheel mobile robot based on event triggering is completed. According to the invention, the trajectory tracking problem of the mobile robot when external disturbances such as sliding exist is solved, and the trajectory tracking precision is ensured under the condition that the calculation burden is effectively reduced.

The invention discloses a self-balancing type light steering wheel for complex terrains. The self-balancing type light steering wheel comprises a wheel carrier, a steering assembly, a driving assembly and a suspension system. The steering assembly drives tires to steer through a motor via a three-stage gear pair. The driving assembly drives tires through a motor and a speed reducer; the suspension system is connected between the driving mounting plate and the wheel carrier and comprises a parallel connecting rod mechanism and symmetrically arranged spring suspension units, self-adaptive buffering is achieved through a compression spring and a fisheye knuckle bearing, and it is ensured that the tire continuously touches the ground on a rugged road surface; the driving speed reducer is integrated in the tire, the driving motor is arranged between the wheel carrier and the tire, and the whole steering assembly does not exceed the turning radius of the tire. The device is compact in structure, has good terrain adaptability and motion stability, and is suitable for an outdoor mobile robot system.

Disclosed is a mobile robot manipulator system for handling railway inter box connectors for securement of shipping containers to the intermodal railcars, in a railway yard under an outdoor working environment, with a unique end-effector design incorporating at least two independently actuated and redundant grippers, supplemented by an additional aerial lift and aerial anchor to help stabilize the position of the movable base of the manipulator, a manipulator docking station to help protect the manipulator, end-effector, vision camera, and other sensitive equipment from damages against shock and under all weather conditions, and a sure grip methodology for safely transporting the railway inter box connector by the robot manipulator.

The invention discloses a mobile robot rolling time domain estimation method fused with threshold filtering. The method comprises the following steps: 1) establishing a mobile robot system model; 2) designing a measurement equation; 3) processing measurement abnormal data; 4) establishing a cost function; 5) establishing constraint conditions; and 6) designing a rolling time domain estimator. According to the method, a self-adaptive scale factor s is introduced to correct measured abnormal data, then rolling time domain estimation is carried out, and an optimization problem is solved, so that the influence of external interference on state estimation in the moving process of the mobile robot trolley is effectively reduced, and the combined positioning capability of a nonlinear system is further improved.

The invention provides a multi-arm mobile robot cooperative control framework and a multi-arm mobile robot system, and is applied to the technical field of mobile composite multi-arm robots. A mechanical arm tail end error estimation module obtains the tail end pose error of each mechanical arm; the multi-arm collaborative cost module obtains the state difference between the mechanical arms; the reinforcement learning module is used for dynamically and adaptively adjusting the collaborative cost weight of the multi-arm collaborative cost module by taking the difference value between the pose predicted value and the expected value of the tail end of each mechanical arm and the state difference between the mechanical arms as input; the mechanical arm tail end error estimation module and the multi-arm cooperative cost module are enabled to iteratively pursue minimization, and a plurality of mechanical arms of the multi-arm mobile robot are controlled to perform cooperative operation. On the basis of the cooperative control framework, action interference existing in cooperative operation control of the multi-arm robot can be avoided, the adaptability, motion precision and stability of the multi-arm robot are improved, and efficient cooperation among multiple arms is achieved.

The invention provides a multi-autonomous mobile robot dynamic collaborative transportation operation method based on data driving, and belongs to the field of trajectory planning and tracking control of multi-autonomous mobile robots. The method comprises the following steps: firstly, planning a feasible global trajectory conforming to kinematics characteristics and safety of each autonomous mobile robot; secondly, obtaining speed information of each track point; then, processing the feasible global trajectory with speed information to obtain a local reference trajectory which can be specifically executed, and fitting the local reference trajectory to obtain a local expected trajectory; and finally, the local expected trajectory is tracked, control parameters are adjusted, and the dynamic collaborative transportation operation of the multiple autonomous mobile robots is completed. The robot trajectory tracking precision and stability can be improved; through real-time local trajectory planning and a self-adaptive parameter adjustment method based on reinforcement learning, the safety and the anti-interference capability of a multi-autonomous mobile robot system are improved while the dynamic collaborative transportation operation of multiple autonomous mobile robots is ensured.

The invention discloses a time-varying formation insurance cost tracking control method of a mobile robot system. According to the method, an interference observer is designed to estimate an unknown interference true value of a mobile robot system, and a corresponding anti-interference controller is provided. In addition, the control cost of the whole process of formation tracking is not endless, and the upper bound of the cost of formation tracking control is estimated through a cost function. And finally, by means of the Lyapunov stability theorem, several sufficient criteria are established and are respectively ensured to be consistent and finally bounded, so that time-varying tracking control is realized.

