Abstract: The described positional awareness techniques employing visual-inertial sensory data gathering and analysis hardware with reference to specific example implementations implement improvements in the use of sensors, techniques and hardware design that can enable specific embodiments to provide positional awareness to machines with improved speed and accuracy.

Abstract: A method for learning a neural network performed by a computing means wherein the neural network receives a marine image and outputs information about a type and a distance of at least one object included in the marine image is provided. The method comprises: obtaining a marine image including a sea and an obstacle; obtaining a labelling data generated based on the marine image; obtaining an output data by using a neural network, wherein the neural network receives the marine image and outputs the output data; calculating an error value by using the labelling data and the output data; and updating the neural network based on the error value; wherein the labelling data and the output data are determined by a combination of information about a type and a distance of an object.

Abstract: A vehicular control system includes a camera and a control having a processor that processes image data captured by the camera. The control determines a projected path of travel of the equipped vehicle. The processor processes captured image data to determine an estimated time to arrival of another vehicle at a location on a road being travelled by the other vehicle that is in the projected path of travel of the equipped vehicle. The projected path of travel of the equipped vehicle may cross a traffic lane being travelled by the other vehicle or may join a traffic lane being travelled by the other vehicle. Responsive at least in part to determination that the estimated time to arrival of the other vehicle is less than a threshold time, the control determines that it is not safe for the equipped vehicle to proceed along the projected path of travel.

Abstract: A target location from a set of points that define a road can be selected. A path, from a plurality of candidate paths, to the target location, from a current vehicle location outside the set of points, based on a path length, a collision risk, a curvature of the path, and a traffic condition on the road can be selected. The vehicle can be navigated according to the selected path.

Abstract: A camera monitoring system for a vehicle includes an interior rearview mirror assembly with a video display screen disposed behind the interior mirror reflective element. The video display screen is operable to display video images derived at least in part from image data captured by at least one video camera of a plurality of video cameras of the equipped vehicle. Image data captured by at least a driver-side viewing video camera and a passenger-side viewing video camera is provided to an image processor and is processed by the image processor to detect vehicles present exterior of the equipped vehicle. Responsive at least in part to detection of another vehicle, video images derived at least in part from image data captured by the driver-side viewing video camera, a rear viewing video camera and/or the passenger-side viewing video camera are displayed by the video display screen.

Abstract: In a specific implementation of the method a reflectance map is constructed based on a position and an Euler angle, obtained through a global optimization and used for constructing a reflectance map, of a center of a laser radar corresponding to each frame laser point cloud used for constructing the reflectance map collected in each collection region. This implementation implements the level-by-level pose optimization of laser point clouds used for constructing a reflectance map that are collected in each collection region in an excessively large region, to obtain an accurate position and Euler angle, used for constructing the reflectance map, of a laser radar center corresponding to each frame laser point cloud used for constructing the reflectance map.

Abstract: Provided is a photoelectric conversion apparatus including: an interlayer insulating film that covers a semiconductor layer and has a contact hole positioned above a gate electrode; a contact plug that is disposed in the contact hole and connected to the gate electrode; a light-shielding film that is positioned between the interlayer insulating film and the semiconductor layer and includes a first part covering a charge holding portion and a second part covering an upper surface of the gate electrode; and a dielectric layer that is positioned between the second part and the gate electrode, in which a relative dielectric constant of the dielectric layer is lower than a relative dielectric constant of the interlayer insulating film.

Abstract: Systems and methods are provided for navigating an autonomous vehicle using reinforcement learning techniques.

Abstract: One general aspect includes a method to provide an alert to a vehicle occupant, the method includes: detecting, via an internal camera, whether the vehicle occupant is paying attention to an environment surrounding the vehicle; detecting, via an external camera, an occurrence of an event in the environment surrounding the vehicle; and based on each of the preceding steps, providing a notification configured to alert the vehicle occupant to transition the vehicle from a stopped state to a moving state.

Abstract: The described positional awareness techniques employing visual-inertial sensory data gathering and analysis hardware with reference to specific example implementations implement improvements in the use of sensors, techniques and hardware design that can enable specific embodiments to provide positional awareness to machines with improved speed and accuracy.

