Abstract: The present technology is directed to training and using a machine learning model to predict a likelihood of a counterfactual safety critical event in autonomous vehicle (AV) driving in a projected scenario occurring after a human takes over control of an AV. An AV management system can identify driving data collected from periods around an occurrence of a human take over event where a human takes over control of an AV. The AV management system can project a scenario that would have resulted if the human did not take over control of the AV based on the driving data and output a counterfactual safety score for the projected scenario. The counterfactual safety score can indicate a probability of a counterfactual collision between the AV and the at least one object in the projected scenario.

Abstract: System, methods, and computer-readable media for configuring an autonomous vehicle based on safety scores determined by a safety score prediction algorithm, and an associated training technique, to output a safety score for a predicted and/or actual path. The safety score is a value indicating a likelihood of risky events per distance. The safety score prediction algorithm is trained with historical human driving datasets associated with paths (predicted or actual) taken by one or more AVs during human driving.

Abstract: The present technology is directed to training and the use of a machine learning model to measure the safety of an autonomous vehicle (AV) driving in simulation. An AV management system can run a simulation of an AV autonomously piloting itself and collect simulation driving data. Further, the AV management system can parse the simulation driving data into kinematic and semantic environmental features and output a simulation safety score of the simulation based on the kinematic and semantic environmental features. The simulation safety score indicates a probability of a safety critical event such as a collision or a near-miss between the AV and the at least one simulated object in the simulation.

Abstract: System, methods, and computer-readable media for configuring an autonomous vehicle based on safety scores determined by a safety score prediction algorithm, and an associated training technique, to output a safety score for a predicted and/or actual path. The safety score is a value indicating a likelihood of risky events per distance. The safety score prediction algorithm is trained with historical human driving datasets associated with paths (predicted or actual) taken by one or more AVs during human driving.

Abstract: The present technology is directed to training and the use of a machine learning model to measure the safety of an autonomous vehicle (AV) driving. An AV management system can identify driving data including sensor data from an AV that is descriptive of an environment around the AV, a path of the AV, kinematic data of the AV, a path of at least one object in the environment, and in-memory data pertaining to data output by one or more algorithms in an autonomous driving stack. As follows, the AV management system can output a safety score for the path of the AV indicating a probability of a collision between the AV and the at least one object.

Abstract: The present technology is directed to training and the use of a machine learning model to measure the safety of an autonomous vehicle (AV) driving in simulation. An AV management system can run a simulation of an AV autonomously piloting itself and collect simulation driving data. Further, the AV management system can parse the simulation driving data into kinematic and semantic environmental features and output a simulation safety score of the simulation based on the kinematic and semantic environmental features. The simulation safety score indicates a probability of a safety critical event such as a collision or a near-miss between the AV and the at least one simulated object in the simulation.

Abstract: The present technology is directed to training and using a machine learning model to predict a likelihood of a counterfactual safety critical event in autonomous vehicle (AV) driving in a projected scenario occurring after a human takes over control of an AV. An AV management system can identify driving data collected from periods around an occurrence of a human take over event where a human takes over control of an AV. The AV management system can project a scenario that would have resulted if the human did not take over control of the AV based on the driving data and output a counterfactual safety score for the projected scenario. The counterfactual safety score can indicate a probability of a counterfactual collision between the AV and the at least one object in the projected scenario.

Abstract: The present technology is directed to determine that an autonomous vehicle needs remote assistance. The present technology may include receiving inputs into a stuck detection algorithm, the inputs including data descriptive of an environment in which the autonomous vehicle is located at a first time, objects surrounding the AV in the environment, data perceived by the autonomous vehicle prior to the first time, and events occurring in an AV stack leading up to a current state. The present technology may also include classifying the current AV state as stuck based on the received inputs by the stuck detection algorithm and initiating remote assistance session.