A mobile robot system is described in having a mobile robot and cloud system. The mobile robot leverages cloud computing to offload Neural Radiance Fields (NeRF) based 3D scene reconstruction. The mobile robot advantageously adopts techniques for view filtering and next-best view selection that optimize the image collection process necessary for training an NeRF model with the cloud system. These techniques enable the mobile robot to discard redundant images that do not provide significant new information about the environment. Additionally, these techniques enable the mobile robot to strategically select next-best views that maximize the information gain, while minimizing a total number of images required and the time required to capture the images. These techniques provide a significant reduction in the overall bandwidth required for providing image data to the cloud system and can result in a more accurate and higher quality 3D reconstruction of the environment.

The invention discloses a multi-mobile-robot formation tracking control method and system based on hybrid control, and the method comprises the steps: S1, constructing a cooperative formation tracking control system, and setting N mobile robots to carry out the navigation-following formation motion; and S2, designing a hybrid formation tracking controller. And S3, designing parameters and pulse control intervals by the controller. And S4, controlling the multi-mobile robot system to complete the formation task according to the controller in the step S2 and the control parameters and the pulse intervals in the step S3. The problem of formation tracking control of a multi-mobile-robot system is solved, and the method can be suitable for a formation tracking scene in which only part of followers can obtain the information of a navigator, and is more suitable for a mobile robot model containing dynamic influence.

The invention provides an advanced avoidance method based on a mobile robot, an advanced avoidance device based on the mobile robot and a computer storage medium. The advanced avoidance method comprises the following steps: in response to an advanced avoidance instruction, obtaining at least two target mobile robots corresponding to the advanced avoidance instruction; obtaining a plurality of candidate avoidance points between the at least two target mobile robots; obtaining avoidance cost values of the plurality of candidate avoidance points; sorting the plurality of candidate avoidance points according to the avoidance cost values, and determining a target avoidance point according to a sorting result; and taking the target avoidance point as an advanced avoidance point in the at least two target mobile robots, and controlling at least one target mobile robot to go to the advanced avoidance point. According to the advanced avoidance method based on the mobile robot, advanced avoidance is carried out by selecting the advanced avoidance point and planning the appropriate avoidance point of the target mobile robot, and the overall operation efficiency of a mobile robot system is improved.

Provided is a robot stop position setting device that sets a stop position of a robot, including a map storage unit for storing map information, a stop position storage unit for storing a robot stop position, a reference position output unit that outputs a reference position for calculating the robot stop position, and a stop position calculation unit that calculates the robot stop position based on the reference position.

One variation of a method includes: accessing a sequence of images of an inventory structure captured by a mobile robotic system during a scan cycle within a facility; detecting a set of features, representing a product descriptor, proximal a slot in an image in the sequence of images; retrieving a set of template features of a product type associated with the product descriptor from a database of template features; detecting absence of product units of the product type in the slot based on absence of features analogous to the set of template features in the image; constructing a three-dimensional image of the inventory structure based on the sequence of images; annotating the three-dimensional image with a marker representing absence of product units of the product type in the slot; and serving the three-dimensional image of the inventory structure to a portal accessed by an associate affiliated with the facility.

One variation of a method for deploying a mobile robotic system to scan inventory structures within a store includes: dispatching the mobile robotic system to navigate along inventory structures within the store during a setup cycle; at the mobile robotic system, while navigating along the inventory structures during the setup cycle, capturing a set of wireless connectivity metrics representing connectivity to a first wireless network; assembling the set of wireless connectivity metrics into a wireless connectivity map of the store; estimating a processing duration from start of the scan cycle to transformation of images of the inventory structures, captured by the mobile robotic system, into a stock condition of the store; and dispatching the mobile robotic system to autonomously capture images of the inventory structures within the store during a scan cycle preceding a scheduled restocking period in the store based on the processing duration.

Described herein are systems, devices, and methods for validating location of a docking station for docking a mobile robot. In an example, a mobile robot system includes a docking station and a mobile cleaning robot. The mobile cleaning robot includes a drive system to move the mobile cleaning robot about an environment including a docking area within a distance of the docking station, and a controller circuit to detect, from an image of the docking area, a presence or absence of one or more obstacles in the docking area. A notification may be generated to inform a user about the detected obstacles. The mobile device may generate a recommendation to the user to clear the docking area or reposition the docking station, or suggest one or more candidate locations for placing the docking station.

