Virtual Humans Archives - RIDE https://ride.ict.usc.edu/tag/virtual-humans/ Rapid Integration & Development Environment Tue, 28 Apr 2026 16:00:09 +0000 en-US hourly 1 https://wordpress.org/?v=7.0.2 https://ride.ict.usc.edu/wp-content/uploads/2020/05/cropped-RIDE_Logo_Icon_250x-32x32.png Virtual Humans Archives - RIDE https://ride.ict.usc.edu/tag/virtual-humans/ 32 32 Large Language Model Comparison https://ride.ict.usc.edu/support/documentation/examples/large-language-model-comparison/?utm_source=rss&utm_medium=rss&utm_campaign=large-language-model-comparison Fri, 08 Dec 2023 00:05:07 +0000 https://ride.ict.usc.edu/?page_id=6818 Demonstrates cloud-based large language models (LLMs) generative AI, comparing OpenAI ChatGPT against Anthropic Claude.

The post Large Language Model Comparison appeared first on RIDE.

]]>
Virtual Humans

Large Language Model Comparison

Overview

Demonstrates cloud-based large language models (LLMs) generative AI, comparing OpenAI ChatGPT against Anthropic Claude.

Page Contents

Example LLM RIDE Chat
ExampleLLM

Purpose

Shows how to leverage large language model generative AI services through REST calls, using RIDE’s common web services system.

Leverages RIDE’s generic NLP C# interface, primarily focused on question-answering interactions, with the principle generally working for user input and agent output. Optionally includes sentiment analysis and entity analysis.

Current Providers

  • OpenAI ChatGPT-4
  • Anthropic – Claude

How to Use

IMPORTANT

If you wish to use the ExampleLLM scene and related web services, you must update your local RIDE config file (ride.json). Please back-up any local changes to the file, including your terrain key. Next, restore your Config to default using the corresponding option in the Config debug menu at run-time, then reapply any customization and terrain key. Refer to the Config File page within Support for more information. 

Provider Comparison UI

  1. Input text in the bottom field and hit enter or click the Ask button. Any input will be sent to both providers simultaneously.
  2. Each service has its own pane which populates with the following information after entering a query:
    1. Response Time
    2. Max Token Count
    3. Returned answer from the provider

Scene Location & Name

Assets/Ride/Examples/NLP/ExampleLLM/ExampleLLM.unity

Setup Requirements 

The ExampleLLM scene utilizes a customizable UI and interchangeable service providers through canvas, scripts and prefabs. Explore the objects in the Hierarchy view for the scene inside the Unity editor and source for Ride.NLP via the API documentation.

The main script is ExampleLLM.cs in the same folder.

Any NLP option implements the INLPQnASystem C# Interface, which itself is based on INLPSystem. These systems provide the main building blocks to interface with an NLP service:

				
					
OpenAIGPT3System m_openAIGPT3;
var openAIGPT3Component = new GameObject("OpenAIGPT3System").AddComponent<OpenAIGPT3System>();
m_openAIGPT3 = openAIGPT3Component;

The specific endpoint and authentication information is defined through RIDE’s configuration system:

				
					
m_configSystems = Globals.api.systemAccessSystem.GetSystem<RideConfigSystem>();
openAIGPT3Component.m_uri = m_configSystems.config.openAI.endpoint;
openAIGPT3Component.m_authorizationKey = m_configSystems.config.openAI.endpointKey;

The NLP system encapsulates the user question into an NLPQnAQuestion or NLPRequest object. This user input is sent through the RIDE common web services system. The results are encapsulated into an NLPQnAAnswer  or NLPResponse object. A provided callback function allows a client (in this case this ExampleNLP) what specifically to do with the result. The NLP system itself handles much of the work, so that the client only requires one line to send the user question: 

				
					
m_openAIGPT3.AskQuestion(userInput, OnCompleteAnswer);

The post Large Language Model Comparison appeared first on RIDE.

]]> Audio-Visual Sensing https://ride.ict.usc.edu/support/documentation/examples/audio-visual-sensing/?utm_source=rss&utm_medium=rss&utm_campaign=audio-visual-sensing Tue, 10 Jan 2023 01:26:23 +0000 https://ride.ict.usc.edu/?page_id=5490 Shows how to leverage commodity audio-visual sensing AI services through REST calls, using RIDE's common web services system.

The post Audio-Visual Sensing appeared first on RIDE.

