Abstract: Systems and methods for autonomous vehicle control are disclosed herein. According to some implementations, a method includes a scenario-specific operation control evaluation module (SSOCEM) based on a route of the vehicle. The SSOCEM includes a preferred model and one or more fallback models that respectively determine candidate vehicle control actions. The method includes instantiating a SSOCEM instance based on the SSOCEM. The SSOCEM determines a candidate vehicle control action by determining an approximate amount of time needed to determine a solution to the preferred model and determining an approximate amount of time until the upcoming scenario is reached. When the approximate amount of time needed to determine the solution is less than the approximate amount of time to reach the upcoming scenario, the candidate vehicle control action is determined based on the preferred model; otherwise, the candidate vehicle control action is determined based on a fallback model.

Abstract: Methods and vehicles may be configured to gain experience in the form of state-action and/or action-observation histories for an operational scenario as the vehicle traverses a vehicle transportation network. The histories may be incorporated into a model in the form of learning to improve the model over time. The learning may be used to improve integration with human behavior. Driver feedback may be used in the learning examples to improve future performance and to integrate with human behavior. The learning may be used to create customized scenario solutions. The learning may be used to transfer a learned solution and apply the learned solution to a similar scenario.

Abstract: A method for resolving an exception situation in autonomous driving includes receiving telemetry data from an autonomous vehicle (AV); identifying, using the telemetry data, features and feature values; identifying, using the features and the feature values, a solution to the exception situation; determining a confidence level of the solution; in response to the confidence level exceeding a threshold, transmitting the solution to the AV; and in response to the confidence level not exceeding the threshold, forwarding the solution to a mobility manager, obtaining, from the mobility manager, a validated solution, and transmitting the validated solution to the AV.

Abstract: Traversing, by an autonomous vehicle, a vehicle transportation network, may include operating a scenario-specific operational control evaluation module instance, wherein the scenario-specific operational control evaluation module instance includes an instance of a scenario-specific operational control evaluation model of a vehicle operational scenario wherein the vehicle operational scenario is a merge vehicle operational scenario or a pass-obstruction vehicle operational scenario, receiving a candidate vehicle control action from the scenario-specific operational control evaluation module instance, and traversing a portion of the vehicle transportation network in accordance with the candidate vehicle control action.

Abstract: Exception handing, such as of obstruction situations, by an autonomous vehicle (AV) is disclosed. A method includes identifying an exception situation; identifying a risk associated with autonomously resolving the exception situation; and in response to the risk exceeding a risk threshold, initiating a request for assistance from a tele-operator, and halting for the tele-operator to respond to the request; and receiving a response from the tele-operator.

Abstract: Systems and methods for autonomous vehicle control are disclosed herein. According to some implementations, a method includes a scenario-specific operation control evaluation module (SSOCEM) based on a route of the vehicle. The SSOCEM includes a preferred model and one or more fallback models that respectively determine candidate vehicle control actions. The method includes instantiating a SSOCEM instance based on the SSOCEM. The SSOCEM determines a candidate vehicle control action by determining an approximate amount of time needed to determine a solution to the preferred model and determining an approximate amount of time until the upcoming scenario is reached. When the approximate amount of time needed to determine the solution is less than the approximate amount of time to reach the upcoming scenario, the candidate vehicle control action is determined based on the preferred model; otherwise, the candidate vehicle control action is determined based on a fallback model.

Abstract: Autonomous vehicle operational management may include traversing, by an autonomous vehicle, a vehicle transportation network. Traversing the vehicle transportation network may include generating an autonomous vehicle operational control environment for operating scenario-specific operational control evaluation module instances. A scenario-specific operational control evaluation module instance may be an instance of a respective scenario-specific operational control evaluation module. A scenario-specific operational control evaluation module may model a respective distinct vehicle operational scenario. A scenario-specific operational control evaluation module instance may generate a respective candidate vehicle control action responsive to the respective corresponding distinct vehicle operational scenario.

Abstract: Introspective autonomous vehicle operational management includes operating an introspective autonomous vehicle operational management controller including a policy for a model of an introspective autonomous vehicle operational management domain. Operating the controller includes, in response to a determination that a current belief state of the policy indicates an exceptional condition, identifying an exception handler for controlling the autonomous vehicle. Operating the controller includes, in response to a determination that the current belief state indicates an unexceptional condition, identifying a primary handler as the active handler.

Abstract: Autonomous vehicle operational management may include traversing, by an autonomous vehicle, a vehicle transportation network. Traversing the vehicle transportation network may include receiving, from a sensor of the autonomous vehicle, sensor information corresponding to an external object within a defined distance of the autonomous vehicle, identifying a distinct vehicle operational scenario in response to receiving the sensor information, instantiating a scenario-specific operational control evaluation module instance, wherein the scenario-specific operational control evaluation module instance is an instance of a scenario-specific operational control evaluation module modeling the distinct vehicle operational scenario, receiving a candidate vehicle control action from the scenario-specific operational control evaluation module instance, and traversing a portion of the vehicle transportation network based on the candidate vehicle control action.

