Abstract: A vehicle data collection system includes a vehicle-mounted sensor; a non-transitory computer readable medium configured to store instructions; and a processor connected to the non-transitory computer readable medium. The processor is configured to execute the instructions for generating an invariant feature map, using a first neural network; and comparing the invariant feature map to template data to determine a similarity between the invariant feature map and the template data, wherein the template data is received from a server. The processor is further configured to execute the instructions for determining whether the determined similarity is exceeds a predetermined threshold; and instructing a transmitter to send the sensor data to the server in response to a determination that the determined similarity exceeds the predetermined threshold.

Abstract: An aircraft control method includes: acquiring a current flight state of the aircraft, in response to the aircraft being in a night flight mode, the aircraft being provided with a visual sensor and a light supplementation lamp configured to provide a fill light function for the visual sensor; controlling the light supplementation lamp to emit light according to a light supplementation rule of the light supplementation lamp, in response to the aircraft being in a first flight state; and controlling the light supplementation lamp to emit light according to an alerting rule of the light supplementation lamp, in response to the aircraft being in a second flight state. The light supplementation rule is configured to control the light supplementation lamp to implement the fill light function in the night flight mode, and the alerting rule is configured to control the light supplementation lamp to implement an aircraft flight alerting function in the night flight mode.

Abstract: One example method for improving the efficiency of robotic surgical procedures via surgical procedure data analysis. The method includes accessing surgical procedure data of a robotic surgical procedure. The surgical procedure data contains data or events associated with the robotic surgical system during the robotic surgical procedure. The method further includes accessing a procedure setup plan for the robotic surgical procedure corresponding to the surgical procedure data and determining an idle period of the surgical procedure based on the surgical procedure data. The method also includes analyzing the surgical procedure data to detect one or more events associated with the idle period to determine a cause of the idle period, and generating a recommendation for modifying the procedure setup plan for the robotic surgical procedure based on the determined cause of the idle period.

Abstract: Systems and methods for autonomous robot distributed processing are provided. A method includes receiving, at a robot, camera output from a camera located on the robot. The method may further include outputting the camera output to a mobile client device. The method may also further include receiving at the robot, from the mobile client device, object recognition metadata based upon the camera output. The method may additionally include outputting a notification from the robot to a user of the mobile client device based upon the object recognition metadata.

Abstract: A method executable by an autonomous mobile device includes moving in a work environment, obtaining environmental data acquired by a sensing device, and determining whether the sensing device is in a suspected ineffective state based on the environmental data. The method also includes based on a determination that the sensing device is in the suspected ineffective state, rotating at a same location for a first predetermined spin angle. The method also includes obtaining an estimated rotation angle based on one or more motion parameters acquired by a dead reckoning sensor, comparing the estimated rotation angle with the first predetermined spin angle, and based on a determination that a difference between the estimated rotation angle and the first predetermined spin angle is greater than a first predetermined threshold value, executing escape instructions to move backwardly for a first predetermined distance and move along a curve or a folded line.

Abstract: A system and a method are disclosed that identifies a source area within a facility comprising a plurality of objects, and determines a destination area within the facility to which the plurality of objects are to be transported and unloaded. The system selects robots within the facility based a capability of the robots and/or a location of the robots within the facility. The system provides an instruction to the robots to transport the plurality of objects from the source area to the destination area. The robots are configured to autonomously select an object based on a position and location of the object within the source area, transport the selected object to a destination area along a route selected by the robot, and unload the selected object at a location within the destination area selected based on a number of objects yet to be unloaded within the destination area.

Abstract: Among other things, techniques are described for driver data guided spatial planning. A spatial structure is generated comprising a plurality of nodes connected by edges. At least some of the nodes and edges represent a path to navigate a vehicle from a first point to a second point. Edges of the spatial structure are labeled as useful based on a distance metric. The spatial structure is pruned by removing one or more edges from the spatial structure according to a respective label of the edges, wherein an extent of the removal is based on a predetermined graph size, a predetermined performance, or any combinations thereof to obtain a pruned graph. A path from the first point to the second point on the pruned graph is identified and the vehicle is navigated in accordance with the path from the first point to the second point on the pruned graph.

