Abstract: Some embodiments include a robot, including: a chassis; a set of wheels coupled to the chassis; at least one encoder coupled to a wheel with a resolution of at least one count for every ninety degree rotation of the wheel; a trailing arm suspension coupled to each drive wheel for overcoming surface transitions and obstacles, wherein a first suspension arm is positioned on a right side of a right drive wheel and a second suspension arm is positioned on a left side of a left drive wheel; a roller brush; a collection bin; a fan with multiple blades for creating a negative pressure resulting in suction of dust and debris; a network card for wireless communication with at least one of: a computing device, a charging station, and another robot; a plurality of sensors; a processor; and a media storing instructions that when executed by the processor effectuates robotic operations.

Abstract: Disclosed is a method and apparatus for extracting data in a deep learning model. The method includes receiving an input query, determining a first decision boundary set being a subset of a decision boundary set corresponding to a target layer of the deep learning model, extracting a decision region including the input query based on the first decision boundary set, and extracting data included in the decision region.

Abstract: A perception system includes a perception module configured to capture first sensor data that includes data from at least one of an external sensor and a camera captured in a first period, a prediction module configured to receive the first sensor data, generate, based on the first sensor data, predicted sensor data for a second period subsequent to the first period, receive second sensor data for the second period, and output results of a comparison between the predicted sensor data and the second sensor data, and a diagnostic module configured to selectively identify a fault in the perception system based on the results of the comparison.

Abstract: A parking assist system is configured to autonomously move a vehicle to a target parking position. The parking assist system includes: a distance acquiring unit configured to acquire a distance between the vehicle and a vehicle stopper provided in the target parking position; and a control unit configured to control a movement of the vehicle to the target parking position based on the distance acquired by the distance acquiring unit.

Abstract: A path planning system includes a path planning algorithm operable to receive a desired harvest width for each pass of a harvester implement, and a boundary of a harvest area to be harvested. The path planning algorithm determine a surface elevation of the harvest area within the boundary, which includes at least one elevation contour establishing a line of constant elevation. The path planning algorithm then defines a harvest path for the harvester implement to follow while harvesting the crop material. The harvest path is defined to substantially parallel the at least one elevation contour, and is incremented in elevation in a parallel manner based on the desired harvest width.

Abstract: A cleaning control method and device including a cleaning robot are provided. The cleaning robot includes a sweeping member and a mopping member which cooperate with each other, and an operating parameter is obtained. A sweeping area formed in real time by the sweeping member, a mopping area formed in real time by the mopping member and a mopped area formed on a lateral side of the cleaning robot are controlled to meet a first preset relationship according to the operating parameter. The first preset relationship includes that a first distance formed between a boundary of the sweeping area closest to the mopped area and a boundary of the mopped area closest to the sweeping area is greater than or equal to a second distance between a boundary of the mopping area closest to the mopped area and a boundary of the mopped area closest to the mopping area.

Abstract: A control apparatus is configured to control advertisement data presented to an occupant of a movable object having an automated driving function, and includes a travel road specification unit for specifying a road scheduled to be travelled by the movable object corresponding to the destination, a setting unit for setting, according to the road scheduled to be travelled, a switching recommendation point for switching a driving mode of the movable object from automated drive to driver-led manual drive, a notification plan generation unit for setting a degree of importance of the advertisement data to be presented according to the driving mode for the road scheduled to be travelled, and generating a notification plan for presenting the advertisement data to the occupant according to the set degree of importance, and a notification control unit for presenting notification data including the advertisement data to the occupant according to the notification plan.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a machine-learned yield model. In particular, the machine-learned yield model can be trained or otherwise configured to receive and process feature data descriptive of objects perceived by the autonomous vehicle and/or the surrounding environment and, in response to receipt of the feature data, provide yield decisions for the autonomous vehicle relative to the objects. For example, a yield decision for a first object can describe a yield behavior for the autonomous vehicle relative to the first object (e.g., yield to the first object or do not yield to the first object). Example objects include traffic signals, additional vehicles, or other objects. The motion of the autonomous vehicle can be controlled in accordance with the yield decisions provided by the machine-learned yield model.

