Towards Humanoid Robot Autonomy: A Dynamic Architecture Integrating Continuous thought Machines (CTM) and Model Context Protocol (MCP)
It addresses the gap in autonomous coding for humanoid robots, offering a reference for achieving human-like autonomous actions, though it appears incremental as it builds on existing concepts.
This work tackled the problem of humanoid robot autonomy in unfamiliar scenarios by designing a dynamic architecture integrating continuous thought machines and model context protocol, and experimental results showed feasibility and effectiveness across seven metrics including task success rate and execution success rate.
To address the gaps between the static pre-set "thinking-planning-action" of humanoid robots in unfamiliar scenarios and the highly programmed "call tool-return result" due to the lack of autonomous coding capabilities, this work designs a dynamic architecture connecting continuous thought machines (CTM) and model context protocol (MCP). It proposes a theoretical parallel solution through tick-slab and uses rank compression to achieve parameter suppression to provide a solution for achieving autonomous actions due to autonomous coding. The researcher used a simulation-based experiment using OpenAI's o4-mini-high as a tool to build the experimental environment, and introduced the extended SayCan dataset to conduct nine epochs of experiments. The experimental results show that the CTM-MCP architecture is feasible and effective through the data results of seven metrics: task success rate (TSR), execution success rate (ESR), average episode length (AEL), ROSCOE, REVEAL, proficiency self-assessment (PSA), task effectiveness (TE). In practice, it provides a reference experience for exploring the autonomous dynamic coding of humanoid robots based on continuous thinking to achieve human-like autonomous actions.