Browse Prior Art Database

Cognitive Road Hazard Life Cycle Management

IP.com Disclosure Number: IPCOM000248334D
Publication Date: 2016-Nov-15
Document File: 3 page(s) / 27K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a system and method to identify and track current road hazards and utilizes a cognitive forward-thinking machine learning and data mining based approach to better manage and predict future road hazards. The approach utilizes Internet of Things (IoT) technology coupled with a cognitive cloud based solution for advanced road repair management.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 01 of 3

Cognitive Road Hazard Life Cycle Management

Roadway hazards (e.g., potholes, bumps, fixed debris, etc.) occur on roadways throughout the world. Vehicles can be damaged when driving over a dangerous road hazard. Road hazard repairs are time consuming and costly. Today, potholes, bumps, and other hazards are manually identified, reported, and tracked. Current methods present an opportunity to manage the lifecycle for the road hazard in question.

The novel solution is a system and method to identify and track current road hazards and utilize a cognitive forward-thinking machine learning and data mining-based approach to better manage and predict future road hazards. The approach utilizes Internet of Things (IoT) technology coupled with a cognitive cloud based solution for advanced road repair management.

The novel system provides a means to track road hazards and abstractions through the lifecycles, until repaired or alleviated. A cognitive system identifies areas prone to specific types of road hazards through data analytics. Machine learning and data mining produce recommendations and predictive outcomes. An IoT sensor method acquires the measurement, location, and type of the road hazard based on specific characteristics.

Utilizing data mining and cognitive techniques, the system better identifies, marks, manages, and predicts potholes, bumps, and anything else considered a road hazard. Using measuring IoT sensors, the system quickly identifies and measures the road hazards. Various measuring techniques can be used and other IoT sensor based data can be collected to acquire knowledge about the road hazard. The system uploads all data into a cloud-based solution. This allows data analytics to occur and a predictive cognitive learning system to obtain vital information over time. Through the continued use of the system, the cognitive machine learning algorithms can provide predictive insight based on various weighting factors such as conditions of the road hazard, time of year, the season, the weather, date, and geological mapping. Other predictive factors can be considered as well, including traffic volume, vehicle speeds, moisture data, and other IoT sensor data.

Following is the process for implementing the system in a preferred embodiment:

1. Initial pothole acquisition (NOTE: This in itself is not a novel step. Existing prior art helps identify and mark potholes and other road hazards).

2. IoT Sensor Deployment. Marking the road hazards can be easily completed through (options are not limited to these):

A. Deploying a small IoT sensor into the pothole via a dropping technique from a road maintenance vehicle's undercarriage

B. Using drones to mark potholes via taking GPS coordinates (or) by deploying the IoT sensor directly into the pothole

C. Utili...