Abstract: A delivery system includes a cooking station, a meal serving station, a drone, a meal conveying device configured to convey a meal from the cooking station to the meal serving station, and a controlling portion. A character of a theme park is displayed on the drone. The controlling portion causes the drone to fly from the cooking station to the meal serving station and causes the meal conveying device to convey the meal from the cooking station to the meal serving station such that, just after the drone has arrived at the meal serving station, the meal conveyed by the meal conveying device is served to a visitor from the meal serving station.

Abstract: To provide personalized data for display on a map, a server device obtains location data for a user and identifies locations that are familiar to the user based on the frequency and recency in which the user visits the locations. The server device then provides the familiar locations in search results/suggestions and annotates the familiar locations with a description of a relationship between the familiar location and the user. The server device also includes the familiar locations as landmarks for performing maneuvers in a set of navigation instructions. Furthermore, the server device provides a familiar location as a frame of reference on a map display when a user selects another location nearby the familiar location. Moreover, the server device includes a familiar location as an intermediate destination when the user request navigation directions to a final destination.

Abstract: A map database stores data describing a set of connected roadways, each having one or more lanes. A coverage system selects lanes from the map database along which AVs can stop, such as parking lanes. The coverage system generates buffer regions for each of the stopping lanes, where each buffer region includes an area within a given distance of the respective lane. The coverage system combines the buffer regions to generate a coverage area, and provides a display of the coverage area overlayed over a map of roads corresponding to the coverage area.

Abstract: Example embodiments relate to using remote assistance to maneuver an autonomous vehicle to a location. A computing device used by a remote operator may receive a request for assistance from a vehicle that indicates the vehicle is stopped at a first location with one or more navigation options for enabling the vehicle to navigate from the first location to a second location. At least one navigation option includes a maneuver technique that requires operator approval prior to execution. The computing device may then display a graphical user interface (GUI) that conveys the one or more navigation options. Based on detecting a selection of a particular navigation option, the computing device may transmit instructions to the vehicle to perform the particular navigation option. The vehicle may configured to navigate from the first location to the second location by performing the particular navigation option while monitoring for changes in the environment.

Abstract: Techniques for determining error models for use in simulations are discussed herein. Ground truth perception data and vehicle perception data can be determined from vehicle log data. Further, objects in the log data can be identified as relevant objects by signals output by a planner system or based on the object being located in a driving corridor. Differences between the ground truth perception data and the vehicle perception data can be determined and used to generate error models for the relevant objects. The error models can be applied to objects during simulation to increase realism and test vehicle components.

Abstract: A vehicular control system determines a planned path of travel for a vehicle along a traffic lane in which the vehicle is traveling on a road. The system determines a respective target speed for waypoints along the planned path that represents a speed the vehicle should travel when passing through the respective waypoint. The system determines a speed profile for the vehicle to travel at as the vehicle travels along the planned path, with at least two different speeds being based on a difference in target speeds of at least two consecutive respective waypoints of the plurality of waypoints. The system determines an acceleration profile for the vehicle to follow as it changes from one speed to another speed of the speed profile. The system controls the vehicle to maneuver the vehicle along the planned path in accordance with the determined speed and acceleration profiles.

Abstract: A grabbing method for an industrial robot is disclosed. The method includes obtaining an object information file. The object information file includes numbers and/or positions of detected objects. The method further includes determining collision boundary lines and collision representative objects according to the object information file. In addition, the method includes determining a collision-free grabbing path of a gripper of the industrial robot based on the determined collision boundary lines and the collision representative objects. The collision-free grabbing path is a linear path that satisfies joint limits of the industrial robot. The disclosure further relates to a grabbing device for an industrial robot, a computer storage medium, and an industrial robot.

Abstract: An apparatus including a processor unit configured to provide a first high-definition map, a sensor unit configured for providing sensor data representing an environmental condition in a periphery of the apparatus and a receiver unit configured to receive data representing a second high-definition map. The processor unit is configured to fuse the second high-definition map and the sensor data so as to provide the first high-definition map. The apparatus further includes a transmitter unit configured for transmitting a result of fusing the second high-definition map and the sensor data, and includes a command generator unit configured to generate a command signal representing a vehicle control command for a vehicle carrying the apparatus based on the first high-definition map.

