Abstract: Sensor data fusion systems that provide noise reduction and fault protection. The sensor data fusion system fuses data acquired by respective accelerometers having different attributes. For example, one accelerometer has low noise and high bias, while another accelerometer has high noise and low bias when measuring specific force. The high-noise, low-bias accelerometer may be a gravimeter. Gravimeters and traditional accelerometers measure the same physical variable, i.e., specific force. By combining an expensive gravimeter and low-cost accelerometers, a synthetic sensor having both low noise and low bias may be achieved. Such synthetic sensors may be utilized in a gravity anomaly-referenced navigation system to achieve improved navigation performance.

Abstract: A driving assistance device comprises: a recognition unit configured to recognize a lighting color of a traffic light from an image captured by a camera that images an outside world of a vehicle; and an alarm output unit configured to output an alarm to a driver of the vehicle when the lighting color is red and there is no braking operation of the vehicle. When a plurality of traffic lights are recognized from the image by processing of the recognition unit, the alarm output unit controls the output of the alarm based on a combination of lighting colors of the plurality of traffic lights.

Abstract: Cooperation among robots is a necessary feature of advanced manufacturing and many other applications. The invention relates to systems and methods for robots to identify each other using simultaneous infrared pulses and wireless messages in 5G or 6G. The wireless message can indicate the wireless address of the transmitting robot, and the infrared signal can indicate which robot, among many, is transmitting the wireless message. Thus the other robots can compare the arrival direction of the infrared signal with an optical image, and thereby localize the transmitting robot. The robots can then begin cooperative actions thereafter. The procedures are suitable for mobile robots in a self-driving and self-managing scenario, fixed and mobile robots cooperating to accomplish a task, and robots intermingled with humans. Multiple operating modes are illustrated across a wide range of industries and use cases.

Abstract: A method, system and computer program product, the method comprising: obtaining a first multiplicity of images from an overhead capture device overlooking a body of water; detecting a swimmer in some of the images, wherein the swimmer is outside the body of water or separated from other swimmers; determining two descriptors of the person, based on the images, the first descriptor related to a portion of the swimmer outside the water, the second related to a portion inside the water, the descriptors determined upon visual characteristics extracted from the images; obtaining a second multiplicity of images from the device; and tracking the swimmer in the second multiplicity of images, said tracking comprises detecting the swimmer using either descriptor, said detecting the swimmer is performed with respect to an image from the second multiplicity of images in which the swimmer is partially occluded by other swimmers or adjacent to other swimmers.

Abstract: Systems and methods for enhancing task performance and computer readable maps produced by robots using modular sensors is disclosed herein. According to at least one non-limiting exemplary embodiment, robots may perform a first set of tasks, wherein coupling one or more modular sensors to the robots may configure a robot to perform a second set of tasks, the second set of tasks includes the first set of tasks and at least one additional task.

Abstract: Disclosed is an image processing method. The method includes the steps of receiving an image obtained from a plurality of vehicles positioned on a road, storing the received images according to acquisition information of the received images; determining a reference image and a target image based on images having the same acquisition information among the stored images, performing an image registration using a plurality of feature points extracted from each of the determined reference image and target image, performing a transparency process for each of the reference image and the target image performed with the image registration, extracting static objects from the transparency-processed image, and comparing the extracted static objects with objects on an electronic map pre-stored to updating the electronic map data, when the objects on the electronic map data pre-stored are different from the extracted static objects.

Abstract: Certain examples described herein enable a robotic device to accurate map a surrounding environment. The robotic device uses an image capture device and at least one of the image capture device and the robotic device move within the environment. Measurements associated with movement of at least one of the image capture device and the robotic device are used to determine a state of the robotic device. The state of the robotic device models the image capture device and the robotic device with respect to a model of the environment that is constructed by a mapping engine. By comparing the state of the robotic device with a measured change in the robotic device, an accurate representation of the state of the robotic device may be constructed. This state is used by the mapping engine to update the model of the environment.

Abstract: A method of operation of a navigation system includes: determining a geographic location, of a vehicle, while a global positioning location is blocked by an obstruction and the geographic location is from an in-vehicle location sensor in the vehicle; extracting an image line from a surrounding image with an artificial intelligence model and the surrounding image is from an in-vehicle image sensor in the vehicle; transforming an image coordinate of the image line to a world coordinate of a HD map local storage based on the geographic location; extracting a map line from the HD map local storage based on the world coordinate; determining a pose relationship between the image line and the map line paired as either horizontal or vertical; generating a map-related location for the vehicle based the geographic location and the pose relationship; and communicating the map-related location for displaying on a user interface.

