1626results about "Autonomous decision making process" patented technology

A sensor data evaluation device may include an artificial neural network, configured to receive and process first testing data, and output a first testing data output, wherein the first testing data represent sensor data of a first sensor detecting a sensor input; and one or more processors, configured to receive sensor deficiency information representing a deficiency of a second sensor; generate second testing data, wherein the second testing data are based on the sensor deficiency information; implement the artificial neural network to receive and process the second testing data; and output from the output layer a second testing data output; determine a difference between the first testing data output and the second testing data output; and if the difference is outside of one or more predetermined ranges or does not satisfy one or more predetermined criteria, send a signal representing a result of the determined difference.

A geo-converged telemetry (GCT) system is described that provides an exchange of geographically-relevant telemetry data amongst various vehicles, devices, and systems for providing a holistic view of a geographic area. Telemetry data from various sources may be continually collected and transmitted to a nearby node of a GCT system, where the data may be converged based on geolocation and processed. The same and / or other vehicles, devices, and systems may operate as telemetry consumers that receive feeds of geo-converged telemetry data that may be tailored to functionalities of the consumer. As a vehicle moves, data that are determined to be geographically-relevant changes. The location of the processing may move from one processing node to another processing node in the edge network such that the processing is located proximate to the vehicle to minimize latency and provide real time or near-real time feedback based on a holistic view of the geographic area.

In various examples, teleoperation architectures for safe control of machines are described. Systems and methods are disclosed that use an end-to-end safety architecture that covers both a vehicle or machine and a remote system providing a control center, where the vehicle or machine is at least partly or temporarily configured for control by the remote system. In some examples, the end-to-end architecture uses a layered safety policy monitoring system, where the remote system uses first policies to ensure that operator commands are viable and the vehicle uses second policies to ensure that the operator commands are safe to perform (e.g., will not cause collisions with other objects). Additionally, in some examples, the end-to-end architecture allows for the vehicle to perform minimum risk maneuvers, also referred to as “control fallbacks,” if problems were to occur.

The technology relates to detection of a nearby occluded object based on illumination emitted from that object. Illumination by the occluded object of one or more areas in the surrounding area, for instance by headlights of an occluded vehicle, is detected by a perception system of a self-driving vehicle. The self-driving vehicle can classify the detected object to determine whether the illumination is caused by a vehicle or other road user, or from objects in the surrounding environment. Illumination data and other information can be evaluated by the self-driving vehicle, for instance to identify a type of the object, a location of the object along a roadway, to disambiguate the direction of travel of the other object, etc. As a result, the self-driving vehicle may infer the behavior of the other object and modify its own driving operations to account for the other object's presence and likely behavior.

A request signal that indicates a quality for a determination of an orientation of a road user is received. The orientation of the road user is determined based on a) image data when the request signal indicates the quality is below a predetermined quality for the determination of the orientation of the road user, or b) on LIDAR data and image data when the request signal indicates the quality is the predetermined quality.

An autonomous vehicle comprises a sensor unit 102 configured to generate an environmental signal corresponding to a surrounding environment. A vector generator unit 108 generates a numeric vector from

There is provided an information processing device that includes an operation controller that controls a moving operation of an autonomous mobile body that travels while maintaining an inverted state, and controls a posture operation of the autonomous mobile body that temporally changes from a reference posture in the inverted state. Furthermore, the information processing device further includes an acquisition unit that acquires motion data corresponding to a posture operation of the autonomous mobile body. The operation controller controls a posture operation of the autonomous mobile body based on the motion data acquired by the acquisition unit.

An autonomous vehicle control system includes one or more sensors configured for coupling with an agricultural vehicle, the one or more sensors configured to determine kinematics of the agricultural vehicle relative to a crop row. The system includes a guidance control module configured to coordinate steering of one or more steering mechanisms of the agricultural vehicle. The guidance control module includes a sensor input configured to receive kinematics of the agricultural vehicle, a vehicle kinematics comparator configured to determine one or more error values using the received vehicle kinematics, a crop curvature generator configured to determine crop row curvature using the one or more error values, and a steering interface configured to provide instructions to a vehicle steering controller to guide the agricultural vehicle using the crop row curvature.

Device, system, and method of autonomous driving and tele-operated vehicles. A vehicular Artificial Intelligence (AI) unit, is configured: to receive inputs from a plurality of vehicular sensors of a vehicle; to locally process within the vehicle at least a first portion of the inputs; to wirelessly transmit via a vehicular wireless transmitter at least a second portion of the inputs to a remote tele-driving processor located externally to the vehicle; to wirelessly receive via a vehicular wireless receiver from the remote tele-driving processor, a remotely-computed processing result that is received from a remote Artificial Intelligence (AI) unit; and to implement a vehicular operating command based on the remotely-computed processing result, via an autonomous driving unit of the vehicle or via a tele-driving unit of the vehicle.

