Abstract: A self-propelled floor processing device with an evaluation unit, which is designed to navigate the floor processing device within an environment based on an area map and, during a movement, to determine a behavior parameter of the floor processing device and a movement path of the floor processing device. The evaluation unit is set up to analyze the behavior parameter and movement path, automatically determine a no-go area which the floor processing device must not traverse depending on the result of the analysis, and enter the determined no-go area in the area map or change a no-go area already entered in the area map.

Abstract: There are included an own vehicle position sensor which detects the position of an own vehicle; a reference path acquisition unit which acquires a reference path on which the own vehicle travels; a reference path determination unit which determines whether or not the own vehicle is traveling on the reference path; a temporary vehicle path calculation unit which, when it is determined by the reference path determination unit that the own vehicle is not traveling on the reference path, calculates a temporary vehicle path from at least two points, a travel start point of the own vehicle and an end point of the reference path; and a vehicle path setting unit which sets either the temporary vehicle path calculated by the temporary vehicle path calculation unit or the reference path on which it is determined by the reference path determination unit that the own vehicle is traveling as the vehicle path of the own vehicle.

Abstract: A robotic device including one or more proximity sensing systems coupled to various portions of a robot body. The proximity sensing systems detect a distance of an object about the robot body and the robotic device reacts based on the detected distance. The proximity sensing systems obtain a three-dimensional (3D) profile of the object to determine a category of the object. The distance of the object is detected multiple times in a sequence to determine a movement path of the object.

Abstract: Techniques for dividing a geographical area into districts are described herein. Geospatial vector data, barrier geospatial vector data, road infrastructure data, and historical delivery demand data for a geographical area may be obtained. A plurality of clusters from a stratified sampling of data points for the delivery demand data and barrier penalties from a barrier-aware road graph are generated. A first set of polygons for the plurality of clusters may be generated using a concave hull algorithm. A second set of polygons may be generated using a barrier constrained network Voronoi algorithm that uses the barrier-aware road graph and the first set of polygons as seeds. The second set of polygons may be modified using a bounded Voronoi algorithm that uses a raster cost allocation based on barrier penalties. Coordinates for each polygon of the modified second set of polygons are determined that divide the geographical area.

Abstract: According to the present invention, a moving body capable of moving within a preset range of movement acquires an image from the environment surrounding the location of the moving body, and determines entry determination conditions for obtaining a result of an entry determination as to whether or not the moving body is allowed to enter a region identified by the location of the moving body and the image. A management terminal outputs the entry determination conditions and the image to an output device, and receives modification information relating to the entry determination conditions from an input device. A server uses the modification information received by the input device of the management terminal to perform learning, including updating of the entry determination conditions, thereby setting the movement range of the moving body, the movement of which is controlled in accordance with the entry determination result.

Abstract: The route generation device includes a controller configured to generate, in response to acceptance of an allowable arrival time period assigned to at least one of the plurality of destinations, an input of information regarding specifics of a task to be performed at the at least one destination, and setting of a required time period according to the specifics of the task, a route that allows the autonomous mobile body to arrive at the at least one destination within the allowable arrival time period, based on the required time period. The controller is configured to control and cause the autonomous mobile body to travel along the generated route.

Abstract: A robot controller includes: axis motor control units that control motors for driving axes of a robot; and an action command generation unit that generates a first action command having the shortest action time when the robot is moved from an action start point to an action goal point without considering an obstacle, and selects, from among the axes, a major axis having the longest action time when the action is performed in accordance with the first action command. The first action command includes another axis command, and a major axis command, and the action command generation unit adjusts the other axis command so as to reduce an action time according to the other axis command and outputs a second action command including the major axis command and the adjusted other axis command and corresponding to a first trajectory when determining that the first trajectory avoids a clash between the robot and the obstacle.

Abstract: A robotic work tool system (200) for defining a stay-out area (120) within a work area (150). The stay-out area (120) is an area which is to be excluded from the work area (150) in which a robotic work tool (100) is subsequently intended to operate. The robotic work tool system (200) comprises a boundary definition unit (130) comprising at least one position unit (175) configured to receive position data and at least one controller (110, 210). The controller (110, 210) is configured to receive a stay-out area definition trigger signal, which indicates that the boundary definition unit (130) has approached the stay-out area to be defined. The controller (110, 210) is further configured to receive, based on the received signal, position data indicating the present position of the boundary definition unit (130) from the position unit (175). The controller (110, 210) is further configured to define the stay-out area (120) as an area centered at an offset from the received position data.

