Towards Humanoid Robot Autonomy: A Dynamic Architecture Integrating Continuous thought Machines (CTM) and Model Context Protocol (MCP)

TL;DR

This paper introduces a dynamic architecture combining continuous thought machines and model context protocol to enhance humanoid robot autonomy, enabling more human-like autonomous actions through simulation experiments and new datasets.

Contribution

It presents a novel architecture integrating CTM and MCP with a theoretical parallel solution and demonstrates its feasibility through simulation and experimental metrics.

Findings

The CTM-MCP architecture is feasible and effective.

Experimental results show high task success and execution rates.

The approach provides a reference for autonomous dynamic coding in humanoid robots.

Abstract

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.