Industry Briefing
A single destination for timely, editor-curated robotics news from around the world.
KAIST's HOUND Robot Reaches 6m/s Speed Using 2D Data for Advanced Parkour Skills
KAIST and Korea University researchers have developed the KAIST HOUND robot, achieving a peak speed of 6m/s while autonomously navigating complex terrains. This advancement showcases the robot's ability to seamlessly switch gaits, such as trotting and bounding, based on environmental conditions without external support. The significance of this achievement lies in the innovative APT-RL framework, which utilizes a simplified 2D dynamics model to generate extensive motion data. This approach allows the robot to learn and adapt its movements in real-world 3D environments, overcoming traditional limitations of motion capture and reinforcement learning strategies. Looking ahead, the research team has demonstrated the robot's capability to handle various scenarios, including jumping and maintaining balance under challenging conditions. Future developments may focus on enhancing the perception system to support high-speed operations, as the current sensing technology has limitations in effective range.
Quadrupedal Robots Robotics Research Reinforcement Learning AI Autonomous Systems
KAIST Unveils Advanced Four-Legged Robot with Autonomous Navigation Technology
KAIST's mechanical engineering team, led by Professor Park Hai-won, announced a breakthrough in robotic technology on July 16. They developed a four-legged robot capable of autonomously selecting and switching between various gaits in real-time, enabling it to navigate complex outdoor environments with speed and stability. This innovation is significant as it integrates a new control architecture called APT-RL (Action Pre-training Reinforcement Learning based on Transformers), which allows the robot to learn movement through computer simulations rather than traditional motion capture. The robot, named KAIST HOUND, demonstrated its capabilities by traversing diverse terrains, achieving peak speeds of 6 meters per second, faster than an average cyclist. Future developments to watch include the potential applications of this technology in disaster response, defense tasks, and industrial inspections. The research was published in the July issue of the journal Science Robotics, highlighting its importance in advancing the field of robotic control and physical AI.
Four-Legged Robots Robotics Technology AI Autonomous Navigation
KAIST Humanoid v0.7: High-Speed Locomotion and the "Moonwalk" of Technical Independence
KAIST’s DRCD Lab has introduced an advanced bipedal robot platform that can run at speeds of up to 12 km/h while exhibiting human-like agility. This innovative technology, revealed recently, utilizes proprietary 3K planetary gearboxes combined with hybrid reinforcement learning techniques. The development aims to enhance robotic mobility and adaptability, potentially paving the way for more sophisticated applications in various fields, including robotics research and human-robot interaction. The lab's efforts reflect a growing trend in robotics to create machines that can navigate environments with the same fluidity and responsiveness as humans.
South Korea k-humanoid-alliance KAIST
Korean Researchers Develop AI Framework for Robot Dog's Adaptive Movement in Complex Terrain
Researchers from Korea have created an AI framework that allows a quadruped robot to autonomously adapt its motor skills while navigating challenging environments. This system enables real-time gait adjustments for traversing forests, climbing stairs, and overcoming obstacles using only onboard sensors and computing capabilities. The significance of this development lies in its potential applications for autonomous search-and-rescue and exploration missions. The Action Pretrained Transformer-based Reinforcement Learning (APT-RL) framework enhances agility by combining pretrained locomotion skills with adaptive decision-making, demonstrating the robot's ability to handle diverse obstacles effectively. Future observations will focus on the framework's deployment in real-world scenarios, as it has already shown impressive performance on KAIST’s quadruped robot, HOUND. The robot's ability to switch between different gaits based on terrain and speed, achieving speeds of up to 6 meters per second, highlights the effectiveness of the APT-RL approach in complex environments. No further timeline was disclosed at the time of publication.
AI and Robotics
Upsampling method sharpens AI vision with up to 16 times less GPU memory
A collaborative research team from KAIST and various international institutions has made significant advancements in computer vision technology, enhancing artificial intelligence's ability to perceive its surroundings. This new technology improves GPU memory efficiency by up to 16 times, allowing AI systems to operate with minimal memory usage. The breakthrough, announced recently, is expected to play a crucial role in advancing the development of humanoid robots and on-device AI, potentially transforming how these technologies are integrated into everyday life. The innovation underscores the growing importance of efficient AI systems in various applications, from smartphones to robotics.
