Max Robotics — Global Service Robot Directory + US Certification

About

Chi-Kai Ho is a robotics researcher whose work centers on solving the fundamental challenge of inverse kinematics (IK) for high-degree-of-freedom (DoF) and kinematically redundant robotic manipulators. His primary contributions lie at the intersection of motion planning and deep learning, where he develops data-driven approaches to navigate the complex, multi-solution joint spaces of robots with seven or more DoF. Ho’s most impactful work, "A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics" (2023, 18 citations), introduces a novel framework that leverages neural networks to efficiently explore and select optimal IK solutions, significantly improving the speed and robustness of numerical computations. He further advanced the field with "LAC-RRT," a constrained motion planning algorithm that integrates configuration transfer models to enhance generalization across tasks. By exploiting joint dependencies through neural networks, Ho has automated the learning of IK for redundant arms, reducing the need for manual tuning and enabling more adaptive, real-time control. His research is pivotal for the next generation of dexterous robotic arms used in manufacturing, surgery, and autonomous systems, offering scalable solutions to one of robotics’ most persistent geometric problems.