314results about "Autonomous decision making process" patented technology

Systems, methods, and apparatus related to sensor data processing for a vehicle to improve operation when sunlight or other bright light enters a sensor of the vehicle. In one approach, adjustable filtering is configured for a sensor of a vehicle. In one example, an optical filter is positioned on the path of light that reaches an image sensor of a camera. For example, the filtering improves ability to stay in adaptive cruise control when driving into direct sunlight at sunset. The optical filters can have controllable properties such as polarization. In one example, a controller of the vehicle is configured to automatically adjust the properties of the optical filter to improve image quality to improve object recognition. In another example, a camera is configured with composite vision that uses sensors in different radiation spectrums (e.g., visible light, and infrared light). The composite vision can provide enhanced vision capability for an autonomous vehicle that is driving in the direction of the sun.

Evaluating a simulation of an autonomous vehicle may be performed by using one or more processors to receive log data collected for a given area, generate environment data for the given area using the log data, run the set of simulations using an autonomous vehicle software, extract one or more metrics from the set of simulations, and evaluate the set of simulations using the one or more metrics. The set of simulations includes one or more of a selection simulation comprising a selection of a location related to the particular maneuver in the given area, a decision process simulation comprising a decision process playthrough for the particular maneuver in the given area, a maneuver simulation comprising a maneuver playthrough of the particular maneuver in the given area, and a replay simulation comprising a replay of the particular maneuver in a run from the log data.

A navigation path can be determined for an object using one or more neural networks. In various embodiments, image data is obtained that is representative of an environment in which the object is to be navigated. Relevant features are identified from the image, and a curve fit to those features. Loss values for the potential paths are scaled based at least in part upon the distance of those features in the real world. This can include, in at least some embodiments, performing the scaling as a function of the curvature of the curve fit to the features. Temporal smoothing can be performed with respect to prior path predictions in order to prevent sudden changes in the predicted path. The paths are analyzed to select a path with a highest confidence value that also at least satisfies a minimum confidence criterion. The path can be converted into three-dimensional navigation information.

An intelligent vehicle charging system for charging a fleet of autonomous vehicles throughout a network of charging stations dispersed throughout a geographic area. The intelligent vehicle charging system includes a remote control system that is in operative communication with each of the autonomous vehicles in the fleet and each of the charging stations in the network. When an autonomous vehicle is in need of a power charge, or as directed by the remote control system, the remote control system will identify an available charging station, guide the autonomous vehicle to the charging station, verify that the autonomous vehicle has arrived at the charging station, initiate the power charging process, account and bill appropriate fees for the charging process, and log all associated activity. The remote control system is also capable of remotely and instantaneously terminating the power charging process to dynamically return a vehicle back to service.

Deep neural networks related to patching deployment for autonomous machine applications. In various examples, rapid resolution of a deep neural network (DNN) failure mode can be achieved by deploying a patch neural network (PNN) trained to operate effectively on the failure mode of the DNN. The PNN can operate on the same or additional data as the DNN and can generate new signals that resolve the failure mode of the DNN in addition to those signals generated using the DNN. A fusion mechanism can be employed to determine which output to rely on for a given instance of the DNN / PNN combination. Thus, failure modes of the DNN can be resolved in a timely manner that requires minimal downtime or shutdown time of the DNN, features controlled using the DNN, and / or semi-autonomous or autonomous functions as a whole.

The invention provides an agricultural work device, an agricultural work management system and a program, which can properly manage agricultural work information and can smoothly execute future agricultural work and business based on the utilization of the agricultural work information. A farming device (1) is provided with: a first imaging device; an agricultural work determination unit (34) that determines whether or not to perform agricultural work on an object on the basis of first image information obtained by capturing an image of the object by means of the first image capturing device; a farming execution unit (36) for executing farming on the basis of the determination result of the farming determination unit (34); a farming information generation unit (38) that generates farming information including farming results; a measuring unit that measures the position of the object; and a farming information management unit (40) that manages farming information and position information indicating the measured position.