The invention belongs to the related technical field of system consistency control, and particularly discloses a multi-mobile-robot system consistency control method and system considering time delay and a medium, kinematics and dynamics models of mobile robots are established, and on the basis, a communication topological graph of a multi-mobile-robot system is constructed. By designing a cost function and a constraint condition of model prediction control, multi-robot system consistency control under communication delay is realized; meanwhile, the stability of the designed controller is guaranteed by adopting the idea of designing the auxiliary controller, and the influence of time delay on the control effect is overcome by estimating the system state under the communication delay and broadcasting the system state. According to the invention, the stability and reliability of consistency control of the multi-mobile robot system can be improved, so that safe and stable operation of the mobile robot system is realized.

The present invention relates to the technical field of robot control, and in particular provides a distributed control method and device for a mobile robot system based on quantization information. The method includes obtaining the discrete-time position information and velocity information of each mobile robot itself, and detecting the discrete-time position information and velocity information of its neighboring robots; constructing a communication topology structure according to the directionality and reachability of the communication links between the mobile robots, defining a signed adjacency weight matrix according to the friendly or adversarial interaction relationships between the mobile robots, and defining a Laplacian matrix corresponding to the signed graph; performing quantization processing on the position information and velocity information; generating a control quantity according to a quantization error compensation mechanism and combining with the signed weights, and updating the state of the mobile robot at the next moment through a discrete kinematic model. This method realizes the distributed coordinated control of the mobile robot system through quantization information and can tend to consistency under antagonistic actions.

A mobile robot system for automated operation of a data center or telecommunications office, includes a moveable robotic platform with a multiplicity of tools integrated therein to operate on a network element within a bay, with integrated RFID (radio-frequency identification) tags and visual alignment markers attached to fiber optic connectors and ports of the network elements. The mobile robot system positions a robot probe arm with an RFID probe for proximity detection to identify a cable and associated fiber optic connector based on a unique RF identifier of a tag on the fiber optic connector. The robot probe arm has a connector gripper to engage and unplug the associated fiber optic connector.

A mobile robot and a system therefor are disclosed. A mobile robot, according to the present invention, comprises: a communication module connected to communicate with a server to transmit data; a processor generating first data including a starting coordinate, a target coordinate, and a moving speed of the mobile robot in response to a moving command in accordance with an allocated task; and a driving unit operating the mobile robot to drive toward the target coordinate. In this case, the processor transmits the first data to the server only once at the starting coordinate so that the server restores the first data in time series. In addition, when the mobile robot reaches the target coordinates according to the operation of the driving unit, second data including the current coordinate of the mobile robot is transmitted to the server. Accordingly, the communication load on the server is minimized.

A mobile robot system includes a thermal protection system comprising an anti-radiation surface coating applied to an exterior of the mobile robot system, and a passive thermal protection system (FTPS) disposed within an inner structure of a frame of the mobile robot system. The mobile robot system also includes an electronics thermal protection system (ETPS) disposed within the FTPS, and a temperature-hardened sensor housing comprising at least one sensor disposed externally on the frame. The mobile robot system additionally includes a control interface configured to control a mobile operation of the mobile robot system.

Systems and methods for handling, manipulating, loading, and / or unloading objects in a retail environment include a mobile robot system. The mobile robot system may include a mobile robot and a first sensor system communicatively coupled to the mobile robot. The first sensor system has a trigger area and generates a signal in response to detecting an object in the trigger area. The mobile robot system further includes a sensor mount coupled to the mobile robot and the first sensor system. The sensor mount includes a gimbal that changes a sensor angle between the first sensor system and the mobile robot and affects a location of the trigger area in response to tilting of the mobile robot relative to a horizontal plane.

Embodiments of the present application provide an object information determination method, a mobile robot system and an electronic device, and are applied to the technical field of robots. The method comprises: acquiring a plurality of images containing a target object collected by a mobile robot in a process of performing a surrounding motion on the target object; for each acquired image, identifying a relative distance between the mobile robot and the target object when the image is collected; and determining contour information of the target object based on the relative distance between the mobile robot and the target object when each image is collected and position information of the mobile robot in a world coordinate system. Through the present solution, the contour information of an object in an environment can be determined.

This invention discloses a fault-tolerant control method for coupled actuator failures in mobile robots, belonging to the field of nonholonomic mobile robot control technology. It includes: establishing an actuator coupling failure model for nonholonomic mobile robots that better reflects actual production conditions; cleverly solving the controllability problem caused by actuator coupling failures in nonholonomic robots by introducing the Proj function to handle unknown actuator failure coefficients; and designing a filter system suitable for nonholonomic mobile robot systems when speed is unmeasurable, avoiding the use of high-precision sensors. This invention improves the robustness of the mobile robot system while reducing its hardware costs.

