Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation

Abstract-- Large Language Models (LLMs) have been recently used in robot applications for grounding LLM commonsense reasoning with the robot's perception and physical abilities. In humanoid robots, memory also plays a critical role in fostering real-world embodiment and facilitating long-term interactive capabilities, especially in multi-task setups where the robot must remember previous task states, environment states, and executed actions. In this paper, we address incorporating memory processes with LLMs for generating cross-task robot actions, while the robot effectively switches between tasks. Our proposed dual-layered architecture features two LLMs, utilizing their complementary skills of reasoning and following instructions, combined with a memory model inspired by human cognition. Our results show a significant improvement in performance over a baseline of five robotic tasks, demonstrating the potential of integrating memory with LLMs for combining the robot's action and perception for adaptive task execution. I. INTRODUCTION Despite the physical limitations due to their embodiment, humanoid robots are particularly effective tools because of their anthropomorphic shape, which can significantly improve Nevertheless, LLM reasoning alone is environments designed for human interaction [1]. Moreover, not yet sufficient for implementing the cognitive system the humanoid physical shape supports collaborating with humans of embodied artificial agents, capable of solving complex whose legibility and predictability of robot actions are tasks and interacting with humans.