Abstract: An autonomous mower conversion kit and method for autonomously controlling a zero-turn mower. The conversion kit include a vehicle control unit containing a navigation processor in data communication with one or more global positioning (GPS) devices configured for inputting GPS coordinates to the navigation processor. The navigation processor is configured to send a signal to a pair of high torque servo motors attached to a housing of a mower. Each of the pair of high torque servo motors has a tie rod removably attached on a first end to one of the pair of high torque servo motors and on a distal end to a mower steering arm. A safety override switch is connected to the vehicle control unit and is configured for converting the mower to autonomous control.

Abstract: An apparatus for automated ground control of an electric vertical takeoff and landing aircraft includes a flight controller and a remote device. Remote device may transmit a location datum to a flight controller. Location datum may store a location of a charger, terminal, airport, or the like. Flight controller may authorize the location datum and direct aircraft using the information from the location datum.

Abstract: Systems and methods for dynamic sensor data adaptation using a deep learning loop are provided. A method includes classifying, using a discriminator model, a first object from first sensor data associated with a first sensing condition, wherein the discriminator model is trained for a second sensing condition different from the first sensing condition; generating, using a generator model in response to the discriminator model failing to classify the first object, second sensor data representing a second object comprising at least a modified element of the first object; classifying, using the discriminator model, the second object from the second sensor data; and adapting, based at least in part on a difference between the first object and the second object in response to the discriminator model successfully classifying the second object, a machine learning model associated with object classification for the first sensing condition.

Abstract: An automated valet parking (AVP) management system manages an AVP service delivered in a predetermined area. A pick-up or drop-off point is away from a parking facility in which a vehicle is parked. When it is not possible to deliver the AVP service to a user in accordance with a user request, notification information is delivered to the user. The notification information includes at least one of: a congestion situation on a route from a current position of the vehicle to a specified pick-up or drop-off point; a congestion situation at the specified pick-up or drop-off point; a waiting time for the user to get on or off the vehicle at the specified pick-up or drop-off point; a recommended time of day of use at the specified pick-up or drop-off point; and a substitute pick-up or drop-off point being a substitute for the specified pick-up or drop-off point.

Abstract: A system and method for providing an RNN-based human trust model that include receiving a plurality of inputs related to an autonomous operation of a vehicle and a driving scene of the vehicle and analyzing the plurality of inputs to determine automation variables and scene variables. The system and method also include outputting a short-term trust recurrent neural network state that captures an effect of the driver's experience with respect to an instantaneous vehicle maneuver and a long-term trust recurrent neural network state that captures the effect of the driver's experience with respect to the autonomous operation of the vehicle during a traffic scenario. The system and method further include predicting a take-over intent of the driver to take over control of the vehicle from an automated operation of the vehicle during the traffic scenario.

Abstract: A navigation system includes a server apparatus connected to vehicles via a network and a navigation apparatus connected to the server apparatus via the network. The server apparatus receives, from a first vehicle, traffic-related information related to snow on a road on which the first vehicle has traveled or slipperiness of the road, and location information of the road; generates difficulty information for the road related to a travel difficulty caused by the snow or the slipperiness; and transmits the difficulty information and the location information to the navigation apparatus movable together with a second vehicle identical to or different from the first vehicle. The navigation apparatus receives the difficulty information and the location information; sets a traffic regulation for passage of the second vehicle through the road; and sets, for the second vehicle, a travel route based on the traffic regulation.

Abstract: Provided is a system including a robot and an application of a communication device. The robot includes a medium storing instructions that when executed by a processor of the robot effectuate operations including: obtaining first data indicative of a relative position of the robot in a workspace; actuating the robot to drive within the workspace to form a map including mapped perimeters that correspond with physical perimeters of the workspace while obtaining second data indicative of movement of the robot; and forming the map of the workspace based on at least some of the first data, wherein the map of the workspace expands as new first data are obtained, until all perimeters of the workspace are included in the map. The application is configured to display information, such as the map, and receive user input.