Abstract: A vehicle occupant monitoring system, OMS, comprises an image acquisition device with a rolling shutter image sensor comprising an array of sub-pixels which are respectively selectively sensitive to: red and infra-red; blue and infra-red; and green and infra-red light. The device is configured to selectively operate in either: a colour mode where a multi-plane image frame corresponding to the full image sensor is provided, each plane derived from red, green or blue sensitive sub-pixels respectively; or a monochrome mode, where sensor information from sub-pixels is aggregated to provide a single image plane.

Abstract: Various embodiments provide a system and method for iterative lane marking localization that may be utilized by autonomous or semi-autonomous vehicles traveling within the lane. In an embodiment, the system comprises a locating device adapted to determine the vehicle's geographic location; a database; a region map; a response map; a plurality of cameras; and a computer connected to the locating device, database, and cameras, wherein the computer is adapted to receive the region map, wherein the region map corresponds to a specified geographic location; generate the response map by receiving information from the camera, the information relating to the environment in which the vehicle is located; identifying lane markers observed by the camera; and plotting identified lane markers on the response map; compare the response map to the region map; and iteratively generate a predicted vehicle location based on the comparison of the response map and the region map.

Abstract: A system comprises an endoscope with a wide-angle lens and a camera. An image of a field of view is captured by the endoscope and a portion of the image is displayed on the display. A popup image is generated and displayed upon image analysis identification of an occurrence of bleeding or motion of edges of an incision that is within the field of view, but outside the portion of the field of view displayed on the display.

Abstract: Provided is a sensing system useful with a follower vehicle configured to track and follow a leader. The sensing system can include a plurality of sensing technologies configured to cooperatively track and follow the leader. In some embodiments, the plurality of sensing technologies can include one or more of a stereoscopic camera ranging system, a wide field of view monocular camera, and a radar imaging system, or other sensor technologies. In various embodiments, the vehicle can comprise a chassis, a drive mechanism supported by the chassis and arranged to drive a plurality of wheels, a body supported by the chassis and, optionally, an internal volume defined within the body. In some embodiments, the follower vehicle can be a two-wheeled mobile carrier, for example.

Abstract: A moving body includes processing circuitry. The processing circuitry is configured to collect an external image of the moving body from an external sensor and collect information associated with an inner state of the moving body from an internal sensor. The processing circuitry is configured to determine whether or not to adopt the external image collected by the external sensor as a first image for estimating a position of the moving body, based on the information associated with the inner state of the moving body collected by the internal sensor. The processing circuitry is configured to estimate a position of the moving body by comparing the first image and a second image associated with a collection position of the first image.

Abstract: An approach is provided for generating navigation data of a geographical location. The approach involves identifying a landmark located along a source road from a source image and segmenting the source image using a deep learning model to identify a segmentation mask. The approach also involves generating a template image based on the segmentation mask and a street image of the landmark, and matching the template image successively with a sequence of images of the landmark to determine a confidence score. The approach further involves, identifying a first image from the sequence of images with confidence score below a predetermined threshold, and selecting a second image with confidence score above the predetermined threshold from the sequence of images. The approach further involves calculating a visibility distance of the landmark based on the source image and the second image, and generating the navigation data based on the calculated visibility distance.

Abstract: A multi-camera vehicle vision system and method. In one embodiment a map is generated about a moving vehicle. Frames of image data are provided with a series of cameras extending along a surface of the vehicle. The image data frames are processed to identify an object of interest. An object of interest is classified among a set of object types and location of an identified object of interest is determined. Object type and location information is provided to a control unit spaced apart from the cameras via a data link. Road map data is generated to illustrate changes in position of the moving vehicle along a roadway based on data other than the image data provided by the cameras. A display of the road map data is generated with the object type and location information overlaid on the road map data to indicate object location relative to the vehicle.

Abstract: A histogram is calculated based on a road surface image of a portion around a vehicle, a running-allowed region in which the vehicle can run is detected based on the histogram, an obstacle region is extracted based on the running-allowed region, and a position of an obstacle in the obstacle region is detected, to further enhance the accuracy of detecting an obstacle around the vehicle as compared with conventional art.

