군집 지능 및 로봇 협업 응용(2025년)

Research on swarm intelligence and robotic collaboration: Swarm intelligence and robotic collaboration will break through the boundaries of individual intelligence and will be widely adopted across various industries.

The "Swarm Intelligence and Robotic Collaboration Application Report 2025" released by ResearchInChina analyzes and summarizes the definition, characteristics, core algorithms, core value, development history, technical architecture and key technologies, technology trends, challenges, key industry applications (including include intelligent warehousing and logistics, performing arts and entertainment, industrial manufacturing, consumer services, fire and rescue, etc.) and suppliers of swarm intelligence technology and robot collaborative applications.

Swarm intelligence (SI), also known as collective intelligence, refers to the method of generating intelligent performance that exceeds the capabilities of a single individual through the collaboration of multiple intelligent agents (such as humans, machines, and other intelligent systems) and resource integration. Its core idea is to achieve more efficient problem-solving, decision-making, or innovation by integrating the knowledge, experience, and judgment of individuals within a group. Swarm intelligence originates from the simulation of biological group behavior. It is a computational paradigm and intelligent mode in which a large number of simple individuals can emerge globally complex intelligent behaviors through local interaction and following simple rules without centralized control, such as ant colonies finding the shortest path and flocks of birds flying in sync.

Robotic collaboration refers to the process by which multiple robots of the same or different types work together under the unified collaborative control system, based on real-time perception data and preset rules, to complete complex tasks that a single robot cannot accomplish independently, achieving a "1+1>2" synergy. These robots can be industrial-grade equipment such as industrial robotic arms and AGVs (automated guided vehicles), or civilian equipment such as service robots and medical robots.

Swarm intelligence technology is the "collaborative brain" for robotic collaboration. Swarm intelligence provides the core logic for "how to collaborate efficiently" for multi-robot systems. For example, 1. the distributed control mechanism of swarm intelligence can avoid the impact of "single point failure" on the overall system operation and improve collaborative robustness; 2. the local information interaction mechanism of swarm intelligence reduces information transmission costs. Robots do not need to obtain all global information. They can achieve optimal global task allocation by exchanging position information and task status with neighboring robots. Robotic collaboration is a key scenario for the implementation of swarm intelligence technology and the solution of complex real-world problems, ultimately contributing to the optimization of swarm intelligence technology.

Swarm intelligence and robotic collaboration can break through the boundaries of individual capabilities.

Compared to individual intelligence, swarm intelligence and robotic collaboration can improve efficiency, expand boundaries, enhance system fault tolerance, and reduce costs and energy consumption.

Stand-alone intelligence focuses on "enhancing individual capabilities". All perception, decision-making and actuation modules are integrated on a single robot, which independently handles problems by relying on its own sensors (cameras, radar) and algorithms, without relying on external devices or other robots. The core of swarm intelligence and robotic collaboration is "optimizing group efficiency," where multiple robots are connected through a communication network and work together to complete tasks that a single robot cannot accomplish. Each robot may only be responsible for a part of the work, achieving a "1+1>2" synergy through data sharing and task allocation.

Key technologies for swarm intelligence and robotic collaboration: task allocation, collaborative control, and real-time communication

Compared to individual intelligence, the key technologies of swarm intelligence and robotic collaboration mainly revolve around "how to enable multiple individuals to form an efficient and orderly whole." The core is to handle three major challenges: task division, behavior coordination, and information sharing. Key technologies include:

1.Dynamic task allocation and scheduling: Individual intelligence only needs to "decide what to do", while collaborative systems break down complex tasks into sub-tasks and allocate them reasonably to each robot. At the same time, in response to task changes, the allocation solution should be continuously adjusted in uncertain environments (such as temporary addition or removal of tasks, robot failures), rather than a one-time static assignment.