]]>
Virtual Humans

Audio-Visual Sensing

Overview

Shows how to leverage commodity audio-visual sensing AI services through REST calls, using RIDE’s common web services system.

Page Contents

Example Face Image 2
ExampleFace

Purpose

Shows how to leverage commodity audio-visual sensing AI services through REST calls, using RIDE’s common web services system.

Leverages RIDE’s generic Sensing C# interface, where a (webcam) image is sent to a server and resulting analysis data is received. 

Initially supported service is Microsoft Azure Face, which provides:

  • Emotion values (e.g., anger, happiness, neutral)
  • Head values (e.g., pitch, roll, occlusions)
  • Characteristics (e.g., gender, age)

Note, Characteristics and Emotion values recently deprecated.

How to Use

Make sure you have a webcam set up and run the scene. Your webcam view should be seen at the top right. Click Cycle if you have multiple webcams.

The Single button sends a single webcam image to the server. Results are shown underneath.

The Start button starts the process of sending an image every second. Stop stops this process.

Scene Location & Name

\Assets\Ride\Examples\Services\Sensing\ExampleFace.unity

Setup Requirements 

The main script is ExampleFace.cs in the same folder.

Any Sensing option implements the ISensingSystem C# Interface. These systems provide the main building blocks to interface with a sensing service:

				
					
ISensingSystem m_azureFace;

The specific endpoint and authentication information is defined through RIDE’s configuration system:

				
					
RideConfigSystem m_configSystem = Globals.api.systemAccessSystem.GetSystem<RideConfigSystem>();
   string requestParameters = "returnFaceId=true&returnFaceLandmarks=false&returnFaceAttributes=age,gender,headPose,smile,facialHair,glasses,emotion,hair,makeup,occlusion,accessories,blur,exposure,noise";
   m_uriAzureFace = m_configSystem.config.azureFace.endpoint + "/face/v1.0/detect?" + requestParameters;
   var azureFaceComponent = new GameObject("AzureFaceSystem").AddComponent<AzureFaceSystem>();
   azureFaceComponent.m_uri = m_uriAzureFace;
   azureFaceComponent.m_endpointKey = m_configSystem.config.azureFace.endpointKey;
   m_azureFace = azureFaceComponent;

The Sensing system encapsulates the input into an SensingRequest object. This user input is sent through the RIDE common web services system. The results are encapsulated into an SensingResponse object. A provided callback function allows a client (in this case this ExampleFace) what specifically to do with the result. The Sensing system itself handles much of the work, so that the client only requires one line to send the user input:

				
					
Globals.api.systemAccessSystem.GetSystem<ISensingEmotionSystem>(m_azureFace.id).AnalyzeEmotions(m_imageData, OnCompleteEmotion);

Referenced by ExampleGroups script for group definitions.

The post Audio-Visual Sensing appeared first on RIDE.

]]> NLP Service Comparison https://ride.ict.usc.edu/support/documentation/examples/nlp-service-comparison/?utm_source=rss&utm_medium=rss&utm_campaign=nlp-service-comparison Tue, 13 Sep 2022 23:53:12 +0000 https://ride.ict.usc.edu/?page_id=5293 Demonstrates the integration of cloud-based Natural Language Processing services for comparison within a Q & A format.

The post NLP Service Comparison appeared first on RIDE.

]]>
Virtual Humans

NLP Service Comparison

Overview

Demonstrates the integration of cloud-based Natural Language Processing services for comparison within a Q & A format.

Page Contents

Example NLP Image 1
ExampleNLP

Purpose

Shows how to leverage commodity NLP AI services through REST calls, using RIDE’s common web services system.

Leverages RIDE’s generic NLP C# interface, primarily focused on question-answering interactions, with the principle generally working for user input and agent output. Optionally includes sentiment analysis and entity analysis.

Current Providers

  • Microsoft Azure Cognitive Service for Language
  • Amazon (AWS) Lex
  • Google DialogFlow
  • OpenAI GPT-3
  • OpenAI ChatGPT-4

How to Use

IMPORTANT

If you wish to use the ExampleNLP scene and related web services, you must update your local RIDE config file (ride.json). Please back-up any local changes to the file, including your terrain key. Next, restore your Config to default using the corresponding option in the Config debug menu at run-time, then reapply any customization and terrain key. Refer to the Config File page within Support for more information. 