Abstract: 5G and especially 6G will enable a multitude of applications for fixed-position and mobile wireless task-devices (“robots”). Most of these applications are based on the assumption that the robots know, or can determine, the locations and wireless identities of other robots in proximity, but this is an unsolved problem. Procedures are provided herein for an arbitrarily large number of fixed-position and mobile robots to autonomously identify each other, determine their locations with speed and precision substantially beyond that provided by navigation satellites, and then to collaborate in performing their tasks, while avoiding interference and collisions. Examples are provided in the fields of automated agriculture, remote oil-spill mitigation, autonomous fire-fighting, hospital management, construction site coordination, manufacturing (including fully autonomous manufacturing), major product warehousing, airport control, and emergency vehicle access.

Abstract: A flight deck system for providing task management assistance in managing the flight path to the flight crew is provided.

Abstract: Augmented reality (AR) telepresence systems and methods are disclosed for obtaining a 3D model of a physical location from a 3D-capture system comprising one or more 3D depth sensors disposed throughout the physical location, generating a truncated 3D model of the physical location, the truncated 3D model corresponding to the intersection of the generated 3D model and a field of view of a user terminal camera at the physical location, and transmitting the truncated 3D model to a remote location.

Abstract: A vehicle hitching assistance system includes a controller acquiring image data from the vehicle and identifying a trailer within a specified area of the image data and then identifying a coupler of the trailer. The specified area is less than a total field of the image data. The controller then outputs a steering signal to the vehicle to cause the vehicle to steer to align a hitch ball of the vehicle with the coupler.

Abstract: Aspects of the disclosure relate to dynamic driving metric output platforms that utilize improved computer vision methods to determine vehicle metrics from video footage. A computing platform may receive video footage from a vehicle camera. The computing platform may determine that a reference marker in the video footage has reached a beginning and an end of a road marker based on brightness transitions, and may insert time stamps into the video accordingly. Based on the time stamps, the computing platform may determine an amount of time during which the reference marker covered the road marking. Based on a known length of the road marking and the amount of time during which the reference marker covered the road marking, the computing platform may determine a vehicle speed. The computing platform may generate driving metric output information, based on the vehicle speed, which may be displayed by an accident analysis platform.

Abstract: Disclosed are a system and method for the application of filtering in the collection and application of facial biometrics to a number of problems common to the vending and gaming environments. A succession of video frames of a scene are analyzed to determine if one or more faces are present. If so, the face most relevant to the application based in its position in the scene is selected. The selected face in each of the succession of video frames is then quality rated according to certain criteria to select the best frame for computing a biometric value of the selected face. One the biometric value has been computed, the value may be compared against a database to determine if a biometric value for a matching face was previously stored. If so, the quality rating of the new image and a quality rating previously stored with the stored biometric are compared.

Abstract: A trailer recognition device of a vehicle includes: a sensor sensing a distance value between the vehicle and a rear object; a controller detecting whether a trailer is connected, depending on an internal signal of the vehicle and the distance value and predicting a first hitch angle based on a vehicle model and a second hitch angle based on the sensor to generate a control signal; and a trailer mode controller controlling a trailer mode of the vehicle in response to the control signal.

Abstract: A method for continuously determining mutually corresponding pixels between a first camera image and a second camera image. The method includes recording the first camera image; recording the second camera image; ascertaining at least one first signature matrix element of a first signature matrix as a function of the first camera image; assigning first coordinates to an ascertained signature value of the first signature matrix element in a signature value position table; ascertaining at least one signature value of a second signature matrix element having second coordinates of a second signature matrix as a function of the second camera image; and determining at least one element of a correspondence matrix as a function of the signature value position table, of the cyclically ascertained signature value of the second signature matrix element and of the second coordinates of this second signature matrix element.

Abstract: A method includes capturing images at a device and analyzing the images at the device using a first analysis model to obtain information regarding an observed object that corresponds to a predetermined object. The method also includes determining whether the information regarding the observed object is consistent with stored mapping information, and, in response to determining that the information regarding the observed object is not consistent with the stored mapping information, modifying the stored mapping information based on the observed object.

Abstract: A method for controlling two lighting modules of a headlight, including the following steps: definition of a non-dazzling region, wherein the non-dazzling region is at least within the second region; reduction of the brightness of the light emitted by the two lighting modules toward the non-dazzling region; determination as to whether an adjacent region exists that directly adjoins the non-dazzling region horizontally and that is a horizontal edge region of the first region; and reduction of the brightness of the light emitted by the first lighting module toward the adjacent region if the adjacent region has been determined.