Abstract: Systems, methods, and computer-readable media are disclosed for autonomous tennis assistant systems. Example methods include determining, by a device, an outer boundary line of a tennis court, generating a digital representation of the tennis court using the outer boundary line, where the digital representation includes at least a portion of an out-of-bounds area adjacent to the outer boundary line, determining a first location of a first tennis ball, and causing a tennis ball retrieval robot to move to the first location to retrieve the first tennis ball, where the tennis ball retrieval robot is wirelessly connected to the device.

Abstract: The present invention relates to a transport device (100) for receiving one or more module units having machine tool accessory devices and for transporting the one or more received module units to a machine tool (1000) set up on a base surface for use of the machine tool accessory devices of the one or more received module units on the machine tool (1000), wherein the transport device (100) is freely movable on the base surface for positioning the one or more received module units relative to the machine tool (1000), in particular within a region in front and/or next to the machine tool (1000) and/or in front and/or next to a working space of the machine tool (1000).

Abstract: An autonomous cleaning robot includes a controller configured to execute instructions to perform operations including moving the autonomous cleaning robot along a first portion of a path toward a waypoint, detecting, with a ranging sensor of the autonomous cleaning robot, an obstacle along the path between the first portion of the path and a second portion of the path, navigating the autonomous cleaning robot about the obstacle along a trajectory that maintains at least a clearance distance between the autonomous cleaning robot and the obstacle, and moving the autonomous cleaning robot along the second portion of the path.

Abstract: A system-directed robotic cart picking system is described. In an example implementation, the system may generate a picking itinerary including pick-to-cart routing based on locations of items in an order fulfillment center and received order data identifying the items, and may transport the carts in the order fulfillment center according to the pick-to-cart routing. The system may determine a zone of the order fulfillment center to which to assign a picker based on the picking itinerary and may determine tasks, such as picking at least one item from the locations to the carts, for the picker located in the zone. In some instances, the system may output pick instructions to a picker client device directing the picker to perform the tasks and may transport the carts to a defined point in the order fulfillment center in response to completion of the tasks.

Abstract: A system for order fulfillment using one or more robots includes: a server configured to receive an order comprising an order item; inventory storage operably connected to the server, the inventory storage comprising order items; an actor robot operably connected to and selected by the server, the actor robot configured to perform one or more of picking the order item from inventory storage, moving the order item, and positioning the order item; and an order robot operably connected to the server, the order robot configured to collect the order item, wherein the order item is positioned by the actor robot so as to be accessible to the order robot, so as to perform order fulfillment using one or more robots.

Abstract: A method for controlling a robot is provided. The method includes the steps of: acquiring information on a sound associated with a robot call in a serving place; determining a call target robot associated with the sound, among a plurality of robots in the serving place, on the basis of the acquired information; and providing feedback associated with the sound by the call target robot.

Abstract: A method for constraining robot autonomy language includes receiving a navigation command to navigate a robot to a mission destination within an environment of the robot and generating a route specification for navigating the robot from a current location in the environment to the mission destination in the environment. The route specification includes a series of route segments. Each route segment in the series of route segments includes a goal region for the corresponding route segment and a constraint region encompassing the goal region. The constraint region establishes boundaries for the robot to remain within while traversing toward the goal region. The route segment also includes an initial path for the robot to follow while traversing the corresponding route segment.

Abstract: A method for estimating a ground plane includes receiving a pose of a robotic device with respect to a gravity aligned reference frame, receiving one or more locations of one or more corresponding contact points between the robotic device and a ground surface, and determining a ground plane estimation of the ground surface based on the orientation of the robotic device with respect to the gravity aligned reference frame and the one or more locations of one or more corresponding contact points between the robotic device and the ground surface. The ground plane estimation includes a ground surface contour approximation. The method further includes determining a distance between a body of the robotic device and the determined ground plane estimation and causing adjustment of the pose of the robotic device with respect to the ground surface based on the determined distance and the determined ground plane estimation.

