PEPA: a Persistently Autonomous Embodied Agent with Personalities

TL;DR

PEPA is developed, a three-layer cognitive architecture that operates through three interacting systems that enables sustained autonomous operation characteristic of persistent embodied systems and confirms that personality-driven cognitive architectures enable sustained autonomous operation characteristic of persistent embodied systems.

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/.

Figures (6)

• Figure 1: Overview of PEPA, the three-layer cognitive architecture. Sys3 generates ultimate/daily goals and intrinsic rewards from personality traits, self-modeling, and accumulated memories. Sys2 combines intrinsic and extrinsic rewards to select optimal actions via MCTS or distilled policies. Sys1 executes actions, monitors system state, and records episodic memories that feed back to Sys3 for goal and reward refinement.
• Figure 2: Architecture of Sys1 on the mobile manipulation platform. Multimodal sensor data is processed by the navigation module for hierarchical path planning and multi-floor traversal, the perception module for localization and object detection, and the manipulation module for visual servoing-based interaction. All execution outcomes are recorded as structured episodic memories for downstream reflection by Sys3.
• Figure 3: Elevator navigation timeline showing five key stages: (a) navigating to the call panel, (b) pressing the call button and waiting, (c) identifying and entering the arriving car, (d) waiting for floor arrival, and (e) exiting to resume navigation on the target floor.
• Figure 4: Snapshots of staircase traversal using the proposed height-aligned costmap. (a)-(c) Ascent sequence: the robot climbs from a lower floor to an upper floor. (d)-(f) Descent sequence: the robot navigates downward. In both cases the robot follows the planned global path smoothly without planner deadlock or emergency stops.
• Figure 5: Action-category distribution across three days for five personalities. Behaviors become increasingly aligned with personality specifications as Sys3 updates intrinsic rewards through daily reflection.