Abstract: The present disclosure relates to systems and methods for displaying vehicle information for an on-demand service. The method may include sending a request for on-demand service to a server. The method may further include obtaining information of a vehicle related to the request for on-demand service. The information of the vehicle may include color information of the vehicle. The method may further include generating, by a processor, a user interface based on the information of the vehicle. The user interface may include at least one user interface element corresponding to the color information of the vehicle.

Abstract: The invention is a system for optimizing a trailer path and a tow vehicle path. The system includes image sensors configured to capture images of a trailer and images of a path of travel both in front of and behind the trailer and tow vehicle, a weight determination system, accelerometers that sense acceleration of the tow vehicle and/or the trailer, a data input device configured to receive input data, and a processing device. The processing device includes a processor and non-volatile memory. The processor is configured to receive image data from the image sensors, receive weight data from the weight determination system, receive accelerometer data from the one or more accelerometers and receive the input data from the data input device. Additionally, the processor is configured to determine a trailer path and a tow vehicle path based on the image data, accelerometer data, and the input data.

Abstract: An image processing apparatus includes a memory, and a processor coupled to the memory and configured to obtain an image of a first camera disposed on a vehicle such that an imaging range of the first camera includes a portion of a vehicle body and images of a second and third cameras that image an area of a blind spot caused by the portion of the vehicle body, combine a blind spot image corresponding to the area of the blind spot in the image of the second camera with the image of the first camera, obtain three-dimensional information of a rear vehicle with stereo vision of the second and third cameras, and store rear vehicle shape information, wherein the processor determines three-dimensional information corresponding to a portion of the rear vehicle, and combines the blind spot image with the image of the first camera using the determined three-dimensional information.

Abstract: A trailer angle identification system comprises an imaging device configured to capture an image. An angle sensor is configured to measure a first angle of the trailer relative to a vehicle. A controller is configured to process the image in a neural network and estimate a second angle of the trailer relative to the vehicle based on the image. The controller is further configured to train the neural network based on a difference between the first angle and the second angle.

Abstract: A trailering assist system includes a receiving device disposed at an equipped vehicle and a trailer camera at a rear of a trailer. When the vehicle is towing the trailer, the trailer camera captures image data and a transmitter at the trailer wirelessly communicates captured image data to the receiving device at the equipped vehicle. The receiving device at the equipped vehicle receives the communicated image data and a display device in the equipped vehicle displays video images derived from the received image data. When another vehicle is towing the trailer, a controller at the trailer determines that the other vehicle is towing the trailer and the transmitter attempts to wirelessly communicate with another receiving device. Responsive to establishing wireless communication with the other receiving device, the transmitter transmits trailer identification information to the other receiving device.

Abstract: A shading device for a vehicle, comprising a dimming glass plate capable of changing a light transmittance thereof, wherein the dimming glass plate is provided at a portion of a vehicular window glass to separate an interior of vehicular compartment from outside of the vehicular compartment or provided at a portion of a surface of the vehicular window glass that faces inside of the vehicular compartment; a display apparatus formed of a light transmitting material and disposed at a surface of the dimming glass plate that faces inside of the vehicular compartment, with a display portion facing inside the vehicular compartment; an image pickup device to capture an area outside of a vehicle to generate image pickup data, wherein the area is at an opposite surface on the dimming glass plate, the opposite surface being opposite a surface on which the display apparatus is provided; a data processing circuit to generate display image data to be displayed on the display portion based on the image pickup data generated

Abstract: An image processing device is provided with an image acquiring unit that acquires the image from an imaging unit mounted on a vehicle, a light determining unit that determines a state of a light mounted on the vehicle, and an adjusting unit that adjusts a relationship between a luminance at an object to be captured by the imaging unit, and a pixel value in the image. The adjusting unit is configured to set, when the light determining unit determines the state of the light is in the low-beam state, the illuminance where the pixel value is at the lower limit, to be lower than that of a case when the light determining unit determines the state of the light is in the high-beam state.