Abstract: The present invention provides a guide display device capable of recognizing a feature in a work area while distinguishing whether the feature is a moving body or not. In a guide display device of a crane, 3D maps are created for continuous frames; an altitude value for each grid in a 3D map that is created at time closest to the current time is obtained as a first altitude value; altitude values for respective corresponding grids in a predetermined number of 3D maps other than the 3D map that is created at time closest to the current time are obtained, and the average of the altitude values is calculated as a second altitude value; and it is determined that the feature is a moving body when the difference between the first altitude value and the second altitude value exceeds a predetermined threshold.

Abstract: A method for 3D object detection is described. The method includes predicting, using a trained monocular depth network, an estimated monocular input depth map of a monocular image of a video stream and an estimated depth uncertainty map associated with the estimated monocular input depth map. The method also includes feeding back a depth uncertainty regression loss associated with the estimated monocular input depth map during training of the trained monocular depth network to update the estimated monocular input depth map. The method further includes detecting 3D objects from a 3D point cloud computed from the estimated monocular input depth map based on seed positions selected from the 3D point cloud and the estimated depth uncertainty map. The method also includes selecting 3D bounding boxes of the 3D objects detected from the 3D point cloud based on the seed positions and an aggregated depth uncertainty.

Abstract: In a method for storing and picking stackable article carriers in an order fulfillment facility, in which transport loading aids are transported between a loading station with an automatically operated loading device, a storage zone and a removal station with an automatically operated unloading device by autonomously moveable, driverless transport vehicles, the transport loading aids are loaded with article carrier stacks in the loading station and the article carrier stacks are discharged from the transport loading aids in the unloading station. Subsequently, the article carriers for a picking order are reloaded onto one or multiple target loading aids. Further, an order fulfillment facility stores and stackable article carriers.

Abstract: A method for controlling motion of a vehicle, the method comprising the steps of: obtaining input information on a vector related to the velocity of said vehicle; computing repeatably a future trajectory of said vehicle based on said input information and trial torques to be applied to at least one wheel of said vehicle for optimizing said future trajectory in view of a target vehicle motion, thereby obtaining target trial torques; and applying the obtained target trial torques to the at least one wheel for controlling the motion of said vehicle.

Abstract: Aspects of the disclosure relate to providing information about a vehicle dispatched to pick up the user. In one example, a request for the vehicle to stop at a particular location is sent. In response, information identifying a current location of the vehicle is received. A map is generated. The map includes a first marker identifying the received location of the vehicle, a second marker identifying the particular location, and a shape defining an area around the second marker at which the vehicle may stop. The shape has an edge at least a minimum distance greater than zero from the second area. A route is displayed on the map between the first marker and the shape such that the route ends at the shape and does not reach the second marker. Progress of the vehicle towards the area along the route is displayed based on received updated location information for the vehicle.

Abstract: An autonomous unmanned aerial vehicle detecting system for monitoring a geographic area includes an unmanned blimp adapted to hover in air, at least one camera mounted on the blimp to scan at least a portion of the geographic area, a location sensor to determine a location of the blimp, and a controller arranged in communication with blimp, the at least one camera, and the location sensor. The controller is configured to position the blimp at a desired location in the air based on inputs received from the location sensor, and monitor the geographic area based on the images received from at least one camera. The controller is also configured to detect a presence of an unmanned aerial vehicle within the geographic area based on the received images, and determine whether the detected unmanned aerial vehicle is an unauthorized unmanned aerial vehicle based on the received images.

Abstract: The disclosure relates to a method for controlling a robot to return to a base. The method includes the robot receives a return-to-base control signal; the robot walks along different preset paths according to different receiving conditions of guidance signals; and when detecting an intermediate signal during walking along a preset path, the robot returns to the base directly under piloting of the intermediate signal instead of walking along the preset path. The guidance signals are signals sent by a charging base, for piloting the robot to return to the base, and include the intermediate signal.