Abstract: A system and method for controlling a merge vehicle travelling along a highway having a merge lane and a main lane. The method includes receiving merge data about the merge vehicle and a surrounding environment of the merge vehicle. The method includes detecting an intent to perform a merge maneuver by the merge vehicle from the merge lane to the main lane based on the merge data. Further, the method includes generating a graph having a plurality of nodes connected by edges. The plurality of nodes includes a start node set to a current position of the merge vehicle and a goal node located in the main lane after the merge lane has ended. The method includes calculating a three-dimensional (3D) trajectory based on the graph by optimizing edge costs from the start node to the goal node, and controlling the merge vehicle based on the 3D trajectory.

Abstract: A vehicle control device includes a behavior instability acquirer, an automated driving advisability determination unit, and a switching time setting unit. The behavior instability acquirer acquires behavior instability of a vehicle. The automated driving advisability determination unit determines whether to continue automated driving on the condition that the vehicle is performing the automated driving. On the condition that the automated driving advisability determination unit determines that the automated driving is noncontinuable, the switching time setting unit determines switching time from the automated driving to manual driving on the basis of the behavior instability.

Abstract: A vehicle includes a communication unit; a memory configured to store information for connection to a person who recently got out from a vehicle by the communication unit; and at least one processor. The processor(s) are configured to: in a case where a user who tries to newly start to use the vehicle gets in the vehicle, obtain information for authentication of the user; connect to the person by the communication unit using the information for connection stored in the memory; send the information for authentication of the user to the person; decide whether the authentication of the user is successful on a basis of an authentication result received from the person; and determine to allow the user to use the vehicle when the authentication of the user is successful.

Abstract: The subject disclosure relates to techniques for increasing a quality of predicted trajectories output from a trained prediction algorithm. A process of the disclosed technology can include receiving by a trained prediction algorithm, information about objects in an environment as perceived by sensors of an autonomous vehicle, receiving by the trained prediction algorithm, information about a location of the autonomous vehicle in the environment, generating by the trained prediction algorithm, a predicted trajectory for an object among the objects in the environment, wherein the predicted trajectory being anchored by a path through a tree of paths including at least two modes, wherein each mode creates a node in the tree, wherein a mode is a semantic classification of a portion of the predicted trajectory, and outputting by the trained prediction algorithm, the predicted trajectory for the object.

Abstract: The action schedule item creation ECU creates action schedule items demanded of an ego vehicle capable of switching between autonomous driving and manual driving. The HUD and the meter display are provided inside a cabin of the ego vehicle. The display control ECU displays the action schedule items created by the action schedule item creation ECU on the HUD and the meter display, and emphasizes display of action schedule items to be performed by manual driving compared to display of action schedule items to be performed by autonomous driving.

Abstract: Provided is a mobile robot including a traveling unit configured to move a main body, a light detection and ranging (LiDAR) sensor configured to acquire external geometry information of the main body, and a controller configured to create node data based on LiDAR data sensed by the LiDAR sensor, to create grid map based on the LiDAR data and the node data, to create first map data based on the node data, to update the grid map based on the first map data, and to image-process the updated grid map to create second map data, where a map may be quickly and safely created without an environmental restriction, by effectively combining a node-based map creating method and a grid-based map creating method.

Abstract: Various embodiments relate to recording event data to identify and resolve anomalies associated with control of driverless vehicles. Some examples include computing vehicular drive parameters to facilitate driverless transit, monitoring control signals, detecting an event, triggering storage of event data, determining transmission control criteria, and transmitting the event data based on the transmission control criteria. Other examples include receiving event data via a communications network from an autonomous vehicle, identifying a computed vehicular drive parameter, extracting sensor data associated with the event, detecting application of control signals, analyzing the control signals, the sensor data, and the subset of computed vehicular drive parameters to identify a type of event, and generating update executable instructions responsive to the type of event.

Abstract: In a conveyance system, a conveyance object is conveyed by use of a plurality of mobile robots autonomously movable inside a facility. In a case where a blockade request event occurs in at least one area inside the facility, the conveyance system receives occurrence information transmitted from a facility management system configured to manage the facility and causes the mobile robots to execute an operation restriction to restrict operations of the mobile robots. In a case where a predetermined condition for the blockade request event is established after the mobile robots execute the operation restriction, the conveyance system reboots the mobile robots.