Abstract: Systems and methods for using radio frequency signals and sensors to monitor environments (e.g., indoor building, industrial environments) are disclosed herein. In one embodiment, a system for providing a wireless asymmetric network comprises a hub having one or more processing units and at least one antenna for transmitting and receiving radio frequency (RF) communications in the wireless asymmetric network and a plurality of sensor nodes each having a wireless device with a transmitter and a receiver to enable bi-directional RF communications with the hub in the wireless asymmetric network.

Abstract: Various embodiments of the present disclosure provide a system and method for iterative lane marking localization that may be utilized by autonomous or semi-autonomous vehicles traveling within the lane. In an embodiment, the system comprises a locating device adapted to determine the vehicle's geographic location; a database; a region map; a response map; a plurality of cameras; and a computer connected to the locating device, database, and cameras, wherein the computer is adapted to receive the region map, wherein the region map corresponds to a specified geographic location; generate the response map by receiving information from the camera, the information relating to the environment in which the vehicle is located; identifying lane markers observed by the camera; and plotting identified lane markers on the response map; compare the response map to the region map; and iteratively generate a predicted vehicle location based on the comparison of the response map and the region map.

Abstract: A vehicle system comprises a hitch assembly mounted on a vehicle, a display, and a controller. The controller is configured to access a saved configuration for the hitch assembly and display the saved configuration on the display. The controller is further configured to receive a selection of the saved configuration and program a characteristic of the hitch assembly based on the selection.

Abstract: A remote control robot system is provided, which includes robotic arm configured to perform a given work, remote control device for an operator to remotely manipulate operation of robotic arm, plurality of cameras configured to image the work of robotic arm, monitor configured to display a captured image that is sent, camera selecting device configured to generate, in response to receiving an operator's selection of one camera from the plurality of cameras, camera selection information for switching captured image displayed on monitor to captured image from selected camera, storage device configured to store information where operational information related to operation of robotic arm in work is associated with camera selection information, as automatic switching information, and an image processor configured to send to monitor the captured image from camera selected from plurality of cameras based on automatic switching information stored in storage device.

Abstract: A vehicular camera apparatus includes an image sensor, and a processor configured to divide an image acquired through the image sensor into a first field of view (FOV) range in a first direction and a second FOV range in the first direction, to process a first region corresponding to the first FOV range in the image, to process a second region corresponding to the second FOV range in the image, and to separately process the first region and the second region.

Abstract: A process for dynamic vehicular threat detection perimeter modification for an exited vehicular occupant includes prior to detecting a vehicular occupant exiting the vehicle, establishing a first sized vehicular geofence surrounding the vehicle as a function of one or more stored vehicular perimeter distances. The first sized vehicular geofence is monitored for a first breach via one of a 360 degree vehicular light imaging and radio wave distancing system. In response to detecting that the vehicular occupant previously inside the vehicle has exited the vehicle, the one or more stored vehicular perimeter distances is modified as a function of a detected location of the exited vehicular occupant to establish a second sized vehicular geofence surrounding the vehicle different than the first sized vehicular geofence. The second sized vehicular geofence is monitored for a second breach via one of the 360 degree vehicular light imaging and radio wave distancing system.

Abstract: An imaging device includes a casing; a plurality of optical systems held by the casing; and a communication antenna held by the casing. The communication antenna is disposed in an area outside an optical path of light of a maximum angle of view of each of the plurality of optical systems.

Abstract: A navigation system useful for providing speed and heading and other navigational data to a drive system of a moving body, e.g., a vehicle body or a mobile robot, to navigate through a space. The navigation system integrates an inertial navigation system, e.g., a unit or system based on an inertial measurement unit (IMU). with a vision-based navigation system unit or system such that the inertial navigation system can provide real time navigation data and the vision-based navigation can provide periodic, but more accurate, navigation data that is used to correct the inertial navigation system's output. The navigation system was designed with the goal in mind of providing low effort integration of inertial and video data. The methods and devices used in the new navigation system address problems associated with high accuracy dead reckoning systems (such as a typical vision-based navigation system) and enhance performance with low cost IMUs.

Abstract: A method for determining object boundaries of an object outside of a transportation vehicle, wherein images of the object are generated by a control apparatus by a camera, and at least one scanline is specified in a first image and a corresponding scanline is specified for each scanline in every other image, and a profile resulting along the scanline is determined for each scanline of the first image, and a corresponding resulting profile is determined along the respective corresponding scanline of every other image, and the corresponding profile of every other image, displaced by a respective displacement distance, is overlaid on the profile of each scanline of the first image, and a reference pattern is determined in the resulting overlay profile of each scanline, and respective boundaries of the reference pattern are indicated as the respective object boundaries.

