# US 2026/0268763 A1 · Systems and methods for optimizing traffic flow based on future roadway conditions

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0268763 A1
- Document ID: US20260268763A1
- Status: Published application
- Kind: A1
- Application number: 19/342,425
- Filed: 2025-09-26
- Published: 2026-09-10
- Earliest claimed: 2025-03-07
- Assignees: Cintra US Services, LLC
- Applicants: Cintra US Services, LLC
- Inventors: Ricardo Sanchez Gomez; Alvaro Prieto Moneo; Joseph Charles McKenzie
- Web page: https://patentgrep.com/patent/US20260268763A1

## CPC

- G08G 1/0129: {for creating historical data or processing based on historical data}
- G07B 15/063: {using wireless information transmission between the vehicle and a fixed station (identification of vehicles G08G)}
- G08G 1/0112: {from the vehicle, e.g. floating car data [FCD]}
- G08G 1/0116: {from roadside infrastructure, e.g. beacons}
- G08G 1/0133: {for classifying traffic situation}
- G08G 1/0141: {for traffic information dissemination}
- G08G 1/0145: {for active traffic flow control}
- G08G 1/08: according to detected number or speed of vehicles
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})
- G07B: TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS

## Abstract

Aspects of the disclosed technology relate to a system and methods for optimizing traffic flow along a roadway. The systems receive, from a connected-automated vehicle (CAV), a request for a travel time along a roadway having a managed lane and a general purpose lane. The system determines real-time traffic data, and using a trained machine learning model, predicts future traffic data along the roadway, determines a time saved by using the managed lane, communicates with the CAV, receives an acknowledgement that the vehicle will use the managed lane, and updates the predicted traffic data. Segment agents may be responsible for discrete segments of the roadway and may communicate with a coordination agent to result in a multi-agent reinforced traffic machine learning system. The system provides a mobility service to CAVs by implementing a reinforcement learning process to understand CAV behavior to optimize and maintain the service level along a roadway.

## Claims

### Claim 1

A computer-implemented method for traffic optimization, the method comprising:
receiving, from a connected-automated vehicle and through a network interface, a route request, the route request including a starting point, a destination, a route along a roadway from the starting point to the destination, and an estimated time of arrival at an entry point of a managed lane along the route;
retrieving, from a traffic database, historical traffic data associated with a plurality of roadway segments along the route at the estimated time of arrival at the entry point of the managed lane, the historical traffic data including traffic speed, traffic density, and managed lane acceptance data;
vectorizing the historical traffic data into a plurality of vectors, each vector corresponding to a single time interval for one of the plurality of roadway segments;
identifying anomalous vectors within the plurality of vectors using an isolation forest anomaly detection algorithm, wherein each anomalous vector represents a time interval where traffic conditions significantly deviate from normal conditions;
clustering the anomalous vectors into a plurality of anomalous vector clusters using a clustering algorithm, wherein each anomalous vector cluster represents a group of similar anomalous traffic conditions;
receiving, from a plurality of real-time roadway sensors, real-time traffic data for the route;
inputting the historical traffic data, the real-time traffic data, and the estimated time of arrival into a machine learning model trained on historical patterns to predict future traffic conditions;
predicting, using the machine learning model, an estimated travel time for the managed lane and a non-managed lane along the route at the estimated time of arrival;
determining, based on the estimated travel times, a time savings for traveling in the managed lane;
determining, based on historical acceptance data stored for the connected-automated vehicle, a user profile including at least one of historical managed lane usage frequency, price sensitivity, or response patterns to prior incentives;
generating, using a reinforcement learning model that has been updated based on prior vehicle acceptances and rejections, an incentive offer for the connected-automated vehicle, wherein the incentive offer is adjusted based on the user profile and the predicted future traffic conditions;
transmitting, via the network interface, the estimated travel time for the managed lane, the estimated travel time for the non-managed lane, the time savings, and the incentive offer to the connected-automated vehicle;
receiving, from the connected-automated vehicle, an acceptance of the incentive offer; and
updating the user profile and the reinforcement learning model based on the acceptance or rejection to improve future incentive generation.

### Claim 2 (depends on 1)

The method of claim 1, wherein the machine learning model additionally comprises one or more of a neural network and a decision tree.

### Claim 3 (depends on 1)

The method of claim 1, further comprising segmenting connected automated vehicles into behavioral cohorts based on one or more of managed lane usage frequency, price sensitivity determined from historical toll acceptances and rejections, and responsiveness to prior incentives.

### Claim 4 (depends on 1)

The method of claim 1, further comprising adjusting the incentive offer in real time when the predicted congestion level for the managed lane exceeds a predetermined threshold.

### Claim 5 (depends on 1)

The method of claim 1, wherein the incentive offer is further adjusted based on at least one of: day of week, holiday designation, or occurrence of a special event.

### Claim 6 (depends on 1)

The method of claim 1, further comprising coordinating incentive offers across a plurality of roadway segments to balance managed lane usage.

### Claim 7 (depends on 6)

The method of claim 6, wherein coordinating the generation of incentive offers comprises:
increasing incentive values for segments predicted to be underutilized; and
decreasing incentive values for segments predicted to be overutilized or congested.