Abstract: Methods, systems, and computer-readable media are disclosed herein that generate computer-executable instructions that are executed by an autonomous vehicle and cause the autonomous vehicle to follow a specific route to deliver or pickup of an item. Using an inference model, historical data of off-street terrain used for prior deliveries and on-street terrain in map data are leveraged to generate candidate routes for the “last 10 feet” of a delivery. One of the candidate routes is selected by the inference model. Then, computer-executable instructions are generated that, when executed by an autonomous vehicle, cause the autonomous vehicle to follow the selected route and perform the last 10 feet of delivery.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive a set of points indicating a lane boundary; select a first subset of the points, wherein the set of points includes a first point that is not in the first subset; determine a path of the lane boundary based on the first subset of the points; and, upon determining that the first point is greater than a threshold distance from the path, add the first point to the first subset.

Abstract: A system receives confirmation that a vehicle has accepted automatic control imposition for a drive within a geo-fenced boundary. The system tracks travel of a plurality of vehicles, including the vehicle, within the geo-fenced boundary. The system may determine that the vehicle has a threshold likelihood of encountering at least one of another vehicle or a boundary of the geo-fence at a threshold speed or above and responsive to the determination, impose automatic control on the vehicle, including at least one of controlled braking or speed limiting.

Abstract: The present invention relates to a method of assigning sentry duty tasks to off-duty first responders. The method includes entering and storing persons of attendance into a watchful record. Then, in operation, scanning and processing the social media of the persons of attendance looking for future event warning signs. Responsive to the future event warning signs and associated threat level generating a sentry duty task that includes a date, a time, a duration, a watch area, the future event warning sign, the first responder need, the threat level, a pay amount, or other items. First responders can accept, schedule, and execute the sentry duty task during their off-duty hours. Upon executed sentry duty task the first responder is electronically paid. Other exemplary embodiments include venue administrators creating a future event warning sign based on a known need, things that they are aware of or observe, or for other reasons.

Abstract: The present invention provides specific systems, methods and algorithms based on artificial intelligence expert system technology for determination of preferred routes of travel for electric vehicles (EVs). The systems, methods and algorithms provide such route guidance for battery-operated EVs in-route to a desired destination, but lacking sufficient battery energy to reach the destination from the current location of the EV. The systems and methods of the present invention disclose use of one or more specifically programmed computer machines with artificial intelligence expert system battery energy management and navigation route control. Such specifically programmed computer machines may be located in the EV and/or cloud-based or remote computer/data processing systems for the determination of preferred routes of travel, including intermediate stops at designated battery charging or replenishing stations.

Abstract: A robot includes: a communication unit that receives a remote operation instruction by a user terminal of a user; a body unit capable of traveling; a head unit attached to the body unit and capable of changing a direction; a camera; a control unit that controls the body unit, the head unit, and the camera, based on the operation instruction; and an operation switching input unit that switches between the operation instruction by the user terminal of the user and an operation instruction by a facility terminal of a facility user, and when switching the operation instruction, the operation switching input unit requests the user for whether to approve user switching, and when the user approves the user switching of the operation instruction via the user terminal, the operation switching input unit switches the operation instruction by the user terminal to the operation instruction by the facility terminal.

Abstract: A reconnaissance UAV and a surveillance flight method of the reconnaissance UAV which can reduce a number of required reconnaissance UAVs are provided. The surveillance flight method for detecting an unauthorized UAV includes: defining multiple flight passages in a UAV no-fly zone for a plurality of reconnaissance UAVs; controlling each of the plurality of reconnaissance UAVs to fly across adjacent flight passages at an interval by crossing a border of the adjacent flight passages; and controlling at least one of an image sensor and a noise sensor mounted on the reconnaissance UAV to dynamically change a direction detection thereof.

Abstract: Systems and methods for improved control of nonholonomic robotic systems are disclosed herein. According to at least one non-limiting exemplary embodiment, a holonomic reference point on or nearby a nonholonomic robot may be determined and utilized to navigate the robot along a target trajectory. Due to the holonomicity of the reference point, control logic of the robotic system may be greatly simplified, thereby enhancing accuracy of navigation and navigation capabilities of nonholonomic robotic systems.

Abstract: A system and method are arranged to provide recommendations to a user of a vehicle. In one aspect, the vehicle navigates in an autonomous mode and the sensors provide information that is based on the location of the vehicle and output from sensors directed to the environment surrounding the vehicle. In further aspects, both current and previous sensor data is used to make the recommendations, as well as data based on the sensors of other vehicles.