Abstract: Broadcasting geolocation information of an Unmanned Aerial Vehicle (UAV) from the UAV by determining current geolocation of the UAV by communicating with a geolocation service and utilizing the geolocation service to geolocate the UAV. Then the UAV prepares a radio frame that includes geolocation information identifying the current geolocation of the UAV and other information associated with the UAV using a radio protocol of one of a 3rd Generation Partnership Project (3GPP) radio protocol, a WiFi radio protocol, a wireless personal area network protocol and a low-power wide-area network protocol and transmits the radio frame to broadcast the current geolocation of the UAV.

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: A method for controlling sensors or components of a vehicle, using a control device. Measurement data of at least one sensor of the vehicle being received and evaluated. A traffic situation, in which the vehicle finds itself, is ascertained by evaluating the measurement data; and the at least one sensor and/or at least one component of the vehicle being activated, deactivated and/or set to a standby mode as a function of the ascertained traffic situation. A control device and a computer program are also described.

Abstract: A driving system includes a vehicle computing device on a vehicle and a cloud computing device at a location physically separated from the vehicle. The vehicle computing device transmits navigation information to the cloud computing device, including destination information, location information of the vehicle, and high-definition map information regarding a surrounding environment of the vehicle. The cloud computing device generates, based on the navigation information, path information including primary path information and backup path information and transmits the path information to the vehicle computing device. The vehicle computing device controls a trajectory of the vehicle based on the received path information.

Abstract: Embodiments of the present invention include a collaborative manufacturing system utilizing a plurality of mobile agents. The mobile agents operate dual robotic arms to improve single and multi-material builds' efficiency. In some embodiments, the dual robotic arms work together in the same area to create multi-functional components. In addition, the mobile agents can change tool heads on the arms to allow for hybrid manufacturing such as pick and place, additive, and subtractive manufacturing. One or more mobile agents interact with other mobile agents, thereby increasing the end product's efficiency and quality. Mobile agents utilize swarm manufacturing techniques to improve the manufactured product's time efficiency further and use machine learning to adjust and re-assign mobile agents constantly.

Abstract: An apparatus for a motor vehicle driver assistance system for an ego vehicle is provided. The apparatus implements a state estimator configured to use a first state of the ego vehicle to calculate a subsequent second state of the ego vehicle, wherein calculating the second state from the first state includes a prediction element and an update element, wherein calculating the second state from the first state includes using an artificial neural network (“ANN”).

Abstract: Provided are a cleaning robot and a method of controlling the same, and more specifically, a cleaning robot provided to detect an obstacle in various directions and a method of controlling the same. The cleaning robot includes a light emitter configured to radiate light, a plurality of light receivers configured to receive a radiation of the light in a predetermined direction among radiations of the light reflected from an obstacle when the radiated light is reflected from the obstacle, a support plate to which the light emitter and the light receiver are fixed and which is rotatably provided, and a controller configured to detect the obstacle on the basis of output signals transmitted from the light emitter and the plurality of light receivers and rotation information of the support plate.

Abstract: A cross-regional travel recommendation method and apparatus, an electronic device and a storage medium are provided, which relates to the fields of intelligent transportation and deep learning. A specific implementation solution is: acquiring a travel request of a user, the travel request comprising a start point and an end point which are located in different regions; extracting user features according to the travel request of the user; and recommending at least one travel plan to the user according to the user features and a pre-trained cross-regional travel recommendation model. The technical solutions can make up for the deficiency of the existing technology, provide a cross-regional travel plan recommendation under a large-space scale and a multimodal environment through a pre-trained cross-regional travel recommendation model and user features extracted based on a travel request of a user, and can satisfy a cross-regional travel request of the user, and is highly practical.

Abstract: An autonomous mobile device (AMD) may move around a physical space performing various tasks. Most of the sensors on the AMD may be directed towards the front and sides of the AMD to facilitate autonomous navigation, interactions with users, and so forth. The AMD may return to a dock to recharge batteries, replenish consumables, transfer payload, and so forth. The AMD uses the sensors to approach the vicinity of the dock. Once in the vicinity, the AMD turns around and backs into the dock. This orientation allows the AMD to continue to operate the forward-facing sensors and interact with users while docked. The AMD uses inductive sensors to detect metallic targets located at particular positions in the dock. Output from the inductive sensors provides information about the relative position of the AMD with respect to the dock and is used to steer the AMD into a desired docked position.