Abstract: A vehicle control device is provided, which includes an engine, an engine control mechanism configured to control torque generated by the engine, and a processor configured to execute a vehicle attitude controlling module to perform a vehicle attitude control in which the engine control mechanism is controlled to reduce the torque so as to decelerate the vehicle, when a condition that the vehicle is traveling and a steering angle related value that is related to a steering angle of a steering device increases is satisfied, and a preventing module to prevent a combustion frequency of the engine per unit time from falling below a given value while the vehicle attitude controlling module executes the vehicle attitude control.

Abstract: A system for providing manual guidance of a vehicle includes a first inertial measurement unit (IMU) attached to a steering wheel, a second IMU attached to a fixed part of the vehicle, a global navigation satellite systems (GNSS) receiver, a data storage device for storing a pre-planned path, and a feedback module. The feedback module is configured to determine a current angle of the steering wheel, determine a deviation of the current position of the vehicle from the pre-planned path, determine a current heading of the vehicle, determine a current velocity of the vehicle, and determine a desired angle of the steering wheel relative to the vehicle. The system further includes a user interface configured to provide a visual indication of the desired angle of the steering wheel or a deviation of the current angle of the steering wheel from the desired angle of the steering wheel.

Abstract: An automotive vehicle includes at least one actuator configured to control vehicle steering, shifting, acceleration, or braking, at least one sensor configured to provide signals indicative of a location and velocity of an object external to the vehicle relative to the vehicle, and at least one controller in communication with the at least one actuator and the at least one sensor. The at least one controller is configured to, in response to a signal from the at least one sensor indicating that a relative velocity between a rearward object and the vehicle exceeds a first threshold and a distance between the rearward object and the vehicle falls below a second threshold, automatically control the at least one actuator to maneuver the vehicle from a first lateral position with respect to a current driving lane to a second lateral position with respect to the current driving lane.

Abstract: A sensor triggering system for a sensor apparatus including a plurality of sensors. The system detects a first sensor pulse and determines a memory address of a lookup table based on the first sensor pulse. In response to the first sensor pulse, the system selectively triggers one or more of the plurality of sensors based at least in part on a codeword stored at the first memory address. For example, the codeword may comprise a number of bits such that each bit of the codeword indicates an activation state for a respective one of the plurality of sensors.

Abstract: A vehicular control system for a vehicle includes a plurality of sensors. Responsive to data processing, the vehicular control system determines respective speeds of the determined vehicles and respective directions of travel of the determined vehicles, and determines respective influence values for the determined vehicles based on determined potential hazards to the equipped vehicle presented by the respective determined vehicles. The determined respective influence value for each determined vehicle is weighted according to direction and/or magnitude of a speed vector of that determined vehicle. The weighted determined respective influence values for the determined vehicles are ranked according to their hazard potential. A path of travel is selected from the plurality of determined paths responsive at least in part to the rankings of the weighted determined respective influence values. The system at least in part controls vehicle steering to guide the equipped vehicle along the selected path of travel.

Abstract: This invention provides a secure self-driving system or drive-assisting system. A drive control system of the present invention has an image recognition unit for detecting the peripheral environment of a vehicle and a drive control apparatus that controls driving of the vehicle, characterized by having a peripheral environment storage unit for storing the peripheral environment of the vehicle and by changing a mode of drive control performed by the drive control apparatus on the basis of a detection performance status of the image recognition unit obtained on the basis of information about the peripheral environment stored in the peripheral environment storage unit and information detected by the image recognition unit.

Abstract: The subject matter described herein includes a modular and extensible approach to integrate noisy measurements from multiple heterogeneous sensors that yield either absolute or relative observations at different and varying time intervals, and to provide smooth and globally consistent estimates of position in real time for autonomous flight. We describe the development of the algorithms and software architecture for a new 1.9 kg MAV platform equipped with an IMU, laser scanner, stereo cameras, pressure altimeter, magnetometer, and a GPS receiver, in which the state estimation and control are performed onboard on an Intel NUC 3rd generation i3 processor. We illustrate the robustness of our framework in large-scale, indoor-outdoor autonomous aerial navigation experiments involving traversals of over 440 meters at average speeds of 1.5 m/s with winds around 10 mph while entering and exiting buildings.

Abstract: The present invention extends to methods, systems, and computer program products for validating gesture recognition capabilities of automated systems. Aspects include a gesture recognition training system that is scalable, efficient, repeatable, and accounts for permutations of physical characteristics, clothing, types of gestures, environment, culture, weather, road conditions, etc. The gesture recognition training system includes sensors and algorithms used to generate training data sets that facilitate more accurate recognition of and reaction to human gestures. A training data set can be scaled from both monitoring and recording gestures performed by a humanoid robot and performed by animated humans in a simulation environment. From a scaled training data set, autonomous devices can be trained to recognize and react to a diverse set of human gestures in varying conditions with substantially improved capabilities.

