EmoBipedNav: Emotion-aware Social Navigation for Bipedal Robots with Deep Reinforcement Learning

2025-03-16

AI Summary

This paper addresses safe navigation of bipedal robots in dynamic social environments. We propose a two-stage deep reinforcement learning (DRL) framework integrating pedestrian emotion perception and gait dynamics constraints. Our key contributions are: (1) the first quantitative modeling of emotion-induced “discomfort zones” as formal navigation constraints; and (2) a hybrid action planning and training mechanism that combines a simplified motion model for real-time control with full-order dynamical embedding to enhance physical feasibility. The method employs sequential LiDAR grid maps, emotion-driven discomfort zone extraction, and a ROM-parameterized policy network. Extensive simulations and real-robot experiments demonstrate significant improvements over model predictive control (MPC) and state-of-the-art DRL baselines in social safety, interaction naturalness, and locomotion stability. Code and real-robot demonstration videos are publicly available.

Technology Category

• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

This study presents an emotion-aware navigation framework -- EmoBipedNav -- using deep reinforcement learning (DRL) for bipedal robots walking in socially interactive environments. The inherent locomotion constraints of bipedal robots challenge their safe maneuvering capabilities in dynamic environments. When combined with the intricacies of social environments, including pedestrian interactions and social cues, such as emotions, these challenges become even more pronounced. To address these coupled problems, we propose a two-stage pipeline that considers both bipedal locomotion constraints and complex social environments. Specifically, social navigation scenarios are represented using sequential LiDAR grid maps (LGMs), from which we extract latent features, including collision regions, emotion-related discomfort zones, social interactions, and the spatio-temporal dynamics of evolving environments. The extracted features are directly mapped to the actions of reduced-order models (ROMs) through a DRL architecture. Furthermore, the proposed framework incorporates full-order dynamics and locomotion constraints during training, effectively accounting for tracking errors and restrictions of the locomotion controller while planning the trajectory with ROMs. Comprehensive experiments demonstrate that our approach exceeds both model-based planners and DRL-based baselines. The hardware videos and open-source code are available at https://gatech-lidar.github.io/emobipednav.github.io/.

Problem

• Addresses bipedal robot navigation in social environments
• Integrates emotion-aware navigation with deep reinforcement learning
• Overcomes locomotion constraints and social interaction complexities

Innovation

• Emotion-aware navigation using deep reinforcement learning
• Two-stage pipeline for bipedal and social constraints
• Sequential LiDAR grid maps for feature extraction