Product Overview
D100 is designed to help humanoid robots move beyond basic hardware demonstration and become interactive service assistants in real-world environments. Through voice interaction, task workflow configuration, knowledge base setup, and visual recognition, the robot can perform reception, explanation, interaction, movement commands, and customized service tasks.
The system supports both web-based backend management and app-based operation, making it easier for users to configure content, manage scenarios, control the robot, and monitor robot vision.
Core Functions
Action & Dance Library
The system includes a built-in action and dance library for humanoid robot performance and interactive scenarios.
Supported Actions Include
- Handshake
- Wave
- Goodbye gesture
- Double-hand flying kiss
- Boxing action set
- Ultraman beam gesture
- High five
- Salute
- Other humanoid actions
Dance Performances Include
- Gong Xi Fa Cai
- Xi Shua Shua
- Phoenix Legend dance
- Tai Chi performance
- Other customized performance actions
Voice Interaction Module
The voice interaction module enables the robot to communicate with users, trigger actions by voice commands, and answer questions based on customized knowledge content.
The system uses noise reduction and directional audio pickup technologies to capture the target speaker more accurately in noisy environments.
Key Capabilities
- Voice wake-up
- Voice-based robot action control
- Voice command for movement
- Knowledge-base Q&A
- Customized reception scripts
- Interrupt and wake-up during conversation
- Multi-language configuration
Language Interaction Versions
Version 1.0
Version 1.0 supports multiple language configurations, including Chinese and English. These two languages are currently available free of charge. Other languages may require additional third-party service fees depending on the customer’s needs.
This version uses a speech recognition, speech synthesis, and language model architecture.
Version 2.0
Version 2.0 includes the basic functions of Version 1.0 and adds end-to-end voice interaction. It supports real-time switching between Chinese and English and can also support some dialects, such as Shaanxi dialect and Sichuan dialect.
It can support singing, emotional speech expression, and more natural voice options. Compared with Version 1.0, it provides faster response speed and a more human-like interaction experience.
Customized Reception Agent
The system supports customized robot voice agents for different reception events, exhibitions, or service scenarios. Users can configure different greeting scripts, background information, and interaction content according to the event.
This allows the robot to flexibly complete reception, explanation, and interactive communication tasks.
Voice-Controlled Actions and Movement
Users can control the robot through voice commands to perform actions, dances, and small-range movements.
Supported Commands Include
- Action performance
- Dance performance
- Move forward
- Move backward
- Move left
- Move right
- Other fixed small-range movement commands
Autonomous Navigation Module
No Remote Controller Required
The D100 system supports autonomous navigation-related functions, allowing the robot to perform predefined guide, reception, and task workflows without relying only on manual remote control.
Hardware Configuration
The system can be equipped with supporting hardware modules to improve voice interaction, audio output, and visual perception.
Standard Hardware Configuration
- Bluetooth speaker: JBL CLIP 5 Bluetooth speaker
- Microphone: DJI dual-channel microphone
- Vision module: Modified hat accessory with eyes and camera
Customized Task Workflow
Users can customize guide workflows, reception workflows, and other task flows according to their own application requirements.
Workflow Configuration Supports
- Fixed-point explanation content
- Customized robot actions
- Photo-taking tasks
- Video recording tasks
- Pause workflow
- Continue workflow
- End workflow
- Loop workflow
Third-Party Interface Integration
The system supports third-party interface integration within task workflows. This allows the robot to connect with external systems during guide or reception tasks.
Supported Integration Examples
- Large screen control
- Lighting control
- System message sending
- Customized API integration
Note: Third-party interface integration requires separate customization and is not included in the standard package.
Web Backend Management
The system provides a web-based management backend that allows users to remotely configure, monitor, and manage robot application content.
Web Backend Functions Include
- Scenario agent configuration
- Knowledge base content upload
- Task workflow management
- Remote configuration
- System monitoring
- Content management
App Operation
The system provides a simple and easy-to-use app operation interface, allowing users to control robot tasks and voice interaction functions.
App Functions Include
- Robot task command execution
- Voice interaction control
- View robot visual feed
- Basic robot operation
Visual Recognition and Analysis
The system supports facial recognition, pedestrian recognition, and visual analysis capabilities. In reception scenarios, the robot can proactively greet visitors based on recognition results.
The system can also connect with visual large models to analyze the current scene and provide intelligent visual understanding for specific application scenarios.
