The disclosed technology uses signaling devices and sensors that are distributed throughout a building in order to provide egress guidance to people located in a building when an emergency occurs. Such signaling devices can be located at or near doors, windows, and/or other junction points between different parts of a building (e.g., passageways between different rooms). Signaling devices can provide audio and/or visual information to people to guide them along a safe pathway that is selected to provide safe egress for the person, including anticipating and protecting the person from changing emergency conditions within the building.

A peer-to-peer system for providing egress guidance. Each of a plurality of egress advisement devices can receive an indication of an emergency in a building and user presence information, transmit to a cloud data store a request for one or more egress plans, receive from the cloud data store a subset of the egress plans that are identified by matching a location identifier for each of the subset of the plans with the location information of the egress advisement device, locally select one of the subset of the plans that is customized for a location of the egress advisement device, a current location of users in the building in proximity to the egress advisement device, and a location of the emergency, and output the selected plan to guide one or more of the users in proximity to the egress advisement device to exit the building.

A system for centrally managing and executing emergency egress guidance. A first computing device can receive an indication of an emergency and user presence information in a building, retrieve, from a local data store, generated egress instructions for the building, select, for each of a plurality of egress advisement devices and based on the emergency indication, user presence information, and location of each egress advisement device, one of the egress instructions that is customized for each egress advisement device, and transmit, to each egress advisement device, the selected instructions to be outputted to guide users to exit the building. Each egress advisement device can determine that communications are terminated between the egress advisement devices and the computing device, obtain the emergency indication and user presence information, and retrieve, from the local data store, a second of the egress instructions associated with the location of the device.

The disclosed system can determine egress guidance during a building emergency using artificial intelligence (AI). The system can include sensors positioned throughout the building to detect building conditions and a computing system to determine egress guidance in the building. The computing system can perform operations including: receiving, from the sensors, information indicating the building conditions, detecting, based on processing the conditions, an emergency in the building, determining, based on applying AI techniques to the information, scenarios indicating potential spreads of the emergency, generating, based on the determined scenarios, egress guidance to assist users in safely egressing from the building. The egress guidance can include at least one egress strategy instructing the users to move along a pathway that avoids the emergency and the potential spreads of the emergency. The egress guidance can be returned for presentation to the users in the building to assist in safely avoiding the emergency.

A method and an apparatus for setting an evacuation exit under a crowd emergency evacuation scenario are provided. A simulation model is constructed based on a social force model, and a behavior parameter of an evacuating crowd under the crowd emergency evacuation scenario is obtained by a numerical approximation method with actual trajectory data of individuals in the evacuating crowd under a specific emergency evacuation scenario as a reference; an evacuation exit set is set, an integer programming solution for evacuation exit decision under the emergency evacuation scenario is constructed, and a total evacuation cost of the evacuation exit is obtained based on the simulation model; and reduction of the total evacuation cost is taken as an optimization target to construct an emergency evacuation optimization model based on constraint conditions, and the emergency evacuation optimization model is solved to obtain a recommended integer programming solution for evacuation exit decision.

A system for dynamically selecting egress plans during an emergency. A computing device can receive signals indicating an emergency in the building and user presence information, determine a type of the emergency, predict locations of the users within the building, transmit, to an emergency responders computing device, the indication of the emergency and predicted locations of the users within the building, receive, from the emergency responders computing device, an estimated responders arrival time based on a current distance of emergency responders from the building, select one or more of the determined egress plans to direct the users to exit the building, send, to signaling devices in the building, signaling instructions for the signaling devices to emit signals indicating to the users the selected one or more egress plans, and send, to the emergency responders computing device, the selected one or more egress plans.

A system for generating emergency egress advisement based on motion data and trained models for the building. A computing device can receive, from first detection devices, frequency of movement indicating routes frequented the most by users in the building, determine an initial emergency egress advisement for the building, receive, from the first detection devices, first motion data about the users, receive, from second detection devices positioned throughout the building or worn by the users, second motion data, iteratively train a model for the building by correlating the initial emergency egress advisement to corresponding (i) first motion data, (ii) second motion data, and (iii) historic user presence information across one or more model layers using one or more machine learning algorithms, the iterative training generating a trained model for the building, and update, based on the trained model, the initial emergency egress advisement for use during an emergency in the building.

A system for practicing suggested emergency egress from a building. An egress advisement device can, during a non-emergency, receive from a first computing device, suggested egress plans that are customized for users in the building based on user presence information and different types of emergencies, output, to a GUI of the egress advisement device, the suggested egress plans, receive first user input indicating a selection of one of the plans, present for playback by the users, the user-selected egress plan, receive after playback of the user-selected egress plan, second user input indicating updates to at least one of the user-selected suggested plan, building information, and the user presence information, transmit, to the computing device, the second user input, receive, from the computing device, updated suggested egress plans based on the second user input, and during an emergency, generate egress advisement instructions based on the updated suggested egress plans.

A system for emergency egress advisement from a building. An egress advisement device can receive a floormap and subset of emergency egress instructions associated with routes within the building, wherein the subset of instructions are associated with a location of the egress advisement device and are used, by the device, to direct users in proximity to the location of the device to egress from that location during an emergency, locally store the floormap and subset of instructions, receive a signal indicative of an emergency, locally select, based on real-time conditions in the building relative to the location of the egress advisement device, one of the subset of instructions, which is customized for users in proximity to the location of the egress advisement device, and output the selected instructions to guide the users in proximity to the location of the egress advisement device to egress from the building.

A system and method for indoor spatial mapping. The system includes a mobile mapping device having a camera; a plan database configured to store 2-D floor plans; and a processor configured to integrate a selected floor plan from the plan database with object data received from the mobile mapping device to create an interactable 3-D spatial mapping of an interior portion of a structure so that one or more objects are moveable relative to a surrounding environment within the 3-D spatial mapping. The processor is configured to recognise objects from an image from the camera and anchor the recognised object within the interactable 3-D spatial mapping.