Abstract: Systems and methods for route building and trip planning with respect to coordinating autonomous and remote driving. Route planning data including a start location is obtained. Potential routes are identified and then optimized based on availability of autonomous driving and remote driving at different locations among the potential routes. The optimization may further account for user status with respect to remote driving service availability for the user, user preferences, or both. The optimized routes may be presented to the user for selection. A trip may be commenced based on one of the optimized routes, where the vehicle switches modes of operation including autonomous operation and remote driving operation according to the optimized route of the trip.

Abstract: A system and method for network feedback simulation injection. A method includes simulating network feedback for one or more communication channels used by a system and injecting the simulated network feedback into one or more decision-making processes. The simulated network feedback includes one or more simulated network parameters indicating values of corresponding network performance metrics. The decision-making processes are configured to make system decisions based on network feedback data.

Abstract: A system and method for initiating safety maneuvers. A method includes creating an interactions chain data structure for an interactions chain, wherein the interactions chain includes a plurality of chain links arranged in an order, the plurality of chain links representing a plurality of components used for communications between a vehicle and at least one operation system, wherein the interactions chain data structure includes a plurality of nodes representing the plurality of chain links and a plurality of edges connecting between nodes of the plurality of nodes; determining a plurality of statuses of the plurality of chain links; and initiating a safety maneuver for the vehicle based on the determined plurality of statuses.

Abstract: A system and method for contextual distribution of remote connected vehicle operation requests. A method includes: classifying a plurality of requests for remote connected vehicle operation into a plurality of classifications, wherein each request corresponds to a respective connected vehicle of a plurality of connected vehicles; determining a distribution for the plurality of requests based on the plurality of classifications, wherein at least a portion of the plurality of requests is assigned to respective operators of a plurality of operators based on capabilities associated with each of the plurality of operators; and transmitting the plurality of requests based on the distribution.

Abstract: Techniques for performing and improving forward error correction (FEC). In an embodiment, a set of base data is grouped into a plurality of base data groups, for example when a trigger event which triggers beginning or altering transmission of FEC data occurs. FEC data including a plurality of FEC data groups is generated based on the plurality of base data groups, where each FEC data group corresponds to a respective base data group of the plurality of base data groups and each FEC data group is redundant with at least a portion of the corresponding base data group. The plurality of FEC data groups are transmitted. Various techniques described herein leverage different connections, links, devices, or combinations thereof, for transmitting FEC data and base data.

Abstract: A system and method for multi-channel network congestion control. A method includes determining a packet routing scheme for a plurality of packets of a data stream, wherein the packet routing scheme includes a routing of each packet to a respective communication channel of a plurality of communication channels, wherein each of the plurality of communication channels is connected to a scheduling component and to a synchronizing component; and sending the plurality of packets via their respective communication channels, wherein each of the sent packets includes timing data, wherein the synchronizing component is configured to synchronize the plurality of packets based on the timing data of each packet and to reconstruct the data stream using the synchronized packets.

Abstract: A system includes at least one imaging sensor and a processor. The processor is configured to acquire detected data describing an environment of a vehicle using the at least one imaging sensor; derive reference data which describes the environment from a predefined map; compute difference data representing a difference between the detected data and the reference data; and transfer the difference data, wherein an image computed based on the difference data and the reference data represents the detected data.

Abstract: A system and method for maintaining safe remote vehicle operation. A method includes analyzing network conditions for a vehicle, wherein at least a portion of vehicle operations for the vehicle are performed based on remote instructions, wherein the remote instructions are sent by a device which is remote from the vehicle; determining at least one safety measure decision for the vehicle based on the analyzed network conditions, wherein the at least one safety measure decision includes a set of safety measure instructions to be sent to a safety system of the vehicle; and implementing the at least one safety measure decision with respect to the vehicle by sending the set of safety measure instructions to the safety system of the vehicle, wherein the safety system controls the vehicle operations based on the set of safety measure instructions.

Abstract: Techniques for improving network connectivity. A method includes creating at least one network connectivity map based on a first set of network connectivity data for historical devices operating within a network; obtaining data for a plurality of devices currently operating within the network, wherein the obtained data includes a second set of network connectivity data for the plurality of devices and a plurality of task statuses for tasks assigned to the plurality of devices; and manipulating a first device of the plurality of devices in order to improve network connectivity of a second device of the plurality of devices, wherein the first device is manipulated based on the second set of network connectivity data, the plurality of task statuses, and the at least one network connectivity map.

Abstract: A system includes at least one imaging sensor and a processor. The processor is configured to acquire detected data describing an environment of a vehicle using the at least one imaging sensor; derive reference data which describes the environment from a predefined map; compute difference data representing a difference between the detected data and the reference data; and transfer the difference data, wherein an image computed based on the difference data and the reference data represents the detected data.