Test the different types of inputs, different lengths of responses, and measure metrics as the average response time for both “hot” and “cold” services.

A service is said to be “cold” when the service requesting the NLP agent makes the very 1st request just after its initialization and deployment and the agent has not been used for a while (here leaving all the respective platform agents idle for >=5 minutes).

When the service requesting the NLP agent has already made very 1st request just after its initialization and deployment, any subsequent service request is considered “hot”.

Single Provider UI

  1. Click Cycle Providers button to cycle through currently available services.
  2. Input text in the bottom field and hit enter or click the Ask button.
  3. The side pane populates with the following information after entering a query:
    1. Response Time
    2. Text Analytics
    3. Entities
  4. If present, a custom or automatic answer will appear between the pane and input field.

Note that most services are domain specific, with just a handful of questions and answers authored, purely for demonstration purposes. Example question: “What is RIDE?” The exception is OpenAI GPT-3, which is a general purpose language model.

Ask the same question and see how the output differs.

Multiple Provider Comparison UI

  1. Click the Compare Providers button to toggle the live, side-by-side comparison interface.
  2. Input text in the bottom field and hit enter or click the Ask button. Any question will be sent to all 3 providers simultaneously.
  3. Each service has its own pane which populates with the following information after entering a query:
    1. Answer
    2. Response Time
    3. Text Analytics
    4. Entities

Scene Location & Name

Assets/Ride/Examples/NLP/ExampleNLP.unity

Setup Requirements 

The ExampleNLP scene utilizes a customizable UI and interchangeable service providers through canvas, scripts and prefabs. Explore the objects in the Hierarchy view for the scene inside the Unity editor and source for Ride.NLP via the API documentation.

The main script is ExampleNLP.cs in the same folder.

Any NLP option implements the INLPQnASystem C# Interface, which itself is based on INLPSystem. These systems provide the main building blocks to interface with an NLP service:

				
					
OpenAIGPT3System m_openAIGPT3;
var openAIGPT3Component = new GameObject("OpenAIGPT3System").AddComponent<OpenAIGPT3System>();
m_openAIGPT3 = openAIGPT3Component;

The specific endpoint and authentication information is defined through RIDE’s configuration system:

				
					
m_configSystems = Globals.api.systemAccessSystem.GetSystem<RideConfigSystem>();
openAIGPT3Component.m_uri = m_configSystems.config.openAI.endpoint;
openAIGPT3Component.m_authorizationKey = m_configSystems.config.openAI.endpointKey;

The NLP system encapsulates the user question into an NLPQnAQuestion or NLPRequest object. This user input is sent through the RIDE common web services system. The results are encapsulated into an NLPQnAAnswer  or NLPResponse object. A provided callback function allows a client (in this case this ExampleNLP) what specifically to do with the result. The NLP system itself handles much of the work, so that the client only requires one line to send the user question: 

				
					
m_openAIGPT3.AskQuestion(userInput, OnCompleteAnswer);

The post NLP Service Comparison appeared first on RIDE.

]]> API Functions VHMsg https://ride.ict.usc.edu/support/documentation/examples/api-functions-vhmsg/?utm_source=rss&utm_medium=rss&utm_campaign=api-functions-vhmsg Tue, 06 Apr 2021 05:32:56 +0000 https://ride.ict.usc.edu/?page_id=3539 Demonstrates how to setup a scene to use VHMsg (ActiveMQ wrapper) in RIDE.

The post API Functions VHMsg appeared first on RIDE.

]]>
Virtual Humans

API Functions VHMsg

Overview

Demonstrates how to setup a scene to use VHMsg (ActiveMQ wrapper) in RIDE.

Page Contents

Purpose

Demonstrates how to setup a scene to use VHMsg (ActiveMQ wrapper) in RIDE.

How to Use

Examine the example scene hierarchy to see which objects you need in order to be VHMsg compatible.

Scene Location & Name

Assets/Ride/Examples/ApiFunctions/ExampleApiFunctionsVHMsg.unity

Setup Requirements 

Add Assets/Ride/Prefabs/RideVHMsgManager.prefab to the scene. This enables the sending and receiving of VHMsgs.

Note, the service relies on the ActiveMQ protocol, which can be downloaded from the location specified in the scene.

The post API Functions VHMsg appeared first on RIDE.