Abstract: A control system including a drive system and a blade system; a collision sensor; a main board having a main processor and in communication with the collision sensor, the drive system, and the blade system; the collision sensor, upon sensing a collision, capable of transmitting a collision signal to the main processor; the main board capable of transmitting an adjustment command to the drive system or the blade system; a vision sensor; a vision processor in communication with the vision sensor and the main processor, and capable of determining whether the image data represent an obstacle; the vision sensor capable of transmitting image data to the vision processor; when the vision processor determines the image data represent an obstacle, the vision processor capable of transmitting a collision-replicating signal to the main processor, prompting the main board to transmit the adjustment command to the drive system and/or the blade system.

Abstract: An autonomous mobile device (AMD) may move around a physical space while performing tasks. Sensor data is used to determine an occupancy map of the physical space. Some objects within the physical space may be difficult to detect because of characteristics that result in lower confidence in sensor data, such as transparent or reflective objects. To include difficult-to-detect objects in the occupancy map, image data is processed to identify portions of the image that includes features associated with difficult-to-detect objects. Given the portion that possibly includes difficult-to-detect objects, the AMD attempts to determine where in the physical space that portion corresponds to. For example, the AMD may use stereovision to determine the physical area associated with the features depicted in the portion. Objects in that area are included in an occupancy map annotated as objects that should persist unless confirmed to not be within the physical space.

Abstract: A work machine loads materials onto a conveyance vehicle. A system for controlling the work machine includes a detection device that detects an operation of the conveyance vehicle, and a controller that controls the work machine. The work machine includes a work implement attached to a rotating body. The controller acquires operation data indicative of an operation of the conveyance vehicle from the detection device. The controller causes the rotating body to rotate toward a predetermined unloading position. The controller determines whether the conveyance vehicle is stopped at a predetermined loading position based on the operation data. The controller causes the work implement to wait on standby at the unloading position upon determining that the conveyance vehicle is operating. The controller controls the work machine to unload materials at the unloading position upon determining that the conveyance vehicle is stopped at the loading position.

Abstract: A location of an occupant within a vehicle and/or an activity engaged in by the occupant may be determined. Based on the location and/or the activity, a point of interest associated with the occupant and/or the vehicle may be determined. One or more systems of the vehicle, such as the steering and/or suspension, may be controlled to minimize acceleration associated with the point of interest, thereby increasing a comfort of the occupant. In instances where the vehicle includes more than one occupant, the vehicle may be adjusted to accommodate the multiple occupants.

Abstract: The steering control apparatus determines whether or not a deviation degree of a current traveling route of a vehicle with respect to a target traveling route is equal to or more than a predetermined threshold, when steering control is switched from manual steering control to automatic steering control. In the automatic steering control, a command steering angle is calculated so that a difference between a real traveling route of the vehicle and the target traveling route is eliminated. However, when the deviation degree is equal to or more than the predetermined threshold, the steering control apparatus recalculates the command steering angle used in the command steering angle tracking control based on a steering angle at the time of starting the automatic steering control and the command steering angle so that a real steering angle after switching to the automatic steering control changes gradually to the command steering angle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for robot motion planning using unmanned aerial vehicles (UAVs). One of the methods includes determining that a current plan for performing a particular task with a robot requires modification; in response, generating one or more flight plans for an unmanned aerial vehicle (UAV) based on a robotic operating environment comprising the robot; obtaining, using the UAV in accordance with the one or more flight plans, a new measurement of the robotic operating environment comprising the robot; and generating, based at least on a difference between the new measurement of the robotic operating environment and a previous measurement of the robotic operating environment, a modified plan for performing the particular task with the robot.

Abstract: A system, including: a non-transitory memory; and one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations including: detecting a first automobile; determining that the first automobile is a self-driving automobile; and in response to determining that the first automobile is a self-driving automobile, causing a second automobile to emulate a motion of the first automobile.

Abstract: State estimation and sensor fusion switching methods for autonomous vehicles thereof are provided. The autonomous vehicle includes at least one sensor, at least one actuator and a processor, and is configured to transfer and transport an object. In the method, a task instruction for moving the object and data required for executing the task instruction are received. The task instruction is divided into a plurality of work stages according to respective mapping locations, and each of the work stages is mapped to one of a transport state and an execution state, so as to establish a semantic hierarchy. A current location of the autonomous vehicle is detected by using the sensor and mapped to one of the work stages in the semantic hierarchy, so as to estimate a current state of the autonomous vehicle.

