Smart and scalable urban signal networks: methods and systems for adaptive traffic signal control

• US 9,159,229 B2
• Filed: 06/18/2014
• Issued: 10/13/2015
• Est. Priority Date: 06/18/2013
• Status: Active Grant

• Current Assignee: Carnegie Mellon University
• Original Assignee: Carnegie Mellon University
• Inventors: Xie, Xiao-Feng, Smith, Stephen F., Barlow, Gregory J.
• Primary Examiner(s): La, Anh V
• Application Number:
  US14/308,238
• Publication Number:
  US 20140368358A1
• Time in Patent Office: 482 Days
• Field of Search: 340/922, 340/907, 340909-913, 340/918, 340/920, 340/921, 340/924, 701/117, 701/118, 701/119
• US Class Current: 1/1
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0145 for active traffic flow control
• CPC Class Codes: G08G 1/08 according to detected number or speed of vehicles

Abstract

Scalable urban traffic control system has been developed to address current challenges and offers a new approach to real-time, adaptive control of traffic signal networks. The methods and system described herein exploit a novel conceptualization of the signal network control problem as a decentralized process, where each intersection in the network independently and asynchronously solves a single-machine scheduling problem in a rolling horizon fashion to allocate green time to its local traffic, and intersections communicate planned outflows to their downstream neighbors to increase visibility of future incoming traffic and achieve coordinated behavior. The novel formulation of the intersection control problem as a single-machine scheduling problem abstracts flows of vehicles into clusters, which enables orders-of-magnitude speedup over previous time-based formulations and is what allows truly real-time (second-by-second) response to changing conditions.

Claims

1. An adaptive traffic control method comprising the steps of:

providing a local adaptive traffic control processor in communication with one or more neighboring adaptive traffic control processors, one or more traffic flow sensors, and a local intersection controller, wherein the local adaptive traffic control processor executes the following steps of the method;

receiving traffic signal status from the local intersection controller;

receiving current traffic flows from the one or more traffic flow sensors;

receiving planned traffic inflows from the one or more neighboring adaptive traffic control processors;

merging the current traffic flows and the planned traffic inflows to form an aggregate traffic inflows;

generating an optimal phase schedule based on the traffic signal status and the aggregate traffic inflows;

transmitting the optimal phase schedule to the one or more neighboring adaptive traffic control processors;

determining whether to extend a current phase by an extension-interval based in the optimal phase schedule; and

transmitting a switch phase instruction to the local intersection controller switch to a next phase for a minimal phase length if the current phase is not to be extended or an extend phase instruction to extend the current phase if the current phase is to be extended, wherein an extend phase message contains the extension interval.

2. The method according to claim 1, wherein the local adaptive traffic control processor further comprises:

a communicator module having a communicator processor and a communicator memory;

a detector module having a detector processor and a detector memory;

an executor module having an executor processor and an executor memory; and

a scheduler module having a scheduler processor and a scheduler memory.

3. The method according to claim 1, wherein the step of receiving current traffic flows from the one or more traffic flow sensors further comprises the steps of:

computing sequence of <

vehicle, arrival time departure time>

triples derived from the current traffic flows to form vehicle sequences; and

aggregating the vehicle sequences into sequences of clusters using gap-threshold parameter and anticipated queue calculation to form local inflow cluster sequences.

4. The method according to claim 1, wherein the step of receiving planned traffic outflows from the one or more neighboring adaptive traffic control processors further comprises the steps of:

querying the one or more neighboring adaptive traffic control processors for most recently generated planned outflows that include neighbor outflow cluster sequences; and

using free travel time to transform the neighbor outflow cluster sequences into non-local inflow cluster sequences.

5. The method according to claim 1, wherein the step of merging the current traffic flows and the planned traffic inflows to form an aggregate traffic inflows further comprises the steps of:

concatenating local and non-local cluster sequences for each phase to form a set of compatible flows; and

apply threshold gap clustering on all clusters in the merged inflow of the set of compatible flows to form phase cluster sequences.

6. The method according to claim 5, wherein the step of generating an optimal phase schedule based on the traffic signal status and the aggregate traffic inflows further comprises the steps of:

a. receiving the phase cluster sequences;

b. initializing a set of partial schedules to empty set;

c. recursively generating possible extension intervals to be stored in the set of partial schedules;

d. selecting minimum cumulative delay solution based on the possible extension intervals;

e. determining whether a maximum phase length constraint are violated based on the minimum cumulative delay solution,

if the maximum phase length constraint is violated, then identify one or more clusters within one or more cluster sequences of the phase cluster sequences that cause the violation of the maximum phase length constraint and split the identified one or more clusters from the one or more cluster sequences to form one or more new cluster sequences, thereby revising the phase cluster sequences, and repeat steps b-e, or

if the maximum phase length constraint is not violated, then continue to step f;

f. determining whether a spillover is projected at an upstream intersection,

if the spillover is projected at the upstream intersection, then shorten a local phase length of the one or more cluster sequences of the phase cluster sequences that causes the spillover and continue to step g, else, continue to step g; and

g. returning the optimal phase schedule.

7. The method according to claim 1, wherein the step of transmitting the optimal phase schedule to the one or more neighboring adaptive traffic control processors further comprises the steps of:

receiving request from the one or more downstream neighboring adaptive traffic control processors for planned outflows based on the optimal phase schedule;

dis-aggregating scheduled clusters of the optimal phase schedule into the planned outflows using flow direction(s) of constituent vehicles and turning proportions; and

communicating the planned outflows to the one or more downstream neighboring adaptive traffic control processors that requested the planned outflows.

8. The method according to claim 1, wherein the step of determining whether to extend a current phase based in the optimal phase schedule further comprises the steps of:

h. receiving the optimal phase schedule;

i. determining whether a schedule prefix of the optimal phase schedule stays in a current phase;

if the schedule prefix does stay in the current phase, then continue to step j, else continue to step k;

j. determine whether the schedule prefix violates a maximum phase length constraint,

if the maximum phase length constraint is not violated, then proceed to stay in the current phase for the extension-interval, else continue to step k; and

k. proceeding to terminate the current phase and shifting to a next phase.