Abstract: Various arrangements for autonomous servicing of a network device are presented. A backend server system may receive status data from various devices. The backend server system may determine, based at least in part on the received status data, a triggering event associated with a first device. In response to the determined triggering event, location information associated with the first device may be sent to an unmanned aerial vehicle (UAV). The UAV may send security information directly to the first device. The first device may be required to validate the security device, then the UAV may modify a physical component of the first device.

Abstract: A method may include obtaining lidar data comprising a plurality of lidar returns from an environment of an autonomous vehicle. The lidar data may be processed with a machine learning model to generate, for the plurality of lidar returns, a plurality of first outputs that each identify a respective lidar return as belonging to an object or non-object and a plurality of second outputs that identify lidar returns belonging to objects as harmful or non-harmful to the autonomous vehicle. A subset of the lidar returns identified as belonging to objects that (i) do not correspond to any of a plurality of pre-classified objects and (ii) were identified as harmful to the autonomous vehicle may be determined. The autonomous vehicle may be controlled based at least in part on the subset of lidar returns.

Abstract: A vehicle control device includes a recognizer configured to recognize a surrounding situation of a vehicle, a driving controller configured to control the vehicle, and a first receiver configured to receive a switching operation on a driving mode. The driving controller causes the vehicle to travel in any one of a plurality of driving modes including a first mode and a second mode that a task imposed on an occupant is milder than that in the first mode, and performs acceleration/deceleration control so that a vehicle speed becomes a target speed in a state that the first mode is being executed and the second mode is executable and switches the driving mode from the first mode to the second mode when the first receiver has received an operation for switching the driving mode to the second mode in a state that the speed has become the target speed.

Abstract: A vehicular cabin monitoring system includes an interior-viewing camera disposed at a vehicle and viewing a driver sitting at a driver seat of the vehicle and viewing at least one other seat of the vehicle. The interior-viewing camera is operable to capture image data. The vehicular cabin monitoring system, via processing of image data captured by the interior-viewing camera, detects an occupant present in the vehicle. The vehicular cabin monitoring system, via processing of image data captured by the interior-viewing camera, monitors the driver sitting at the driver seat of the vehicle. Control of the vehicle is adjusted based at least in part on the monitoring of the driver and the detected occupant.

Abstract: Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a distribution of predicted positions for the object in the future that meet a criterion, allowing for more efficient sampling. A predicted position of the object in the future may be determined by sampling from the distribution.

Abstract: Systems and methods are disclosed for determining a distraction level of a driver. A real-time driver analysis computer may receive sensor data from one or more driver analysis sensors. The real-time driver analysis computer may analyze the sensor data to determine a distraction level of a driver. Based on the distraction level, the real-time driver analysis computer may send one or more control signal to the vehicle and output one or more alerts to a mobile device associated with the driver.

Abstract: Provided is an electronic apparatus, including: a sensor; a camera; a storage configured to store first and second artificial intelligence models; a first processor; and a second processor. The second processor is configured to: input an image obtained through the camera to the first artificial intelligence model and identify the object of the first type in the image, and input the image obtained through the camera to the second artificial intelligence model and identify the object of the second type, at least a part of which is not viewable in the image. The first processor is configured to: determine a distance between the object of the first type and the object of the second type based on sensing data received from the sensor; and control the electronic apparatus to travel based on the determined distance.

Abstract: A system 100 for remote assistance of an autonomous agent can include and/or interface with any or all of: a sensor suite 110, a computing system 120, a communication interface 130, and/or any other suitable components. The system can further optionally include a set of infrastructure devices 140, a teleoperator platform 150, and/or any other suitable components. The system 100 functions to enable information to be exchanged between an autonomous agent and a tele-assist. Additionally or alternatively, the system 100 can function to operate the autonomous agent (e.g., based on remote inputs received from a teleoperator, indirectly, etc.) and/or can perform any other suitable functions.

Abstract: Techniques associated with generating and maintaining sparse geographic and map data. In some cases, the system may maintain a factor graph comprising a plurality of nodes. In some cases, the nodes may comprise pose data and sensor data associated with an autonomous vehicle at the geographic position represented by the node. The nodes may be linked based on shared trajectories and shared sensor data.