Abstract: An information processing system includes: a first server associated with a first region, the first server including a first processor configured to output information concerning a predetermined service to a vehicle traveling in the first region; and the vehicle including a second processor, wherein the first processor is configured to perform handover processing for outputting information concerning the vehicle held by the first server to a second server associated with a second region adjacent to the first region when the vehicle moves from the first region to the second region in a case where the vehicle has moved to an outside of the first region and to an outside of an extended region obtained by extending the first region.

Abstract: This application relates to apparatus and methods for automatic delivery route generation and assignment. In some examples, a computing device determines delivery locations for each of a plurality of previous routes taken by each of a plurality of drivers over a period of time. The computing device also obtains a plurality of current routes to be assigned to the plurality of drivers. Further, the computing device determines a familiarity value for each of the plurality of drivers for each of the plurality of current routes based on the delivery locations of the previous routes taken by each driver. The computing device assigns each of the plurality of drivers to a current route based on the determined familiarity values, and stores the assignments in a data repository. In some examples, the computing device transmits the assignments to another computing device, such as a computing device of each driver.

Abstract: A movement control method for a multi-vehicle system for moving multiple vehicles to target positions individually set for the vehicles includes: acquiring first positions of the vehicles; determining control input for moving the vehicles from the first positions to second positions away from the target positions by a first distance or more while the vehicles satisfy a predetermined condition; and updating the first distance to be a shorter distance when a distance between the second position and the target position of each of the vehicles becomes equal to or more than the first distance and within an updating distance.

Abstract: A robot including a driver configured to move a main body, a memory configured to store an obstacle map with respect to a cleaning area, a sensor configured to collect information about the cleaning area, a communication interface configured to communicate with a second robot, and a controller is disclosed. The controller is configured to, when receiving an obstacle map including position information for a liquid region in the cleaning area from the second robot, control the main body to move to the liquid region and clean the liquid region.

Abstract: Systems and methods for remotely controlling a system using video are provided. A method in accordance the present disclosure includes detecting a video signal of an auxiliary system at a video input, wherein the video signal including images encoded with control information. The method also includes determining that the images included in the video signal include the control information. The method further includes extracting the control information from the images. Additionally, the method includes modifying operations of the system based on the control information.

Abstract: A method including determining a total amount of unprocessed material that has been dumped into the material processing device during a first time period determining a total amount of unprocessed material that has been processed during the first time period; determining a reference level of unprocessed material at the first point in time; predicting, based on the current level of unprocessed material contained in the material processing device and on an expected future processing rate of the material processing device at least one of an earlier and a later point in time at which the level of unprocessed material is expected to fall below a lower or upper limit; establishing a desired time-of-arrival period extending between a start point and an end point corresponding to the earlier and later points in time respectively; and adapting a speed of the first load-carrying vehicle.

Abstract: A method includes generating a training data set comprising a plurality of training examples, wherein each training example is generated by receiving map data associated with a road portion, receiving sensor data associated with a road agent located on the road portion, defining one or more corridors associated with the road portion based on the map data and the sensor data, extracting a plurality of agent features associated with the road agent based on the sensor data, extracting a plurality of corridor features associated with each of the one or more corridors based on the sensor data, and for each corridor, labeling the training example based on the position of the road agent with respect to the corridor, and training a neural network using the training data set.

Abstract: An unmanned aerial vehicle (UAV) or “drone” executes a neural network to assist with inspection, surveillance, reporting, and other missions. The drone inspection neural network may monitor, in real time, the data stream from a plurality of onboard sensors during navigation to an asset along a preprogrammed flight path and/or during its mission (e.g., as it scans and inspects an asset).

Abstract: Techniques are described herein for generating trajectories for autonomous vehicles using velocity-based steering limits. A planning component of an autonomous vehicle can receive steering limits determined based on safety requirements and/or kinematic models of the vehicle. Discontinuous and discrete steering limit values may be converted into a continuous steering limit function for use during on-vehicle trajectory generation and/or optimization operations. When the vehicle is traversing a driving environment, the planning component may use steering limit functions to determine a set of situation-specific steering limits associated with the particular vehicle state and/or driving conditions. The planning component may execute loss functions, including steering angle and/or steering rate costs, to determine a vehicle trajectory based on the steering limits applicable to the current vehicle state.

