Browse Prior Art Database

Method and System for Predicting and Recommending Drone Travel Routes based on Historical Data and Real-time Data Feeds

IP.com Disclosure Number: IPCOM000241624D
Publication Date: 2015-May-18
Document File: 3 page(s) / 29K

Publishing Venue

The IP.com Prior Art Database

Abstract

A method and system is disclosed for predicting and recommending drone travel routes based on historical data and real-time data feeds.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 41% of the total text.

Page 01 of 3

Method and System for Predicting and Recommending Drone Travel Routes based on Historical Data and Real-time Data Feeds

Typically, drones are used for delivering products from one location to another location. Based on a warehouse location and a customer location, different drones follow different paths or routes. Currently, travel routes for drones are statically defined from Global Positioning System coordinates or missions. The travel routes for drones are controlled by remote devices/operators.

Disclosed is a method and system for predicting and recommending drone travel routes based on historical data and real-time data feeds. The historical data and the real-time streaming data feeds are on environmental factors and obstacles. Drones include different sensors and cameras installed which helps the drones to modify the route whenever required. The environmental factors and obstacles are captured by the sensors and cameras. Based on real-time data feeds and current situation, a drone can modify the path. For example, location A has many birds in path in the morning time. While travelling through location A during morning, the system predicts that the drone may have problem navigating due to birds. The feeds from the sensors and cameras identify the presence of birds, and accordingly the drone changes the travel route. However, at night time or mid-day, the system can predict that the route is safe of birds normally. Occurrences are tracked to account for unforeseen events such as birds being driven to area from another event or migration. The drone identifies all these data points and transmits the data points to a centralized knowledge base in real-time. Thereafter, the data is used for future route recommendations and predictions. Thus, the route of different drones is tracked and the feeds from the sensors and cameras of the drones are gathered to recommend or predict future routes.

In an implementation, the system includes components which are a drone, a knowledge base and a cognitive system. The drone includes a camera to observe surroundings and identify objects within the environment in coordination with the cognitive system. The drone also includes sensors that detect objects nearby. With the use of camera, the drone captures data on location, date, time and conditions. The drone is controlled remotely and the drone takes guidance from a real-time decision made via Application Programming Interface (API). The real-time decision is made based on the current location and environmental factors. The travel routes and data points captured from the camera and the sensors are streamed to the knowledge base.

The knowledge base stores historical data on sensory. The knowledge base also stores image data captured and streamed to the knowledge base from the drones. The cognitive system performs analysis of a destination and defines a travel route using the historical data in the knowledge base and the current environmental factor...