Abstract: The use of multiple horizon optimization for vehicle dynamics and powertrain control of a vehicle is provided. Long horizon optimization for a trip of the vehicle is performed, and an optimal value function is determined. Data is received from powertrain and/or connectivity features from one or more of components of the vehicle. Short horizon optimization for the trip is performed using a rollout algorithm, the optimal value function, and the received data. The operation of the vehicle is adjusted using results of the short horizon optimization.

Abstract: An information processing method is to be executed by a computer. The information processing method includes: receiving, from an autonomous moving body, a first processing result that is a result of first preprocessing of travel control processing in autonomous movement processing of the autonomous moving body, and sensing data received by the autonomous moving body; executing second preprocessing based on the sensing data to receive a second processing result, the second preprocessing being more advanced than the first preprocessing; determining a difference between the first processing result and the second processing result; and outputting, to the autonomous moving body based on the difference determined, a change request to change the first processing result to the third processing result, the third processing result being received based on at least one of the first processing result or the second processing result.

Abstract: An autonomously traveling vehicle includes a main body, a storage, an autonomous travel plan generator and a traveling controller. The main body includes a traveling carriage. The storage stores partial traveling route data generated for subareas including an individual coordinate system, and route connection data connecting the partial traveling routes. The autonomous travel plan generator generates an autonomous traveling schedule for autonomous travel by associating the selected partial traveling route data and the selected route connection data that connects the partial traveling routes. The traveling controller controls the traveling carriage in accordance with the autonomous traveling schedule to move the main body.

Abstract: A system, method, and computer program for updating calibration lookup tables within an autonomous vehicle or transmitting roadway marking changes between online and offline mapping files is disclosed. A LIDAR sensor may be used for generating an online (rasterized) mapping file with online intensity values which are compared against a correlated offline (rasterized) mapping file having offline intensity values. The online intensity value may be used to acquire a lookup table having a normal distribution that is compared against the offline intensity value. The lookup table may be updated when the offline intensity value is within the normal distribution. Or the vehicle may transmit a roadway marking change when the offline intensity value is outside the normal distribution.

Abstract: A UAV having a GPS spoofing detector allowing the UAV to determine during flight if the GPS is being spoofed by a third party. The UAV includes a 3-axis magnetometer that is utilized by a controller to determine if the GPS data is correct, or if it is incorrect and perhaps being spoofed. The controller compares GPS heading data with heading data provided by the 3-axis magnetometer. The controller generates an alert if heading are not correlated. This allows the controller to respond to the spoofing detection, such as by directing the UAV to return home.

Abstract: A control system of a mobile object that can move in any one operation mode determined from a plurality of operation modes is provided. The control system includes: a storage device configured to store instructions; and one or more processors, wherein the one or more processors execute the instructions stored in the storage device to: generate evaluation information for a trajectory of the mobile object including a trajectory on a sidewalk; each of the plurality of operation modes being associated with an acceptance level for an event that may occur when the mobile object moves along a trajectory; and generate the evaluation information for the trajectory based on the acceptance level in the operation mode associated with an event that occurs when moving along the trajectory.

Abstract: In a vehicle measuring device unit, a data processing device includes a plurality of input parts each connected to a different one of the plurality of detectors, an output part connected to a control device provided in a vehicle, and an integrated data generation part that generates integrated data using detection data input from the plurality of detectors via the plurality of input parts and outputs the generated integrated data via the output part. The number of wires connecting the control device with the integrated data generation part is smaller than the number of wires connecting the integrated data generation part with the plurality of detectors.

Abstract: A control apparatus of an autonomously navigating work machine driven by drive units while servicing a work area which is equipped with an information acquisition unit that acquires information relating to a navigation-desired region where navigation is desired inside or outside of the work area, a search unit that searches for a navigation route from a current location of the work machine to a desired location based on acquired information relating to the navigation-desired region, and a control unit that drives the work machine to run by driving the drive units in accordance with the navigation route searched by the search unit.

Abstract: Disclosed are methods, systems, and non-transitory computer-readable medium for determining guidance information for a vehicle. For instance, the method may include: determining whether the vehicle requires a charging event at least based on a state of charge of a battery system of the vehicle; determining a charging location of a charging station from a plurality of charging stations based on data associated with the vehicle and/or data associated with each of the plurality of charging stations; determining a current location of the vehicle; determining information to guide the vehicle from the current location to the determined charging location and align a charging interface of the vehicle to a charging interface of the charging location; and causing display of the determined information.