2.Path planning and obstacle avoidance: When multiple robots work in the same space, path conflicts (such as collisions) or resource competition (such as competing for the same charging spot) are likely to occur. Cooperative control is necessary to ensure orderly behavior. Obstacle avoidance strategies use path planning algorithms to plan non-overlapping paths for each robot, or use time scheduling (such as having robots pass through narrow passages in sequence) to avoid conflicts. In industrial settings, "digital twin" technology will also be introduced to rehearse robot movements in a virtual environment, allowing for the early detection and resolution of conflicts.

3.Collaborative control: This includes motion synchronization control and force/torque collaborative control. Essentially, it aims to ensure that the position, velocity, force, and other parameters of multiple robots remain consistent according to preset rules when performing tasks, so as to achieve efficient collaboration. Collaborative control revolves around several core objectives, including time synchronization, trajectory synchronization, and force/torque synchronization, to ensure the accuracy and stability of collaboration.

4.Real-time communication: This is the foundation for efficient robotic collaboration. It is responsible for data transmission and interaction between devices and between devices and systems, including location information, task progress, and fault information.

Swarm intelligence and collaborative robot application: will be widely adopted across all industries

The application of swarm intelligence and robotic collaboration spans various industries, including warehousing and logistics, entertainment, industrial manufacturing, commercial consumer services, fire and rescue, security inspection, agriculture, and healthcare. Examples include intelligent sorting and warehousing in warehousing and logistics, drone art, robot stage performances, collaborative assembly in manufacturing, collaborative food delivery in large restaurants/hotels, and air-ground collaborative rescue.

Currently,the application of swarm intelligence and robotic collaboration in the field of intelligent warehousing and logistics is relatively mature, covering cargo loading/unloading/handling, cargo classification/sorting, collaborative handling of large items, stacking and warehousing, cross-warehouse scheduling, flexible production lines, and last-mile delivery. For example, the HaiQ Intelligent Warehouse Management Software Platform of Hai Robotics realizes "goods-to-person" picking through a variety of equipment such as bin robots, lurking autonomous mobile robots (AMRs), and intelligent forklift robots, and completes collaborative operations such as inbound and outbound, inventory, sorting, and handling.

The application of swarm intelligence and robotic collaboration in the field of drone art is maturing, with China leading the world in this field and repeatedly breaking Guinness World Records in terms of an increasing number of and scale of performances.

In September 2024, DAMODA broke two Guinness World Records in Shenzhen with 10,197 drones by controlling the most drones simultaneously with a single computer and forming the largest number of aerial patterns.

In April 2025, DAMODA set a new Guinness World Record for the most drones forming aerial patterns with a performance of 10,518 drones in Ho Chi Minh City, Vietnam. The light show celebrated the 50th anniversary of the Liberation of the South and National Reunification.

In June 2025, DAMODA set a Guinness World Record for the "Largest aerial image formed by multirotors/drones" with 11,787 drones in Chongqing.

In October 2025, Highgreat Technology successfully challenged two Guinness World Records at the 17th Liuyang Fireworks Culture Festival in Hunan Province. It broke the world record for "most drones simultaneously by a single computer" with 15,947 drones, and also broke the world record for "most fireworks launched by drones in the air" with 7,496 fireworks.

The application of swarm intelligence and robotic collaboration has shifted from "single-mode robotic collaboration" to "multimodal robotic collaboration" and from "structured scenarios" to "complex dynamic scenarios". In the future, with the support of 5G/6G communications, digital twins, brain-inspired computing and other technologies, swarm intelligence and robotic collaboration will empower all walks of life and facilitate deeper and larger-scale application. Unmanned factories, unmanned restaurants, and unmanned farms are coming soon, promoting changes in social production and lifestyles.