Detecting pedestrians with objects is described (pushing stroller, carts, opening doors, carrying umbrellas, etc.). In an example, a perception component of a vehicle can receive sensor data from sensor(s) associated with the vehicle. The perception component can determine, by a model, observation(s) associated with the sensor data, wherein an observation comprises a first object (e.g., a pedestrian). The perception component can determine whether the first object is associated with a second object (e.g., a pedestrian object), wherein the first object and the second object are associated with a compound object (e.g., a pedestrian / pedestrian object system). The perception component can provide the indication of the first object or an indication of the compound object to at least one of a prediction component or a planning component of the vehicle for controlling the vehicle.

Disclosed are a system and method for using an extended learning model for autonomous civil engineering vehicles. The method may include receiving a second set of sensor data, generating a first compressed vector from the second set of sensor data by processing the second set of sensor data with a first machine learning model at least partially, and selecting an action to be performed by the vehicle by processing the first compressed vector with a second machine learning model at least partially. The method may further include taking one or more samples of sensor data from the first set of sensor data, generating a second compressed vector by fine-tuning the first machine learning model by processing one or more samples of sensor data at least partially, and fine-tuning the second machine learning model by processing the second compressed vector at least partially.

In one aspect, a system for automatically assigning vehicle identifiers for autonomous vehicles can include a registry server computing system configured to perform operations. The operations can include receiving, at the registry server computing system and from a vehicle computing system onboard an autonomous vehicle, data describing the autonomous vehicle and generating, at the registry server computing system, a vehicle identifier for the autonomous vehicle based on the data describing the autonomous vehicle. The vehicle identifier can be different than and distinct from the data describing the autonomous vehicle. The operations can include associating, at the registry server computing system, the data describing the autonomous vehicle with the vehicle identifier for the autonomous vehicle in a vehicle registry. The vehicle registry can include respective vehicle identifiers associated with a plurality of autonomous vehicles.

Techniques for determining whether a machine-learned model has improved or regressed in response to an update, as well as verifying whether those improvements or regressions impact overall vehicle safety, are described herein. The techniques may include running a simulation in which a simulated vehicle traverses a simulated environment. During the simulation, sensor data associated with the simulated environment may be input to the machine-learned model, which is configured for use in the real vehicle. As such, perception data outputs associated with objects detected in the simulated environment may be received from the machine-learned model during the simulation, and one or more error models may be generated based on the outputs and a ground truth. If the error model indicates that an error meets or exceeds a threshold error, the machine-learned model may be updated to reduce the error below the threshold.

An onboard device 1 acquires, from map DB 10 including voxel data, reliability information included in the voxel data corresponding to voxels around the route when determining that the accuracy of an estimated position has decreased. Then, on the basis of the acquired reliability information, the onboard device 1 sets a voxel suitable for estimating the own vehicle position as a reference voxel Btag. Then, the onboard device 1 output, to an electronic control device of the vehicle, control information for correcting the target track of the vehicle so as for the vehicle to pass the position suitable for measuring the reference voxel Btag.

To provide a system and a method available for adjusting field of view volumes of one or more sensors of an autonomous vehicle.SOLUTION: In a system and a method, each sensor in one or more sensors is configured to operate in accordance with a field of view volume equal to or less than a maximum field of view volume. The system and the method include determining an operation environment of an autonomous vehicle. The system and the method also include based on the determined operation environment of the autonomous vehicle, adjusting a field of view volume of at least one sensor in the one or more sensors from a first field of view volume to an adjusted field of view volume which is different from the first field of view volume. In addition, the system and the method include controlling the autonomous vehicle so as to operate using at least one sensor having the adjusted field of view volume.SELECTED DRAWING: Figure 9

Determining classification(s) for object(s) in an environment of autonomous vehicle, and controlling the vehicle based on the determined classification(s). For example, autonomous steering, acceleration, and / or deceleration of the vehicle can be controlled based on determined pose(s) and / or classification(s) for objects in the environment. The control can be based on the pose(s) and / or classification(s) directly, and / or based on movement parameter(s), for the object(s), determined based on the pose(s) and / or classification(s). In many implementations, pose(s) and / or classification(s) of environmental object(s) are determined based on data from a phase coherent Light Detection and Ranging (LIDAR) component of the vehicle, such as a phase coherent LIDAR monopulse component and / or a frequency-modulated continuous wave (FMCW) LIDAR component.

