Abstract: A system for vehicle decision-making using sequential information probing generates a first world model for a feature of a vehicle operational scenario. The first world model is a copy of a second world model that represents the vehicle operational scenario using incomplete state information for the feature. The first world model represents the vehicle operational scenario using complete state information for the feature. A first expected reward is determined for a sequence of actions of an artificial intelligence (AI) agent using the first world model. A second expected reward is determined for the sequence of actions using the second world model. An expected loss in decision-making performance associated with the incomplete state information for the feature is calculated based on the first and second expected rewards. The expected loss is used to inform a decision-making process for controlling an autonomous vehicle to traverse a portion of a vehicle transportation network.

Abstract: System and method for dynamically refining custom classes using zero-shot image classifiers. The system uses a CLIP model to generate text embeddings of object descriptions and image embeddings of captured images, and determines similarity scores between the text and image embeddings. When a similarity score exceeds a threshold, the system notifies a user that a captured image includes the object, and the system stores the relevant text prompt and captured image as a custom class.

Abstract: Vehicle decision-making is analyzed and can be used to modify a decision-making process. For subsets of features comprising a vehicle operational scenario, a first value is generated that quantifies behavior of an artificial intelligence (AI) agent as the AI agent performs a sequence of actions within a first world model based on a complete set of observations for the subset of features. A first world model is a copy of a second world model for sequential decision making. A second value is generated that quantifies behavior of an AI agent as the AI agent performs a sequence of actions in the second world model based on an incomplete set of observations for the subset of features. A difference between the first and second values determines the impact of individual features on the AI agent within the second world model. A decision-making process of the AI agent can be updated.

Abstract: Vehicle decision-making is analyzed and can be used to modify a decision-making process. For subsets of features comprising a vehicle operational scenario, a first value is generated that quantifies behavior of an artificial intelligence (AI) agent as the AI agent performs a sequence of actions within a first world model based on a complete set of observations for the subset of features. A first world model is a copy of a second world model for sequential decision making. A second value is generated that quantifies behavior of an AI agent as the AI agent performs a sequence of actions in the second world model based on an incomplete set of observations for the subset of features. A difference between the first and second values determines the impact of individual features on the AI agent within the second world model. A decision-making process of the AI agent can be updated.