Prof. Han-Lim Choi’s research team at KAIST has introduced an innovative navigation system, Learned-imitation on Cluttered Space (LiCS), designed to address the complex challenge of navigating unmanned ground vehicles (UGVs) in cluttered and narrow indoor environments. Utilizing 2D LiDAR and odometry, the system employs a transformer-based neural network combined with behavior cloning to learn expert navigation strategies. A critical enhancement in this method is the injection of Gaussian noise during training, which strengthens the model's ability to handle unexpected obstacles and recover from near-collision states, ensuring safe and robust navigation. LiCS leverages imitation learning, a method that offers distinct advantages over traditional optimization-based algorithms. Learning-b...read more
The Interactive Robotic Systems (IRiS) Lab aims to enhance human lives through cutting-edge robotic technologies, including teleoperation, exosuits, soft robotics and autonomous mobility.
Prof. Kong’s group developed a wearable pressure sensor for real-time estimation of plantar flexion muscle force by modeling intramuscular pressure.
Prof. Minkyu Je’s group developed integrated circuit chips and systems that can efficiently extract energy from a shoe-mounted electromagnetic energy harvester and transfer the harvested energy through the human body to power wearable devices located at various places on the body.
A research team led by Distinguished Professor Sang Yup Lee has developed an Escherichia coli strain for high-efficiency production of aromatic polyesters using systems metabolic engineering.
Professor Sangyong Jon’s group has developed an organ-selective drug delivery platform based on a library of glycocalyx-mimicking nanoparticles (GlyNPs). Direct in vivo library screening enables identification of GlyNP hits targeting the liver, spleen, lung, kidneys, heart, and brain. When liver-, kidney-, and spleen-selective GlyNP hits are equipped with therapeutics, the formulations effectively alleviated symptoms in organ-associated disease models.
Prof. Wanyeong Jung’s group has developed VVIP, a SIMD-based processor for efficient edge computing. It achieved 10.1× speedup with only 2.8% area overhead, enhancing multi-bit multiplication and sparse operations.
In robotics, achieving accurate motion tracking is a basic and fundamental challenge. For accurate tracking, robust control methods such as the Disturbance Observer (DOB) have been studied to eliminate uncertainties such as external forces and joint friction. However, the need for safe interactions has grown as robots increasingly share workspaces with humans. This creates a paradox: robots must not only track accurately but also respond safely to external forces that occur by human interactions. To address this, Prof. Min Jun Kim’s group at KAIST developed the Constrained Disturbance Observer (CDOB) framework, which adds intelligence to the ordinary DOB through optimization techniques. Consequently, while maintaining accuracy during free motion, robots are also capable of managing safety constraints and interacting with unknown environments.
Prof. Inkyu Park’s group has developed a wireless, battery-free optoelectronic sensor integrated into a pH-sensitive, colorimetric wound dressing for advanced wound care.
Visitor KIR 2024.03.11 Prof. Sebastian Scherer, CMU Demonstrated an autonomous quadruped robot system, which won 1st place in the IEEE ICRA’23 QRC (Quadruped Robot Challenge) and autonomous drone category. KIHST 2024.03.12 Prof. Jose L. Pons of Shirley Ryan Ability Lab Visited KIHST and gave a presentation on a wearable transition for rehabilitation of neurological conditions.