Abstract: An apparatus, system and method of for certifying a sensor that at least partially navigates an autonomous mobile robot. The apparatus may include at least a robot body; at least one light source resident on the robot body proximate to the sensing camera such that the at least one light source is capable of at least partially irradiating a field of view (FoV) of the sensing camera, wherein the at least one light source has characteristics substantially mated to the sensing camera; and at least one processing system that provides the at least partial navigation. The at least one processing system may execute the steps of: actuating the at least one light source at a predetermined time and for a predetermined duration; monitoring data from the sensing camera for confirmation of the actuating; calculating at least one of the latency, throughput, and reactivity of the sensing camera based on the monitoring; and at least partially navigating based on the calculating.

Abstract: A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.

Abstract: A robot includes a controller configured to: detect a virtual wall signal; identify a virtual wall according to a signal threshold and the virtual wall signal; and when the virtual wall is identified, adjust the signal threshold, and control the robot to travel along an outer side of the virtual wall according to an adjusted signal threshold and the virtual wall signal, such that a driving wheel of the robot is located at the outer side of the virtual wall when the robot is traveling along the outer side of the virtual wall; wherein the outer side of the virtual wall is a side of the virtual wall within an active region of the robot.

Abstract: Techniques for active and semi-active damping include a system including a processor and a linkage having a first link, a second link, and a damper coupling the second link to the first link. The processor is configured to receive a movement command for moving the linkage; determine one or more first vibrations expected to occur in the linkage as a result of performing the movement command; determine a movement profile for moving the linkage to reduce the one or more first vibrations; and drive, using a drive component, the linkage to move according to the movement profile.

Abstract: A storage array system including an open undeterministic transport surface, a navigation array disposed in connection with the transport surface, the navigation array includes a distributed feature, a first waypoint at a first position of the distributed feature, a second waypoint displaced from the first waypoint along the distributed feature and offset with respect to the first waypoint in a direction angled to the distributed feature, and a guided bot, arranged to traverse the transport surface, with a non-holonomic steering system, the guided bot having a bot pose determination system employing sensor data detecting the distributed feature, wherein the guided bot includes a controller configured to generate a substantially smooth curved bot traverse path on the transport surface connecting the first and second waypoints with a predetermined optimal trajectory of the guided bot along the traverse path determined based on a bot dynamic model.

Abstract: A smart power transmission line inspection system, related to the technical field of robotic inspection. The smart power transmission line inspection system comprises an inspection robot, an activation/deactivation device, and a control and processing terminal. The activation/deactivation device is used for activating or deactivating the inspection robot according to an activation/deactivation instruction. The inspection robot is used for inspection along a power transmission line according to an inspection instruction, and the inspection robot is also used for obtaining inspection data and for transmitting the inspection data to the control and processing terminal, wherein the inspection instruction is a pre-set inspection instruction pre-set for the inspection robot, or the inspection instruction is sent by the control and processing terminal and received by the inspection robot.

Abstract: Implementations set forth herein relate to generating training data, such that each instance of training data includes a corresponding instance of vision data and drivability label(s) for the instance of vision data. A drivability label can be determined using first vision data from a first vision component that is connected to the robot. The drivability label(s) can be generated by processing the first vision data using geometric and/or heuristic methods. Second vision data can be generated using a second vision component of the robot, such as a camera that is connected to the robot. The drivability labels can be correlated to the second vision data and thereafter used to train one or more machine learning models. The trained models can be shared with a robot(s) in furtherance of enabling the robot(s) to determine drivability of areas captured in vision data, which is being collected in real-time using one or more vision components.

Abstract: Systems and methods are disclosed for optimizing values of a set of tunable parameters of an autonomous driving vehicle (ADV). The controllers can be a linear quadratic regular, a “bicycle model,” a model-reference adaptive controller (MRAC) that reduces actuation latency in control subsystems such as steering, braking, and throttle, or other controller (“controllers”). An optimizer selects a set tunable parameters for the controllers. A task distribution system pairs each set of parameters with each of a plurality of simulated driving scenarios, and dispatches a task to the simulator to perform the simulation with the set of parameters. Each simulation is scored. A weighted score is generated from the simulation. The optimizer uses the weighted score as a target objective for a next iteration of the optimizer, for a fixed number of iterations. A physical real-world ADV is navigated using the optimized set of parameters for the controllers in the ADV.

