An era in which robots decide "how to walk" on their own has arrived. A four-legged robot has been developed that, much like a person or an animal, autonomously chooses the appropriate gait strategy for its surroundings — changing its gait on stairs, leaping over gaps, and keeping its balance on forest trails.
KAIST (President Choongsik Bae) announced on the 16th of July that a research team led by Professor Hae-Won Park from the Department of Mechanical Engineering has developed a core control technology for four-legged robots that lets a single controller select and switch in real time among walking, running, jumping, and other locomotion skills, allowing the robot to move quickly and stably, even in real outdoor environments.
Four-legged robots move on four legs, giving them an advantage over wheeled robots on rough terrain. But in real outdoor settings, obstacles such as stairs, ledges, stepping stones, gaps, and tree branches appear one after another in different forms, meaning the ability to simply walk and run fast is not enough.
Existing four-legged robots have excelled at running quickly across flat ground or clearing simple obstacles, but they have struggled to maintain both speed and stability in real-world environments where obstacles combine in complex ways. Because walking, running, jumping, and other gaits had to be controlled individually, the robots were also limited in how naturally they could switch between them as conditions changed.
To overcome these limitations, the research team developed a new learning-based control technology called APT-RL (Action Pretrained Transformer-based Reinforcement Learning).
APT-RL is a control technology designed to enable a robot to first learn a range of locomotion skills — such as walking, running, and jumping — and then freely combine and transition among them in real-world environments as the situation demands.
Rather than filming the movements of real people or animals, the team generated 15.5 hours of training data covering a variety of gaits using computer simulations alone, in just eight minutes. That data was used to teach the robot basic movement capabilities, drawing on robot dynamics (a mathematical model of how a robot moves) and trajectory optimization (a technique for calculating the efficient path of movement). The approach is far faster and more efficient than earlier methods that relied on motion capture, a technology that records human or animal movement using sensors.
The team then applied reinforcement learning — an artificial intelligence technique in which an agent learns optimal behavior through repeated trial and error — so the robot could autonomously select and switch gaits suited to complex three-dimensional terrain such as stairs, ledges, and gaps. Finally, the team combined a depth camera (which measures the distance to objects in order to obtain three-dimensional information) with LiDAR (Laser Detection and Ranging, a sensor that uses lasers to measure the distance and shape of the surrounding environment in three dimensions), enabling the robot to recognize its surroundings and target speed in real time and choose the most appropriate walking strategy.
The team tested the control technology on its own four-legged robot, 'KAIST HOUND.' The experiments were conducted not only on an indoor obstacle course but also in real outdoor environments, including KAIST's campus and forest trails.
KAIST HOUND moved stably across urban terrain that included stairs, grass, and slopes, as well as irregular natural terrain such as fallen trees, exposed roots, and paths covered in fallen leaves, switching gaits in real time to match the conditions. In rugged terrain with obstacles, the robot reached a peak instantaneous speed of six meters per second (about 22 kilometers per hour), demonstrating that it can achieve both fast movement and stability in real outdoor environments.
The experiments showed that KAIST HOUND autonomously selected and switched between a trot (alternating diagonal legs) and a bound (a leaping gait using the front and back leg pairs together) depending on the terrain and target speed, and that it could integrate walking, running, jumping, and ledge-clearing into a single controller.
Professor Hae-Won Park said "We expect this to become a foundational technology that expands the potential uses of physical-AI-based walking robots in rugged environments such as disaster sites, defense missions, and industrial facility inspections."
Jun-Gill Kang (affiliated with the Agency for Defense Development (ADD) at the time of the research) and Jaehyun Park, a Ph.D. candidate in KAIST's Department of Mechanical Engineering, are co-first authors of the study. Professor Hae-Won Park and Professor Seungwoo Hong from Korea University are co-corresponding authors. The research was selected as the cover paper for the July issue of Science Robotics, the world's leading academic journal in robotics, and was published on July 15 (U.S. Eastern time).
※ Paper title: "Agile perceptive multi-skill locomotion for quadrupedal robots in the wild"
※ DOI: 10.1126/scirobotics.adz7397
※ Authors: Jun-Gill Kang (the Agency for Defense Development at the time of the research, co-first author), Jaehyun Park (KAIST, co-first author), Hae-Won Park (KAIST, corresponding author), Seungwoo Hong (Korea University, corresponding author)
※ Related Video: https://drive.google.com/drive/folders/1306_hddGZGh7xwvWFc4B-9lLXwYisirN
This research was supported by funding from the Ministry of Trade, Industry and Resources (MOTIR) and the Korea Planning & Evaluation of Industrial Technology (KEIT) (RS-2024-00427719), as well as by the Agency for Defense Development's Future Challenge Defense Technology R&D program (912768601).