Table of Contents

Chapter 1 Overview of Swarm Intelligence and Robotic Collaboration

• 1.1 Introduction to Swarm Intelligence and Robotic Collaboration
  • 1.1.1 Swarm Intelligence Technology Originates from the Simulation of Biological Group Behavior
  • 1.1.2 Algorithms of Swarm Intelligence Technology
  • 1.1.3 Genetic Algorithms and Swarm Intelligence are Combined to Solve Complex Collaborative Problems
  • 1.1.4 Core Characteristics of Swarm Intelligence Technology
  • 1.1.5 Swarm Intelligence Is the "Brain" of Robot Collaboration
  • 1.1.6 The Core Value of Robotic Collaboration Lies in Higher Operational Efficiency and Wider Operational Boundaries
  • 1.1.7 Essential Difference between Robotic Collaboration and Standalone Intelligence: Breaking through the Boundaries of Individual Capabilities through Collaboration
  • 1.1.8 Development History of Robot Collaboration
• 1.2 Key Technologies for Swarm Intelligence and Robotic Collaboration
  • 1.2.1 Technology Architecture
  • 1.2.2 Key Technology: Task Allocation
  • 1.2.3 Key Technologies: Path Planning and Obstacle Avoidance
  • 1.2.4 Key Technology: Cooperative Control
  • 1.2.5 Key Technology: Communication
  • 1.2.6 System Software Architecture
• 1.3 Trends in Swarm Intelligence and Robot Collaboration Technologies
  • 1.3.1 In-depth Application of Edge Computing
  • 1.3.2 Fusion of Foundation Models
  • 1.3.3 Cross-modal Collaboration
  • 1.3.4 Deepened Human-Machine Integration
• 1.4 Development Challenges for Swarm Intelligence and Robotic Collaboration
  • 1.4.1 Hardware
  • 1.4.2 Challenge: Technology
  • 1.4.3 Challenge: Practical Application and Deployment
  • 1.4.4 Challenge: Talents
  • 1.4.5 Challenge: Security
  • 1.4.6 Challenge: Ethics and Attribution of Responsibility
  • 1.4.7 Challenge: Policies and Standards
  • 1.4.8 Standardization and Platformization Process of Swarm Intelligence and Robotic Collaboration
• 1.5 Application Fields of Swarm Intelligence and Robotic Collaboration

Chapter 2 Application and Suppliers of Swarm Intelligence and Robotic Collaboration in Warehousing and Logistics