Abstract: The present disclosure relates to a support braking apparatus and method for a vehicle capable of detecting braking target candidates for a vehicle, matching a braking amount required for the detected braking target candidates with a braking amount of a driver to select a specific braking target, and braking a subject vehicle by following up braking required for the selected braking target even if the driver does not maintain a braking control for the selected braking target.

Abstract: Systems and methods directed to projecting a current trajectory path of the autonomous vehicle on a surface of road is disclosed. In some embodiments, an autonomous vehicle with a light projector is disclosed, where the light projector is on a top surface of an autonomous vehicle. Additionally, in some embodiments, the autonomous vehicle may include an electronic control unit for controlling an operation of the light projector, where the electronic control unit detects whether the autonomous vehicle is turned on. In further embodiments, the electronic control unit receives data of an environmental condition surrounding the autonomous vehicle and receives an upcoming trajectory path of the autonomous vehicle. The electronic control unit may also project a light from the light projector onto a surface of a road indicating the upcoming trajectory path of the autonomous vehicle.

Abstract: A system to identify vision sensor impairment, the system including: a memory with one or more executable instructions; a controller to execute the executable instructions; a vision sensor located on a vehicle to capture at least one image of at least a portion of an environment surrounding the vehicle; where the executable instructions enable the controller to: receive a request communicated from a mobile computing device; in response to the request, communicate an activation signal to the vision sensor, the activation signal to activate the vision sensor to capture an image of the environment surrounding the vehicle; receive the captured image from the vision sensor; determine whether the view of the captured image includes a substantially impairing weather debris object; and based on this determination, generate a notification and communicate the notification to the mobile computing device.

Abstract: Systems and methods for communicating autonomous vehicle operations are provided. In one example embodiment, a computer implemented method includes obtaining data associated with the autonomous vehicle. The method includes identifying an object within the surrounding environment of the autonomous vehicle or a planned vehicle motion action of the autonomous vehicle based at least in part on the data associated with the autonomous vehicle. The method includes determining an audible vehicle indication that is associated with the identified object or the planned vehicle motion action. The audible vehicle indication is indicative of a type of the object or a type of the planned vehicle motion. The method includes outputting, via one or more output devices onboard the autonomous vehicle, the audible vehicle indication.

Abstract: Improved processing of sensor data (e.g., LiDAR data) can be used to distinguish between free space and objects/hazards. Autonomous vehicles can use such information for performing autonomous driving and/or parking operations. LiDAR data can include a plurality of range measurements (e.g., forming a 3D point cloud). Each of the range measurements can correspond to a respective LiDAR channel and azimuth angle. The processing of LiDAR data can include identifying one or more of the plurality of range measurements as ground points or non-ground points based on one or more point criteria. The one or more point criteria can include a ground projection criterion and an angular variation criterion.

Abstract: A position correction device includes: a reception unit, a position acquisition unit, a determination unit and a position information transmission unit. The reception unit receives a position information S1 of a vehicle from a navigation apparatus. The position acquisition unit acquires a position information S2 of the vehicle with a higher accuracy than the navigation apparatus. The determination unit determines whether a difference between the position information S1 and the position information S2 exceeds a predetermined threshold, or determines whether a traveling road identified by the position information S1 matches a traveling road identified by the position information S2. At least when it is determined that the difference exceeds the threshold, or when it is determined that the identified traveling roads do not match, the position information transmission unit transmits the position information S2 to the navigation apparatus.

Abstract: A camera facing the front of a vehicle while the vehicle is moving on the road may be calibrated by receiving sequential images from the camera. Image key points in the area limited by the road location are selected. The key points are tracked using an optical flow method. A filtering procedure is applied to the key points to identify the straight-line motion of the vehicle. At least two straight lines corresponding to opposite sides of the road. A calibration algorithm is applied to the at least two lines to determine a vanishing point. The pitch and/or yaw angles of the camera are then calculated.

Abstract: A system includes a wearable device that receives, via a wireless transceiver on the wearable device, a code from a wireless ignition device of a vehicle. The code is usable to start or stop an engine of the vehicle. One or more sensors on the wearable device detect a gesture performed by a user wearing the wearable device. Responsive to detecting the gesture, the wireless transceiver transmits the code to start or stop the engine of the vehicle to the wireless ignition device effective to cause the ignition device to start or stop the engine of the vehicle.