]]> Speech Recognition https://ride.ict.usc.edu/support/documentation/examples/speech-recognition/?utm_source=rss&utm_medium=rss&utm_campaign=speech-recognition Tue, 06 Apr 2021 00:43:33 +0000 https://ride.ict.usc.edu/?page_id=3519 Demonstrates how to use Microsoft speech recognition in RIDE.

The post Speech Recognition appeared first on RIDE.

]]>
Virtual Humans

Speech Recognition

Overview

Demonstrates how to use Microsoft speech recognition in RIDE.

Page Contents

Example Speech Recognition Image
ExampleSpeechRecognition

Purpose

Demonstrates how to use Microsoft speech recognition in RIDE.

How to Use

  1. Hit Play
  2. Click on the Continuous speech button
  3. Talk into your microphone
  4. See that the words that you spoke appear on the UI

Scene Location & Name

Assets/Ride/Examples/Speech/SpeechRecognizer/ExampleSpeechRecognition.unity

Setup Requirements 

A microphone is required for this scene to function properly.
 
Add the Assets/Ride/Examples/Speech/SpeechRecognizer/SpeechManager.prefab to enable the service and Assets/Ride/Examples/Speech/SpeechRecognizer/SpeechRecognitionMenuobject.prefab into the scene in order to provide an interface for the user.
 
Reference ExampleSpeechRecognizer.cs to see how the speech recognizer service is setup.

The post Speech Recognition appeared first on RIDE.

]]> State Machine https://ride.ict.usc.edu/support/documentation/examples/state-machine/?utm_source=rss&utm_medium=rss&utm_campaign=state-machine Sat, 14 Nov 2020 01:52:50 +0000 https://ride.ict.usc.edu/?page_id=1840 Basic Agent state machine that can be modified as needed for simulations.

The post State Machine appeared first on RIDE.

]]>
Virtual Humans

State Machine

Overview

Basic Agent state machine that can be modified as needed for simulations.

Page Contents

Example State Machine Image
ExampleStateMachine

Purpose

Basic Agent state machine that can be modified as needed for simulations.

Features

  • Enter / Exit callbacks
  • Enter from / Exit to callbacks
  • OnUpdate callbacks
  • Fire Events with arbitrary parameters
  • Set permissions on which transitions are allowed for a state and the conditions of the transtions
  • Hierarchical

How to Use

Creating States

				
					
AgentStateMachine sm = new AgentStateMachine(agent.agentName, animatorWrapper, agent, agentSystem, worldStateSystem);
 
// Idle
sm.Configure(IdleState)
  .OnEnter(() => sm.animator.Play(IdleAnim01))
  .Permit((int)Trigger.Move, MoveState)
  ;
 
// Move
m.Configure(MoveState)
  .OnEnter(() => sm.animator.SetParameter(MoveParam, Mathf.Clamp01(agent.speed / agent.maxSpeed)))
  .OnUpdate(() => sm.animator.SetParameter(MoveParam, Mathf.Clamp01(agent.speed / agent.maxSpeed)))
  .OnExit(() => sm.animator.SetParameter(MoveParam, 0.0f))
  .Permit((int)Trigger.Idle, IdleState)
  ;
 
// Dead
sm.Configure(DeadState)
  .OnEnter(() => sm.animator.SetParameter(DeadParam, true))
  .OnExit(() => sm.animator.SetParameter(DeadParam, false))
  ;
 
// Crouch
sm.Configure(CrouchState)
  .OnEnter(() => sm.animator.SetParameter(StanceParam, 1))
  .OnExit(() => sm.animator.SetParameter(StanceParam, 0))
  ;
 
// Combat Engage
sm.Configure(CombatEngageState)
  .OnEnter(() => sm.animator.SetParameter(EngagedParam, true))
  .OnExit(() => sm.animator.SetParameter(EngagedParam, false))
  ;
 
// FireTwoHandedGunState
sm.Configure(FireGunState)
  .OnEnter(() => sm.animator.SetTrigger(FireParam))
  .SubstateOf(CombatEngageState)
  ;
 
 
sm.SetDefault(IdleState);
sm.Transition(IdleState);
Player Finite State Machine Image
PlayerFiniteStateMachine

RidePlayerFiniteStateMachine.drawio

Setting Agent States

				
					
Globals.api.agentSystem.SetAgentState(agent, StateMachineUtils.CrouchState);

Scene Location & Name

Assets/Ride/Examples/StateMachine/StateMachine.unity

The post State Machine appeared first on RIDE.

]]>