• 2.1 Application of Multi-robot Collaboration Based on Swarm Intelligence in Warehousing and Logistics
  • 2.1.1 Panoramic View of the Smart Warehousing Industry Chain
  • 2.1.2 Development History of the Smart Warehousing Industry
  • 2.1.3 Application of Multi-robot Collaboration Based on Swarm Intelligence Improves Warehousing and Logistics Efficiency in Multiple Dimensions
  • 2.1.4 Application Scenarios of Multi-robot Collaboration Based on Swarm Intelligence in Warehousing and Logistics
  • 2.1.5 Intelligent Warehousing and Logistics System Architecture of Multi-robot Collaboration Based on Swarm Intelligence
  • 2.1.6 Application Cases of Multi-robot Collaboration Based on Swarm Intelligence in Warehousing and Logistics
• 2.2 Supplier - Geek+
  • 2.2.1 Profile
  • 2.2.2 Revenue
  • 2.2.3 Development History
  • 2.2.4 Founding Team
  • 2.2.5 Equity Structure
  • 2.2.6 Robots
  • 2.2.7 Smart Warehouse Software System
  • 2.2.8 Solutions and Customer Cases
  • 2.2.9 Continuous Upgrade of Warehouse Automation Algorithm Technology
• 2.3 Supplier - Quicktron
  • 2.3.1 Profile
  • 2.3.2 Overview of Mobile Robot Hardware Products
  • 2.3.3 Software System
  • 2.3.4 Solution: QuickBin Intelligent Robot Solution
  • 2.3.5 Solution: Intelligent Picking
  • 2.3.6 Solution: Intelligent Material Handling
  • 2.3.7 Customer Cases
  • 2.3.8 Overseas Layout
  • 2.3.9 Strategic Cooperation with BZS
  • 2.3.10 Dynamics
• 2.4 Supplier - Hai Robotics
  • 2.4.1 Profile
  • 2.4.2 Robots
  • 2.4.3 HaiQ Intelligent Warehouse Management Software Platform
  • 2.4.4 Intelligent Warehousing Solution: HaiPick System
  • 2.4.5 Carton-to-People Automated Picking Solution
  • 2.4.6 Multi-format Mixed Storage and Picking Solution
  • 2.4.7 Ultra-high-density Intelligent Picking Solution
  • 2.4.8 Production and Warehousing Integrated Solution
  • 2.4.9 Typical Solution Application Cases in Various Industries
• 2.5 Supplier - IPLUSMOBOT
  • 2.5.1 Profile
  • 2.5.2 Robots
  • 2.5.3 Intelligent Warehousing System Hardware
  • 2.5.4 Intelligent Logistics and Warehousing Software System
  • 2.5.5 Application Cases of Smart Warehousing Solutions in Different Industries
  • 2.5.6 Partners
  • 2.5.7 Dynamics
• 2.6 Supplier - Megvii
  • 2.6.1 Profile
  • 2.6.2 Smart Logistics Hardware: 3A
  • 2.6.3 Warehousing and Logistics Software Platform
  • 2.6.4 Smart Logistics Warehousing Solution
• 2.7 Supplier - KSEC Intelligent Technology
  • 2.7.1 Profile
  • 2.7.2 Revenue
  • 2.7.3 Intelligent Equipment
  • 2.7.4 Logistics and Warehousing Software and Automated Control System
  • 2.7.5 Intelligent Logistics System
  • 2.7.6 Customer Cases in Logistics and Warehousing
  • 2.7.7 Joint Laboratory with Kunming University
• 2.8 Supplier - Mooe Robot
  • 2.8.1 Profile
  • 2.8.2 Core Technology
  • 2.8.3 Intelligent Transport Vehicle
  • 2.8.4 Logistics Transit Warehouse Solution
  • 2.8.5 Supermarket Distribution Warehouse Solution
  • 2.8.6 Manufacturing Parts Warehouse Solution
  • 2.8.7 Partners

Chapter 3 Application and Suppliers of Swarm Intelligence and Robotic Collaboration in Entertainment Performances

• 3.1 Application of Swarm Intelligence and Robotic Collaboration in Drone Art
  • 3.1.1 Introduction to Drone Art
  • 3.1.2 Drone Art ndustry Chain
  • 3.1.3 Drone Art System Hardware Architecture
  • 3.1.4 Core Development Trends of Drone Art
  • 3.1.5 Challenges for Drone Art
  • 3.1.6 Business Model and Market Size of Drone Art
  • 3.1.7 Major Players in the Drone Art Field
• 3.2 Application of Swarm Intelligence and Robotic Collaboration in Stage Performance
  • 3.2.1 Overview
  • 3.2.2 Challenges
  • 3.2.3 Prospect
  • 3.2.4 Application Scenarios and Cases
• 3.3 Supplier - Highgreat Technology
  • 3.3.1 Profile
  • 3.3.2 Products and Solutions
  • 3.3.3 Typical Drone Art Projects
  • 3.3.4 Performance-type Drones
  • 3.3.5 Latest Updates on Drone Art
• 3.4 Supplier - DAMODA
  • 3.4.1 Profile
  • 3.4.2 Drones and Application Scenarios
  • 3.4.3 Performance-type Drones
• 3.5 Supplier - CroStars
  • 3.5.1 Profile
  • 3.5.2 Representative Drone Art Projects
  • 3.5.3 C5 Intelligent Drone Art System
• 3.6 Supplier - EFY Technology
  • 3.6.1 Profile
  • 3.6.2 Products and Solutions
  • 3.6.3 Drone Art
  • 3.6.4 Partners and Latest Development Dynamics
• 3.7 Supplier - EHang
  • 3.7.1 Profile
  • 3.7.2 Drones
  • 3.7.3 Drone Art

Chapter 4 Application Cases of Swarm Intelligence and Robotic Collaboration in Other Fields

