Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle. The high-priority agents can be identified based on a set of mutual importance scores in which each mutual importance score indicates an estimated mutual relevance between the vehicle and a different agent from a set of agents on planning decisions of the other. The mutual importance scores can be calculated based on importance scores assessed from the perspectives of both the vehicle and the agents.

Abstract: An autonomous vehicle can classify and prioritize agent of interest (AOI) objects located around the autonomous vehicle to manage computational resources. An example method performed by an autonomous vehicle includes determining, based on a location of the autonomous vehicle and based on a map, an area in which the autonomous vehicle is operated, determining, based on sensor data received from sensors located on or in the autonomous vehicle, attributes of objects located around the autonomous vehicle, where the attributes include information that describes a status of the objects located around the autonomous vehicle, selecting, based at least on the area, a classification policy that includes a plurality of rules that are associated with a plurality of classifications to classify the objects, and for each of the objects located around the autonomous vehicle: monitoring an object according to a classification of the object based on the classification policy.

Abstract: The present invention discloses a collaborative design method using an event-triggered scheme (ETS) and a Takagi-Sugeno (T-S) fuzzy H? controller in a network environment. For the problem about the unmanned surface vehicle control based on a switching T-S fuzzy system under an aperiodic DoS attack, the present invention provides an H? controller design method based on the event-triggered scheme. The characteristics of the unmanned surface vehicle system under the DoS attack are analyzed, and external disturbance in the navigation process is added into an unmanned surface vehicle motion model to establish an unmanned surface vehicle switching system model. The stability of the system is analyzed by piecewise Lyapunov functionals, such that controller gain and event-triggered scheme weight matrix parameters are obtained, thus ensuring that a networked unmanned surface vehicle navigation system has the ability to resist the DoS attack and the external disturbance.

Abstract: The present application provides a system for unmanned aerial vehicle (UAV) parachute landing. An exemplary system includes a detector configured to detect at least one of a flight speed, a wind speed, a wind direction, a position, a height, and a voltage of a UAV. The system also includes a memory storing instructions and a processor configured to execute the instructions to cause the system to: determine whether to open a parachute of the UAV in accordance with a criterion, responsive to the determination to open the parachute of the UAV, stop a motor of the UAV that spins a propeller of the UAV, and open the parachute of the UAV after stopping the motor of the UAV for a first period.

Abstract: A path providing device configured to provide a path information to a vehicle includes a communication unit configured to receive, from a server, map information including a plurality of layers of data, an interface unit configured to receive sensing information from one or more sensors disposed at the vehicle, and a processor. The processor is configured to determine an optimal path for guiding the vehicle from an identified lane, generate autonomous driving visibility information based on the sensing information and the determined optimal path, update the optimal path based on dynamic information related to a movable object located on the optimal path and the autonomous driving visibility information, receive different types of sensor data from a plurality of sensors, and update at least one of the autonomous driving visibility information or the optimal path based on information generated by combining at least two types of sensor data.

Abstract: A vehicle control system includes a memory, a processor connected to the memory, and a functional section. The functional section is configured by a first device and a second device having equivalent functionality to each other, and the functional section is connected in a communicable manner to the processor which serves as a driving assistance control section configured to perform driving assistance including at least braking control of a vehicle, and services as an autonomous driving control section configured to perform autonomous driving of the vehicle. The processor is configured to use the first device at least during execution of driving assistance of the vehicle, and to use the second device at least during execution of autonomous driving of the vehicle.

Abstract: A method and an apparatus for recognition a position and generating a path for autonomous driving of a mobile robot in an orchard environment are provided. The method converts three-dimensional (3D) point cloud data for the orchard environment into a 2D grid map, obtains a position of the mobile robot by performing local scan matching and global scan matching on the 2D grid map, and extracts a tree from the 2D grid map based on occupancy of each grid of the 2D grid map. Then, an effective line based on center points of extracted trees is obtained, a destination based on the obtained effective line is generated, and a driving path according to the generated destination and the position of the mobile robot is generated.