An embodiment of the present invention provides a robot vacuum cleaner system characterized by comprising: one or more heterogeneous docking stations which can be arranged within a travel area and are assigned different docking signals according to the type; and a robot cleaner that receives the docking signals from the one or more heterogeneous docking stations and attempts docking, wherein the robot cleaner includes: a driving unit that moves a main body; a battery supplying power to the driving unit; and a sensor unit that receives the docking signal from the one or more docking stations for charging the battery, and when docking is necessary, the robot cleaner docks onto a docking station by determining the type of the docking station from the docking signals sensed by the sensor unit and determining a docking mode according to the type of the docking station. Therefore, when the heterogeneous docking stations are arranged in a single space, the robot cleaner can recognize a specific docking station and perform a docking operation for docking thereon to prevent a docking error. In addition, when the plurality of heterogeneous docking stations are arranged in a single space, the plurality of heterogeneous docking stations transmit different docking signals, and the robot charger can read the corresponding docking signals and travel to a specific docking station to reduce travel loss.

Systems and methods for generating a secure area for a mobile robot are described. The system and method may include receiving information about a cargo car or roof device to be used on a mobile robot, such as a size and number of posts of the cargo car. The system and method may also include generating a safe area based on the type of mobile robot and information about the cargo car or roof device. The system and method may also include operating the mobile robot based on the secure area such that a controlled stop of the mobile robot is triggered when an object is detected within the secure area.

The present invention provides a transport system comprising an Autonomous Mobile Robot (AMRs) (1) and the equipment to be moved (2), which can be operated safely and efficiently within an industrial / commercial environment, while the AMRs (1), as well as the equipment to be moved (2), can be produced in a cost-efficient way. A particular object of the invention is to: providing supporting members (4) of the equipment to be moved, which have no or only a negligible impact on the safety system, providing equipment to be moved (2) which can carry heavy payloads, preferably of hundreds and thousands of kilograms; providing a safety sensor system for an AMR, which can provide protective zones (5) around the AMR and the equipment to be moved and where the supporting members (4) of the equipment to be moved (2) have no or only a negligible impact on the safety of transportation. Another object of the invention is the correct attachment of the cart / shelf (2) to the AMR (1) is ensured before and during driving.

This invention provides a fully autonomous embodied intelligent mobile robot system architecture, including a structural and mobility subsystem, a perception subsystem, a power supply subsystem, a thermal control subsystem, an intelligent computing subsystem, and a wireless communication subsystem. The power supply subsystem provides power; the structural and mobility subsystem controls the movement of the embodied intelligent mobile robot and obtains motion data; the perception subsystem senses and measures the environment and the state of the embodied intelligent robot, obtaining measurement data; the thermal control subsystem acquires temperature information for insulation and heat dissipation; the wireless communication subsystem enables communication between the embodied intelligent robot and other intelligent agents, acquiring relevant data from other intelligent agents; and the intelligent computing subsystem processes the acquired motion data, measurement data, temperature information, and related data to determine the task to be executed. Based on this system architecture, the embodied intelligent mobile robot can achieve autonomous navigation and task planning in complex and unknown environments where GNSS is denied.

The invention relates to an anti-theft method, and the method comprises the steps: controlling a self-moving robot to execute an anti-theft action if the real-time position of the self-moving robot is located outside an anti-theft region, and the anti-theft action at least comprises the alarm sending and authentication interface display. Therefore, the self-moving robot is prevented from being stolen, the anti-theft function is comprehensive, and the user experience feeling is better.

The application relates to a loop detection method based on a point cloud semantic graph descriptor and position information, comprising the following steps: acquiring laser point cloud data and satellite positioning data of a current frame, performing semantic segmentation processing on the laser point cloud data, converting into a preset point cloud semantic graph descriptor form, screening a loop candidate frame from historical frame data through distance matching and node matching; converting the current frame and the loop candidate frame into a circular ring graph form, and attempting to obtain a target loop frame through similarity verification and geometric consistency verification. Compared with the prior art, the application solves the problems of difficult loop detection, large loop matching calculation amount and low loop matching accuracy in a mobile robot SLAM system, and improves the positioning accuracy and system robustness of the mobile robot.

Systems and methods are described for detecting changes at a location based on image data by a mobile robot. A system can instruct navigation of the mobile robot to a location. For example, the system can instruct navigation to the location as part of an inspection mission. The system can obtain input identifying a change detection. Based on the change detection and obtained image data associated with the location, the system can perform the change detection and detect a change associated with the location. For example, the system can perform the change detection based on one or more regions of interest of the obtained image data. Based on the detected change and a reference model, the system can determine presence of an anomaly condition in the obtained image data.