Abstract: A control method for carpet drift in robot motion, a chip, and a cleaning robot are disclosed. The control method includes: performing fusion calculation on a current position coordinate of the robot according to data sensed by a sensor every first preset time, calculating amount of drift, relative to a preset direction, of the robot, according to a relative position relationship between a current position and an initial position of the robot, and accumulating to obtain a drift statistical value; and calculating the number of acquisitions of the position coordinate within a second preset time, averaging to obtain a drift average value, determining a state of the robot deviating from the preset direction according to the drift average value, and setting a corresponding Proportion Integration Differentiation (PID) proportionality coefficient to synchronously adjust speeds of left and right drive wheels of the robot while reducing a deviation angle of the robot.

Abstract: Multi-mode personal transportation and delivery devices and methods of use are disclosed herein. A device can include a communications interface, the communications interface configured to provide vehicle-to-everything communications, a device controller comprising: a processor; and a memory for storing instructions, the processor executing the instructions to: receive a first message from a service provider that the transportation device is to relocate to a location based on user demand; and activate a redistribution mode to cause the transportation device to autonomously navigate to the location.

Abstract: Methods and systems are provided for providing real world assistance by a robot utility and interface device (RUID) are provided. A method provides for identifying a position of a user in a physical environment and a surface within the physical environment for projecting an interactive interface. The method also provides for moving to a location within the physical environment based on the position of the user and the surface for projecting the interactive interface. Moreover, the method provides for capturing a plurality of images of the interactive interface while the interactive interface is being interacted with by the use and for determining a selection of an input option made by the user.

Abstract: A robot device according to various embodiments comprises a camera, a robot arm, and a control device electrically connected to the camera and the robot arm, wherein the control device can be configured to collect a robot arm control record about a random operation, acquire, from the camera, a camera image in which a working space of the robot arm is photographed, implement an augmented reality model by rendering a virtual object corresponding to an object related to objective work in the camera image, and update a control policy for the objective work by performing image-based policy learning on the basis of the augmented reality model and the control record.

Abstract: A method for controlling a patrolling robot is provided. The method includes the steps of: acquiring, as first situation information on the patrolling robot, at least one of weight information on a support coupled to the patrolling robot and image information on the support and information on a location of the patrolling robot in a patrolling place; and determining a task and a travel route of the patrolling robot on the basis of the first situation information.

Abstract: An electronic device and method for controlling a robot is provided. The electronic device includes a wireless communication unit, a camera, a touch display, a memory, and a processor configured to be operatively connected to the wireless communication unit, the camera, the touch display, and the memory. The processor is configured to recognize a marker of the robot photographed using the camera; generate an indicator indicating a space around the recognized robot; acquire location information for moving the robot to an area within the indicator by using the touch display; and transmit the acquired location information to the robot to move the robot to a location corresponding to the acquired location information.

Abstract: A surface cleaning apparatus includes a proximity-triggered user interface, and configured to provide one or more indicia to a user based on the proximity of the user to the surface cleaning apparatus. The surface cleaning apparatus can be provided with one or more proximity sensors, and the user interface is configured to receive input from the one or more proximity sensors and provide one or more indicia to the user based on the input.

Abstract: Inspection robots with center encoders are described. An example inspection robot may have a housing, and a drive module, where the drive module has a wheel and a motor and is operatively coupled to the housing. The example inspection robot may also have an encoder to provide a movement value, where the encoder is positioned within a footprint of the housing. The example inspection robot may also have a controller with an encoder conversion circuit to calculate a distance value in response to the movement value, a location circuit to determine at least one of a robot location value or a robot speed value, and a position command circuit to provide a position action command in response to the robot location value or the robot speed value. The drive module may be responsive to the position action command to move the inspection robot.

Abstract: A robot and an operating system, a control device, a control method and a storage medium thereof, wherein the robot includes a processor configured to execute the following operation commands: controlling the robot to move to a designated position corresponding to an interaction scenario, wherein the interaction scenario is a scenario in which the robot interacts with a user; controlling the robot to perform an operation corresponding to an operation of the user in the interaction scenario, thereby realizing the robot can perform a complex interaction with the user based on the colorful interaction scenario and solving the technical problem of the prior art that the interaction scenario and the interactive content between the user and the robot are excessively monotonous.