Techniques are provided which may be implemented using various methods and / or apparatuses in a vehicle to utilize vehicle external sensor data, vehicle internal sensor data, vehicle capabilities and external CV2X input to determine, send, receive and utilize data elements to determine inter-vehicle spacing, intersection priority, lane change behavior and spacing and other autonomous vehicle behavior.

A task execution system and method of a vehicle operation system according to a preferred embodiment of the present application, wherein the task execution system of the vehicle operation system includes a task information extraction section that extracts task information related to an event signal received from an application from a preset event chain table, a task execution cycle setting section that sets a task execution cycle using the extracted task information, a task execution section that executes one task of a plurality of tasks according to the task execution cycle, and a waiting time providing section that provides a task waiting time to the task execution section to wait for a next task execution if the one task execution is completed.

To provide a system and a method for parallel processing of a vehicle path planning suitable for parking.SOLUTION: To determine a path through a pose configuration space, trajectories of poses may be evaluated in parallel based at least on translating the trajectories along at least one axis of the pose configuration space (e.g., an orientation axis). A trajectory may include at least a portion of a turn having a fixed turn radius. Turns or turn portions that have the same turn radius and initial orientation can be translatively shifted along and processed in parallel along the orientation axis as they are translated copies of each other, but with different starting points. Trajectories may be evaluated based at least on processing variables used to evaluate reachability as bit vectors with threads, effectively performing large vector operations in synchronization. A parallel reduction pattern may be used to account for dependencies that may exist between sections of a trajectory for evaluating reachability, allowing for the sections to be processed in parallel.SELECTED DRAWING: Figure 1A

In an embodiment, a wireless LAN is installed in a factory. Mechanical equipment 4 of the factory includes a short-range wireless communication unit 41. An unmanned aerial vehicle 2 stores segmented regions of a three-dimensional map or a two-dimensional map of the factory, and wireless stations to which the unmanned aerial vehicle 2 is to connect in the respective regions. The unmanned aerial vehicle 2 switches the wireless stations to connect to, in accordance with a region in which an own location is present on the three-dimensional map or the two-dimensional map.

Systems and methods are disclosed for controlling operations of autonomous vehicles and systems in, for example, logistics yards at distribution, manufacturing, processing and / or other centers for the transfer of goods, materials, and / or other cargo. In some embodiments, an autonomous yard tractor or other vehicle can include one or more systems for locating an over-the-road trailer parked in a yard of a distribution center, engaging the trailer, and moving the trailer to a loading dock for loading / unloading operations in accordance with a workflow procedure provided by a central control system. In other embodiments, an autonomous yard tractor can locate the trailer at the loading dock after the loading / unloading operations, engage the trailer, and move the trailer to a parking location in the yard. In some embodiments, the autonomous yard tractor can include a sensor system configured to detect the position of the trailer relative to, for example, the tractor, and / or the dock station can include a sensor system configured to detect the position of the trailer relative to, for example, the dock station during a docking procedure.

Cleaning robots, comprehensive: a communication interface; at least one sensor; at least one camera (120); a drive unit; and a processor (140) that is configured: to input an image taken by at least one camera into a trained artificial intelligence model in order to obtain information about an object contained in the captured image: to obtain information that is captured by at least one sensor; To obtain recognition information about each of several work surfaces in a home based on information about the object, wherein the recognition information about each of the several work surfaces includes type information about each of the several work surfaces; to generate a map that displays the multiple work areas, using the information obtained about the object, the captured information, and the recognition information for each of the multiple work areas; based on a user voice instructing a cleaning operation to control the drive unit to move to at least one of the multiple work surfaces; and based on moving to the at least one work surface, a cleaning operation for the at least one work surface is to be carried out, where the recognition information for each of the multiple work surfaces includes a name for each of the multiple work surfaces.

