This repository is a curated list of academic papers and resources focused on robot social navigation, addressing the challenges of robots moving safely and efficiently in human-populated environments. It serves as a comprehensive reference for researchers and engineers in robotics, AI, and human-robot interaction, consolidating advancements in methods, datasets, and benchmarks.

How It Works

The list categorizes research into Surveys, Datasets/Benchmarks, and Methods. Methodologies span traditional model-based approaches like Velocity Obstacles (RVO, ORCA) and Model Predictive Control (MPC), to modern learning-based techniques including supervised learning, reinforcement learning (RL), and imitation learning. Emerging areas like Foundation Models for Social Navigation, explainability, and user studies are also tracked, providing a broad overview of the field's evolution.

Quick Start & Requirements

This repository is a curated list of academic resources and does not contain executable code or software for installation.

Highlighted Details

• Methodologies: Covers a wide spectrum from established model-based techniques (e.g., RVO, ORCA, DWA, TEB, MPC) to diverse learning-based approaches (Supervised Learning, Reinforcement Learning, Imitation Learning) and recent Foundation Models leveraging LLMs/VLMs.
• Datasets & Benchmarks: Features extensive collections of both real-world datasets (e.g., NCLT, SCAND, MuSoHu) and simulated environments/benchmarks (e.g., CrowdNav, SocNavBench, AI Habitat, Pedsim-ROS), crucial for evaluating navigation algorithms.
• Emerging Trends: Highlights recent research in explainability, trust, environment modeling (pedestrian behavior, dynamic scene modeling), and user studies, reflecting the field's maturation.
• Scope: Includes papers from leading robotics and AI conferences and journals such as ICRA, IROS, RA-L, T-RO, and IJRR.

Maintenance & Community

The repository is actively maintained and developed by the author, who encourages community contributions via pull requests for missing works or corrections. No specific community channels (e.g., Discord, Slack) are listed.

Licensing & Compatibility

As a curated list of academic papers, no software license is specified. Compatibility for commercial use or closed-source linking is not applicable.

Limitations & Caveats

The primary limitation is the inherent challenge of maintaining a comprehensive and up-to-date list of rapidly evolving research. The author actively seeks community input to address any omissions or inaccuracies.