Abstract: A method for operating a car park parking system of a car park involves determining a current state of occupancy of the car park and assigning a quick-access parking space to a motor vehicle to be parked depending on the determined state of occupancy. The motor vehicle to be parked is brought driverlessly to the assigned quick-access parking space. An information message is communicated to a user of the motor vehicle to be parked depending on a decision criterion. The information message proposes a pick-up time, and, following acceptance of the proposed pick-up time by the user, the motor vehicle to be parked is brought driverlessly from the quick-access parking space to a long-stay parking space.

Abstract: Methods and apparatus for selecting and combining items in an outbound container through the use of autonomous vehicles, each of which includes means for automatically loading and unloading a payload, to perform both transfer and transport functions in moving containers of items within a workspace via a network of roadways. Under computer control, said autonomous vehicles transfer and transport case containers of item units between incoming receiving stations, intermediate storage locations, and outgoing order-assembly stations where entire containers or individual item units are combined in the outbound container.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for intervention behavior prediction. One of the methods includes receiving data characterizing a scene that includes a first agent and a second agent in an environment. A confounder prediction input generated from the data is processed using a confounder prediction model. A plurality of predicted conditional probability distributions is generated, wherein each predicted conditional probability distribution is conditioned on: (i) a planned intervention by the second agent, and (ii) the confounder variable belonging to a corresponding confounder class.

Abstract: An augmented navigational system is provided for autonomous vehicles. The augmented navigational system may further be coupled to an artificial intelligence system that provides object recognition and image recognition. A machine learning system may provide further feedback as to whether the pickup and drop off location was appropriate, and whether the recognition of one or more objects was appropriate.

Abstract: An automated parking system and a method enable a driverless vehicle to autonomously travel and park in a vacant parking slot through communication with a parking infrastructure. The automated parking system and method also control the driverless vehicle to autonomously travel from a parking slot to a pickup area through communication with the parking infrastructure.

Abstract: Systems and methods are provided for using sensors and signal processing to detect vehicle surface impacts. In particular, a sensor and signal processing approach is provided for detecting impacts, with the results having a low false positive rate. The approach reduces operator costs by reducing operator involvement through improved automated detection technology. Additionally, systems and methods are provided for distinguishing chassis-driven fascia vibration from impact-driven fascia vibration.

Abstract: The disclosure generally relates to a system comprising a memory and a processor configured to access the memory and execute the machine-executable instructions stored on the memory to determine that a target vehicle is engaging in an abnormal driving, determine that the abnormal driving exceeds a notification threshold parameter of an abnormal driving notification system, generate a notification, and monitor the ego vehicle and/or driver to alter notification threshold values based on the reactions of the ego vehicle and/or driver inputs.

Abstract: An automatic driving control apparatus for a vehicle is capable of switching a driving mode between a manual driving mode in which a driver manually performs a driving operation of the vehicle and an automatic driving mode in which a driving operation is automatically performed along a set target traveling route. The automatic driving control apparatus includes a driving mode switching unit configured to monitor a manual operation by the driver during traveling in the manual driving mode, and to control so as to switch the driving mode to the automatic driving mode after traveling a set range by manual driving.

Abstract: A vehicle control system includes an imaging device configured to capture an image of a travel route on which a vehicle is traveling, and a delimiting line estimating unit configured to estimate a position of a delimiting line on the travel route based on the image captured by the imaging device. The delimiting line estimating unit is configured to generate a first delimiting point sequence, generate a second delimiting point sequence that is offset rearward in a vehicle travel direction with respect to the first delimiting point sequence, generate a corrected delimiting point sequence based on the first delimiting point sequence and the second delimiting point sequence, and estimate the position of the delimiting line on the travel route based on the corrected delimiting point sequence.

Abstract: Among other things, a determination is made that intervention in an operation of one or more autonomous driving capabilities of a vehicle is appropriate. Based on the determination, a person is enabled to provide information for an intervention. The intervention is caused in the operation of the one or more autonomous driving capabilities of the vehicle.