Abstract: A method and apparatus for determining a route of a vehicle are provided. The method includes activating fail operative steering in response to detecting an electronic power steering (EPS) failure, determining a length of a lane map fusion ring, calculating a desired route based on a line of the lane map fusion ring if the determined length is greater than a first predetermined distance, and calculating desired route based on offset information and heading information of the lane map fusion ring and curvature information and curvature derivative information calculated from map data if the determined length is less than the first predetermined distance.

Abstract: A system for operating an automated vehicle includes a perception-sensor, a display, and a controller-circuit. The perception-sensor is used to determine a rendering of an area proximate to a host-vehicle. The display is operable to convey to an operator of the host-vehicle a position of an object present in the area in accordance with the rendering. The controller-circuit is in communication with the perception-sensor and the display. The controller-circuit is configured to operate the host-vehicle in an autonomous-mode, and operate the display to convey to the operator a history of the position of the object in accordance with the rendering. The history is conveyed in response to initiating a transition of operation of the host-vehicle from the autonomous-mode to a manual-mode.

Abstract: In one embodiment, a system receives a reference trajectory including a reference path in which the ADV is to follow. The system controls the ADV along the reference path using a path tracking algorithm, including: determining a first lateral distance error, determining a second lateral distance error based on the first lateral distance error using a proportional-integral-derivative (PID) control system, where the second lateral distance error compensates for a lateral drift, and generating a steering command based on the second lateral distance error using the path tracking algorithm to control the ADV to minimize a lateral distance error, e.g., a lateral distance between an actual path taken by the ADV and the reference path.

Abstract: An example method and apparatus are disclosed. An infrastructure device is mounted to construction equipment located at a road construction zone with an input view of a predefined area of a road. The device may receive sensor data of road users and the road construction zone. Responsive to the sensor data, the device classifies objects as construction lane markers and determines coordinates of the construction lane markers. Using map data indicative of drivable lane boundaries of the road construction zone, the device determines whether the construction lane markers are within the drivable lane boundaries. Responsive to the determination, temporary lane boundaries for the construction zone are computed and transmitted in a data set to at least one autonomous vehicle.

Abstract: An autonomous driving device is configured to switch a driving mode, and includes a destination setting type autonomous driving mode in which a vehicle is made to travel to a destination and a following road autonomous driving mode in which, when a destination is not set, the vehicle is made to travel along a road. The autonomous driving device includes a display unit and an electronic control unit. The electronic control unit is configured to, when the display unit is made to display a traveling route along a following road traveling route, make the display unit display a traveling route from a current position of the vehicle to a nearest branch road in front in a moving direction along the following road traveling route and a moving direction on the nearest branch road along the following road traveling route.

Abstract: A smart device display for an autonomous vehicle, comprising a first display section that displays an external view of the autonomous vehicle, a second display section that displays vehicle actions that the autonomous vehicle will take and a third display section that displays alternative vehicle actions that an authorized passenger of the autonomous vehicle may select to override the vehicle actions. Such system can also comprise an artificial intelligence module that learns the alternative vehicle actions the authorized passenger selects in various intervention situations, wherein the artificial intelligence module uses machine learning algorithms to decide the best alternative vehicle actions that the authorized passenger is likely to select for similar future situations.

Abstract: During a measurement technique, an electronic device may receive first sensor information associated with a first field of view and a first timestamp, and second sensor information associated with a second field of view and a second timestamp. For example, the electronic device may perform a first measurement using a first sensor and performing a second, different type of measurement using a second sensor. Therefore, the first sensor information and the second sensor information may be associated with different types of sensors. Moreover, the first timestamp and the second timestamp may be concurrent or in close temporal proximity, and the first field of view and the second field of view may at least substantially overlap. Then, the electronic device may store the first sensor information and the second sensor information in memory. In some embodiments, the electronic device stores the first timestamp and the second timestamp in the memory.