### Claim 8 (depends on 6)

The method of claim 6, wherein coordinating incentive offers comprises:
communicating, by a coordination agent and with a plurality of segment agents, each segment agent monitoring real-time traffic data for an associated roadway segment;
receiving, at the coordination agent, real-time traffic data from each segment agent;
generating, by the coordination agent, instructions for each segment agent to control incentive offers based on the predicted future traffic conditions; and
transmitting the instructions from the coordination agent to each segment agent.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
storing, by each segment agent, historical acceptance data for connected-automated vehicles that have traveled through a roadway segment associated with the segment agent;
analyzing the historical acceptance data to identify patterns of managed lane usage by individual connected-automated vehicles; and
generating targeted incentives for transmission to the individual connected-automated vehicles based on the identified patterns.

### Claim 10 (depends on 1)

The method of claim 1, wherein generating the incentive offer comprises:
calculating a gradient of predicted congestion levels across the plurality of segments;
determining an optimal distribution of vehicles between managed and non-managed lanes using the reinforcement learning model; and
computing a personalized incentive value that maximizes a probability of achieving the optimal distribution while minimizing total incentive costs.

### Claim 11 (depends on 1)

The method of claim 1, further comprising:
reducing computational load by clustering similar user profiles and generating batch incentive offers for each cluster;
wherein the clustering uses at least one of k-means clustering or density-based spatial clustering.

### Claim 12 (depends on 1)

The method of claim 1, wherein determining the user profile comprises:
identifying connected-automated vehicles that consistently accept and use the managed lanes;
categorizing the identified connected-automated vehicles as frequent users; and
wherein generating the incentive offer includes providing exclusive incentives to the frequent users, the exclusive incentives including at least one of: guaranteed pricing, personalized route recommendations, or partner discounts.

### Claim 13 (depends on 1)

The method of claim 1, further comprising:
vectorizing the real-time traffic data into a vector in n-dimensional space;
calculating an anomaly score for the vector using an isolation forest trained on historical traffic data; and
when the anomaly score exceeds a predetermined threshold, adjusting the incentive offer according to a predetermined adjustment rule associated with anomalous traffic conditions.

### Claim 14 (depends on 1)

The method of claim 1, further comprising
dynamically updating the incentive offer by continuously monitoring the progression of current traffic conditions for the managed lane and non-managed lane along the route, and automatically recalculating and transmitting an updated incentive offer to the connected-automated vehicle whenever a change in the current traffic conditions exceeds a predetermined threshold.

### Claim 15

A computer-implemented method for improving managed lane usage in a traffic optimization system, the method comprising:
monitoring, by a plurality of real-time roadway sensors, real-time traffic data for a roadway having a plurality of segments, each segment having a managed lane and a non-managed lane;
receiving, via a network interface, a route request from a connected-automated vehicle, the route request including a starting point, a destination, and an estimated time of arrival at an entry point of the managed lane;
predicting, using a machine learning model trained on historical traffic patterns, future traffic conditions for at least one segment of the roadway for a future time interval based on the real-time traffic data and historical traffic data;
determining, based on historical acceptance data stored for the connected-automated vehicle, a user profile including at least one of: historical managed lane usage frequency, price sensitivity, or response patterns to prior incentives;
generating, using a reinforcement learning model that has been updated based on prior vehicle acceptances and rejections, an incentive offer for the connected-automated vehicle, wherein the incentive offer is dynamically adjusted based on the user profile and the predicted future traffic conditions;
transmitting, via the network interface, the incentive offer to the connected-automated vehicle;
receiving, from the connected-automated vehicle, an acceptance or rejection of the incentive offer; and
updating the user profile and the reinforcement learning model based on the acceptance or rejection to improve future incentive generation.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
receiving, via the network interface, actual travel time data from the connected-automated vehicle after completion of travel in the managed lane;
comparing the actual travel time data to the predicted estimated travel times; and
further updating the machine learning model based on the comparison to improve future predictions.

### Claim 17 (depends on 15)

The method of claim 15, further comprising:
determining a capture rate representing a frequency at which connected-automated vehicles accept managed lane usage for the roadway segments;
using the capture rate to predict future managed lane density; and
adjusting the incentive offer based on the predicted future managed lane density to maintain a target level of service.

### Claim 18 (depends on 15)

The method of claim 15, wherein the reinforcement learning model implements a multi-agent system comprising:
a plurality of segment agents, each responsible for monitoring and managing traffic in an associated roadway segment; and
a coordination agent that aggregates data from the plurality of segment agents and coordinates incentive strategies across the roadway segments.

### Claim 19 (depends on 15)

The method of claim 15, further comprising:
receiving navigation data from the connected-automated vehicle indicating a change in the connected-automated vehicle's route after accepting the incentive offer; and
further updating the machine learning model based on the navigation data to improve future predictions.

### Claim 20 (depends on 15)

The method of claim 15, wherein transmitting the incentive offer comprises:
transmitting the incentive offer directly to a navigation application associated with the connected-automated vehicle via at least one of: dedicated short-range communications (DSRC), cellular vehicle-to-everything (C-V2X), vehicle-to-infrastructure (V2I), or 5G communications; and
causing the navigation application to display the incentive offer to an occupant of the connected-automated vehicle.