Abstract: A method for identifying a doorway, including receiving, with a processor of an automated mobile device, sensor data of an environment of the automated mobile device from one or more sensors coupled with the processor, wherein the sensor data is indicative of distances to objects within the environment; identifying, with the processor, a doorway in the environment based on the sensor data; marking, with the processor, the doorway in an indoor map of the environment; and instructing, with the processor, the automated mobile device to execute one or more actions upon identifying the doorway, wherein the one or more actions comprises finishing a first task in a first work area before crossing the identified doorway into a second work area to perform a second task.

Abstract: An example implementation includes (i) receiving sensor data that indicates topographical features of an environment in which a robotic device is operating, (ii) processing the sensor data into a topographical map that includes a two-dimensional matrix of discrete cells, the discrete cells indicating sample heights of respective portions of the environment, (iii) determining, for a first foot of the robotic device, a first step path extending from a first lift-off location to a first touch-down location, (iv) identifying, within the topographical map, a first scan patch of cells that encompass the first step path, (v) determining a first high point among the first scan patch of cells; and (vi) during the first step, directing the robotic device to lift the first foot to a first swing height that is higher than the determined first high point.

Abstract: Methods, devices, and systems for identifying charging devices are provided. In one aspect, a method of identifying a charging device include: capturing an infrared image and a depth image of a current field of view with a depth camera; determining, according to the infrared image, that there are one or more suspected charging device areas that satisfy first specified conditions; determining, according to the depth image, that there is a target charging device area whose height relative to a depth camera is within a specified range in the one or more suspected charging device areas; and identifying the charging device according to the target charging device area. The first specified conditions indicate that a gray-scale value of each of pixels in an area is greater than a second specified value, and a number of the pixels in the area is greater than a third specified value.

Abstract: A system of robotic cleaning devices and a method of a master robotic cleaning device of controlling at least one slave robotic cleaning device. The method performed by a master robotic cleaning device of controlling at least one slave robotic cleaning device includes detecting obstacles, deriving positional data from the detection of obstacles, positioning the master robotic cleaning device with respect to the detected obstacles from the derived positional data, controlling movement of the master robotic cleaning device based on the positional data, and submitting commands to the at least one slave robotic cleaning device to control a cleaning operation of said at least one slave robotic cleaning device, the commands being based on the derived positional data, wherein the cleaning operation of the slave robotic cleaning device is controlled as indicated by the submitted commands.

Abstract: Implementations of the disclosed subject matter provide a method of receiving, at an actuated mobile device, at least one dosage level for a predetermined area, where the at least one dosage level is based on a first dosage of ultraviolet (UV) light to be output from at least one light source for at least a portion of the predetermined area. The method may include moving the actuated mobile device in a path within the predetermined area and outputting the UV light from the at least one light source onto one or more first surfaces based on the received at least one dosage level. The method may include moving the actuated mobile device within the path, and outputting the UV light onto one or more second surfaces based on the received at least one dosage level.

Abstract: A robot including a plurality of joints each configured to rotate about an axis line; a torque sensor S1 configured to detect torque about the axis line of a target joint as one of the plurality of joints; angle information detection units configured to detect information related to a rotation angle of each of the joints about the axis line; a torque change amount estimation unit configured to estimate a change amount of the torque detected by the torque sensor due to a load other than the torque about the axis line of the target joint based on the detected information; and a correction unit configured to correct the torque detected by the torque sensor by using the estimated change amount.

Abstract: Systems and methods assisting a robotic apparatus are disclosed. In some exemplary implementations, a robot can encounter situations where the robot cannot proceed and/or does not know with a high degree of certainty it can proceed. Accordingly, the robot can determine that it has encountered an error and/or assist event. In some exemplary implementations, the robot can receive assistance from an operator and/or attempt to resolve the issue itself. In some cases, the robot can be configured to delay actions in order to allow resolution of the error and/or assist event.

Abstract: A robot control method includes: obtaining force information associated with a left foot and a right foot of the robot; calculating a zero moment point of a COM of a body of the robot based on the force information; updating a motion trajectory of the robot according to the zero moment point of the COM of the body to obtain an updated position of the COM of the body; performing inverse kinematics analysis on the updated position of the COM of the body to obtain joint angles of a left leg and a right leg of the robot; and controlling the robot to move according to the joint angles.