Large Model Configuration
The system supports large model configuration according to project needs, including language large models and visual large models.
This enables the robot to support more intelligent interaction, visual understanding, and scenario-based response.
Multi-Robot Group Control
The system supports group control for multiple robots, allowing several robots to perform unified actions, dances, and voice broadcasts.
This function is suitable for exhibitions, performances, commercial events, and large-scale interactive scenarios.
Operation, Maintenance and Deployment
Software Operation and Maintenance
Annual software operation and maintenance service is available as an optional service.
Service Includes
- Software issue fixing
- Software upgrade if new functions are available
- Cloud service
- First-year service can be included
Reference fee: RMB 10,000 per year.
Large Model Token Package
The large model token package is used for AI model interaction and continuous intelligent response.
Available annual packages may include RMB 6,000, RMB 12,000, RMB 24,000 and other options. The current quotation can use a RMB 5,000 package, and additional tokens can be recharged if usage is insufficient.
Reference: RMB 6,000 per year includes 10 million tokens.
On-Site Deployment Service
On-site deployment service includes one technical engineer for up to 4 days.
On-Site Deployment Includes
- Mapping
- Point setting
- Task workflow configuration
- System training
- Navigation debugging
- Voice interaction debugging
Optional Value-Added Services
Value-Added Service 1: Mini Program for Visitors
A visitor-side mini program can be added to support interactive Q&A, action and dance interaction, and other visitor-facing functions.
It is suitable for scenarios that require large-scale interaction between general visitors and robots, such as museums, hospitals, science museums, and public venues.
Value-Added Service 2: Private Software Deployment
Private software deployment is available for customers with higher data security or independent system management requirements.
Private Deployment Includes
- Software private deployment authorization
- Voice service deployment implementation
- Backend service deployment implementation
- On-site operation and maintenance implementation
Note: Private deployment is only available as an add-on service after purchasing the basic package.
Value-Added Service 3: PPT Teaching and Explanation
The PPT teaching and explanation function enables humanoid robots to act as teaching or presentation assistants.
Main Capabilities
- Before the lecture starts, the robot can visually scan the classroom and interact with students.
- During the lecture, the robot can teach autonomously, automatically turn PPT pages, and keep the spoken content aligned with the PPT content.
- If students ask questions during the lecture, the robot can pause the lecture, interact with students, answer questions, and then return to the teaching workflow.
Value-Added Service 4: Multimodal AI Function
The multimodal function allows the humanoid robot to connect with multimodal large models and support visual understanding-based natural voice interaction.
The robot can perceive its surroundings through cameras, recognize objects, understand scenes, identify people, make task judgments, and respond through voice.
Application Examples
Safety Supervision
In safety supervision scenarios, the robot can follow predefined steps to perform visual recognition and judgment. When abnormalities are detected, the robot can provide voice reminders or perform follow-up responses.
Intelligent Reception
The agent can import images, documents, and customer information in advance, allowing the robot to have short-term visual memory and contextual understanding.
For example, before a customer visit, the customer profile can be uploaded into the robot system. When the customer appears at the entrance, the robot can recognize the customer, call the customer by name, and complete reception, introduction, guidance, and interaction according to the preset process.
Recommended Applications
- Exhibition halls
- Corporate showrooms
- Museums
- Science and technology museums
- Schools and laboratories
- Hospitals and public service spaces
- Commercial reception areas
- Large-scale events and performances
- Multi-robot performance scenarios
What You Get
- D100 Embodied AI System Software
- Built-in action and dance library
- Voice interaction module
- Customized knowledge base Q&A
- Customized reception agent
- Voice command control
- Autonomous navigation task workflow
- Web backend management
- App-based operation
- Visual recognition and analysis
- Large model configuration
- Multi-robot group control
- Optional on-site deployment
- Optional private deployment
- Optional PPT teaching function
- Optional multimodal AI function
Notes
- Robot hardware is not included in the D100 software package and needs to be purchased separately if the customer does not already have a robot platform.
- Third-party interface integration requires separate customization and quotation.
- Token usage, annual service renewal, private deployment, and on-site travel expenses may be quoted separately based on project requirements.
- Some third-party language services may generate additional fees.
- Private deployment is only available after purchasing the basic system package.
Call to Action
Tell us your robot model, application scenario, deployment location, language requirements, and optional function needs. Our team will recommend the most suitable D100 system configuration for your project.
Request a Quote