4. Multimodal Visual Understanding and Voice Interaction

Note: The Raspberry Pi 5 1GB without a large model package cannot run. Due to performance limitations, the 2GB and 4GB versions cannot run offline. You can refer to the tutorial for online large models.

1. Concept Introduction

1.1 What is "Visual Understanding"?

In the largemodel project, the multimodal visual understanding feature enables robots to go beyond simply "seeing" a matrix of pixels and truly "understand" the content, objects, scenes, and relationships within an image. This is like giving the robot a pair of thinking eyes.

The core tool for this feature is seewhat. When a user issues a command such as "see what's here," the system invokes this tool, triggering a series of background operations that ultimately provide the user with AI-generated analysis of the live image in natural language.

1.2 Implementation Principles

The basic principle is to feed two different types of information—images (visual information) and text (linguistic information)—into a powerful multimodal large model (such as LLaVA).

1. Image Encoding: The model first uses a visual encoder to convert the input image into a computer-interpretable numerical vector that captures features such as color, shape, and texture.

2. Text Encoding: Simultaneously, the user's question (e.g., "What's on the table?") is also converted into a text vector.

3. Cross-modal Fusion: The most critical step is to fuse the image and text vectors in a special "attention layer." Here, the model learns to "focus" on the parts of the image relevant to the question. For example, when asked about the word "table," the model will pay more attention to areas of the image that match the characteristics of a table.

4. Answer Generation: Finally, a large language model (LLM) generates a descriptive text answer based on this fused information.

Simply put, it uses text to highlight corresponding parts of the image, and then describes the highlighted parts verbally.

2. Code Analysis

Key Code

1. Tool Layer Entry (largemodel/utils/tools_manager.py)

The seewhat function in this file defines the tool's execution flow.

​x
# From largemodel/utils/tools_manager.py

class ToolsManager:
    # ...

    def seewhat(self):
        """
        Capture camera frame and analyze environment with AI model.
        
        :return: Dictionary with scene description and image path, or None if failed.
        """
        self.node.get_logger().info("Executing seewhat() tool")
        image_path = self.capture_frame()
        if image_path:
            # Use isolated context for image analysis. 
            analysis_text = self._get_actual_scene_description(image_path)

            # Return structured data for the tool chain. 
            return {
                "description": analysis_text,
                "image_path": image_path
            }
        else:
            # ... (Error handling)
            return None

    def _get_actual_scene_description(self, image_path, message_context=None):
        """
        Get AI-generated scene description for captured image.
        
        :param image_path: Path to captured image file.
        :return: Plain text description of scene.
        """
        try:
            # ... (Building Prompt)
            
            # Force use of a plain text system prompt with a clean, one-time context.
            simple_context = [{
                "role": "system",
                "content": "You are an image description assistant. ..."
            }]

            result = self.node.model_client.infer_with_image(image_path, scene_prompt, message=simple_context)
            # ... (Processing results)
            return description
        except Exception as e:
            # ...

2. Model interface layer(largemodel/utils/large_model_interface.py)

The infer_with_image function in this file is the unified entry point for all image understanding tasks. It is responsible for calling the specific model implementation according to the configuration.

xxxxxxxxxx
# From largemodel/utils/large_model_interface.py

class model_interface:
    # ...
    def infer_with_image(self, image_path, text=None, message=None):
        """Unified image inference interface. """
        # ... (Prepare Message)
        try:
            # Determine which specific implementation to call based on the value of self.llm_platform
            if self.llm_platform == 'ollama':
                response_content = self.ollama_infer(self.messages, image_path=image_path)
            elif self.llm_platform == 'tongyi':
                # ... Logic for calling the Tongyi model
                pass
            # ... (Logic of other platforms)
        # ...
        return {'response': response_content, 'messages': self.messages.copy()}

Code Analysis

This feature's implementation involves two main layers: the tool layer defines the business logic, and the model interface layer is responsible for communicating with the large language model. This layered design is key to achieving platform versatility.

