Real-time adaptive geospatial mapping with autonomous vehicles

A computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:

• receive a sensor suite data from an autonomous vehicle (AV), wherein the sensor suite data indicates that the AV has switched from operating in an autonomous driving mode to operating in a non-autonomous driving mode, or that the AV has switched from operating in a non-autonomous driving mode to operating in an autonomous driving mode;
• determine an AV location based on the sensor suite data using a neural network trained on the sensor suite data fused with global positioning system data;
• determine a non-AV location of a non-AV based on the global positioning system data;
• map a digital environment based on the sensor suite data and the non-AV location, wherein the mapping includes extracting features from the sensor suite data to identify one or more objects within a real-world environment, and wherein the mapping further includes dynamically updating the digital environment based on changes in the extracted features;
• generate a route for the non-AV in the digital environment based on the sensor suite data, the AV location, and the non-AV location, wherein the route is configured to avoid the AV location in response to the sensor suite data indicating that the AV has switched to operating in the autonomous driving mode, and wherein the route is dynamically modified in response to the sensor suite data indicating that the AV has switched to operating in the non-autonomous driving mode;
• and
• communicate the route to a device of the non-AV.

A system comprising:

• a processor set, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:
• receive a sensor suite data from an autonomous vehicle (AV), wherein the sensor suite data indicates that the AV has switched from operating in an autonomous driving mode to operating in a non-autonomous driving mode, or that the AV has switched from operating in a non-autonomous driving mode to operating in an autonomous driving mode;
• determine an AV location based on the sensor suite data using a neural network trained on the sensor suite data fused with global positioning system data;
• determine a non-AV location of a non-AV based on the global positioning system data;
• map a digital environment based on the sensor suite data and the non-AV location, wherein the mapping includes extracting features from the sensor suite data to identify one or more objects within a real-world environment, and wherein the mapping further includes dynamically updating the digital environment based on changes in the extracted features;
• generate a route for the non-AV in the digital environment based on the sensor suite data, the AV location, and the non-AV location, wherein the route is configured to avoid the AV location in response to the sensor suite data indicating that the AV has switched to operating in the autonomous driving mode, and wherein the route is dynamically modified in response to the sensor suite data indicating that the AV has switched to operating in the non-autonomous driving mode;
• and
• communicate the route to a device of the non-AV.