This is a Unity application that helps first responders to get trained on difficult to recreate environments such as floods, and how to empathize with affected victims in the environment with conversation, gaining their trust and then proceeding to evacuate them
- Dynamic Water Mechanics
- Speech to Text using Azure Speech Services
- Text to Speech using Azure Speech Services
- Conversational AI using Azure LUIS
- Avatar Lip Sync
- Avatar Voice using Azure Custom Voice
- Stress Calculation
The LUIS AI is trained on intents around the following. Feel free to speak around them to get the objective complete. You dont have to speak the exact sentences, just on the same context.
- Hi/Hello
- What is your name?
- How old are you?
- Are you okay?
- I'm here to help
- Where is your family?
- Do you live here?
- What happened?
- Are you hungry?
- Are you injured?
- Can you move?
- Come with me
This project is built using Unity 2019.1
Click on the link below to download the demo of the solution which was ported to run on Windows Desktops or Laptops to be tested if you do not own a VR device like HTC Vive.
- Download the
Floods.Victim.Evacuation.Executable.zipfrom above link - Unzip the folder.
- Run the
Flood_Victim.exefile to start using the demo.
This was run on low end systems and ran with at least 30fps. THis should run on most Windows 10 Systems.
The project source code needs Unity 2019.1 and SteamVR to run. It is VR Ready and was tested using HTC Vive Pro It is preferred to use Unity 2019.1 version series to avoid any package dependency conflicts during compile and build.
The source code was too big to push directly so it is uploaded to GitHub as a release.
Click here to download the Unity Source Code.
- Download
disaster_recovery_training.zip - Open as Project in
Unity 2019.1 - Play to preview in editor
The code for the backend is documented and pushed to this repository https://github.com/pourabkarchaudhuri/empathy-engine-luis
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent