Writing
Thoughts on robotics, AI, control systems, and building technology.
How AI Learns to Understand Walking
How wearable sensors reveal walking: a visual journey through gait, pose estimation, ground forces, and human motion foundation models—with the networks and equations explained.
From Real Data to a Better Robot Dog Simulator
How we use suspended-leg and ground experiments, system identification, actuator modelling and domain randomisation to bring Angel D01’s simulation closer to the real robot.
The Model Context Protocol: Transforming AI Agents from Isolated Systems to Connected Ecosystems
An in-depth exploration of the Model Context Protocol (MCP) - the open standard that's enabling AI agents to break free from context limitations and interact dynamically with external systems.
Human-Centric Depth Vision: Intelligent Environment Recognition for Powered Exoskeletons
Exploring how depth cameras and IMU sensors can create intelligent terrain recognition systems that augment human decision-making in powered exoskeleton control, while maintaining the pilot as the ultimate authority.