Abstract: Dynamic communications paths for sensors in an autonomous vehicle, comprising: detecting a fault associated with a first sensor of a plurality of sensors associated with a same sensing space of the autonomous vehicle; severing, in response to detecting the fault, a first communications path in a switched fabric between a processing unit and the first sensor; and establishing, via the switched fabric, in response to detecting the fault, a second communications path between the processing unit and a second sensor of the plurality of sensors.

Abstract: Error handling in an autonomous vehicle, including: receiving, by a control system of the autonomous vehicle, from an automation computing system, a remediation sequence comprising a first plurality of operational commands determined to bring the autonomous vehicle to a stop; determining, by the control system, that the error state associated with the autonomous vehicle has been reached; and executing, by the control system, in response to the error state being reached, the first plurality of operational commands.

Abstract: Transmitting remotely valued data in an autonomous vehicle, including: acquiring sensor data from a plurality of sensors of the autonomous vehicle, the sensor data comprising a plurality of portions; generating an index for the sensor data; transmitting the index to a server; receiving, based on the index, a value for each portion of the sensor data; and transmitting, based on the value for each portion of the sensor data, the one or more portions of the sensor data.

Abstract: Device initialization by an access-restricted virtual machine, including: restricting access by a first operating system to a device during one or more device initialization operations, wherein the first operating system is executing in a first virtual machine supported by a hypervisor; determining, by a second operating system executing in a second virtual machine supported by the hypervisor, one or more modifications attempted by the first operating system to the device; and performing, by the second operating system, the one or more modifications to the device.

Abstract: Device security across multiple operating system modalities, including: allocating, by a hypervisor, to a first virtual machine comprising a first operating system, based on the first modality, a first one or more access privileges to one or more resources; allocating, by the hypervisor, to a second virtual machine comprising a second operating system, based on the second modality, a second one or more access privileges to the one or more resources; and modifying, by the hypervisor, the second one or more access privileges in response to a change in an execution state of the first virtual machine

Abstract: Value-based data transmission in an autonomous vehicle may include acquiring sensor data from a plurality of sensors of the autonomous vehicle, the sensor data comprising a plurality of portions; determining, for each portion of the sensor data, a value; determining, based on the values for the sensor data, an upload policy; and transmitting, based on the upload policy, one or more portions of the sensor data to a server.

Abstract: Device operation across multiple operating system modalities, including: performing, by a first operating system, one or more device initialization operations for a device; determining that the device is in an initialized state; and performing, by a second operating system, one or more device operations of the device in the initialized state.

Abstract: A redundant sensor fabric in an autonomous vehicle may include receiving, by a processing unit, sensor data from a first sensor of a plurality of sensors associated with a same sensing space of the autonomous vehicle; detecting a fault associated with the first sensor; establishing, via a switched fabric, a communications path between the processing unit and a second sensor of the plurality of sensors; and receiving, by the processing unit, sensor data from the second sensor instead of the first sensor.

Abstract: Device security across multiple operating system modalities may include allocating, by a hypervisor, to a first virtual machine comprising a first operating system of a first modality, based on the first modality, a first one or more access privileges to one or more resources; and allocating, by the hypervisor, to a second virtual machine comprising a second operating system of a second modality, based on the second modality, a second one or more access privileges to the one or more resources.

Abstract: Fault state transitions in an autonomous vehicle may include determining that a first node of a plurality of nodes has failed; determining, in response to the first node failing, a failure state; determining, based on the failure state, a configuration for the plurality of nodes excluding the first node; and applying the configuration.

Abstract: Timed memory access, including: determining, in response to a memory access request, based on a time value, an entry in an access permissions table; and determining, based on the entry, whether to allow the memory access request that can include determining, based on a modulo of the time value and a number of entries in the access permissions table, a table index and determining, based on the table index, the entry.

Abstract: Scene filtering using motion estimation, including identifying, in camera data from an autonomous vehicle, based on motion relative to the autonomous vehicle, one or more pixels; filtering, from the camera data, the one or more pixels; and training, based on the filtered camera data, a neural network.

Abstract: Determining control operations for an autonomous vehicle may include receiving, by an operational model, an operational model input based on camera data from one or more cameras of an automated vehicle; determining, by the operational model, based on the input, a current environmental state and a predicted environmental state; providing, to a rules module, a differential between the current environmental state and a previously predicted environmental state; and determining, based on the rules module, one or more control operations for the automated vehicle.

Abstract: Camera data normalization for an autonomous vehicle are described herein, including: receiving, from one or more cameras of the autonomous vehicle, camera data; applying a color normalization to the camera data; applying a spherical reprojection to the camera data; and applying, based on a registration point, a stabilization to the camera data.

Abstract: Motion-based scene selection for an autonomous vehicle may include identifying, in camera data from an autonomous vehicle, based on a plurality of motion vectors associated with the camera data, one or more image objects; determining, for each image object of the one or more image objects, based on the one or more motion vectors, a corresponding label of one or more labels; and encoding the one or more labels in association with the camera data.

Abstract: Controlling an automated vehicle using visual anchors, including receiving, from one or more cameras of an autonomous vehicle, first video data; identifying one or more visual anchors in the first video data; determining one or more differentials between the one or more visual anchors and one or more predicted visual anchors; and determining, based on the one or more differentials, one or more control operations for the autonomous vehicle to reduce the one or more differentials.

Abstract: Detecting out-of-model scenarios for an autonomous vehicle including: determining, based on first sensor data from one or more sensors, an environmental state relative to the autonomous vehicle, wherein operational commands for the autonomous vehicle are based on a selected machine learning model, wherein the selected machine learning model comprises a first machine learning model; comparing the environmental state to a predicted environmental state relative to the autonomous vehicle; and determining, based on a differential between the environmental state and the predicted environmental state, whether to select a second machine learning model as the selected machine learning model.

Abstract: Rules-based structured data filtering in an autonomous vehicle may include acquiring sensor data from a plurality of sensors of the autonomous vehicle; applying, based on one or more rules, one or more filtering operations to the sensor data; and transmitting the filtered sensor data to a server.

Abstract: Model-based structured data filtering in an autonomous vehicle may include acquiring sensor data from a plurality of sensors of the autonomous vehicle; applying, based on one or more machine-learning models, one or more filtering operations to the sensor data; and transmitting the filtered sensor data to a server.

Abstract: Value-based data transmission in an autonomous vehicle may include acquiring sensor data from a plurality of sensors of the autonomous vehicle, the sensor data comprising a plurality of portions; determining, for each portion of the sensor data, a value; determining, based on the values for the sensor data, an upload policy; and transmitting, based on the upload policy, one or more portions of the sensor data to a server.