Abstract: A method for monitoring a parked motor vehicle, including the following steps: monitoring an interior of the motor vehicle and/or a surrounding field of the motor vehicle with the aid of a monitoring infrastructure that is assigned to an infrastructure external relative to the parked motor vehicle; monitoring the interior of the motor vehicle and/or the surrounding field of the motor vehicle with the aid of one or more sensors onboard the motor vehicle; transmitting monitoring data based on both monitorings via a wireless communication network to a mobile terminal; in response to reception of a control command transmitted from the mobile terminal via the wireless communication network for controlling one or more components of the motor vehicle and/or for controlling one or more components of the external infrastructure, controlling the one or more corresponding components as a function of the control command.

Abstract: Methods and apparatus are disclosed for vision-based determining of trailer presence. An example vehicle includes a camera to capture a plurality of frames. The example vehicle also includes a controller to calculate feature descriptors for a set of features identified in a first frame, compute respective match magnitudes between the feature descriptors of the first frame and for a second frame, calculate respective feature scores for each feature of the set of features, and determine if a trailer is present by comparing a feature score of a feature to a threshold.

Abstract: A vehicle driving assist apparatus of the invention does not execute a road end line departure prevention control when a next lane vehicle traveling in a next lane is acquired as a road end line and an amount of an operation input to a steering wheel of an own vehicle to cause the own vehicle to move into the next lane, is larger than or equal to a predetermined operation amount.

Abstract: A specific implementation of the method includes: constructing a reflectance map based on a position and an Euler angle, obtained through a global pose optimization and used for constructing a reflectance map, of a center of a laser radar corresponding to each frame laser point cloud used for constructing the reflectance map. This implementation implements the level-by-level pose optimization of key frame laser point clouds, sample frame laser point clouds, regular frame laser point clouds selected from laser point clouds used for constructing a reflectance map, to obtain an accurate position and Euler angle, used for constructing the reflectance map, of a center of the laser radar corresponding to each frame laser point cloud used for constructing the reflectance map, so that accurate coordinates of laser points in each frame laser point cloud used for constructing the reflectance map in a world coordinate system can be obtained.

Abstract: Disclosed are an apparatus and a method for electric vehicle collision avoidance. The apparatus for electric vehicle collision avoidance may include: a camera unit configured to acquire an image of the surrounding of an electric vehicle; a monitoring unit configured to control the camera unit such that the image is acquired as a preset number of image frames, monitor changes in consecutive image frames to recognize an object present in the image, estimate a distance between the electric vehicle and the object based on the position of the recognized object in the image, and generate a power cutoff command signal if the estimated distance is smaller than or equal to a preset distance; and a power management unit configured to cut off the power of a battery pack of the electric vehicle in response to the power cutoff command signal.

Abstract: The invention relates to a device, to a vehicle, and to a method for measuring a dimension between at least two points on surfaces. The device comprises an image-generating apparatus configured to scan the surroundings of the vehicle, and a display apparatus configured to display a representation of the surroundings of the vehicle. The device also includes an input apparatus configured to define at least two points as measuring points between which a dimension is to be determined in the displayed representation, a surroundings sensor configured to sense a distance and a direction of each of the measuring points with respect to the vehicle, and an evaluation apparatus configured to determine the dimension based on the sensed distances and directions of the measuring points, wherein the evaluation apparatus is further configured to output the determined dimension.

Abstract: A robotic system for driving a vehicle to a destination is configured for placement inside the vehicle, and it utilizes an imaging system for acquiring image data of at least a part of the interior of the vehicle and image data of external surroundings of the vehicle, and a control system for processing the image data acquired by the imaging system. The control system is configured to identify in the image data of at least part of the interior of the vehicle image data of the vehicle state indicators, and determine therefrom at least vehicle status data. The control system is adapted to determine from the image data of external surroundings road status data, and analyze the vehicle status data and the road status data for generating control instructions for driving the vehicle along the road.

Abstract: A method of determining at least one of position and attitude in relation to an object is provided. The method includes capturing at least two images of the object with at least one camera. Each image is captured at a different position in relation to the object. The images are converted to edge images. The edge images of the object are converted into three-dimensional edge images of the object using positions of where the at least two images were captured. Overlap edge pixels in the at least two three-dimensional edge images are located to identify overlap points. A three dimensional edge candidate point image of the identified overlapped points in an evidence grid is built. The three dimensional candidate edge image in the evidence grid is compared with a model of the object to determine at least one of a then current position and attitude in relation to the object.

Abstract: Systems and methods are provided for navigating an autonomous vehicle using reinforcement learning techniques.