Abstract: The present disclosure provides a general purpose operating system (GPROS) that shows particular usefulness in the robotics and automation fields. The operating system provides individual services and the combination and interconnections of such services using built-in service extensions, built-in completely configurable generic services, and ways to plug in additional service extensions to yield a comprehensive and cohesive framework for developing, configuring, assembling, constructing, deploying, and managing robotics and/or automation applications. The disclosure includes GPROS extensions and features directed to use as an autonomous vehicle operating system. The vehicle controlled by appropriate versions of the GPROS can include unmanned ground vehicle (UGV) applications such as a driverless or self-driving car. The vehicle can likewise or instead include an unmanned aerial vehicle (UAV) such as a helicopter or drone.

Abstract: Among other things, techniques are described for controlling, using a control circuit, motion of a vehicle based objects identified using LiDAR. For example, respective classes of points of a point cloud are determined, and based on the determined respective classes of the points of the point cloud, objects in the vicinity of the vehicle are identified.

Abstract: provided is an information processing device comprising: a map database in which a control parameter for controlling the behavior of the vehicle is recorded for each vehicle type at each point on a road; a data reading unit that acquires vehicle information including at least vehicle type information and positional information of the vehicle and reads the control parameter corresponding to the travel point of the vehicle from the map database based on the vehicle information; a parameter setting unit that sets an application control parameter to be applied to control of the vehicle based on the control parameter read by the data reading unit; and a data update unit that acquires an observation value related to the behavior of the vehicle controlled based on the application control parameter from the vehicle and updates the map database based on the observation value.

Abstract: The invention relates to a machine (1) for handling loads (24), comprising: —a wheeled chassis (2), —a drive system (3) for moving the wheeled chassis (2), —a load handling system (4) carried by the chassis (2), —a control unit (5), a device (6) for controlling the load handling system (4) that can be manually actuated by an operator, the control unit (5) being configured to receive control signals from said control device (6), a member (7) for activating the manually actuatable control device (6). The handling machine (1) comprises a sensor (8) of a parameter representative of a movement of the machine (1), and the control unit (5) is configured to allow the control of the handling system (4) with the control device (6) as a function of at least the parameter representative of a movement of the machine (1).

Abstract: Systems and method are provided for defining map data used in controlling a vehicle. In one embodiment, a method includes: receiving, by a processor, telemetry data; determining, by the processor, distribution data of a path based on the telemetry data; determining, by the processor, a plurality of sample data based on a trained machine learning model and the distribution data; generating, by the processor, at least one of lane line data and road edge data based on the sample data and a second machine learning model; and storing, by the processor, the map data including the lane line data and road edge data for use in controlling the vehicle.

Abstract: In a vehicle collision determination apparatus, a position calculation unit calculates a trajectory of a target that is a movement trajectory of the target, and calculates an entrainment trajectory of the vehicle that is a movement trajectory of the vehicle during a turn, and calculate a position of collision where a collision is likely to occur between the vehicle and the target based on the trajectory of the target and the entrainment trajectory of the vehicle. A time calculation unit calculates a time to collision (TTC) that is a time it takes for the target to reach the position of collision. In response to the time to collision being equal to or less than a predefined determination threshold, a risk determination unit determines that there is a risk of collision between the vehicle and the target.

Abstract: An information presentation method that is executed by a computer includes acquiring travelling path information that includes a cleaning path and a relocation path, the cleaning path showing positions cleaned by a self-propelled vacuum cleaner in each of a plurality of regions included in a specific area, and the relocation path showing a route of the self-propelled vacuum cleaner that has travelled from one region to another region different from the one region out of the regions, the route being included in the specific area; generating presentation information that includes the cleaning path and the relocation path and that changes the mode of display of at least one of the cleaning path or the relocation path when a specific condition is satisfied; and presenting the presentation information to the user as the travelling path of the self-propelled vacuum cleaner in the specific area.

Abstract: An apparatus includes processing circuitry configured to determine an actual driving performance of a driver in a manual driving mode and a projected driving performance if the vehicle had been operated in an autonomous driving mode, compare the driving performance in the manual driving mode and the autonomous driving mode, and transmit a feedback to the driver based on the comparison. The processing circuitry can be further configured to determine a driver state of the driver in the manual driving mode, determine environmental driving condition of the vehicle, and establish a baseline behavior of the driver as a function of the driver state and the environmental driving condition.