In one embodiment, a method includes receiving sensor data associated with an object external to a vehicle. The sensor data includes a sequence of data packets. Each data packet corresponds to a time frame in a sequence of time frames. The method includes determining a classification of the object based at least on the sensor data, determining that a particular data packet corresponding to a particular time frame in the sequence of time frames is corrupt or missing, generating a replacement data packet based on one or more data packets that correspond to one or more time frames adjacent to the particular time frame, generating a sequence of visual representations of the object corresponding to the sequence of time frames. At least one visual representation in the sequence of visual representations corresponding to the particular time frame is generated based on the replacement data packet.

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.

Apparatuses, systems, and techniques to process luminance and / or radiance values of one or more images from one or more cameras using one or more neural networks to perform a machine vision task. In at least one embodiment, one or more neural networks determine detection difficulty levels of objects within the one or more images and performs a machine vision task based on the determined detection difficulty levels of objects within images associated with that ask.

Various examples are directed to systems and methods for routing a plurality of autonomous vehicles. A batch routing system may receive a first general route cost request from a first autonomous vehicle. The batch routing system may determine a first set of general routes for the first autonomous vehicle. The batch routing system may send a first general route cost reply to the first autonomous vehicle. The first general route cost reply may indicate a first set of costs associated with the first set of general routes. The first set of costs may comprise a first general cost for the first general route and a second general cost for the second general route.

Systems and techniques are described for implementing autonomous control of earth-moving construction and / or mining vehicles, including to automatically determine and control autonomous movement of part or all of one or more such vehicles (e.g., a vehicle's arm(s) and / or attachment(s), such as a digging bucket, claw, hammer, blade, etc.) to move materials or perform other actions in a manner that is based at least in part on data from simulated operation of the vehicle(s). For example, the systems / techniques may include using data from simulated operation of the earth-moving vehicle(s) in various manners, such as for use in training one or more machine learning models that are used in implementing the autonomous operations, determining optimal or otherwise preferred hardware component configurations to use, determining optimal or otherwise preferred implementation plans to use for one or more tasks and / or multi-task jobs, enabling user what-if experimentation activities, etc.

A method includes identifying suspension stiffness data and suspension deflection data associated with corresponding distal ends of one or more axles of an autonomous vehicle (AV). The method further includes determining, based on the suspension deflection data and the suspension stiffness data, driving constraint data for traveling at least a portion of a route. The method further includes causing, based on the driving constraint data, performance of a corrective action associated with the AV during the traveling of the at least a portion of a route.

A monitoring system can receive sensor data from one or more sensors of a vehicle to monitor an exterior of the vehicle. Based on monitoring the exterior of the vehicle, the system can detect movement of one or more pedestrians in the exterior of the vehicle. Based at least in part on detecting the movement of the one or more pedestrians in the exterior of the vehicle, the system can output an alert to a driver of the vehicle via one or more output devices of the vehicle.

Described herein is a system for tracking objects and performing dynamic entity resolution using image data. For example, the system may build an environment map and populate the map with objects present in the environment. As the devices move about the environment it may capture image data and, based on its position and / or configuration of its components, may determine updated locations of objects that move in the environment. Upon receiving a query from a user, based on the location of the objects relative to the device / user, the system can interpret gestures and voice commands to infer which object is specified by the voice command. To build the environment map, the system performs object detection to generate bounding boxes associated with an object, then clusters the bounding boxes into a three-dimensional (3D) object associated with 3D coordinates. As the system tracks the object using the 3D coordinates while maintaining two-dimensional (2D) information (e.g., bounding boxes and other features), the system can use existing 2D models to process objects in 3D.

Techniques for determining environmental data of an environment associated with a vehicle are discussed herein. The vehicle can use the data to determine a vehicle configuration data, a trajectory for the vehicle to traverse, a route to a destination, or orientation for ingress / egress. The vehicle can determine control data based on the vehicle configuration data, the trajectory, or the route. The vehicle configuration data may be associated with a setting of a suspension component, a speed, or other component. The trajectory may be biased based on a source of the wind. The route may be selected from a first candidate route and a second candidate route using a first wind score associated with the first candidate route and a second score associated with the second candidate route. The vehicle can use a sensor, such as a wind sensor, to capture or otherwise determine the wind data.

Methods, apparatus, systems, and articles of manufacture are disclosed to display acquisition paths. An example apparatus includes a display handler to, in response to a directional condition of an autonomous vehicle satisfying a threshold, render an acquisition path for the autonomous vehicle, the acquisition path specifying a route along which the autonomous vehicle is to travel to acquire a guidance path; and a vehicle condition controller to, in response to determining that a real time display criterion is satisfied, redetermine whether the directional condition of the autonomous vehicle satisfies the threshold to cause the display handler to re-render the acquisition path.