Abstract: Introspective autonomous vehicle operational management includes operating an introspective autonomous vehicle operational management controller including a policy for a model of an introspective autonomous vehicle operational management domain. Operating the controller includes, in response to a determination that a current belief state of the policy indicates an exceptional condition, identifying an exception handler for controlling the autonomous vehicle. Operating the controller includes, in response to a determination that the current belief state indicates an unexceptional condition, identifying a primary handler as the active handler.

Abstract: Autonomous vehicle operational management may include traversing, by an autonomous vehicle, a vehicle transportation network. Traversing the vehicle transportation network may include operating a scenario-specific operational control evaluation module instance, wherein the scenario-specific operational control evaluation module instance is an instance of a scenario-specific operational control evaluation module, wherein the scenario-specific operational control evaluation module implements a partially observable Markov decision process. Traversing the vehicle transportation network may include receiving a candidate vehicle control action from the scenario-specific operational control evaluation module instance, and traversing a portion of the vehicle transportation network based on the candidate vehicle control action.

Abstract: Autonomous vehicle operational management including blocking monitoring may include traversing, by an autonomous vehicle, a vehicle transportation network. Traversing the vehicle transportation network may include operating a blocking monitor instance, which may include identifying operational environment information including information corresponding to a first external object within a defined distance of the autonomous vehicle, determining a first area of the vehicle transportation network based on a current geospatial location of the autonomous vehicle in the vehicle transportation network and an identified route for the autonomous vehicle, and determining a probability of availability for the first area based on the operational environment information. Traversing the vehicle transportation network may include traversing a portion of the vehicle transportation network based on the probability of availability.

Abstract: Autonomous vehicle operational management with visual saliency perception control may include operating a perception unit and an autonomous vehicle operational management controller. Operating the perception unit may include generating external object information based on image data received from image capture units of the vehicle and saliency information received from the autonomous vehicle operational management controller.

Abstract: Autonomous driving simulation using recorded driving data is disclosed. A method of simulating autonomous driving includes receiving recorded driving data from a recorded autonomous vehicle (AV), the recorded driving data includes decision-making data generated using a first decision-making algorithm, sensing data, and movement data including positions of the recorded AV; obtaining simulation data from the recorded driving data by excluding the decision-making data from the recorded driving data; and simulating, by a simulation AV, a second decision-making algorithm using the simulation data. The simulating the second decision-making algorithm includes determining a first position of the simulation AV at a first time and adjusting a playback speed of the simulation data based on a difference between the first position and a second position of the positions of the recorded AV at the first time.

Abstract: Traversing, by an autonomous vehicle, a vehicle transportation network, may include identifying a policy for a scenario-specific operational control evaluation model of a distinct vehicle operational scenario, receiving a candidate vehicle control action from the policy, wherein, in response to a determination that an uncertainty value for the distinct vehicle operational scenario exceeds a defined uncertainty threshold, the candidate vehicle control action is an orientation-adjust vehicle control action, and traversing a portion of the vehicle transportation network in accordance with the candidate vehicle control action, wherein the portion of the vehicle transportation network includes the distinct vehicle operational scenario.

Abstract: Autonomous driving simulation using recorded driving data is disclosed. A method of simulating autonomous driving includes receiving recorded driving data from a recorded autonomous vehicle (AV), the recorded driving data includes decision-making data generated using a first decision-making algorithm, sensing data, and movement data including positions of the recorded AV; obtaining simulation data from the recorded driving data by excluding the decision-making data from the recorded driving data; and simulating, by a simulation AV, a second decision-making algorithm using the simulation data. The simulating the second decision-making algorithm includes determining a first position of the simulation AV at a first time and adjusting a playback speed of the simulation data based on a difference between the first position and a second position of the positions of the recorded AV at the first time.

Abstract: Autonomous vehicle operational management may include traversing, by an autonomous vehicle, a vehicle transportation network. Traversing the vehicle transportation network may include receiving, from a sensor of the autonomous vehicle, sensor information corresponding to an external object within a defined distance of the autonomous vehicle, identifying a distinct vehicle operational scenario in response to receiving the sensor information, instantiating a scenario-specific operational control evaluation module instance, wherein the scenario-specific operational control evaluation module instance is an instance of a scenario-specific operational control evaluation module modeling the distinct vehicle operational scenario, receiving a candidate vehicle control action from the scenario-specific operational control evaluation module instance, and traversing a portion of the vehicle transportation network based on the candidate vehicle control action.