Abstract: Systems, apparatus, and methods are described for robotic learning and execution of skills. A robotic apparatus can include a memory, a processor, sensors, and one or more movable components (e.g., a manipulating element and/or a transport element). The processor can be operatively coupled to the memory, the movable elements, and the sensors, and configured to obtain information of an environment, including one or more objects located within the environment. In some embodiments, the processor can be configured to learn skills through demonstration, exploration, user inputs, etc. In some embodiments, the processor can be configured to execute skills and/or arbitrate between different behaviors and/or actions. In some embodiments, the processor can be configured to execute skills and/or behaviors using cached trajectories or plans. In some embodiments, the processor can be configured to execute skills requiring navigation and manipulation behaviors.

Abstract: Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.

Abstract: A driverless transportation vehicle for piece goods has a chassis, a traction drive, a load-transfer device with a load-transfer drive, and a control system. The chassis has at least two wheels arranged on an axle and the traction drive is configured to drive the wheels. The load-transfer device picks up an item of piece goods and transfer its center of mass on the vehicle. The control system controls the traction drive to prevent the transportation vehicle from tilting about the axle of the chassis, while the driverless transportation vehicle balances on only the at least two wheels. The control system additionally actuates the load-transfer drive in such a way that the position of the center of mass of the cargo is adapted for a driving maneuver that is to be carried out.

Abstract: An automatic detection and recovery device for residual agricultural mulch film, and a method of using the device, comprising a quadcopter, a wheeled robot (9), and a host computer (8); the quadcopter is provided with a controller (1), a near infrared water content analyzer, and a WiFi module that are used to measure water content in soil and communicate with the host computer; the wheeled robot (9) comprises a water sprinkling device (2), a soil grabbing device (3), a sifting device (4), a delivery device (5), a recognition device (6), and a sorting device (7).

Abstract: A computing system is providing for managing a fleet of spraying vehicles by selecting one or more field zones to be sprayed by a fleet of spraying vehicles. The system reviews spraying requirements including material and quantity to be sprayed and reviews spraying vehicle parameters for each spraying vehicle in of the fleet. The system then calculates a travel plan for each spraying vehicle such that the selected field zones can be sprayed accordingly without spraying areas outside the selected field zones. Once in operation, the system verifies travel plan execution of each spraying vehicle and adjusts one or more travel plans in case of vehicle malfunctions, unexpected weather conditions, and unexpected field obstacles.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for optimizing robot-implemented tasks based at least in part on historical task and location correlated duration data collected from one or more robots. Historical task and location correlated duration data may, in some implementations, include durations of different tasks performed in different locations by one or more robots in one or more particular environments, and knowledge of such durations may be used to optimize tasks performed by the same or different robots in the future.

Abstract: The invention discloses high-precision mobile robot management and scheduling system, and relates to the technical field of industrial robots, comprising industrial robot, AGV, secondary positioning device and upper computer, wherein the secondary positioning devices are arranged on corresponding workstations of processing machine tool, when the processing machine tool performs processing tasks, the upper computer selects the AGV arranged with industrial robot and navigates the same to the secondary positioning device, and after the secondary positioning device and the chassis of the industrial robot are locked, the industrial robot can assist the processing machine tool in parts machining. The system in the invention perfectly combines the mobile robot and fixed robot, thereby achieving not only flexibility of mobile robot, but also the high precision of the fixed robot.

Abstract: Systems, apparatuses and methods may provide for controlling one or more end effectors by generating a semantic labelled image based on image data, wherein the semantic labelled image is to identify a shape of an object and a semantic label of the object, associating a first set of actions with the object, and generating a plan based on an intersection of the first set of actions and a second set of actions to satisfy a command from a user through actuation of one or more end effectors, wherein the second set of actions are to be associated with the command.

Abstract: A robotic system includes a multi-sectional show robot. The multi-sectional show robot includes a primary robot with a controller and one or more sensors. The one or more sensors are configured to acquire feedback indicative of an environment surrounding the primary robot. The multi-sectional show robot also includes a secondary robot configured to removably couple to the primary robot to transition the multi-sectional show robot between a disengaged configuration, in which the primary robot is decoupled from the secondary robot, and an engaged configuration, in which the primary robot is coupled to the secondary robot. The controller is configured to operate the primary robot based on the feedback and a first control scheme with the multi-sectional show robot in the disengaged configuration and to operate the primary robot based on a second control scheme with the multi-sectional show robot in the engaged configuration.

