PEPA: a Persistently Autonomous Embodied Agent with Personalities

2026-02-21

AI Summary

This work addresses the challenge of achieving long-term autonomous operation for embodied agents in dynamic, unstructured environments, where reliance on external task instructions limits adaptability. The authors propose PEPA, a novel three-layer cognitive architecture that uniquely incorporates personality traits as an intrinsic organizational mechanism to drive autonomous goal generation, action planning, and interactive behavior. In this framework, Sys3 leverages personality and episodic memory to generate endogenous goals, Sys2 performs deliberative reasoning and planning, and Sys1 handles perception and motor execution, with continuous self-reflection and real-world interactions—such as elevator navigation—enabling situated adaptation. Deployed on a quadruped robot in a multi-floor office environment, the system demonstrates that five distinct personality prototypes each produce stable, trait-consistent autonomous behaviors, successfully achieving sustained operation without predefined task instructions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Embodied AI

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Living organisms exhibit persistent autonomy through internally generated goals and self-sustaining behavioral organization, yet current embodied agents remain driven by externally scripted objectives. This dependence on predefined task specifications limits their capacity for long-term deployment in dynamic, unstructured environments where continuous human intervention is impractical. We propose that personality traits provide an intrinsic organizational principle for achieving persistent autonomy. Analogous to genotypic biases shaping biological behavioral tendencies, personalities enable agents to autonomously generate goals and sustain behavioral evolution without external supervision. To realize this, we develop PEPA, a three-layer cognitive architecture that operates through three interacting systems: Sys3 autonomously synthesizes personality-aligned goals and refines them via episodic memory and daily self-reflection; Sys2 performs deliberative reasoning to translate goals into executable action plans; Sys1 grounds the agent in sensorimotor interaction, executing actions and recording experiences. We validate the framework through real-world deployment on a quadruped robot in a multi-floor office building. Operating without reliance on fixed task specifications, the robot autonomously arbitrates between user requests and personality-driven motivations, navigating elevators and exploring environments accordingly. Quantitative analysis across five distinct personality prototypes demonstrates stable, trait-aligned behaviors. The results confirm that personality-driven cognitive architectures enable sustained autonomous operation characteristic of persistent embodied systems. Code and demo videos are available at https://sites.google.com/view/pepa-persistent/.

Problem

• persistent autonomy
• embodied agent
• personality
• intrinsic goals
• autonomous behavior

Innovation

• persistent autonomy
• personality-driven agent
• cognitive architecture
• embodied AI
• goal generation