1. Tool Layer (tools_manager.py):

   • The seewhat function is the core business of the visual understanding function. It encapsulates the entire "seeing" action process: first, it calls the capture_frame method to obtain an image, then calls _get_actual_scene_description to prepare a prompt for the model to analyze the image.

   • The most critical step is calling the infer_with_image method of the model interface layer. It does not care about the underlying model; it only passes the two core data elements, "image" and "analysis instructions," to the model interface layer.

   • Finally, it packages the analysis results (plain text descriptions) received from the model interface layer into a structured dictionary and returns them. This allows upper-layer applications to easily use the analysis results.

2. Model Interface Layer (large_model_interface.py):

   • The infer_with_image function acts as a "dispatching center." Its primary responsibility is to check the current platform configuration (self.llm_platform) and, based on the configuration, dispatch tasks to specific handlers (such as ollama_infer or tongyi_infer).

   • This layer is key to adapting to different AI platforms. All platform-specific operations (such as data encoding and API call formats) are encapsulated within their respective handlers.

   • In this way, the business logic code in tools_manager.py remains unchanged to support a variety of different large-model backend services. It simply interacts with the unified, stable infer_with_image interface.

In summary, the seewhat tool's execution flow demonstrates a clear separation of responsibilities: ToolsManager defines the "what" (acquiring an image and requesting analysis), while model_interface defines the "how" (selecting the appropriate model platform based on the current configuration and interacting with it). This makes the tutorial's parsing universal; the core code logic remains consistent regardless of whether the user is online or offline.

3.1 Configuring the Offline Large Model

3.1.1 Configuring the LLM Platform(yahboom.yaml)

This file determines which large model platform the model_service node loads as its primary language model.

First, enter the Docker container by entering the command in the terminal:

xxxxxxxxxx
./ros2_docker.sh

If you need to enter other commands in the same Docker container later, simply enter ./ros2_docker.sh again in the host terminal.

1. Open the file in the terminal:

   xxxxxxxxxx
   vim ~/yahboom_ws/src/largemodel/config/yahboom.yaml
   

2. Modify/Confirm llm_platform:

   xxxxxxxxxx
   model_service:                          #Model server node parameters
     ros__parameters:
       language: 'zh'                      #Large Model Interface Language
       useolinetts: True                   #This item is invalid in text mode and can be ignored
   
       # Large model configuration
       llm_platform: 'ollama'              # Key: Make sure it's 'ollama'
       regional_setting : "China" 
   

3.1.2 Configuring the Model Interface (large_model_interface.yaml)

This file defines which visual model to use when the ollama platform is selected.

1. Open the file in a terminal.

xxxxxxxxxx
vim ~/yahboom_ws/src/largemodel/config/large_model_interface.yaml

2. Find the Ollama-related configuration

xxxxxxxxxx
#.....
## Offline Large Language Models
# Ollama Configuration
ollama_host: "http://localhost:11434"  # Ollama server address
ollama_model: "llava"            # Key: Change this to the multimodal model you downloaded, such as "llava"
#.....

Note: Please ensure that the model specified in the configuration parameters (e.g., llava) can handle multimodal input.

3.2 Starting and Testing the Function

Note: Using a model with a small number of parameters or when running at a very low memory usage will result in poor performance. For a better experience with this feature, please refer to the corresponding section in <Online Large Model (Text Interaction)>.

1. Start the largemodel main program: Open a terminal, enter the Docker container, and run the following command:

   xxxxxxxxxx
   ros2 launch largemodel largemodel_control.launch.py
   

2. After successful initialization, say the wake-up word and begin asking questions: "What do you see?" or "Describe your current environment."

3. Observe the Results: In the first terminal where you run the main program, you will see log output indicating that the system received the text command, invoked the seewhat tool, and ultimately printed out the text description generated by the LLaVA model. The speaker will also announce the generated results.

4. Common Problems and Solutions

4.1 Very Slow Responses

Problem: After asking a question, it takes a long time for the voice response to arrive. Solution: Multimodal models have a much higher inference cost than text-only models, so higher latency is expected.

1. Use a Smaller Model: In large_model_interface.yaml, try using a lighter multimodal model.