Embodied Intelligence
Our Embodied Intelligence research focuses on how intelligence emerges from the interaction between an agent's physical body and its control systems. We develop AI methods that leverage this physical embodiment to enhance adaptability in changing environments, creating more robust and responsive autonomous systems.
This research focuses on developing advanced motion planning techniques for quadruped robots operating in complex environments. We integrate traditional control methods with learning-based approaches to enable robust locomotion over challenging terrains. Our methods incorporate real-time adaptation to changing environmental conditions while maintaining stability and energy efficiency.
We investigate how sensory information can be effectively integrated with motor control in robotic systems to improve adaptability and responsiveness. This research draws inspiration from biological systems to create more natural movement patterns and better environmental interaction capabilities in robots.