Robotics
Robots are closing in on human-like judgments, addressing a key challenge in physical AI
Researchers at KAIST have made significant strides in advancing the commercialization of physical AI by creating a groundbreaking technology that allows artificial intelligence to autonomously learn human judgment criteria from a limited number of videos. This development, which emerged from ongoing efforts to enhance AI's adaptability and decision-making capabilities, represents a crucial step toward integrating AI more effectively into real-world applications. The innovation was unveiled recently, highlighting the potential for AI systems to better understand and replicate human-like reasoning in various contexts. By streamlining the learning process, this technology could pave the way for more intuitive and responsive AI solutions across multiple industries, ultimately enhancing user interaction and satisfaction.
Robotics
Breakthrough in Shape Memory Alloys: Korean Team Achieves 140° Reversible Deformation in 1 Second
A research team at the Korea Advanced Institute of Science and Technology (KAIST) has unveiled a revolutionary bi-directional shape memory alloy/polymer composite actuator. This new actuator boasts an impressive 82% recovery rate and a deformation range of 140 degrees, significantly improving the functionality of actuators used in robotics and aerospace. The development, which promises to enable rapid and reversible movements, was driven by the need for more efficient and versatile components in advanced technological applications. Researchers achieved this breakthrough through innovative material engineering techniques, positioning the actuator as a potential game-changer in the fields of robotics and aerospace engineering.
Shape Memory Alloys Smart Actuators Robotics Aerospace Technology Material Science
From 30% to 91.7% Success Rate: What the RLDX-1 Reveals About Current Robot Models
A team of researchers from Korea, in partnership with KAIST, has unveiled the RLDX-1 model, a groundbreaking advancement in robotics designed to overcome the limitations of current robot models in dynamic environments. This innovative robot enhances task performance by incorporating advanced features such as motion perception, long-term memory, and physical sensing capabilities. As a result, the RLDX-1 has achieved an impressive success rate of 91.7% in executing complex operations, marking a significant leap forward in robotic technology.
Robotics AI Machine Learning Automation
This robot sees danger, decides its route and powers over obstacles while carrying loads
A research team at KAIST has made significant advancements in quadrupedal robot technology, enabling these robots to navigate varied terrains without relying solely on visual input. This innovative system allows the robots to assess their surroundings using cameras and LiDAR sensors, enabling them to make autonomous decisions while walking, akin to how animals adapt their movements based on visual terrain analysis. The team anticipates that this technology will be applicable to a range of robotic platforms, including wheeled-legged robots and humanoid robots, potentially broadening the scope of robotic mobility and functionality.
Robotics
Video Friday: Humanoid Learns Tennis Skills Playing Humans
IEEE Spectrum robotics has released its latest edition of Video Friday, showcasing a variety of innovative robotics videos and announcing upcoming events in the field. Notable events include the International Conference on Robotics and Automation (ICRA) scheduled for June 1-5, 2026, in Vienna, and a Summer School on Multi-Robot Systems from July 29 to August 4, 2026, in Prague. Among the featured advancements, researchers have developed LATENT, a system designed to teach humanoid robots tennis skills by learning from imperfect human motion data. This innovation addresses the challenges of replicating human-like athleticism in robotics. Additionally, a breakthrough has been achieved in robotic manipulation, with a robot successfully peeling an apple using dual dexterous hands, showcasing significant progress in bimanual tasks. The development of MoDE-VLA, a control system that integrates vision, language, force, and touch data, further enhances the robot's ability to perform complex tasks with stability and precision. This shared-autonomy approach allows human operators to guide robots in executing intricate movements. In other highlights, collaborations between Tesollo and Hanyang University have led to advancements in robotic hand technology, while the Fluent Robotics Lab at the University of Michigan is set to present a paper on operational PR2 robots. The KAIST DRCD Lab has also demonstrated the capabilities of its humanoid robot, trained through deep reinforcement learning. As robotics continues to evolve, these innovations reflect the ongoing efforts to bridge the gap between human-like dexterity and robotic functionality.
Humanoid-robots Video-friday Robot-locomotion Nvidia Robot-manipulation Quadruped-robotsRobotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