Abstract: Object detection systems and methods can include identifying an object of interest within an image obtained from a camera, obtaining a first supplemental portion of data associated with the object of interest determining an estimated location of the object of interest within three-dimensional space based at least in part on the first supplemental portion of data and a known relative location of the camera, determining a portion of the LIDAR point data corresponding to the object of interest based at least in part on the estimated location of the object of interest within three-dimensional space, and providing one or more of at least a portion of the image corresponding to the object of interest and the portion of LIDAR point data corresponding to the object of interest as an output.

Abstract: A backup assist system for a vehicle reversing a trailer includes a controller receiving a driver control signal and outputting a vehicle backing steering command based on the control signal and limited by one of a first angle limit corresponding with a calculated maximum controllable angle and a second angle limit at a maneuverability threshold below the maximum controllable angle. The system further includes an interface outputting an indication of the one of the first and second angle limits.

Abstract: A vision system for a vehicle includes a plurality of cameras and a processor operable to process image data captured by the cameras to generate images derived from image data captured by at least some of the cameras. The processor generates a vehicle representation. A display screen, viewable by a driver of the vehicle, displays the generated images and the vehicle representation as would be viewed from a virtual camera viewpoint exterior to and higher than the vehicle itself. A portion of the vehicle representation is rendered as displayed to be at least partially transparent to enable viewing at the display screen of an object present exterior of the vehicle that would otherwise be partially hidden by non-transparent display of that portion of the vehicle representation.

Abstract: An active lighting device of a bicycle includes a first optical system with a first light source arrangement for long-distance illumination, which is controlled by a control unit, and a second optical system with a second light source arrangement for short-distance illumination, which is controlled by the control unit. A light sensor determines the light intensity of a location of the bicycle and allows the control unit to adapt the light intensity of the light sources, if they are activated and if the ambient light intensity is below a threshold. A speed sensor determines the speed of the bicycle, so that the control unit controls the activation of the light sources of the first light source arrangement from a speed threshold. An orientation or inclination detector selects and adjusts the light intensity of light sources.

Abstract: An image processing apparatus includes a communication interface configured to receive a first captured image capturing a face of a subject in a moving body, and a controller configured to change at least one of a position and a size of a specific region in either the first captured image or a second captured image different from the first captured image, according to at least one of a position and an orientation of the face of the subject determined on the basis of the first captured image, as well as a direction of a line-of-sight of the subject.

Abstract: A process for dynamic vehicular threat detection perimeter modification for an exited vehicular occupant includes prior to detecting a vehicular occupant exiting the vehicle, establishing a first sized vehicular geofence surrounding the vehicle as a function of one or more stored vehicular perimeter distances. The first sized vehicular geofence is monitored for a first breach via one of a 360 degree vehicular light imaging and radio wave distancing system. In response to detecting that the vehicular occupant previously inside the vehicle has exited the vehicle, the one or more stored vehicular perimeter distances is modified as a function of a detected location of the exited vehicular occupant to establish a second sized vehicular geofence surrounding the vehicle different than the first sized vehicular geofence. The second sized vehicular geofence is monitored for a second breach via one of the 360 degree vehicular light imaging and radio wave distancing system.

Abstract: The disclosure relates to a pivot angle detection device and a method for detecting a pivot angle between a vehicle and a trailer coupling device that is coupled to the vehicle. A transmitter is hereby provided, which is designed for producing an electromagnetic field, as well as a receiver which is designed to detect a field strength of the electromagnetic field, whereby the transmitter and receiver are arranged towards each other on the vehicle and trailer coupling device in such a way that a change of the pivot angle produces a dependent change in the field strength that is detected by the receiver. Additionally, an evaluation device for determining the pivot angle based on the detected field strength is also provided. The disclosure also relates to a transmitter, a receiver and an evaluation device, that are designed for this purpose.

Abstract: A step detection device, including a distance measurement unit which detects the height of the road surface around a vehicle, approximates with a curve, the gradient of the road surface in a travelable region in the vehicle width direction, based on the height of the road surface, and detects a step on the road surface, based on the agreement degree of the height of a measurement point relative to the curve and the agreement degree of the height of a measurement point relative to a curve with which the gradient of the road surface in an extended region defined by extending the travelable region in the vehicle width direction is approximated.