Devices and methods to facilitate escape from a venue with a sudden hazard

• US 9,921,068 B2
• Filed: 03/09/2017
• Issued: 03/20/2018
• Est. Priority Date: 03/09/2017
• Status: Active Grant

• Current Assignee: Thomas Danaher Harvey
• Original Assignee: Thomas Danaher Harvey
• Inventors: Harvey, Thomas Danaher
• Primary Examiner(s): Shaawat, Mussa A
• Assistant Examiner(s): Jha, Abdhesh K
• Application Number:
  US15/453,996
• Publication Number:
  US 20170176190A1
• Time in Patent Office: 376 Days
• Field of Search: None
• CPC Class Codes: A62B 5/00 Other devices for rescuing from fire ladders E06C
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks

Abstract

A device and associated methods for escaping from a venue when a threat is detected is described. Venues can be buildings or outside areas and contain the area where the threat constitutes a hazard to a protected person. Threats include fire, terrorists, gunmen, explosion, collapse, loss of critical resources and crowd panic. The device incorporates a machine learning system implemented with a neural network or other pattern matching system and is trained in steps. Pre-training is based on general requirements such as edge-detection and audio analysis. Principles and data for venue layouts and human behavior can be included. The produced model is further trained from data gathered from sensors and servers after entry into the venue. Operation of the model produces warnings of threats and a plan of escape with steps of the plan communicated to the protected person by audio, visual or tactile sensory channels.

Claims

1. A method of planning escape from a threat in a venue comprising:

operating a machine learning system implemented on a first processor with a machine learning model subsequent to the detection of the threat to produce a plan of escape from the venue, wherein;

(a) the model has been pre-trained in a first step on a second processor with data concerning at least one of layout of venues, methods of escape from venues, and behavior of persons attempting to escape from a venue in a hazardous condition;

(b) the model has been transferred to one of the first processor and a third processor subsequent to the first step and prior to entry into the venue by a person;

(c) the model has been trained in a second step subsequent to the transfer and subsequent to entry into the venue by the person on one of the first processor and the third processor with data gathered subsequent to the entry with a sensor concerning at least one of a location of the person in the venue and behavior of persons attempting to escape from the venue; and

(d) the model subsequent to the second step is used to produce the plan of escape;

(e) the first processor has a memory containing a program to use the machine learning model to produce an instruction to escape from the venue subsequent to the detection of a hazard in the venue; and

(f) using an output device guides the person in escape from the venue.

2. The method of claim 1 wherein:

the output device is a least one of a visual display, an audible transducer and a tactile transducer.

3. The method of claim 1 further comprising:

a vehicle to escape the venue wherein the vehicle is adapted to be operated autonomously to escape from the venue in accordance with the plan of escape.

4. The method of claim 1 wherein:

the data of the first step concerns layout of the venue.

5. The method of claim 1 wherein:

the data of the first step concerns methods of escape from venues.

6. The method of claim 1 wherein:

the data of the first step concerns behavior of persons attempting to escape from venues in a hazardous condition.