Abstract: A drive assist apparatus includes a position acquisition unit that acquires a position of an own vehicle, a position of a tollgate present ahead of the position of the own vehicle, and a position of a target lane in a road present ahead of the tollgate, a scheduled traveling route creation unit that creates a scheduled traveling route from the position of the own vehicle to the position of the target lane through the position of the tollgate, and a travel control unit that controls the own vehicle so as to travel along the scheduled traveling route.

Abstract: A vehicle travel control apparatus includes an anomaly monitoring section for determining, through monitoring, whether or not a driver is in an anomalous state in which the driver has lost his or her ability to drive the vehicle, and a deceleration section for automatically stopping the vehicle by decelerating the vehicle after a final anomaly determined time which is a point in time when the anomaly monitoring section finally determines that the driver is in the anomalous state. The deceleration section prohibits deceleration of the vehicle in the case where the deceleration section determines that the vehicle is present in the deceleration prohibited section after the final anomaly determination time.

Abstract: A system for determining a distance to an object comprises an image capture device (101) which has a coded aperture and an image sensor which is positioned out of a focus plane of the coded aperture. A receiver (103) receives an image of a scene from the image sensor and a detector (105) detects at least two image objects of the image corresponding to ghost images of the object resulting from different openings of the coded aperture in response to an optical characteristic of the object. A distance estimator (107) then determines a distance to the object in response to a displacement in the image of the at least two image objects. The distance may be to a person and the image may be a bright pupil image wherein pupils are enhanced by reflection of light by the retina. The image may be compensated by a dark pupil image of the scene.

Abstract: A method for performing localization and mapping of a mapping device. The method includes: capturing images of environment by a visual sensor of the mapping device, and processing the captured images to obtain a set of high-resolution images and a set of low-resolution images; determining motion-scale measurement of the mapping device using an inertial sensor and an odometer; generating, by a controller of the mapping device, a first mask corresponding to dynamic features in the low-resolution images; extracting features from the high-resolution images; recovering, by the controller, poses of the mapping device based on the high-resolution images and the motion-scale measurements; filtering out, by the controller, the features from the high-resolution images that correspond to the first mask, to obtain filtered features; and performing, by the controller, localization and mapping using the poses and the filtered features.

Abstract: A method receives situation data including images from vehicles; clusters, into an image cluster, the images included in the situation data of vehicle(s) located in a geographic region from among the vehicles; locates related situation object(s) in image(s) of the image cluster; matches images from different vehicles in the image cluster, the matched images having corresponding feature(s) of the related situation object(s); determines three-dimensional (3D) sensor coordinates of the related situation object(s) relative to a sensor position of a target vehicle associated with at least one matched image, using the corresponding feature(s) of the related situation object(s) in the matched images; converts the 3D sensor coordinates of the related situation object(s) to geolocation coordinates of the related situation object(s) using geolocation data of the different vehicles associated with the matched images; and determines a coverage area of a traffic situation based on the geolocation coordinates of the relate

Abstract: A ceiling map building method includes estimating a scale of each ceiling image based on information related to the ceiling image and information related to another ceiling image including a same object as included in the ceiling image, the scale being represented as a ratio of an amount of movement of the object between the two ceiling images to an amount of movement of the camera (6) between the positions thereof when the two ceiling images were respectively captured (ST16), and building a ceiling map (2) (ST2) by converting the ceiling images in accordance with the respective scales so as to have sizes suitable for the ceiling map and combining the converted ceiling images (ST84).

Abstract: The present disclosure provides an inspection device, a control method and a control apparatus for the same, and relates to the technical field of inspection patrol. The inspection device can patrol in a lane which has at least one lane line. The control method includes collecting an environment image around the inspection device. The control method includes identifying the lane line from the environment image. The control method includes determining a distance between the inspection device and the lane line. The control method includes determining a deviation between the inspection device and a preset route in the lane according to the distance between the inspection device and the lane line. The control method includes controlling the inspection device to move toward the preset route according to the deviation.

Abstract: Aspects of the disclosure relate providing a lane change notification when a vehicle is to perform a lane change. One or more computing devices may generate and display a video, where the video is generated from a perspective of a virtual camera at a default position and default pitch. The one or more computing devices may receive an indication that the vehicle is to perform a lane change from a first lane to a second lane and adjust, after the vehicle receives the indication, the default position and default pitch of the virtual camera to an updated position further above the vehicle relative to ground than the default position and an updated pitch directed more towards the ground than the default pitch. The video may be generated and displayed from the perspective of the virtual camera at the updated position and updated pitch.