Abstract: A computer that includes a processor and a memory, the memory including instructions executable by the processor to generate first traffic scenarios including one or more objects based on initial object locations and initial object trajectories of the one or more objects, wherein the first traffic scenarios are generated with a three-dimensional simulation engine. Probabilities of impact can be determined between the one or more objects included in the first traffic scenarios; selecting a subset of the first traffic scenarios that include the probabilities of impact greater than a user-selected threshold. Second traffic scenarios can be generated based on perturbing the selected subset of the first traffic scenarios wherein the second traffic scenarios are generated with the three-dimensional simulation engine. A machine learning system can be trained based on the first and the second traffic scenarios.

Abstract: An apparatus includes a robot body, at least one sensor coupled to the robot body and positioned to receive stimuli from a passenger cabin of a vehicle, an actuatable component coupled to the robot body, and a computer coupled to the robot body and communicatively coupled to the sensor and the actuatable component. The computer is programmed to predict an imminent anomalous event in the vehicle based on data from the at least one sensor, and in response to the determination, actuate the actuatable component to remediate the anomalous event.

Abstract: An apparatus includes a robot body, at least one sensor coupled to the robot body and positioned to receive stimuli from a passenger cabin of a vehicle, an actuatable component coupled to the robot body, and a computer coupled to the robot body and communicatively coupled to the sensor and the actuatable component. The computer is programmed to predict an imminent anomalous event in the vehicle based on data from the at least one sensor, and in response to the determination, actuate the actuatable component to remediate the anomalous event.