System and method for estimating arrival time of a vehicle at a destination
Methods and systems for estimating a time of arrival for a vehicle at a destination are disclosed. The system will access an adjacency graph comprising nodes and edges. Each node is associated with a unique location in a geographic area in which the vehicle is traveling. Each edge connects two of the nodes and is associated with an estimated travel time between the two connected nodes. The system will select, from the locations in adjacency graph, a first location that is near the vehicle and a second location that is near the destination. The location and destination are each associated with nodes in adjacency graph. The system will calculate a shortest path along the edges in the adjacency graph from the location and destination nodes, and it will calculate an estimated time of arrival for the vehicle as a function of the estimated travel times along the shortest path.
1. A method of determining an estimated time of arrival (ETA) at which a vehicle will arrive at a destination, the method comprising, by a processor:
receiving navigation data indicating a present location of the vehicle as autonomous driving operations of the vehicle are being controlled to cause the vehicle to travel along a route to a location in a geographic area;
accessing an adjacency graph comprising a plurality of nodes and edges, in which:
each node is associated with a unique location in the geographic area, and
each edge connects two of the nodes and is associated with an estimated travel time between the two nodes to which the edge is connected;
selecting, from locations in the adjacency graph, a first location that is near the present location of the vehicle and a second location that is near the destination, wherein the first location is associated with a first node in the adjacency graph and the second location is associated with a second node in the adjacency graph;
calculating a shortest path along the edges in the adjacency graph from the first node to the second node using Dijkstra's algorithm, Floyd's algorithm, a depth-first search algorithm, a breadth-first search algorithm, or a Bellman-Ford algorithm;
calculating the ETA as a function of the estimated travel times of the edges along the shortest path;
generating a message that includes the ETA for a trip; and
performing operations by a control system to control movement of the vehicle along a route planned for the trip.
2. The method of claim 1 , wherein selecting the second location comprises sending a request to a service that stores the adjacency graph to identify, from the nodes in the adjacency graph, a node having coordinates closest to the destination.
3. The method of claim 2 , wherein the request also comprises a request to not return any node having coordinates that are not reachable from the route.
4. The method of claim 1 , wherein calculating the shortest path comprises disqualifying from inclusion in the shortest path any edge that leads to a node that is not reachable via the route.
5. The method of claim 1 , wherein calculating the ETA comprises generating a sum of the estimated travel times of the edges along the shortest path.
6. The method of claim 5 , wherein calculating the ETA further comprises:
receiving traffic data for one or more geographic areas that correspond one or more of the nodes along the shortest path; and
adjusting one or more of the estimated travel times based on the traffic data.
7. The method of claim 5 , further comprising, before calculating the shortest path:
receiving traffic data for a geographic area that corresponds to an identified node in the adjacency graph; and
adjusting the estimated travel times for each edge to which the identified node is connected each based on the traffic data.
8. The method of claim 1 , further comprising generating the adjacency graph by:
accessing a set of points that represent potential destinations in the geographic area;
converting each of the points to a lane in the geographic area to yield a set of lanes;
for each lane in the set, applying Dijkstra's algorithm until another lane in the set is reached to yield at least one adjacent vertex for the lane; and
generating a mapping of each lane in the set to each of its adjacent vertices to yield the adjacency graph.
9. A system for estimating a time of arrival for a vehicle at a destination, the system comprising:
a processor; and
a computer-readable medium containing programming instructions that are configured to instruct the processor to:
receive navigation data indicating a present location of the vehicle as autonomous driving operations of the vehicle are being controlled to cause the vehicle to travel along a route to a location in a geographic area;
access an adjacency graph comprising a plurality of nodes and edges, in which:
each node is associated with a unique location in the geographic area in which the vehicle is traveling; and
each edge connects two of the nodes and is associated with an estimated travel time between the two nodes to which the edge is connected,
select, from locations in adjacency graph, a first location that is near a present location of the vehicle and a second location that is near the destination, wherein the first location is associated with a first node in the adjacency graph and the second location is associated with a second node in the adjacency graph,
calculate a shortest path along the edges in the adjacency graph from the first node to the second node using Dijkstra's algorithm, Floyd's algorithm, a depth-first search algorithm, a breadth-first search algorithm, or a Bellman-Ford algorithm,
calculate an estimated time of arrival (ETA) for the vehicle as a function of the estimated travel times of the edges along the shortest path, and
generate a message that includes the ETA for a trip; and
control operations of the vehicle to move along a route planned for the trip.
10. The system of claim 9 , wherein the instructions to select the second location comprise instructions to send a request to a service that stores the adjacency graph to identify, from the nodes in the adjacency graph, a node having coordinates closed to the destination.
11. The system of claim 10 , wherein the request also comprises a request to not return any node having coordinates that are not reachable from the route.
12. The system of claim 9 , wherein the instructions to calculate the shortest path further comprise instructions to disqualify from inclusion in the shortest path any edge that leads to a node that is not reachable via the route.
13. The system of claim 9 , wherein the instructions to calculate the ETA comprise instructions to generate a sum of the estimated travel times of the edges along the shortest path.
14. The system of claim 13 , wherein the instructions to calculate the ETA further comprise instructions to:
upon receiving traffic data for one or more geographic areas that correspond one or more of the nodes along the shortest path, adjust one or more of the estimated travel times based on the traffic data.
15. The method of claim 13 , further comprising instructions to, before calculating the shortest path:
upon receiving traffic data for a geographic area that corresponds to an identified node in the adjacency graph, adjust the estimated travel times for each edge to which the identified node is connected each based on the traffic data.
16. The system of claim 9 , further comprising instructions to generate the adjacency graph by:
accessing a set of points that represent potential destinations in the geographic area;
converting each of the points to a lane in the geographic area to yield a set of lanes;
for each lane in the set, applying Dijkstra's algorithm until another lane in the set is reached to yield at least one adjacent vertex for the lane; and
generating a mapping of each lane in the set to each of its adjacent vertices to yield the adjacency graph.
17. A computer program product for estimating a time of arrival for a vehicle at a destination, the computer program product comprising a memory and programming instructions that are configured to instruct a processor to:
receive navigation data indicating a present location of the vehicle as autonomous driving operations of the vehicle are being controlled to cause the vehicle to travel along a route to a location in a geographic area;
access an adjacency graph comprising a plurality of nodes and edges, in which:
each node is associated with a unique location in the geographic area in which the vehicle is traveling, and
each edge connects two of the nodes and is associated with an estimated travel time between the two nodes to which the edge is connected;
select, from locations in adjacency graph, a first location that is near a present location of the vehicle and a second location that is near the destination, wherein the first location is associated with a first node in the adjacency graph and the second location is associated with a second node in the adjacency graph;
calculate a shortest path along the edges in the adjacency graph from the first node to the second node using Dijkstra's algorithm, Floyd's algorithm, a depth-first search algorithm, a breadth-first search algorithm, or a Bellman-Ford algorithm;
calculate an estimated time of arrival (ETA) for the vehicle as a function of the estimated travel times of the edges along the shortest path; and
generate a message that includes the ETA for a trip; and
control operations of the vehicle to move along a route planned for the trip.
18. The computer program product of claim 17 , further comprising programming instructions to generate the adjacency graph by:
accessing a set of points that represent potential destinations in the geographic area;
converting each of the points to a lane in the geographic area to yield a set of lanes;
for each lane in the set, applying Dijkstra's algorithm until another lane in the set is reached to yield at least one adjacent vertex for the lane; and
generating a mapping of each lane in the set to each of its adjacent vertices to yield the adjacency graph.