Abstract: A computer-implemented method is disclosed which includes determining a current activity of an individual, comparing movements of the individual while performing the current activity to corresponding movements in a reference activity, determining whether a performance level of respective movements of the individual while performing the current activity are within a predetermined performance range for corresponding movements in the reference activity, generating, via a generative adversarial network (GAN), a directional guidance recommendation based, at least in part, on: a comparative analysis of the movement of the individual while performing the current activity and the corresponding movement included in the reference activity, and a degree of deviation between the performance level of the at least one movement of the individual and an optimal performance level of the corresponding movement included in the reference activity, and displaying the generated directional guidance recommendation to the individual

Abstract: A robot includes an image sensor that captures the environment of a storage site. The robot visually recognizes regularly shaped structures to navigate through the storage site using various object detection and image segmentation techniques. In response to receiving a target location in the storage site, the robot moves to the target location along a path. The robot receives the images as the robot moves along the path. The robot analyzes the images captured by the image sensor to determine the current location of the robot in the path by tracking a number of regularly shaped structures in the storage site passed by the robot. The regularly shaped structures may be racks, horizontal bars of the racks, and vertical bars of the racks. The robot can identify the target location by counting the number of rows and columns that the robot has passed.

Abstract: A navigation controller system and method for retrieving control of a remotely controlled device includes an onboard primary controller supportable on a remotely controlled device and adapted to control operation thereof, a base controller adapted to communicate with the onboard primary controller by a first mode of communications to provide instructions to control and operate the remotely controlled device, and an auxiliary controller module supportable on the remotely controlled device either separately from or integrated into the onboard primary controller and adapted to communicate with the base controller by a second mode of communications not the same as the first mode of communications so that the auxiliary controller module acts as a backup to disable, disconnect or otherwise take over control from the onboard primary controller when it is rendered non-responsive to communications from the base controller.

Abstract: A system to prevent depletion of a robotic energy source includes: a mobile robot; a server operably connected to the robot via a communication system, the server configured to manage the robot; a robotic energy source configured to provide energy to the robot; a controller operably connected to the robot, the controller operably connected to the server, the controller configured to control the robot, the controller further configured to monitor an energy level of the robot; and a charging station configured to operably connect to the energy source, the charging station further configured to replenish the energy source.

Abstract: A mapping method of a lawn mower robot may include a first image mapping operation of generating a first travel image of a three-dimensional region based on an aerial image of a work target region, a first map displaying operation of dividing the first travel image into a mowing region and an obstacle region, converting the first travel image into a first travel map, and displaying the first travel map. The mapping method may include a first anchor displaying operation of recommending the number and installation locations of anchors on the first travel map, an anchor location determination operation of determining whether the anchors are installed at the installation locations, and a path generation operation of generating a travel path of the lawn mower robot on the first travel map. The mapping method may improve work efficiency of the lawn mower robot.

Abstract: A method for creating a map by a moving robot includes receiving sensor data regarding a distance to an external object through a distance measurement sensor, and creating a cell-based grid map based on the sensor data. Image processing is performed to distinguish between regions in the grid map and to create a boundary line between the regions. An optimal boundary line is selected from the one or more boundary lines, and a path to the optimal boundary line is planned. The grid map is updated while the moving robot is moving along the path such that the map may be automatically created.

Abstract: A system includes a first robotic machine having a first set of capabilities for interacting with a target object on stationary equipment; a second robotic machine having a second set of capabilities for interacting with the target object; and a task manager that can determine capability requirements to perform a task on the target object. The task has an associated series of sub-tasks. The task manager can assign a first sequence of sub-tasks for performance by the first robotic machine based on the first set of capabilities and a second sequence of sub-tasks for performance by the second robotic machine based on the second set of capabilities. The first and second robotic machines can coordinate performance of the first sequence of sub-tasks by the first robotic machine with performance of the second sequence of sub-tasks by the second robotic machine to accomplish the task.

Abstract: The present disclosure relates to a low mass system for releasably securing a robotic arm to a spacecraft and also securing various payloads to the robotic arm and to each other, permitting the robotic arm to be both moved from one location to another suitably equipped location on a spacecraft to another and to allow the free end of the robotic arm to be secured to any payload also similarly equipped such that this payload may be manipulated by the robotic arm.