• 4.1 Application of Swarm Intelligence and Robotic Collaboration in Industrial Manufacturing
  • 4.1.1 Overview
  • 4.1.2 Development History
  • 4.1.3 Industry Chain
  • 4.1.4 Typical Application Scenarios
  • 4.1.5 Challenges and Mitigation Strategies
  • 4.1.6 Development Trends
  • 4.1.7 Application Cases
• 4.2 Industrial Manufacturing Supplier - UBTECH
  • 4.2.1 Profile
  • 4.2.2 Revenue
  • 4.2.3 Robots
  • 4.2.4 Development Strategy and Planning
  • 4.2.5 Core Technology System
  • 4.2.6 Application Scenario of Multi-robot Collaboration: Smart Factory
  • 4.2.7 Partners
  • 4.2.8 Dynamics
• 4.3 Applications of Swarm Intelligence and Robotic Collaboration in Consumer Services
  • 4.3.1 Overview
  • 4.3.2 Development History
  • 4.3.3 Consumer Service Robot Market Competition Landscape and Swarm Intelligence Deployment
• 4.3.4 Challenges and Mitigation Strategies
  • 4.3.5 Development Trends
  • 4.3.6 Application Cases
• 4.4 Consumer Services Supplier - Yunji Technology
  • 4.4.1 Profile
  • 4.4.2 Revenue
  • 4.4.3 Robots
  • 4.4.4 Application Scenario of Multi-robot Collaboration: Hotel
  • 4.4.5 Partners
  • 4.4.6 Dynamics
• 4.5 Consumer Services Supplier - Gausium
  • 4.5.1 Profile
  • 4.5.2 Products
  • 4.5.3 Core Technology: Robotics Technology
  • 4.5.4 Intelligent Cloud Platform
  • 4.5.5 Remote Control Via Mobile App, Fully Autonomous Operation
  • 4.5.6 Application Scenarios of Commercial Cleaning Solutions
  • 4.5.7 Application Cases of Multi-robot Collaboration in Commercial Cleaning Services
• 4.6 Consumer Services Supplier - Keenon
  • 4.6.1 Profile
  • 4.6.2 Robots
  • 4.6.3 Solution: Catering
  • 4.6.4 Solution: Hotel
  • 4.6.5 Application Cases of Multi-robot Collaboration
  • 4.6.6 Partners
• 4.7 Consumer Services Supplier - Pudu Robotics
  • 4.7.1 Profile
  • 4.7.2 Robots
  • 4.7.3 Industry Solutions
  • 4.7.4 Application Cases of Multi-robot Collaboration
  • 4.7.5 Partners
  • 4.7.6 Dynamics
• 4.8 Consumer Services Supplier - Excelland Robotics
  • 4.8.1 Profile
  • 4.8.2 Products
  • 4.8.3 Solutions
• 4.9 Application of Swarm Intelligence and Robotic Collaboration in Fire and Rescue
  • 4.9.1 Overview
  • 4.9.2 Development History
  • 4.9.3 Major Suppliers of Fire and Rescue Robots
  • 4.9.4 Challenges and Mitigation Strategies
• 4.9 Development Trends
  • 4.9.6 Application Cases
• 4.10 Application of Swarm Intelligence and Robotic Collaboration in Facility Inspection
  • 4.10.1 Overview
  • 4.10.2 Development History
  • 4.10.3 Commercial Model of Facility Inspection Robots
  • 4.10.4 Deployment of Facility Inspection Robot Suppliers
  • 4.10.5 Challenges and Mitigation Strategies
  • 4.10.6 Development Trends
  • 4.10.7 Application Cases
• 4.11 Application of Swarm Intelligence and Robotic Collaboration in Agriculture
  • 4.11.1 Overview
  • 4.11.2 Development History
  • 4.11.3 Competitive Strategies of Robot Suppliers in Agriculture
  • 4.11.4 Deployment of Agricultural Robot Suppliers
  • 4.11.5 Challenges and Mitigation Strategies
• 4.11 Development Trends
  • 4.11.7 Application Cases