Abstract: A system and method for multi-channel network congestion control. A method includes determining a packet routing scheme for a plurality of packets of a data stream, wherein the packet routing scheme includes a routing of each packet to a respective communication channel of a plurality of communication channels, wherein each of the plurality of communication channels is connected to a scheduling component and to a synchronizing component; and sending the plurality of packets via their respective communication channels, wherein each of the sent packets includes timing data, wherein the synchronizing component is configured to synchronize the plurality of packets based on the timing data of each packet and to reconstruct the data stream using the synchronized packets.

Abstract: A system includes at least one imaging sensor and a processor. The processor is configured to acquire detected data describing an environment of an autonomous vehicle using the imaging sensor; derive reference data which describes the environment from a predefined map; compute difference data representing a difference between the detected data and the reference data; and transfer the difference data, wherein an image computed based on the difference data and the reference data represents the detected data. Other embodiments are also described.

Abstract: A system and method for multi-channel network congestion control. A method includes establishing multi-channel control over a plurality of communication channels by connecting each of the plurality of communication channels to a scheduling component and to a synchronizing component; determining a packet routing scheme for a plurality of packets of a data stream based on feedback from each of the plurality of communication channels, wherein the packet routing scheme includes a routing of each packet to a respective communication channel of the plurality of communication channels; and sending the plurality of packets via their respective communication channels, wherein each of the sent packets includes timing data, wherein the synchronizing component is configured to synchronize the plurality of packets based on the timing data of each packet and to reconstruct the data stream using the synchronized packets.

Abstract: Techniques for improving network connectivity. A method includes creating at least one network connectivity map based on a first set of network connectivity data for historical devices operating within a network; obtaining data for a plurality of devices currently operating within the network, wherein the obtained data includes a second set of network connectivity data for the plurality of devices and a plurality of task statuses for tasks assigned to the plurality of devices; and manipulating a first device of the plurality of devices in order to improve network connectivity of a second device of the plurality of devices, wherein the first device is manipulated based on the second set of network connectivity data, the plurality of task statuses, and the at least one network connectivity map.

Abstract: A system and method for multi-channel network congestion control. A method includes establishing multi-channel control over a plurality of communication channels by connecting each of the plurality of communication channels to a scheduling component and to a synchronizing component; determining a packet routing scheme for a plurality of packets of a data stream based on feedback from each of the plurality of communication channels, wherein the packet routing scheme includes a routing of each packet to a respective communication channel of the plurality of communication channels; and sending the plurality of packets via their respective communication channels, wherein each of the sent packets includes timing data, wherein the synchronizing component is configured to synchronize the plurality of packets based on the timing data of each packet and to reconstruct the data stream using the synchronized packets.

Abstract: A method includes generating a plurality of training vectors relating to different respective historical service requests generated by respective autonomous vehicles, each of the training vectors including respective features associated with the historical request to which the training vector relates. The method further includes, using the training vectors, training a model configured to generate a prediction relating to one or more future service requests, generating the prediction using the model, and outputting the generated prediction. Other embodiments are also described.

Abstract: A vehicle computing unit and method for collision avoidance. The method includes calculating a dynamic trajectory of a vehicle, wherein the dynamic trajectory of the vehicle indicates a projected movement path of the vehicle; determining whether at least one risk location is within the dynamic trajectory of the vehicle; operating the vehicle based on a driving decision selected from among a first driving decision and a second driving decision when at least one risk location is within the dynamic trajectory of the vehicle, wherein the first driving decision is determined based on inputs by an operator of the vehicle, wherein the second driving decision is determined by a vehicle computing unit of the vehicle; and operating the vehicle based on the inputs by the operator of the vehicle when no risk location is within the dynamic trajectory of the vehicle.

Abstract: A system includes at least one imaging sensor and a processor. The processor is configured to acquire detected data describing an environment of an autonomous vehicle using the imaging sensor; derive reference data which describes the environment from a predefined map; compute difference data representing a difference between the detected data and the reference data; and transfer the difference data, wherein an image computed based on the difference data and the reference data represents the detected data. Other embodiments are also described.

Abstract: Techniques for improving data transmission in teleoperation systems including a method for dynamic packet routing. The method includes identifying an optimal channel of a plurality of channels based on a network connectivity status of a system and historical connectivity data related to a current location of the system, wherein the system includes a plurality of network authorization devices, wherein each network authorization device is configured to enable communications via an associated channel; and routing packets to the optimal channel using a network authorization device of the plurality of network authorization devices that is associated with the optimal channel.

Abstract: A system includes at least one imaging sensor and a processor. The processor is configured to acquire, using the imaging sensor, detected data describing an environment of an autonomous vehicle. The processor is further configured to derive reference data, which describe the environment, from a predefined map, to compute difference data representing a difference between the detected data and the reference data, and to transfer the difference data. Other embodiments are also described.