Ming-Chieh Yang

About

Ming-Chieh Yang is a robotics researcher whose work focuses on the intersection of bio-inspired locomotion and reinforcement learning, particularly for hexapod robots operating in unpredictable environments. His most notable contribution is the development of a heuristic Q-learning framework that enables six-legged robots to autonomously adapt their gait patterns during emergency-response scenarios, such as navigating rubble or uneven terrain after disasters. This approach, detailed in his 2019 paper "Emergency-Response Locomotion of Hexapod Robot with Heuristic Reinforcement Learning Using Q-Learning," demonstrates how combining classical control heuristics with model-free reinforcement learning can produce robust, real-time locomotion strategies without requiring extensive pre-programmed motion libraries. While his citation count (6) reflects the specialized nature of this emerging field, Yang's work has been recognized for bridging the gap between theoretical reinforcement learning and practical robotic deployment in high-stakes environments. His research has implications for search-and-rescue operations, where adaptive locomotion is critical. Yang continues to explore how learning algorithms can enhance the autonomy of legged robots in unstructured settings, contributing to the growing body of work on resilient, intelligent robotic systems for humanitarian applications.

Research Focus

Key Achievements

Top Papers

1. 1
   Emergency-Response Locomotion of Hexapod Robot with Heuristic Reinforcement Learning Using Q-Learning

   6 citations · 2019

Key Collaborators

Contact & Links