Predictive traffic management using virtual lanes

• US 10,102,744 B2
• Filed: 09/27/2016
• Issued: 10/16/2018
• Est. Priority Date: 09/27/2016
• Status: Active Grant

• Current Assignee: DoorDash, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Dhondse, Amol Ashok, Nunez, Selene M. O., Pikle, Anand, Sivakumar, Gandhi, Veerkamp, Ana P. H.
• Primary Examiner(s): LANG, MICHAEL DEAN
• Application Number:
  US15/277,695
• Publication Number:
  US 20180089994A1
• Time in Patent Office: 749 Days
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0145 for active traffic flow control
• CPC Class Codes: G08G 1/056 with provision for distinguishing direction of travel
• CPC Class Codes: G08G 1/07 Controlling traffic signals
• CPC Class Codes: G08G 1/08 according to detected number or speed of vehicles
• CPC Class Codes: G08G 1/087 Override of traffic control, e.g. by signal transmitted by an emergency vehicle
• CPC Class Codes: G08G 1/09 Arrangements for giving variable traffic instructions railroad crossing signals B61L; reflectors E01F, G08B; indicating arrangements for variable information by selection or combination of individual elements G09F9/00
• CPC Class Codes: G08G 1/096725 where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096741 where the source of the transmitted information selects which information to transmit to each vehicle
• CPC Class Codes: G08G 1/096775 where the origin of the information is a central station

Abstract

A computing system for predictive traffic management using virtual lanes. In an embodiment, the system dynamically monitors and collects traffic conditions in real time, performs analytics on the collected traffic data, utilizes a neural network or other self-learning computer to assist in predictive traffic modeling, and interfaces with a public transfer system to provide an allocation/reallocation of lanes available for traffic use to optimize traffic flow and/or control traffic signals, and can provide vehicles (human driver or driverless/self-driving) with real time optimal route guidance, including use of alternate routes and a holographic image that shows and may also provide audio indications of lane allocation.

Claims

1. A system for providing predictive traffic management and lane allocation based on a vehicle'"'"'s current position, comprising:

a) a plurality of sensors adapted for positioning along a roadway, detecting the movement of vehicles operatively passing said sensor and generating vehicle movement data, and transmitting said vehicle movement data;

b) a public transfer system;

c) a vehicle sub-system, comprising;

i) a first geo-location based transmitter adapted for attachment to the vehicle and generating and transmitting vehicle position; and

ii) a navigation assistant;

iii) one or more customized route or routing preferences; and

d) a computing system located remote from said plurality of sensors, said public transfer system, and said vehicle sub-system, and is configured to exchange data with said public transfer system, comprising;

i) a digital receiver configured to receive said vehicle movement data transmitted from said plurality of sensors, and further configured to aggregate the vehicle movement data from the plurality of sensors into aggregate vehicle movement data;

ii) a digital controller adapted to receive;

(i) said aggregate vehicle movement data from said digital receiver; and

(ii) said vehicle position data from said first geo-location based transmitter; and

(iii) processed traffic data comprising route guidance from a traffic control management module;

iii) a traffic control management module configured to process traffic data and transmit said processed traffic data to said digital controller as route guidance for one or more vehicles;

iv) a predictive traffic flow modeler comprising an inference engine configured to generate predictive traffic data model which predicts one or more traffic patterns on the roadway using at least historic traffic data, information from a traffic density analyzer comprising traffic density conditions at a plurality of time points for the roadway, information from a geo-location based data unit comprising vehicle geo-location data, and information from a self-learning data processor, wherein the predictive traffic flow modeler is configured to send said predictive traffic data model to said traffic control management module;

v) a traffic flow optimizer configured to optimize said processed traffic data utilizing at least said aggregate vehicle movement data and said predictive traffic data model to generate optimized traffic flow data comprising one or more optimized routes, wherein the traffic flow optimizer is configured to send said optimized traffic flow data to said traffic control management module;

vi) a preference-based personal advisor configured to receive personal advisor data comprising;

(i) the one or more predetermined customized route or routing preferences;

(ii) one or more weather conditions along at least a portion of the roadway; and

(iii) one or more roadway reports received from one or more drivers or vehicles, and further configured to send said personal advisor data to said traffic control management module; and

vii) a digital transmitter configured to receive optimized route guidance data from said digital controller and transmit said data to said navigation assistant;

wherein the traffic control management module is adapted to generate optimized route guidance data based at least in part on said predictive traffic data model, said optimized traffic flow data, and said personal advisor data.

