EXPLORINEER
en

KR — ZDNet Korea

Learning by Digging in Virtual Space: HD Hyundai Accelerates Development of Unmanned Excavators

Robotics3 min read

HD Hyundai Site Solutions has won a Korean government project to build a virtual test space for unmanned excavators. The space copies how machines move and how soil reacts, so AI can learn to dig before it runs on real equipment.

What happened

HD Hyundai Site Solutions was chosen to lead a national project from the Ministry of Trade, Industry and Energy. The project will build a digital twin platform, which is a computer copy of a real machine and its surroundings. The platform will use high-precision simulation to help develop AI that runs excavators without a driver. The project runs until December 2029.

Key facts

  • Total project budget: 6.33 billion won (about 633 million won in the source's unit: 63억 3000만원).
  • Runs until December 2029.
  • Consortium: HD Hyundai Site Solutions, Simjee, the Korea Construction Equipment Research Institute, the Korea Institute of Industrial Technology, and the Korea Construction Equipment Industry Association.
  • Machines covered: excavators, wheel loaders, and articulated dump trucks.

Why a virtual space is needed

Testing self-driving machines on real job sites is slow and risky. It takes many machines and special conditions, and it can be unsafe. A virtual space lets engineers test many situations quickly. The team will first check the self-driving skills in simulation, then compare the results with data from real machines to make them more accurate.

Why it matters

Construction sites around the world are short of skilled workers and need better safety. If unmanned machines work well, they could help fill those gaps. HD Hyundai Site Solutions says this project will grow its AI and digital business. It also plans to use data from its past field tests to help the technology reach the market.

What to watch

  • Whether the simulation matches results from real machines.
  • How the parts database standards are set and shared.
  • Field tests and scenario checks led by HD Hyundai Site Solutions.
  • Whether the technology moves toward commercial sales before the project ends in 2029.

Same story, different eyes

More in this topic

RoboticsVnExpress

Guardian Robot Can Lift Cars and Disarm Attackers

Unitree Robotics of China showed its H2-X humanoid guardian robot in a video released on October 21, demonstrating disarming an armed intruder and lifting a car to rescue a trapped victim. The company has not disclosed key specifications, commercialization plans, release timing, or how the robot perceives threats and makes decisions.

RoboticsTechCrunch

Warhound raises $200M to engineer war dogs and arm them with Anduril gear

Warhound, a company born from a idea by Colossal Biosciences' Ben Lamm and Anduril's Palmer Luckey, emerged from stealth with $200 million in funding from investors including In-Q-Tel, Sequoia, and 8VC, valuing it at $1.2 billion. It aims to genetically engineer working dogs for military, law enforcement, and emergency teams, and to equip them with Anduril hardware and software. The company cites a shortage of suitable military working dogs, noting that over 80% come from Europe and fewer than half are fit for service.

RoboticsZDNet Korea

From Patrol Robots to Ultra-Light AI for Air-Gapped Networks: Eight Tech Firms, Eight Distinct Approaches Catch Attention

At the 8th International Public Safety Industry Expo in Incheon (held 21–24 at Songdo Convensia), companies showcased AI and robot-based policing technologies, including patrol robots that detect fires and falls and AI that finds missing persons in crowds. The eight firms presented approaches ranging from video analytics to digital forensics, and visitors praised their ideas for addressing public safety problems.

RoboticsTechNode

China’s Magnetic-Sensor Champion Bets on Robot Joints

Sinomags, an Anhui-based magnetic sensor maker, is preparing a Hong Kong IPO and ranks first among Chinese magnetic sensor companies and tenth globally, with a 0.6% share, based on 2025 revenue. The company plans to use the listing proceeds to expand precision sensors for applications including robotics and to upgrade its German manufacturing capability.