Abstract: A robot includes a drive system configured to maneuver the robot about an environment and data processing hardware in communication with memory hardware and the drive system. The memory hardware stores instructions that when executed on the data processing hardware cause the data processing hardware to perform operations. The operations include receiving image data of the robot maneuvering in the environment and executing at least one waypoint heuristic. The at least one waypoint heuristic is configured to trigger a waypoint placement on a waypoint map. In response to the at least one waypoint heuristic triggering the waypoint placement, the operations include recording a waypoint on the waypoint map where the waypoint is associated with at least one waypoint edge and includes sensor data obtained by the robot. The at least one waypoint edge includes a pose transform expressing how to move between two waypoints.

Abstract: A robot climbing control method is disclosed. A gravity direction vector in a gravity direction in a camera coordinate system of a robot is obtained. A stair edge of stairs in a scene image is obtained and an edge direction vector of the stair edge in the camera coordinate system is determined. A position parameter of the robot relative to the stairs is determined according to the gravity direction vector and the edge direction vector. Poses of the robot are adjusted according to the position parameter to control the robot to climb the stairs.

Abstract: An autonomous path treatment system and associated path treatment method uses a mobile path recording device having a locator, a processor and firmware to capture a sequence of coordinates and directions of travel of a path as the mobile device is moved along the path and generate a path program file. The system also has an autonomous path treatment robot having: a treatment mechanism for treating the path; a controller having a processor and memory storing firmware that when executed obeys steps of the path program file to control the motor and the treatment mechanism to treat the path; and a server configured to execute a path program to process the captured sequence of coordinates and directions into the path program file containing instructions for controlling the autonomous path treatment robot to treat the path based upon the coordinates.

Abstract: An apparatus comprises at least one sensor to collect localization information indicating a location of a first robotic agent of a plurality of robotic agents; and a processor comprising circuitry. The processor is to cause the first robotic agent to move and to utilize the at least one sensor and other robotic agents of the plurality of robotic agents to determine the location of the first robotic agent during a first period of time in which the first robotic agent is not selected as an anchor reference point; and cause the first robotic agent to remain stationary during a second period of time in which the first robotic agent is selected as an anchor reference point to assist other robotic agents of the plurality of robotic agents in location determination.

Abstract: Graphical user guidance for a robotic surgical system is provided. In one embodiment, a graphical user interface for a robotic surgical system comprises a first region and a second region. The first region is used to display an endoscopic view of a surgical site inside a patient taken by an endoscopic camera of the robotic surgical system, and the second region is used to display user feedback information. The graphical user interface overlays a guidance message on top of the endoscopic view of the surgical site in the first region to provide user instructions for interacting with a user input device to engage a robotic arm of the robotic surgical system. Other embodiments are provided.

Abstract: A method of removing mites includes: acquiring a target path for mite removal and switching from a hibernation state to a crawling state upon receiving a mite removing instruction; in the crawling state, crawling according to the target path and performing mite removal during the crawling process; and after crawling to an end position of the target path, switching from the crawling state to the hibernation state.

Abstract: An autonomous mower including a housing; a mowing module, a traveling module, an information collection device, an energy module, a control module and the control module includes an identification unit, and an alarm module. The autonomous mower has a security patrol working mode in which the identification unit analyzes and judges whether an abnormal object exists in the working area according to the information collected by the information collection device; if the abnormal object exists, the control module controls the alarm module to send an alarm signal to the outside. Therefore, the autonomous mower can achieve a security patrol function in addition to having a function of trimming the lawn. The autonomous mower has multiple uses, so as to save the cost.

Abstract: An apparatus is disclosed including a robotic system having a robotic picking workstation, tote storage and retrieval and transit decks. The system has bots that autonomously transport totes from the storage and retrieval system to the robotic picking workstation via the transit decks. The robotic picking workstation may have a picking lane where a robotic handler transports eaches from totes on the bots to order totes in the workstation. The robotic picking workstation further has a queuing buffer where bots are cued for the picking lane.

Abstract: The trajectory tracking method for a mobile electronic device may include tracking a trajectory of the electronic device by using results of pose estimation using odometry and results of pose estimation using visual localization (VL) as camera pose information.

Abstract: The present invention discloses a method of tracking control for a foot force and moment of a biped robot. According to the method, a double-spring damping model is designed, and a force tracking controller is designed by using an LQR optimization method, so as to realize tracking of the foot force and moment of the biped robot. Further, a desired force on a foot and a desired moment on the foot are calculated through a planned ZMP distribution method, thereby eventually achieving better ZMP tracking of the biped robot and adapting to ground of certain unevenness.