2. The system according to claim 1, wherein said public transfer system comprises a lane controller and a traffic light controller.

3. A method for providing predictive traffic management and lane allocation based on a vehicle'"'"'s current position, comprising the steps of:

a) receiving in a computing system data representative of sensed vehicular traffic from traffic lanes on a roadway, wherein the data comprises vehicle positions transmitted by a plurality of geo-location based transmitters each attached to a vehicle;

b) aggregating said sensed vehicular traffic data in a computer controller;

c) receiving in said computing system geolocation data for a vehicle;

d) providing said computing system with data representative of preferred traffic guidance for said vehicle, said preferred traffic guidance comprising (i) one or more predetermined customized route or routing preferences for said vehicle;

(ii) one or more weather conditions along at least a portion of the roadway; and

(iii) one or more roadway reports received from one or more drivers or vehicles;

e) generating, by a predictive traffic flow modeler of said computing system and comprising an inference engine, modeled data representative of predictive traffic flow for said traffic lanes, wherein the predictive traffic flow modeler is configured to generate said modeled data using at least historic traffic data, information from a traffic density analyzer comprising traffic density conditions at a plurality of time points for the roadway, information from a geo-location based data unit comprising vehicle geo-location data, and information from a self-learning data processor;

f) generating, by a traffic flow optimizer of said computing system using said vehicle data representative of route guidance instructions based upon said predictive traffic flow data, said vehicular traffic data, and said preferred traffic guidance data, optimized vehicle route guidance instructions;

g) transmitting, from said computing system to said vehicle, said optimized route guidance instructions; and

h) transmitting from said computing system to a public transfer system data to control traffic lights and lane allocations.

4. The method according to claim 3, further comprising generating a visual image in said vehicle of a virtual driving lane representative of said route guidance instructions.

5. The method according to claim 3, further comprising generating navigation assistance in said vehicle representative of said route guidance instructions.

6. A computer program product providing predictive traffic management and lane allocation based on a vehicle'"'"'s current position, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions are readable by a computer to cause the computer to perform a method comprising:

a) receiving in a computing system data representative of sensed vehicular traffic from traffic lanes on a roadway, wherein the data comprises vehicle positions transmitted by a plurality of geo-location based transmitters each attached to a vehicle;

b) aggregating said sensed vehicular traffic data in a computer controller;

c) receiving in said computing system geolocation data for a vehicle;

d) providing said computing system with data representative of preferred traffic guidance for said vehicle, said preferred traffic guidance comprising (i) one or more predetermined customized route or routing preferences for said vehicle;

(ii) one or more weather conditions along at least a portion of the roadway; and

(iii) one or more roadway reports received from one or more drivers or vehicles;

e) generating, by a predictive traffic flow modeler of said computing system and comprising an inference engine, modeled data representative of predictive traffic flow for said traffic lanes, wherein the predictive traffic flow modeler is configured to generate said modeled data using at least historic traffic data, information from a traffic density analyzer comprising traffic density conditions at a plurality of time points for the roadway, information from a geo-location based data unit comprising vehicle geo-location data, and information from a self-learning data processor;

f) generating, by a traffic flow optimizer of said computing system using said vehicle data representative of route guidance instructions based upon said predictive traffic flow data, said vehicular traffic data, and said preferred traffic guidance data, optimized vehicle route guidance instructions;

g) transmitting, from said computing system to said vehicle, said optimized route guidance instructions; and

h) transmitting from said computing system to a public transfer system data to control traffic lights and lane allocations.

7. The computer program product according to claim 6, wherein the program instructions readable by a computer to cause the computer to perform a method further comprise generating a visual image in said vehicle of a virtual driving lane representative of said route guidance instructions.

8. The method according to claim 6, wherein the program instructions readable by a computer to cause the computer to perform a method further comprise generating navigation assistance in said vehicle representative of said route guidance instructions.