System and method for predicting non-operational design domain (ODD) scenarios
A system and method for predicting non-operational design domain (ODD) scenarios are disclosed. In one aspect, a server includes a network communication device configured to communicate with an autonomous vehicle over a network, a memory, and a processor configured to receive information related to the navigation of the autonomous vehicle from a plurality of data sources. The processor is further configured to predict whether the autonomous vehicle will encounter a non-ODD scenario based on the received information and transmit a signal to the autonomous vehicle in response to predicting that the autonomous vehicle will encounter the non-ODD scenario.
1. A server comprising:
a network communication device configured to communicate with an autonomous vehicle over a network;
a memory; and
at least one processor configured to:
receive information related to navigation of the autonomous vehicle from a plurality of data sources,
predict whether the autonomous vehicle will encounter a non-operational design domain (ODD) scenario based on the received information, and
transmit a signal to the autonomous vehicle in response to predicting that the autonomous vehicle will encounter the non-ODD scenario;
wherein the at least one processor is further configured to:
assign a numerical value to the information received from each of the plurality of data sources, and
sum the numerical values, wherein the prediction of whether the autonomous vehicle will encounter the non-ODD scenario is further based on the sum of the numerical values;
wherein, in response to the signal, the autonomous vehicle takes an action in response to the predicted non-ODD scenario.
2. The server of claim 1 , wherein at least one of the plurality of data sources is available via the cloud.
3. The server of claim 1 , wherein at least one of the plurality of data sources comprises another autonomous vehicle within a same fleet as the autonomous vehicle.
4. The server of claim 1 , wherein the at least one processor is further configured to:
compare a result of the sum to a threshold value, and
predict that the autonomous vehicle will encounter the non-ODD scenario in response to the result of the sum being greater than the threshold value.
5. The server of claim 1 , wherein the at least one processor is further configured to:
determine the action for the autonomous vehicle to take in response to the predicted non-ODD scenario.
6. The server of claim 5 , wherein the determination of the action is based on the information received from the plurality of data sources as well as one or more of the following: a distance between the autonomous vehicle and a location of the non-ODD scenario, a number and location of another autonomous vehicle within a same fleet as the autonomous vehicle, and details of a predetermined map between the autonomous vehicle, the location of the non-ODD scenario, a destination, and/or a point of origin of the autonomous vehicle.
7. The server of claim 5 , wherein the action comprises one or more of the following: execute a minimal risk condition (MRC) maneuver, pull over to a side of a road, take a next exit, take any exit before a location of the non-ODD scenario, reroute to a destination, and return to a point of origin.
8. The server of claim 1 , wherein the plurality of data sources include one or more of the following: an accident information source, a construction zone source, a road condition source, a traffic information source, and a weather information source.
9. A method of predicting whether an autonomous vehicle will encounter a non-operational design domain (ODD) scenario, comprising:
receiving information related to navigation of the autonomous vehicle from a plurality of data sources;
predicting whether the autonomous vehicle will encounter the non-ODD scenario based on the received information;
transmitting a signal to the autonomous vehicle in response to predicting that the autonomous vehicle will encounter the non-ODD scenario;
assigning a numerical value to the information received from each of the plurality of data sources; and
summing the numerical values, wherein the prediction of whether the autonomous vehicle will encounter the non-ODD scenario is further based on the sum of the numerical values;
wherein, in response to the signal, the autonomous vehicle takes an action in response to the predicted non-ODD scenario.
10. The method of claim 9 , further comprising:
detecting one or more conditions related to the navigation of the autonomous vehicle based on the received information; and
assigning the numerical value to each of the one or more conditions.
11. The method of claim 10 , further comprising:
comparing a result of the sum to a threshold value; and
predicting that the autonomous vehicle will encounter the non-ODD scenario in response to the result of the sum being greater than the threshold value.
12. The method of claim 10 , wherein a first condition of the one or more conditions is detected based on information from a first group of multiple data sources of the plurality of the data sources.
13. The method of claim 12 , wherein:
the one or more conditions comprise a plurality of conditions, and
a second condition and a third condition of the plurality of conditions are detected based on information from a single data source of the plurality of the data sources.
14. The method of claim 9 , further comprising:
applying a decision tree of binary options for a plurality of conditions used to predict whether the autonomous vehicle will encounter the non-ODD scenario.
15. The method of claim 14 , wherein the decision tree identifies a plurality of combinations of the plurality of conditions which are predictive of the autonomous vehicle encountering the non-ODD scenario.
16. The method of claim 9 , further comprising:
generating instructions to the autonomous vehicle to take an exit ahead of a location of the non-ODD scenario,
wherein the signal comprises the instructions.