Abstract: An unmanned aerial vehicle may include: a sensor part configured to acquire inertia information or position information of the unmanned aerial vehicle; and a controller. The controller is configured to estimate the position of the unmanned aerial vehicle by applying the information acquired by the sensor part to an extended Kalman filter and control movement of the unmanned aerial vehicle, based on the estimated position of the unmanned aerial vehicle. The sensor part includes: an inertia sensor configured to acquire the inertia information of the unmanned aerial vehicle; a tag recognition sensor configured to recognize a tag attached to a rack and acquire absolute position information of the unmanned aerial vehicle; and an image sensor attached to the unmanned aerial vehicle so as to acquire an image of the movement environment of the unmanned aerial vehicle.

Abstract: Provided are dynamic region division and region passage identification methods and a cleaning robot. The dynamic region division method includes: acquiring environment information collected by a robot when working in a first region; determining whether the robot has completed a work task in the first region, when a presence of a passage entering a second region is determined based on the environment information; and complementing a boundary at the passage to block the passage, when the work task is not completed. According to the technical solution provided by the embodiment of the present application, the occurrence probability of repeated sweeping and miss sweeping is reduced, and the cleaning efficiency is high. In addition, the technical solution provided by the embodiment of the present application relies on the environment information collected during the work, rather than relying on historical map data, so that the environmental adaptability is high.

Abstract: Systems, methods, and computer-readable media are provided for controlling a robotically delivered manipulator. One system includes a robotic manipulator having a base and a surgical instrument holder configured to move relative to the base, a surgical instrument removably coupled to the surgical instrument holder, a user interface configured to present information related to least one of the robotic manipulator or the surgical instrument, a gesture detection sensor configured to detect a gesture made by a user representing a desired movement of the robotic manipulator, and a controller configured to actuate the robotic manipulator in a predetermined manner corresponding to the detected gesture.

Abstract: A method of controlling movement of a robotic cleaning device over an area to be cleaned. The method includes acquiring a visual representation of the robotic cleaning device on a display of a wireless communication device, identifying the robotic cleaning device in the visual representation, computing a coordinate transform between the visual representation and a robotic cleaning device coordinate system, creating an instruction by receiving user-indicated spatial information on the display or how the robotic cleaning device should move over the area to be cleaned, applying the transform to the spatial information, transforming the spatial information to the robot coordinate system, and sending the instruction to the robotic cleaning device via wireless communication, to cause the robotic cleaning device to move over said area in accordance with the transformed spatial information.

Abstract: A disruptor projectile includes a shaft made up of an elongate rod. A head piece assembly is connected to an end of the elongate rod. A post is located inside the head piece assembly. A tether line having an end with an eye splice attached around the post. The length of the tether line extends parallel to the elongate rod.

Abstract: A robotic device comprising: an energy storage device; and a controller configured to determine whether a quantity of energy stored in the energy storage device is below a predetermined energy level, wherein: the robotic device is configured to perform a cleaning task if the determined quantity of energy is not below the predetermined energy level; if the determined quantity of energy is below the predetermined energy level: the controller is configured to estimate a likelihood of the robotic device being capable of locating a recharging base station; and in dependence on the estimated likelihood, the robotic device is configured to seek the recharging base station or perform the cleaning task.

Abstract: An adjustable system for facilitating establishment of an operative connection between a charging station and a rechargeable power supply on an operating unit that is propelled by a drive. The adjustable system has: an arm assembly on one of the charging station and the operating unit and supporting at least one connector; and at least one connector on the other of the charging station and the operating unit. The connectors, when engaged, establish an operative charging connection. The arm assembly is configured so that the at least one connector on the arm assembly can move in at least two dimensions relative to the one of the charging station and the operating unit to align with and engage the at least one connector on the other of the arm assembly and operating unit as an incident of the operating unit moving from a position spaced fully from the charging station into the charging position.

Abstract: A therapeutic system comprising a posture-mimicry robot comprising a head-assembly, a neck assembly, and a body assembly comprising a hemispherical bottom portion; and a base portion comprising three rotary actuators; wherein the posture-mimicry robot is configured to perform rotational movement in each of yaw, pitch, and roll axes to perform therapeutic interactive movements, gestures, and audio-visual cues.