Abstract: To operate an autonomous vehicle, a rail agent is detected in a vicinity of the autonomous vehicle using a detection system. One or more tracks are determined on which the detected rail agent is possibly traveling, and possible paths for the rail agent are predicted based on the determined one or more tracks. One or more motion paths are determined for one or more probable paths from the possible paths, and a likelihood for each of the one or more probable paths is determined based on each motion plan. A path for the autonomous vehicle is then determined based on a most probable path associated with a highest likelihood for the rail agent, and the autonomous vehicle is operated using the determined path.

Abstract: An apparatus may automatically move one or more assets to or from one or more storage units to or from a delivery bot. The apparatus and the one or more storage units and the delivery bot may be stored in a logistics vehicle. The delivery bot may be configured to deliver or pick up the one or more assets to or from one or more delivery or pickup locations that are outside of the logistics vehicle.

Abstract: An autonomous work system includes a first work machine, a plurality of second work machines having different functions, a setting device that stores work schedule information indicating work schedule content, performance of the first work machine, and performance of the plurality of second work machines, and a terminal. The first work machine acquires a state of work performed by its own device and transmits detection result information indicating the acquired state of work to the setting device. The setting device discriminates whether additional work is required based on the detection result information and the work schedule information, and in a case where the additional work is required, selects the second work machine, and transmits additional work information including work content for the second work machine and information relating to the second work machine to at least one of the terminal and the second work machine.

Abstract: A control system (10, 19, 185C) for a vehicle (100), the system comprising a processing means (10, 19) arranged to receive, from terrain data capture means (185C) arranged to capture data in respect of terrain ahead of the vehicle by means of one or more sensors, terrain information indicative of the topography of an area extending ahead of the vehicle (100), wherein the terrain information comprises data defining at least one 2D image of the terrain ahead of the vehicle, wherein the processing means (10, 19) is configured to: perform a segmentation operation on image data defining one said at least one 2D image and identify in the image data edges of a predicted path of the vehicle; calculate a 3D point cloud dataset in respect of the terrain ahead of the vehicle based on the terrain information; determine the 3D coordinates of lateral edges of the predicted path of the vehicle by reference to the point cloud dataset, based on the coordinates of edges of the predicted path identified in the 2D image, to dete

Abstract: A method of determining a trajectory for an autonomous vehicle (AV) is disclosed. When the AV's on-board system detects another actor near the AV, it will generate a virtual doppelganger that is co-located with the autonomous vehicle. The system will predict possible modalities for the other actor and, for each of the modalities, one or more possible trajectories for the other actor. The system then forecast candidate actions of the virtual doppelganger, each of which corresponds to one or more of the possible trajectories of the other actor. The computing system will then determine candidate trajectories of the autonomous vehicle, and it will select one of the candidate trajectories as a selected trajectory for the autonomous vehicle to follow.

Abstract: A system for testing an autonomous vehicle obtains a list of required tests the autonomous vehicle is to run, where each test is part of a commissioning process for the autonomous vehicle. The system causes the list to be displayed on a display device of the autonomous vehicle, receives a selection of a selected test from an operator of the autonomous vehicle, and receives a test input profile associated with the selected test. The system causes the autonomous vehicle to execute at the instructions of the test input profile, and logs response data to one or more log files. During execution of the test instructions, the system generates metadata associated with the selected test. The system logs the metadata to the one or more log files, and transmits at least a portion of the one or more log files to an electronic device located remotely from the autonomous vehicle.

Abstract: A system receives historical vehicle battery data from a gateway device connected to a vehicle. Some vehicles with plug-in rechargeable batteries recommend/require that the vehicle computer be turned off when recharging. Thus, obtaining a current state of charge while a vehicle is charging can be difficult because the vehicle computer can be off. While the vehicle/gateway device is unable to transmit current battery data, the systems estimate a battery charge from the historical data.

Abstract: An autonomous traveling work vehicle includes a traveling vehicle body, a positioning device mounted on the traveling vehicle body and configured to acquire self-vehicle position information indicative of a self-vehicle position, a work device for effecting a work for a field, a determining device for determining a condition of at least either one of the traveling vehicle body and the work device during traveling of the traveling vehicle body, an abnormality detection section for detecting abnormality in the field based on determination data determined by the determining device, and an abnormality information outputting section for outputting, as abnormality information, the self-position information in the case of detection of abnormality by the abnormality detection section.

Abstract: A method and processor for controlling steering of a Self-Driving Car (SDC) are disclosed. The method includes: acquiring SDC state data associated with vertices in a graph-structure, using the SDC state data for building a polynomial curve, using the polynomial curve for simulating a candidate trajectory of the SDC as if the SDC is steered in accordance therewith and such that a closest allowed steering wheel position to a non-allowed steering wheel position is used instead of the non-allowed steering wheel position, determining an offset between the simulated state and a target state of the SDC, selecting candidate steering profile as a target steering profile of the SDC based on the offset, and using the target steering profile of the SDC for controlling steering of the SDC. A method of training a Machine Learning Algorithm for predicting steering wheel positions to control steering of the SDC is also disclosed.

Abstract: Systems and methods described herein relate to estimating risk associated with a vehicular maneuver. One embodiment acquires a geometric representation of an intersection including a lane in which a vehicle is traveling and at least one other lane; discretizes the at least one other lane into a plurality of segments; determines a trajectory along which the vehicle will travel; estimates a probability density function for whether a road agent external to the vehicle is present in the respective segments; estimates a traffic-conflict probability of a traffic conflict in the respective segments conditioned on whether an external road agent is present; estimates a risk associated with the vehicle following the trajectory by integrating a product of the probability density function and the traffic-conflict probability over the at least one other lane and the plurality of segments; and controls operation of the vehicle based, at least in part, on the estimated risk.

Abstract: A dynamic obstacle avoidance method based on real-time local grid map construction includes: acquiring and inputting Red-Green-Blue-RGBD image data of a real indoor scene into a trained obstacle detection and semantic segmentation network to extract obstacles of different types and semantic segmentation results in the real indoor scene and generate 3D point cloud data with semantic information; according to the 3D point cloud data, extracting and inputting state information of a dynamic obstacle to a trained dynamic obstacle trajectory prediction model, and predicting a dynamic obstacle trajectory in the real indoor scene to build a local grid map; and based on a dynamic obstacle avoidance model, sending a speed instruction in real time to the mobile robot to avoid various obstacles during the navigation process.

Abstract: To make it possible to correct a current position detected by an autonomous traveling work machine to the correct position with a simple configuration. A robot lawn mower includes a first position detecting unit for detecting a current position by using odometry and a second position detecting unit for detecting a current position by using an image capture. When position detection accuracy of both of the first and second position detecting units decreases to less than or equal to a predetermined value, the robot lawn mower is controlled to travel to either of zones Z1 and Z2 in which the position detection accuracy of the second position detecting unit is relatively high, and when the robot lawn mower moves to either of the zones Z1 and Z2, a current position used for autonomous traveling is corrected to the current position detected by the second position detecting unit.

Abstract: An autonomous vehicle safety system may activate to prevent collisions by detecting that a planned trajectory may result in a collision. If the safety system is overly sensitive, it may cause false positive activations, and if the system isn't sensitive enough the collision avoidance system may not activate and prevent a collision, which is unacceptable. It may be impossible or prohibitively difficult to detect false positive activations of a safety system and it is unacceptable to risk a false negative, so tuning the safety system is notoriously difficult. Tuning the safety system may include detecting near-miss events using surrogate metrics, and tuning the safety system to increase or decrease a rate of near-miss events as a stand-in for false positives.