Training an encoder is provided. The method comprises inputting a current state of a number of aircraft into a recurrent layer of a neural network, wherein the current state comprises a reduced state in which a value of a specified parameter is missing. An action applied to the aircraft is input into the recurrent layer concurrently with the current state. The recurrent layer learns a value for the parameter missing from current state, and the output of the recurrent layer is input into a number of fully connected hidden layers. The hidden layers, according to the current state, learned value, and current action, determine a residual output that comprises an incremental difference in the state of the aircraft resulting from the current action.

To provide a control system and method for controlling the operation of a legged robot.SOLUTION: A control system for controlling a legged robot comprises a processor and a memory. The present control system initializes a probabilistic filter using a parameter associated with a state of a reference pathway of a legged robot in response to a reception of a task, the parameter being previously determined for the task, allows the legged robot to move according to the task, and encodes a reference pathway including a combination of different reference pathways, relative to a coordinated motion primitive of different actuators of the legged robot. The present control system furthermore generates a reference pathway by decoding the parameter and executes the probabilistic filter to repeatedly track a state of a reference pathway satisfying a performance target as to the state of the legged robot in response to a reception of a feedback signal, and updates the parameter.SELECTED DRAWING: Figure 1

A route setting device is provided with a status confirmation part and a change route setting part. The status confirmation part receives, with respect to a work vehicle that is moving along a preset work route in a field, an instruction by which the work vehicle moves to a stop position not included in the work route, and acquires the position of the work vehicle. The change route setting part creates a change route along which the work vehicle moves to the stop position on the basis of the instruction. The starting point of the change route represents the position of the work vehicle at a time when a waiting time for change equaling or exceeding a delay time set on the basis of the processing time for creating the change route has elapsed after receiving the instruction.

To provide an operation support method capable of improving convenience of an operation terminal that displays information related to traveling of a work vehicle, an operation support system, and an operation support program.SOLUTION: A display processing unit 711 causes a work screen D1 to be displayed in an operation device 17 used for automatic traveling of a work vehicle 10. The display processing unit 711 causes a display region A0 included in the work screen D1 to display travel information G0 related to a position of the work vehicle 10. A setting processing unit 713 switches between setting of causing display regions A1 to A4 included in the work screen D1 to display travel information G0 to G4 related to a travel state of the work vehicle 10 and setting of causing the display regions A1 to A4 not to display the travel information G0 to G4.SELECTED DRAWING: Figure 9

Methods and systems are provided for autonomous vehicle operation for collision avoidance. One method involves identifying an autonomous operating mode and one or more settings associated with the autonomous operating mode prior to entering an autonomous collision avoidance mode in response to an output from a collision avoidance system, and after entering the autonomous collision avoidance mode, automatically restoring autonomous operation upon deactivation of the autonomous collision avoidance mode. For example, the autonomous operating mode may be automatically reinitiated based on the current vehicle status using the one or more settings in response to deactivation of the autonomous collision avoidance mode when it is determined that the autonomous operating mode is viable based on a relationship between a current vehicle status and the one or more settings associated with the autonomous operating mode.

A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and / or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and / or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and / or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

A simulation may be used to determine a difference between progress of a manually-driven vehicle and progress of a simulated autonomous vehicle. The method includes retrieving log data collected for the manually-driven vehicle driving along a route, generating a plurality of path segments for a portion of the route. The plurality of path segments corresponds to points in a lane that the manually-driven vehicle traveled through on the portion of the route. The method also includes running, using a software of the autonomous vehicle, a simulation of the autonomous vehicle driving along the plurality of path segments, extracting metrics from the log data and the simulation, and determining the difference between a first progress of the manually-driven vehicle and a second progress of the simulated autonomous vehicle based on the metrics.

Systems and methods are disclosed for navigating a host vehicle. In one implementation, at least one processor may be programmed to receive an image captured by a camera; identify an oncoming target vehicle; determine that a planned trajectory for the host vehicle includes a turn that crosses a projected trajectory of the oncoming target vehicle in a potential turn-across-path event; determine a driving jurisdiction associated with the road; determine, based on the driving jurisdiction, whether the target vehicle is approaching a road feature that negates the potential turn-across-path event; and either implement or forego implementing a remedial action based on whether the target vehicle is approaching a road feature that negates the potential turn-across-path event.