Exploring Socially Robot Navigation via LLM-Based Human Interaction

Robot navigation is an important research field with applications in various domains. However, traditional approaches often prioritize efficiency and obstacle avoidance, neglecting a nuanced understanding of human behavior or intent in shared spaces. With the rise of service robots, there’s an increasing emphasis on endowing robots with the capability to navigate and interact in complex real-world environments. Socially aware navigation has recently become a key research area. However, existing work either predicts pedestrian move- ments or simply emits alert signals to pedestrians, falling short of facilitating genuine interactions between humans and robots. In this paper, we introduce the Hybrid Soft Actor- Critic with Large Language Model (HSAC-LLM), a novel model for robot socially aware navigation that seamlessly integrates deep reinforcement learning and large language models, which concurrently handles the robot’s continuous and discrete actions. When a collision risk with a pedestrian is detected, it initiates a conversation either by emitting speech or receiving the pedestrian’s speech. After the dialogue concludes, the robot adjusts its motion based on the conversation’s outcome. Experimental results in a 2D simulation and Gazebo environment demonstrate that HSAC-LLM not only efficiently enables interaction with humans but also exhibits superior performance in navigation and obstacle avoidance compared to state-of-the-art DRL algorithms. We believe this innovative paradigm opens up new avenues for effective and socially aware human-robot interactions in dynamic environments.