During the recent Helvia summit, Helvia’s Project Manager Eleni Panopoulou, presented to the team the progress of the LAW-GAME project.

Overview

LAW-GAME aims to elevate the experiential training of Law Enforcement Agencies (LEAs) and first responders through virtual reality (VR) and Artificial Intelligence (AI)s. Police officers will have the option to practice in real-life scenarios with gamification technologies in a safe and controlled virtual environment.

The main objectives of the project are to:

  1. Create fully immersive 3D virtual environments for training
  2. Create a complete gamified training system for LEAs
  3. Build an interactive gaming experience
  4. Design and develop a novel terrorist attack prevention, analysis and training framework based on serious gaming
  5. Provide a comprehensive framework to measure training effectiveness.
  6. Build a secure environment that will provide data resources, simulation tools, expert access, and unique collaboration capabilities.
  7. Validate and test the solution in realistic law enforcement exercises and increase the project impacts.

The training system

LAW-GAME will create a complete gamified training system that will help LEAs to develop the core competencies required for crime scene investigation & illegal acts prediction. The key elements of the training system will include a 3D game engine, Serious Games Modes, Human Modeling & Emotional Intelligence, learning environment, analysis tools, and AI-assisted procedures:

Game modes

The project includes 4 distinct game modes to provide dedicated training to police officers in Forensic Examination, Interrogation & Negotiation, Terrorism Prediction and Vehicle Dynamics & Card Accident Analysis:

  1. CSI Game - Forensic Examination

The game’s objective is to survey the incident scenes in VR in order to discover, analyze and evaluate all the evidence and solve the case, following typical investigator procedures and using virtual instruments.

2. Police Interview Game - Interrogation & Negotiation techniques and protocols

The game’s objectives are to:

  • Converse with NPC to validate the gathered evidence and get confession of the crime or of any involvement in it (Interrogation)
  • Find out background and reason for the actions and manipulate the perpetrator to deliver him/her to the Authorities without any human losses (Negotiation)

3. Terrorist Attack Prevention Game - Terrorism Prediction

The game’s objective is to analyze various data / terrorism indicators and other players’ moves in order to recognize and prevent an impending terrorist attack by

  • Identifying the members of the terrorist group
  • Foreseeing the time and place of the attack
  • Identifying the target of the attack
  • Identifying the modus operandi of the attack, e.g., weapons or explosives
  • Understanding the motivation for the attack

4. Car Accident Game - Vehicle Dynamics & Card Accident Analysis

The game’s objective is to inspect the accident scenes in order to discover, analyze and evaluate all the evidence and determine what happened, following typical police procedures, inspecting the scene, collecting evidence with the use of virtual instruments.

Helvia’s role in the LAW-GAME project

Helvia’s role is to build interactive chatbots that support the use cases of the project, and more specifically conversational characters for training experiences that take place in gaming and VR environments.

Helvia is leading the development of the following components:

  1. Interactive Storytelling Engine
  • Handles interactive dialogues manifested via chat NPCs
  • Handles unfolding of “branching” storylines based e.g., on player’s emotions and game events

2. AI Narrator

  • Narrates the game mode/scenario to the player
  • Pops up to provide guidance and hints to the player
  • Available to answer player’s questions

3. Training Scenario Configurator

  • Provides UI for scenario configuration by the trainers

Find out more about the LAW-GAME project at https://lawgame-project.eu/.

LAW-GAME project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 101021714. Content reflects only the authors’ view and European Commission is not responsible for any use that may be made of the information it contains.