Abstract: Surgical kit inspection systems and methods are provided for inspecting surgical kits having parts of different types. The surgical kit inspection system comprises a vision unit including a first camera unit and a second camera unit to capture images of parts of a first type and a second type in each kit and to capture images of loose parts from each kit that are placed on a light surface. A robot supports the vision unit to move the first and second camera units relative to the parts in each surgical kit. One or more controllers obtain unique inspection instructions for each of the surgical kits to control inspection of each of the surgical kits and control movement of the robot and the vision unit accordingly to provide output indicating inspection results for each of the surgical kits.

Abstract: A cleaning method and a cleaning robot are provided. The method includes: after the cleaning robot obtains a cleaning instruction for a target scene, acquiring a current power of the cleaning robot and a scene map for the target scene; if it is determined that the current power is insufficient to clean all areas to be cleaned in the target scene, determining a target cleaning area from all the areas to be cleaned in the target scene, based on a target dirtiness level for each of the areas to be cleaned; cleaning the target cleaning area based on the scene map, the target dirtiness level for the target cleaning area and the current power. A more intelligent cleaning robot and a more reasonable cleaning process are realized.

Abstract: We generally describe a method comprising: processing (S602) data relating to a path of movement of a robotic device (122) comprising or coupled to a sensor (124) in radio communication with a cloud platform (112); and updating (S604), based on the processed data, the path of movement to improve the radio communication.

Abstract: The present disclosure relates to a user interactive electronic system, the user interactive electronic system comprising a robotic arm and at least an attachment detachably affixed to a distal end of the robotic arm. The present disclosure also relates to a method for operating such a user interactive electronic system and to a computer program product.

Abstract: An artificial intelligence (AI) mobile robot and a method of controlling the same for learning an obstacle are configured to capture an image while traveling through an image acquirer, to store a plurality of captured image data, to determine an obstacle from image data, to set a response motion corresponding to the obstacle, and to operate the set response motion depending on the obstacle, and thus, the obstacle is recognized through the captured image data, the obstacle is easily determined by repeatedly learning an image, and the obstacle is determined before the obstacle is detected or from a time point of detecting the obstacle to perform an operation of a response motion, and even if the same detection signal is input when a plurality of different obstacles is detected, the obstacle is determined through the image and different operations are performed depending on the obstacle to respond to various obstacles, and accordingly, the obstacle is effectively avoided and an operation is performed depending o

Abstract: A system includes a robotic system including a robot disposable at a mobile workstation, where the robot is configured to perform an automated operation on a workpiece. The system includes one or more transfer robots configured to transfer the robotic system to or from the mobile workstation. The system includes a control system configured to command the transfer robot to perform a transfer operation of the robotic system, where the transfer operation includes at least one of disposing the robotic system at the mobile workstation or retrieving the robotic system from the mobile workstation. The control system is configured to control the mobile workstation and the robotic system based on image data from the one or more infrastructure sensors, position data from the one or more on-board position sensors, the automated operation to be performed by the robot, or a combination thereof.

Abstract: Provided is a system for robotic collaboration. A first robotic device includes a tangible, non-transitory, machine readable medium storing instructions that when executed by a processor of the first robotic device effectuates first operations including: receiving first information from a processor of a second robotic device; actuating the first robotic device to execute a first action based on the first information; and transmitting second information to the processor of the second robotic device. The second robotic device includes a tangible, non-transitory, machine readable medium storing instructions that when executed by the processor of the second robotic device effectuates second operations including: receiving the second information transmitted from the processor of the first robotic device; actuating the second robotic device to execute a second action based on the second information; and transmitting third information to the processor of the first robotic device.

Abstract: A multifunctional light-duty soft robot includes paired wheel power mechanisms, soft contact mechanisms, buffer spring mechanisms and a middle frame deformation mechanism. Each of the paired wheel power mechanisms includes a wheel frame and a wheel rotatably connected thereto. The wheel frame is internally provided with a power mechanism connected with a wheel axis of the wheel. Each of the soft contact mechanisms includes a flexible cantilever and a soft transmission belt. The two paired wheel power mechanisms are respectively arranged at two ends of each of the flexible cantilevers. The wheel on one of the paired wheel power mechanisms is connected with the wheel on the other of the paired wheel power mechanisms. The buffer spring mechanisms are arranged between the wheel frames and the wheels. The middle frame deformation mechanism includes a connection unit and two movable units rotatably connected to the connection unit respectively.