Abstract: The embodiments of the disclosure provide a space recognition method, an electronic device and a non-transitory computer-readable storage medium. The method includes the following steps. Sensor data for detecting obstacle positions is obtained from a sensor associated with an electronic device. A plurality of coordinates respectively corresponding to the obstacle positions are generated based on the sensor data. Boundary line information of a space surrounding the electronic device is updated according to the coordinates until an optimization condition is met for each boundary line. A spatial range of the space surrounding the electronic device is identified based on the boundary line information. The spatial range is used to guide a movement of the electronic device.

Abstract: Systems and methods for determining whether a user employs System 1 type thinking or System 2 type thinking when engaged in a task are disclosed. The systems and methods include determining one or more properties of the task based on information regarding the task received from a database storing information regarding the task, determining one or more properties of the user with respect to the task, determining a state of the user based on one or more physiological sensors configured to sense one or more characteristics of the user, and determining that the user employs System 1 type thinking or System 2 type thinking when engaged in the task based on the determined one or more properties of the task, the determined one or more properties of the user, and the determined state of the user.

Abstract: A robot includes: a moving mechanism; an elevating mechanism including columnar members; a table which is configured to be elevated and lowered by the elevating mechanism; an arm base which is configured to be elevated and lowered by the elevating mechanism; an arm which is attached to the arm base; a sensor which is configured to detect an object placed on the table and the surrounding area of the robot; and a controller. A circumscribed space circumscribing the robot except for the arm is in the shape of a cuboid having a bottom face that is a face of a quadrilateral that circumscribes, in a top view, the shape of the robot except for the arm. The arm has a structure capable of accessing the outside of the circumscribed space.

Abstract: Disclosed is a robot lawnmower including a body frame, a main wheel disposed on both sides of the body frame, a motor to drive the main wheel, a first edge blade provided in a region of the body frame corresponding to the main wheel and coupled to be rotatable with respect to the body frame by receiving a driving force of the motor, and a second edge blade disposed between the body frame and the main wheel to rotate together with the main wheel and cut a grass by a relative rotation of the first edge blade and the main wheel.

Abstract: An example implementation involves controlling robots with non-constant body pitch and height. The implementation involves obtaining a model of the robot that represents the robot as a first point mass rigidly coupled with a second point mass along a longitudinal axis. The implementation also involves determining a state of a first pair of legs, and determining a height of the first point mass based on the model and the state of the first pair of legs. The implementation further involves determining a first amount of vertical force for at least one leg of the first pair of legs to apply along a vertical axis against a surface while the at least one leg is in contact with the surface. Additionally, the implementation involves causing the at least one leg of the first pair of legs to begin applying the amount of vertical force against the surface.

Abstract: For processing a signal from an event-based sensor having an array of sensing elements facing a scene, the method comprises: receiving the signal including, for each sensing element, successive events originating from said sensing element depending on variations of incident light from the scene; analyzing the signal to detect a frequency pattern in a light profile sensed by at least one sensing element; and extracting information from the scene in response to detection of the frequency pattern.

Abstract: Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.

Abstract: An outer space-based reusable manufacturing and assembly system including at least one joint that comprises at least one receiver component, at least one strut that engages the at least one receiver component on the at least one joint and a joining element that provides for engaging and disengaging the at least one joint with at least the at least one strut so that either the at least one joint and the at least one strut are usable for another mission. Two other systems are also disclosed.

Abstract: The present disclosure relates to a method for detecting a skidding of a robot, a mapping method and a chip. A method for detecting a skidding of a robot, comprising the following steps: By an odometer on existing driving wheels of a robot and a gyroscope and a processor in a body of the robot, a first angle change rate generated by two driving wheels within a preset time and a second angle change rate generated by the gyroscope within the preset time are detected and calculated, so as to determine an angular velocity change error rate of the robot. Finally, by judging whether the angular velocity change error rate is greater than or equal to a preset value, it is determined whether the robot is in the skidding state.