Abstract: Systems, methods, and other embodiments described herein relate to resolving one or more deficiencies in autonomous driving requirements for a road segment. In one embodiment, a method includes receiving sensor data for a portion of the road segment from at least one sensor of a vehicle, and determining autonomous driving requirements for the portion of the road segment. The method includes identifying the one or more deficiencies in the autonomous driving requirements for the portion of the road segment based on the received sensor data and the determined autonomous driving requirements for the portion of the road segment. The method includes determining an alteration to the portion of the road segment to overcome the one or more deficiencies in the autonomous driving requirements for the portion of the road segment.

Abstract: A system and method including, predicting a first set of Doppler velocity information for a first point set to produce a first predicted set of Doppler velocity information for the first point set; determining one or more Doppler velocity errors based on the first predicted set of Doppler velocity information and a second set of Doppler velocity information; predicting a third set of Doppler velocity information for the second point set to produce a second predicted set of Doppler velocity information for the second point set; determining one or more Doppler velocity errors based on at least one of the second predicted set of Doppler velocity information and a fourth set of Doppler velocity information; and producing a transform that aligns the one or more points of the first point set with the one or more points of the second point set.

Abstract: Aspects of the disclosure relate to generating a puddle occupancy grid including a plurality of cells. For instance, a first probability value for a puddle being located at a first location generated using sensor data from a first sensor may be received. A second probability value for a puddle being located at a second location generating using sensor data from a second sensor different from the first sensor may be received. A first cell may be identified from the plurality of cells using the first location. The first cell may also be identified using the second location. A value for the cell may be generated using the first probability value and the second probability value.

Abstract: A self-driving cleaner includes a main body and a driving unit for driving in a cleaning area. The cleaner suctions foreign material on the floor in the cleaning area. The cleaner includes a first pattern irradiation unit and a second pattern irradiation unit on the front surface of the main body, the first and second pattern irradiation units radiating light in a preset pattern towards the front lower side and the front upper side of the main body, respectively. The cleaner includes a camera on the front surface of the main body, for capturing, at a preset interval, an image including a first light pattern and a second light pattern formed by the first and the second pattern irradiation units, respectively. The cleaner includes a control unit for determining whether a first obstacle exists at a location upwardly spaced apart from the floor, using the image captured by the camera.

Abstract: A moving body includes: a main body section provided with a moving mechanism; a peripheral information detection sensor configured to detect an obstacle peripheral to the main body section; and a control section configured to cause the main body section to autonomously travel by controlling the moving mechanism based on information regarding the peripheral obstacle detected by the peripheral information detection sensor, and configured to cause information relating to the peripheral obstacle, in a direction of progress of the main body section, to be displayed in a surrounding area of the main body section.

Abstract: The disclosed technology provides solutions for implementing dynamic autonomous vehicle (AV) dispatch services. A process of the disclosed technology can include steps for receiving a dispatch request from a mobile device associated with a user, wherein the dispatch request comprises a first pick-up location associated with the user, dispatching a first autonomous vehicle (AV) to the first pick-up location in response to the dispatch request, and automatically receiving an updated location of the mobile device associated with the user. In some aspects, the process can further include steps for determining a second pick-up location based on a change between the first pick-up location and the updated location, and transmitting an updated dispatch request based on the updated location of the mobile device. Systems and machine-readable media are also provided.

Abstract: A robotic work tool system, comprising a charging station and a robotic work tool, said robotic work tool comprising two charging connectors arranged on an upper side of the robotic work tool and said charging station comprising two charging connectors and a supporting structure arranged to carry said charging connectors and to extend over and above said robotic work tool as the robotic work tool enters the charging station for establishing electrical contact between the charging connectors of the robotic work tool and the charging connectors of the charging station from above, wherein said supporting structure is arranged to allow the robotic work tool exit the charging station by driving through the charging station without reversing.