Abstract: An apparatus for forward collision avoidance assist-junction turning of a vehicle includes a sensor for acquiring at least one of a steering angle, a steering angle speed, or a yaw rate of a vehicle, or a size, a position, or a speed of an opposite target. A traveling path area for a left-turn or a right-turn is calculated by a controller based on the steering angle or the yaw rate of the vehicle. The traveling path area is then corrected by the controller based on at least a portion of the steering angle, the steering angle speed, or the yaw rate of the vehicle, or the size, the position, and the speed of the opposite target. A warning against the collision between the vehicle and the opposite target and a control operation to prevent the collision are performed based on the corrected traveling path area.

Abstract: The embodiment of the present disclosure provides a method for setting time of traffic lights in a smart city and an Internet of Things system. The method is implemented by an Internet of Things system for setting time of traffic lights in a smart city, which includes a user platform, a service platform, a management platform, a sensor network platform, and an object platform. The method includes: obtaining pedestrian information and intersection information of a target intersection, and the target intersection being an intersection provided with the traffic lights; determining, based on the pedestrian information and the intersection information, the scheme for setting time of the traffic lights at the target intersection; and sending a control instruction corresponding to the scheme for setting the time to the object platform, and in response to the received control instruction, controlling lighting duration of the traffic lights by the object platform.

Abstract: The present disclosure provides a driving data processing method, an apparatus, a device, an automatic driving vehicle, a medium and a product, including: collecting first driving data generated by using a target structure in a driving system of a target vehicle, where the first driving data uses a binary number system; determining a target descriptor corresponding to the target structure, where the target descriptor is used to describe member information of the target structure; parsing the target descriptor to obtain at least one piece of member information of the target structure; parsing the first driving data according to the at least one piece of the member information to obtain target data corresponding to each of the at least one piece of the member information; and performing a data processing operation based on the target data corresponding to each of the at least one piece of the member information.

Abstract: A moving track prediction method includes obtaining an initial state, of a moving target that includes an initial location and an initial motion state, generating one or more destination states of the moving target based on the initial state of the moving target and preset path information, and predicting a moving track of the moving target based on the initial state of the moving target and the one or more destination states to obtain one or more predicted moving tracks.

Abstract: A parking assistance method according to the present disclosure is a method of performing autonomous travel of a vehicle based on a travel route generated using teaching travel by a driver. The parking assistance method including: acquiring as absolute position and an azimuth is the a travel direction of the vehicle; and determining, based on the absolute position and the azimuth in the travel direction, whether or not the vehicle is located oriented with a prescribed azimuth in a prescribed position, which are registered in association with the travel route.

Abstract: When an autonomous driving vehicle picks a user up, a control device performs departure condition confirmation processing.

Abstract: Heuristic evaluation systems and methods for spatial information deliverability for electric vehicle (EV) owners who are traveling and looking for charging location suggestions via their navigation systems, mobile applications, and/or the like. Suggestions are captured based on prior knowledge and user desires. In general, the system knows that a user is traveling from point A to point B and has a suggested optimal distance and/or time and/or cost to reach point B. The systems gathers information related to the traveler's desires in relation to lesser known dimensions, to enhance the overall quality of the travel and charging experience.

Abstract: Systems and methods for dynamic predictive control of autonomous vehicles are disclosed. In one aspect, an in-vehicle control system for a semi-truck includes one or more control mechanisms configured to control movement of the semi-truck and a processor. The system further includes computer-readable memory in communication with the processor and having stored thereon computer-executable instructions to cause the processor to receive a desired trajectory and a vehicle status of the semi-truck, determine a dynamic model of the semi-truck based on the desired trajectory and the vehicle status, determine at least one quadratic program (QP) problem based on the dynamic model, generate at least one control command for controlling the semi-truck by solving the at least one QP problem, and provide the at least one control command to the one or more control mechanisms.

Abstract: The present invention relates to a road crossing method for a mobile robot. The road crossing method comprises the mobile robot approaching a road crossing. Further, the road crossing method comprises estimating, with a data processing unit, a location and time of collision with at least one dynamic object on the road crossing. Further still, the road crossing method comprises generating, with the data processing unit, control commands for the mobile robot to avoid collision with the at least one dynamic object based on the estimated location and time of collision with the at least one dynamic object. In addition, the present invention relates to a mobile robot comprising the data processing unit and configured to carry out the road crossing method.