Abstract: A cloud service receives locations of priority vehicles (PVs) and non-priority vehicles in a metropolitan area. The cloud service accesses a database storing indicia of restricted road portions in the metropolitan area. The cloud service allocates restricted road portions from the database to the NPVs based on the locations of the PVs, the locations of the NPVs, and locations of the restricted road portions. The allocating includes preventing some of the restricted road portions in the database from being available to be allocated to the NPVs based on determining, according to the locations of the PVs and NPVs and according to pre-stored routes of the PVs, that estimated uses of the road portions by the NPVs would conflict with estimated uses of the road portions by the PVs as they travel along the pre-stored routes. Routes generated to include the respectively allocated road portions are provided to the NPVs.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to identify patterns in first high anticipation scenarios based on user identification, wherein high anticipation scenarios include video sequences wherein a first vehicle will be within a specified distance of a first object in a first environment around the first vehicle, wherein user identification is determined by viewing portions of a respective video sequence. A first model including a first deep neural network can be trained to determine second high anticipation scenarios based on the patterns identified in the first high anticipation scenarios and a second model including a second deep neural network can be trained to modify locations and velocities of second objects in the first high anticipation scenarios and output modified high anticipation scenarios.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to identify patterns in first high anticipation scenarios based on user identification, wherein high anticipation scenarios include video sequences wherein a first vehicle will be within a specified distance of a first object in a first environment around the first vehicle, wherein user identification is determined by viewing portions of a respective video sequence. A first model including a first deep neural network can be trained to determine second high anticipation scenarios based on the patterns identified in the first high anticipation scenarios and a second model including a second deep neural network can be trained to modify locations and velocities of second objects in the first high anticipation scenarios and output modified high anticipation scenarios.