E2Map: Experience-and-Emotion Map for Self-Reflective Robot Navigation with Language Models
This addresses the challenge of unreliable robotic navigation in dynamic settings for robotics applications, representing an incremental improvement over prior LLM-based approaches.
The paper tackles the problem of LLM-based robotic navigation failing in stochastic environments by introducing E2Map, which integrates agent experiences and emotional responses to enable one-shot adjustments, significantly enhancing performance in simulations and real-world scenarios compared to existing methods.
Large language models (LLMs) have shown significant potential in guiding embodied agents to execute language instructions across a range of tasks, including robotic manipulation and navigation. However, existing methods are primarily designed for static environments and do not leverage the agent's own experiences to refine its initial plans. Given that real-world environments are inherently stochastic, initial plans based solely on LLMs' general knowledge may fail to achieve their objectives, unlike in static scenarios. To address this limitation, this study introduces the Experience-and-Emotion Map (E2Map), which integrates not only LLM knowledge but also the agent's real-world experiences, drawing inspiration from human emotional responses. The proposed methodology enables one-shot behavior adjustments by updating the E2Map based on the agent's experiences. Our evaluation in stochastic navigation environments, including both simulations and real-world scenarios, demonstrates that the proposed method significantly enhances performance in stochastic environments compared to existing LLM-based approaches. Code and supplementary materials are available at https://e2map.github.io/.