Abstract: Aspects of the present disclosure relate to automated vehicle condition grading. In examples, a set of images for a vehicle are processed using a machine learning engine to generate an optical vehicle condition grade for each image of the set. The resulting set of optical vehicle condition grades may be aggregated to generate an aggregate optical vehicle condition grade for the vehicle. In some examples, additional information associated with the vehicle is processed, which may be used to generate an adjustment grade. Accordingly, the adjustment grade and the aggregate optical vehicle condition grade are used to generate a final vehicle condition grade for the vehicle. The final vehicle condition grade is associated with the vehicle in a vehicle condition grade data store for subsequent use by the vehicle grading service and/or by an associated client device, among other examples.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that validate the performance of a dispatch model, such as a directive-based model, utilized for facilitating transportation matching services. For example, the disclosed systems can generate critical situations clusters composed of groups of critical transportation provider performance scenarios. From the critical situation clusters, the disclosed systems can sample one or more critical transportation provider situations that present a risk of degradation for the transportation matching services. Accordingly, the disclosed systems can measure a performance of the dispatch model by employing a simulation model that utilizes the dispatch model to propagate the critical transportation provider situations through time.

Abstract: Methods and systems for autonomous and semi-autonomous vehicle routing are disclosed. Roadway suitability for autonomous operation is scored to facilitate use in route determination. Maps of roadways suitable for various levels of autonomous operation may be generated. Such map data may be used by autonomous vehicles or other computer devices in determining routes based upon criteria for vehicle trips. Such routes may be automatically updated based upon changes in road conditions, vehicle conditions, operator conditions, or environmental conditions. Emergency routing using such map data is described, such as automatic routing and travel when a passenger is experiencing a medical emergency.

Abstract: A method of Light Detection and Ranging (LIDAR) includes generating a first optical pulse that propagates towards a target and receiving an optical return signal reflected from the target resulting from the generated first optical pulse. The optical return signal is processed to determine a number of additional optical pulses desired to be propagated towards the target to meet a performance criteria. The determined number of additional optical pulses is then generated and propagated towards the target. The additional optical return signals reflected from the target are received and processed to obtain one or more LIDAR measurements.

Abstract: Examples of the disclosure relate to example systems and methods for operating a see-through display for a vehicle. An example system includes a video camera positioned to capture video related to a vehicle structure that blocks a view of the driver. The system also includes a see-through display disposed inside the vehicle between the vehicle structure and the driver. The system also includes a processor configured to identify a closest object within a field of view of the video camera, determine a distance to the closest object, and process the captured video based, at least in part, on the distance to determine a portion of the captured video to be displayed on the see-through display. The processor renders the portion of the captured video to create a see-through effect relative to the vehicle structure.

Abstract: Provided are methods for semantic annotation of sensor data using unreliable map annotation inputs, which can include training a machine learning model to accept inputs including images representing sensor data for a geographic area and unreliable semantic annotations for the geographic area. The machine learning model can be trained against validated semantic annotations for the geographic area, such that subsequent to training, additional images representing sensor data and additional unreliable semantic annotations can be passed through the neural network to provide predicted semantic annotations for the additional images. Systems and computer program products are also provided.

Abstract: Systems and methods herein describe accessing a set of feature flags, a first feature flag in the set of feature flag describing vehicle navigation behavior on a routing graph, the routing graph representing the roadway, associating the set of feature flags with a vehicle, applying the associated set of feature flags to a graph traversal algorithm to generate a modified graph traversal algorithm, generating the route using the modified graph traversal algorithm; and transmitting instructions to the vehicle to begin executing the route.

Abstract: A remote parking apparatus executes a remote parking control to park the own vehicle in a designated parking space by controlling operations of the driving apparatus and the braking apparatus in response to commands from outside of the own vehicle. The remote parking apparatus executes a braking-drive process to apply the braking force to the own vehicle by the braking apparatus and apply the driving force to the own vehicle by the driving apparatus before starting to move the own vehicle by the remote parking control. The remote parking apparatus starts to move the own vehicle by the remote parking control on the condition that the own vehicle is maintained stopped until a predetermined time elapses from starting the braking-drive process.

Abstract: Object avoidance by an autonomous vehicle (AV) is disclosed. A method includes detecting a first object along a coarse driveline of a drivable area of the AV; receiving a predicted path of the first object; determining, based on the predicted path of the first object, an adjusted drivable area; and determining a trajectory of the AV through the adjusted drivable area. A system includes a trajectory planner configured to detect a first object along a coarse driveline of a drivable area of the AV; receive a predicted path of the first object; determine, based on the predicted path of the first object, an adjusted drivable area; and determine a trajectory of the AV through the adjusted drivable area.