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

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.

I claim: 
     
         1 . A device to facilitate movement in a venue comprising:
 (a) a first processor with a memory containing a program for machine learning and a model of a venue wherein the model has been pre-trained using a second processor with information 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) a sensor to detect a person in the venue and a sensor to acquire information to be used in training the model using the first processor concerning at least one of a location of the person in the venue and behavior of persons attempting to escape from the venue;   (c) a program comprised in the memory of the first processor to use the model and data from at least one of the sensors to produce an instruction to escape from the venue subsequent to the detection of a hazard in the venue; and   (d) an output device using the instruction to guide the person in escape from the venue.   
     
     
         2 . The device of  claim 1  wherein:
 the instruction to escape from the venue is determined by training of the model with data acquired from the sensor subsequent to entry of the person into the venue. 
 
     
     
         3 . The device of  claim 1  wherein:
 the instruction to escape from the venue is determined by training of the model from information acquired from a server subsequent to entry of the person into the venue. 
 
     
     
         4 . The device of  claim 3  wherein:
 the information from the server is selected on the basis of the information acquired from the sensor. 
 
     
     
         5 . The device of  claim 1  wherein:
 the output device is a least one of a visual display, an audible transducer and a tactile transducer. 
 
     
     
         6 . The device 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 instruction. 
 
     
     
         7 . The device of  claim 1  wherein:
 the output device comprises a vehicle to carry the person. 
 
     
     
         8 . A device for facilitating escape from a venue comprising:
 (a) a sensor adapted to be carried by a person entering the venue and to acquire information about potential escape routes from the venue,   (b) a memory containing at least one of prerecorded information concerning physical layout of the venue and information acquired from a communication system concerning physical layout of the venue,   (c) a first processor with a program to calculate an escape route based on the memory and the information gathered by the sensor, and   (d) an output device to guide the person escaping from the venue when a threat is detected by the device comprising at least one of a visual display and of an audible transducer;   
       wherein:
 (a) the program comprises a machine learning model transferred from a second processor subsequent to training concerning methods of escape from venues in hazardous conditions; and 
 (b) the program has been trained using the information. 
 
     
     
         9 . The device of  claim 8  wherein:
 the program is configured to train the machine learning from the information acquired by the sensor, and the escape route is calculated on the basis of the model. 
 
     
     
         10 . The device of  claim 8  further comprising:
 a processor with a program to determine a presence of a threat based on information gathered by the sensor. 
 
     
     
         11 . The device of  claim 8  further comprising:
 at least one of a visual display and an audible transducer to warn a person of a presence of a threat in the venue. 
 
     
     
         12 . The device of  claim 8  wherein:
 the program is configured to train a model of the venue by machine learning from pre-acquired information accessed by a communication system. 
 
     
     
         13 . The device of  claim 12  wherein:
 information accessed by the communication system is selected by use of the information acquired by the sensor. 
 
     
     
         14 . The device of  claim 8  wherein:
 the output device comprises a vehicle to carry the person. 
 
     
     
         15 . A method of escaping a threat in a venue comprising:
 (a) gathering information about conditions in the venue with a sensor after a person enters the venue with the sensor;   (b) training a machine learning system implemented on a computer with the information,   (c) operating the machine learning system to produce a plan of escape from the venue subsequent to detection of a threat to safety of a person by the machine learning system;   (d) transmitting a step of the plan of escape with an output device; and   (e) performing the step of the plan of escape in accordance with the transmission.   
     
     
         16 . The method of  claim 15  wherein:
 the output device is a least one of a visual display, an audible transducer and a tactile transducer. 
 
     
     
         17 . The method of  claim 15  wherein:
 the machine learning system is trained with at least one of data concerning venue layouts in a class of venues and routes for escape from venues in a class of venues. 
 
     
     
         18 . The method of  claim 15  wherein:
 the machine learning system is trained prior to entry to the venue by a person to be protected with at least one of data concerning a layout of the venue, data concerning layouts of a group of venues selected to represent a class of venues, routes for escape from the venue and routes to escape from a group of venues selected to represent a class of venues, and 
 the machine learning system is trained with the information subsequent to entry of the person into the venue. 
 
     
     
         19 . The method of  claim 15  further comprising:
 warning the person of the presence of the threat with the output device. 
 
     
     
         20 . The method of  claim 15  wherein:
 the output device is a vehicle adapted to be directed autonomously by the step of the plan.