Abstract: A mobile robot is configured for operation in a commercial or industrial setting, such as an office building or retail store. The robot can patrol one or more routes within a building, and can detect violations of security policies by objects, building infrastructure and security systems, or individuals. In response to the detected violations, the robot can perform one or more security operations. The robot can include a removable fabric panel, enabling sensors within the robot body to capture signals that propagate through the fabric. In addition, the robot can scan RFID tags of objects within an area, for instance coupled to store inventory. Likewise, the robot can generate or update one or more semantic maps for use by the robot in navigating an area and for measuring compliance with security policies.

Abstract: An active imaging system uses a MEMS Micro-Mirror Array to form and scan an optical beam over a first portion of scene within a first edge region of the field-of-view of the optical receiver in the direction of motion of the imaging system. In addition to tip and tilt control of the mirrors, the MMA may have piston control which can be used to minimize diffraction losses when focusing and scanning the beam, provide wavefront correction or to compensate for path length variations. The MMA may be partitioned into segments to independently form and scan a plurality of optical beams, which may be used to scan the first or different portions of the scene. The different segments may be provided with reflective coatings at different wavelengths to provide for multi-spectral imaging. The different segments may be used to combine multiple optical sources to increase power or provide multi-spectral illumination.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating paths for a robot based on optimizing multiple objectives. One of the methods includes: receiving, by a motion planner, request to generate a path for a robot between a start point and an end point in a workcell of the robot, wherein the workcell is associated with one or more soft margin values that define spaces in which the robot should avoid when transitioning between points in the workcell; classifying path segments within the workcell as being inside the soft margin or outside the soft margin; generating a respective cost for each of the plurality of path segments within the workcell; generating a plurality of alternative paths; evaluating the plurality of alternative paths according to the respective costs; and selecting an alternative path based on respective total costs of the plurality of alternative paths.

Abstract: A mobile manipulation control method of a quadruped robot with an operation arm, including: obtaining current pose information of the legged mobile manipulator; decomposing a task into subtasks, and prioritizing the subtasks; based on the pose information and a dynamic model, generating a motion trajectory under each subtask; based on the dynamic model, optimizing an optimal plantar force of a supporting leg and an end-of-arm force under each subtask; based on a multi-task spatial projection method, calculating desired control quantity of all joints under different subtasks; and (d) optimizing the optimal plantar force and the desired control quantity with the whole-body dynamic model as a constraint to obtain control torques; and based on the control torques, controlling the legged mobile manipulator's motion. A control system is further provided.

Abstract: A conveyance system includes a plurality of conveyance robots, a storage unit, a stability information acquisition unit, a selection unit, and a system controller, which serves as a controller. The plurality of conveyance robots convey a wagon that accommodates a conveyed object. The storage unit stores robot information regarding features that the plurality of respective conveyance robots include. The stability information acquisition unit acquires stability information regarding stability when the conveyed object is conveyed. The selection unit selects one of the plurality of conveyance robots based on the robot information and the stability information that have been acquired. The system controller instructs the one conveyance robot that has been selected to convey the conveyed object.

Abstract: A configuration that exerts floor reaction force directly to a force sensor in a foot of a legged mobile robot requires a sensor having a large withstand load. A foot (10f) includes an upper frame (44) that is connected to a movable leg and receives the load of a robot, a lower frame (48) that is deployed under the upper frame (44) and contacts with a walking surface, a high rigidity spring (50) attached the lower frame (48) and elastically supporting the upper frame (44) against the load, and a plurality of sensor mechanisms that detect floor reaction force at positions different from each other on the lower frame (48).

Abstract: In example implementations, an apparatus is provided. The apparatus includes a microphone, a radar, a memory, and a processor in communication with the microphone, the radar, and the memory. The microphone is to receive audio signals. The radar is to collect data on users in a location. The memory is to store known body positions associated with having a side-conversation. The processor is to determine that a user is having a side-conversation based on the data collected by the radar compared to the known body positions associated with having a side-conversation and filter noise associated with the side-conversation received by the microphone from a direction associated with the user.

Abstract: An autonomous cleaning robot includes a drive system to move the autonomous cleaning robot about a floor surface in a space, a cleaning system to clean a floor surface in the space as the drive system moves the autonomous cleaning robot about the floor surface, and a controller configured to execute instructions to perform one or more operations.