Abstract: Among other things, a vehicle drives autonomously on a trajectory through a road network to a goal location based on an automatic process for planning the trajectory without human intervention; and an automatic process alters the planning of the trajectory to reach a target location based on a request received from an occupant of the vehicle to engage in a speed-reducing maneuver.

Abstract: A moving robot includes: a sensor to acquire terrain information; a memory to store node data for at least one node; and a controller, and the controller determines whether at least one open movement direction exists among a plurality of movement directions, based on sensing data and the node data, generates a new node in the node data when at least one open movement direction exists, determines any one of the open movement directions as a traveling direction for the robot, determines whether at least one of the nodes needs to be updated exists, based on the node data when the open movement direction does not exist, controls the moving robot to move to one of the nodes that need to be updated, and generates of a map including the at least one node, based on the node data, when the node that needs to be updated does not exist.

Abstract: A method including determining a direct distance between the vehicle position and a position of the roadside unit and a planar distance between the vehicle position in a horizontal plane containing the vehicle position, and a projection of the position of the roadside unit onto the plane. The method further includes calculating a height of a roadside unit relative to the vehicle position using the direct distance and the planar distance determined for the vehicle position. The method also includes setting a value indicative of the height of the roadside unit relative to the vehicle position as a height correction value and storing the height correction value of the vehicle position in association with information indicative of the vehicle position as the height correction function.

Abstract: Techniques are provided for generating a driving trajectory for a vehicle while the vehicle is blocked (e.g., the sensor of the vehicle have detected an object results in the vehicle being unable to move) by an object (e.g., another vehicle, bicycle, or a pedestrian) and executing the driving trajectory when the vehicle becomes unblocked. In addition, techniques are provided for updating a portion of a driving trajectory of a vehicle based on a determination that an object will cross a segment of the current driving trajectory at a later point, without recalculating the whole trajectory.

Abstract: One embodiment of the present invention provides an intersection point pattern recognition system using sensor data of a mobile robot, comprising: a mobile robot that autonomously drives by using sensor data received from a sensor unit and an intersection point pattern recognition model provided by a management server; and the management server that receives usage environment information of the mobile robot and generates the intersection point pattern recognition model of the mobile robot to provide the intersection pattern recognition model to the mobile robot, wherein the management server comprises: a map generation unit for receiving the usage environment information of the mobile robot and generating a route map of the mobile robot on the basis of the usage environment information; a normalization unit for generating a virtual map by normalizing the route map according to a preset rule; and a learning unit for generating the intersection point pattern recognition model by using the virtual map and the se

Abstract: Systems and techniques for detecting a difference in orientation between a lawn mower and a surface on which the mower is mowing, or between portions of such surface, based on one or more of sensor data or map data are discussed. The difference in orientation may then be used to control the lawn mower by, for example, raising a deck height or idling a blade speed, though other actuations are contemplated. In some examples, an amount the deck height is raised may be based on the difference in orientation. Based on a subsequent difference detected being at or below a threshold difference, the mower may return to previous operating conditions including, but not limited to, returning a blade speed to a previous blade speed and/or returning the deck height to a previous deck height, among other controls.

Abstract: An operation method of an optimal route searching device includes: acquiring topology transformed map information; extracting a plurality of candidate routes based on the topology transformed map information; calculating a travel cost for each of the plurality of candidate routes based on a cost function; and determining a candidate route corresponding to a lowest cost one of the calculated travel costs as a travelling route.

Abstract: A vehicle for predicting a risk of collision includes a controller configured to: calculate distances between the vehicle and left and right lines of a first lane, respectively, using a position of the vehicle and first lane width information of the first lane, calculate distances between the surrounding vehicle and left and right lines of a second lane, respectively, using a position of the surrounding vehicle and second lane width information of the second lane, calculate a second distance between the vehicle and the surrounding vehicle by reflecting the calculated distances between the vehicle and the left and right lines of the first lane or the calculated distances between the surrounding vehicle and the left and right lines of the second lane to a first distance, and predict a risk of collision between the vehicle and the surrounding vehicle based on the second distance.