Disclosed are systems and methods that can be used for adjusting the field of view of one or more sensors of an autonomous vehicle. In the systems and methods, each sensor of the one or more sensors is configured to operate in accordance with a field of view volume up to a maximum field of view volume. The systems and methods include determining an operating environment of an autonomous vehicle. The systems and methods also include based on the determined operating environment of the autonomous vehicle, adjusting a field of view volume of at least one sensor of the one or more sensors from a first field of view volume to an adjusted field of view volume different from the first field of view volume. Additionally, the systems and methods include controlling the autonomous vehicle to operate using the at least one sensor having the adjusted field of view volume.

A processing system is for a motorized mobile system that provides powered mobility to one or more users. The motorized mobile system may consist, for example, of one or more of a mobile chair, a mobility scooter, an electronic conveyance vehicle, a riding lawn mower, a grocery cart, an all-terrain vehicle, an off-road vehicle, and a golf cart. The processing system comprises at least one sensor to measure one or more kinematic states of an object proximate to the motorized mobile system and at least one processor to use at least one object kinematic model as at least one state estimator. The at least one processor predicts a first kinematic state estimate of the object at a first time based on a prior knowledge of state for the object. The at least one processor uses the first kinematic state estimate of the object at the first time and a measured kinematic state observed by the sensor at a second time to determine a second kinematic state estimate of the object at the second time, wherein the first time is less than the second time. The at least one processor outputs the first kinematic state estimate at the first time from the object kinematic model for use by at least one other process of the motorized mobile system, wherein the at least one other process causes one or more actions to be taken by the motorized mobile system based on the first kinematic state estimate of the object at the first time. The at least one processor uses the second kinematic state estimate at the second time as an input to the object kinematic model to predict another kinematic state estimate of the object.

A system for notifying emergency services of a vehicular crash may (i) receive sensor data of a vehicular crash from at least one mobile device associated with a user; (ii) generate a scenario model of the vehicular crash based upon the received sensor data; (iii) store the scenario model; and / or (iv) transmit a message to one or more emergency services based upon the scenario model. As a result, the speed and accuracy of deploying emergency services to the vehicular crash location is increased. The system may also utilize vehicle occupant positional data, and internal and external sensor data to detect potential imminent vehicle collisions, take corrective actions, automatically engage autonomous or semi-autonomous vehicle features, and / or generate virtual reconstructions of the vehicle collision.

A mobile agricultural machine obtains an agricultural characteristic map indicative of agricultural characteristics of a field, wherein the agricultural characteristic map is based on data collected at or prior to a first time. The mobile agricultural machine obtains supplemental data indicative of characteristics relative to the worksite, the supplemental data collected after the first time. An agricultural characteristic confidence output, indicative of a confidence level in the agricultural characteristics indicated by the agricultural characteristic map, is generated based on the agricultural characteristic map and the supplemental data. In some examples, an action signal is generated to control an action of the mobile agricultural machine based on the agricultural characteristic confidence output.

An autonomous vehicle navigation system includes a controller configured or programmed to receive information of a work vehicle, receive data input from a user, and cause the work vehicle to traverse a first plot, exit the first plot; traverse a margin area located between the first plot and an adjacent area or a second plot, and perform a turning maneuver process before entering a second row in the first plot. When the work vehicle performs the turning maneuver, the controller allows at least a portion of the work vehicle to reverse into the adjacent area or a third row included in the second plot based on the controller judging whether or not at least one or more conditions is satisfied, the one or more conditions being based on data detected from at least one sensor and / or the input data from the user.

An Unmanned Aerial Vehicle (UAV) control method and apparatus, a base station and a UAV relate to the technical field of wireless communication. The method can include receiving an access message from a UAV, the access message carrying a type identifier of the UAV, acquiring target supervision strategy information based on the access message, the target supervision strategy information indicating a flight criterion of the UAV, and sending a control instruction to the UAV based on the target supervision strategy information, the UAV being configured to control flight based on the control instruction. A base station, when receiving the access message of the UAV, acquires the target supervision strategy information of the UAV based on the access message and controls flight of the UAV based on the target supervision strategy information, so that it is ensured that flight of the UAV meets a supervision requirement.

A method includes generating a data structure including states and actions to be executed at those states as determined by an AI policy of behavior, determining, with a first computing system that is offline, state factors associated with the states and responsibility scores for the state factors, each responsibility score indicating a causal impact for each of the actions associated with one of the states, generating, with the first computing system, a causal ML model based on the state factors and the responsibility scores, determining, with a second computing system that is online based on the causal ML model, state factors associated with a current state, and identifying one or more of the state factors as a causal reason for an action resulting from the current state. Other example methods and systems for providing explanation of an AI policy of behavior with causal reasoning are also disclosed.