Traffic control for autonomous vehicles

Patent metadata

Field	Value
Publication number	US-11270583-B2
Application number	US-201715822346-A
Country	US
Kind code	B2
Filing date	Nov 27, 2017
Priority date	Nov 27, 2017
Publication date	Mar 8, 2022
Grant date	Mar 8, 2022

Abstract

Embodiments of the present invention disclose a method, computer program product, and computer system for traffic control. A computer determines an uncommitted demand and receives a supply pattern from an adjacent downstream node. The computer aggregates the supply pattern with its own supply pattern before propagating the supply pattern to an adjacent upstream node. Moreover, the computer receives a committed demand and demand weight pattern from an upstream node and aggregates the committed demand and demand weight patterns with its own before propagating the aggregated committed demand and demand weight patterns to an adjacent downstream node. The computer further allocates a remaining downstream supply to the uncommitted demand based on weight and detects pending slot position conflicts. Based on detecting a pending slot position conflict, the computer configures a pattern shift and commits the available downstream supply as upstream committed demand. Lastly, the computer weights the unmet uncommitted demand.

First claim

What is claimed is:

1. A method for controlling autonomous vehicles within a traffic control network, the method comprising:
a computer associated with a node of one or more nodes determining an uncommitted demand pattern for the node detailing one or more vehicles waiting in an on-ramp corresponding to the node;
the computer receiving a supply pattern from one or more nodes downstream of the node detailing one or more slots that are unoccupied;
the computer receiving a committed demand pattern detailing one or more slots that are occupied and a weight demand pattern detailing one or more vehicles waiting in an on-ramp corresponding to and from one or more nodes upstream of the node;
the computer determining whether the supply pattern exceeds the committed demand pattern;
based on the determining that the supply pattern exceeds the committed demand pattern, the computer allocating the excess supply pattern to the uncommitted demand pattern based on the weight demand pattern;
the computer detecting a slot position conflict in one or more slots of the one or more nodes;
the computer determining whether a slot of the one or more slots within a threshold distance of the slot position conflict is unoccupied;
based on determining that the slot of the one or more slots within the threshold distance of the slot position conflict is unoccupied, the computer modifying one or more slot speeds of the one or more slots to occupy the slot and accommodate the at least one of the uncommitted demand pattern and weight demand pattern;
the computer aggregating the excess supply pattern into the committed demand pattern; and
based on the determining that the supply pattern does not exceed the committed demand pattern, the computer weighting the uncommitted demand pattern exponentially based on a wait time.

2. The method of claim 1 , wherein weighting the uncommitted demand pattern is further based on a destination.

3. The method of claim 1 , wherein receiving the supply pattern from the one or more nodes downstream of the node further comprises:
the computer splitting the received supply pattern; and
the computer propagating the split supply pattern to the one or more upstream nodes.

4. The method of claim 1 , wherein receiving the committed demand pattern and the weight demand pattern from the one or more nodes upstream of the node further comprise:
the computer aggregating the received committed demand pattern and the weight demand pattern, respectively; and
the computer propagating the aggregated committed demand pattern and the aggregated weight demand pattern to the one or more downstream nodes.

5. The method of claim 1 , wherein operations of the computer associated with the node are instead performed by one or more vehicles occupying one or more slots of the node as a distributed computing network.

6. A computer program product for controlling autonomous vehicles within a traffic control network, the computer program product comprising:
one or more computer-readable storage media and program instructions stored on the one or more computer-readable storage media, the program instructions comprising:
program instructions to determine an uncommitted demand pattern for a node of one or more nodes detailing one or more vehicles waiting in an on-ramp corresponding to the node;
program instructions to receive a supply pattern from one or more nodes downstream of the node detailing one or more slots that are unoccupied;
program instructions to receive a committed demand pattern detailing one or more slots that are occupied and a weight demand pattern detailing one or more vehicles waiting in an on-ramp corresponding to and from one or more nodes upstream of the node;
program instructions to determine whether the supply pattern exceeds the committed demand pattern;
based on the determining that the supply pattern exceeds the committed demand pattern, program instructions to allocate the excess supply pattern to the uncommitted demand pattern based on the weight demand pattern;
program instructions to detect a slot position conflict in one or more slots of the one or more nodes;
program instructions to determine whether a slot of the one or more slots within a threshold distance of the slot position conflict is unoccupied;
based on determining that the slot of the one or more slots within the threshold distance of the slot position conflict is unoccupied, program instructions to modify one or more slot speeds of the one or more slots to occupy the slot and accommodate the at least one of the uncommitted demand pattern and weight demand pattern;
program instructions to aggregate the excess supply pattern into the committed demand pattern; and
based on the determining that the supply pattern does not exceed the committed demand pattern, program instructions to weight the uncommitted demand pattern exponentially based on a wait time.

7. The computer program product of claim 6 , wherein the program instructions to weight the uncommitted demand pattern is further based on a destination.

8. The computer program product of claim 6 , wherein the program instructions to receive the supply pattern from the one or more nodes downstream of the node further comprises:
program instructions to split the received supply pattern; and
program instructions to propagate the split supply pattern to the one or more upstream nodes.

9. The computer program product of claim 6 , wherein the program instructions to receive the committed demand pattern and the weight demand pattern from the one or more nodes upstream of the node further comprise:
program instructions to aggregate the received committed demand pattern and the weight demand pattern, respectively; and
program instructions to propagate the aggregated committed demand pattern and the aggregated weight demand pattern to the one or more downstream nodes.

10. The computer program product of claim 6 , wherein operations of the computer program product are performed by one or more vehicles occupying one or more slots of the node as a distributed computing network.

11. A computer system for controlling autonomous vehicles within a traffic control network, the computer system comprising:
one or more computer processors, one or more computer-readable storage media, and program instructions stored on one or more of the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
program instructions to determine an uncommitted demand pattern for a node of the one or more nodes detailing one or more vehicles waiting in an on-ramp corresponding to the node;
program instructions to receive a supply pattern from one or more nodes downstream of the node detailing one or more slots that are unoccupied;
program instructions to receive a committed demand pattern detailing one or more slots that are occupied and a weight demand pattern detailing one or more vehicles waiting in an on-ramp corresponding to and from one or more nodes upstream of the node;
program instructions to determine whether the supply pattern exceeds the committed demand pattern;
based on the determining that the supply pattern exceeds the committed demand pattern, program instructions to allocate the excess supply pattern to the uncommitted demand pattern based on the weight demand pattern;
program instructions to detect a slot position conflict in one or more slots of the one or more nodes;
program instructions to determine whether a slot of the one or more slots within a threshold distance of the slot position conflict is unoccupied;
based on determining that the slot of the one or more slots within the threshold dis

Assignees

• IBM

Inventors

• Kumar Keeranoor G

Classifications

• G08G1/0133

  for classifying traffic situation · CPC title

• G08G1/096811

  where the route is computed offboard · CPC title

• G08G1/081 Primary

  Plural intersections under common control · CPC title

• G05B15/02

  electric · CPC title

• G08G1/0145

  for active traffic flow control · CPC title