[Paper Review] Core Challenges of Social Robot Navigation: A Survey

Christoforos Mavrogiannis, Francesca Baldini+5 more|arXiv (Cornell University)|Mar 9, 2021

Evacuation and Crowd DynamicsEngineering34 citations

TL;DR

This survey synthesizes three decades of social robot navigation research, outlining core planning, behavioral, and evaluation challenges, and offering future directions.

ABSTRACT

Robot navigation in crowded public spaces is a complex task that requires addressing a variety of engineering and human factors challenges. These challenges have motivated a great amount of research resulting in important developments for the fields of robotics and human-robot interaction over the past three decades. Despite the significant progress and the massive recent interest, we observe a number of significant remaining challenges that prohibit the seamless deployment of autonomous robots in public pedestrian environments. In this survey article, we organize existing challenges into a set of categories related to broader open problems in motion planning, behavior design, and evaluation methodologies. Within these categories, we review past work, and offer directions for future research. Our work builds upon and extends earlier survey efforts by a) taking a critical perspective and diagnosing fundamental limitations of adopted practices in the field and b) offering constructive feedback and ideas that we aspire will drive research in the field over the coming decade.

Motivation & Objective

• Define social robot navigation and its key components.
• Classify planning, behavioral, and evaluation challenges in social navigation.
• Critically assess decoupled versus coupled prediction-planning approaches.
• Identify fundamental open problems and propose directions for future work.

Proposed method

• Review and taxonomize existing literature across three decades.
• Formal definitions of social navigation and its problem space.
• Critique of current practices and modeling assumptions from a computational perspective.
• Discussion of coupling prediction and planning through frameworks like POMDPs, game theory, and braid dynamics.
• Synthesis of open problems including modeling interaction, behavioral assumptions, and contextual adaptation.

Experimental results

Research questions

• RQ1 What are the fundamental planning challenges when navigating through crowds while respecting social norms?
• RQ2 How do decoupled and coupled prediction-planning approaches compare in terms of feasibility, safety, and efficiency?
• RQ3 What behavioral models and social signals are essential for robust social robot navigation?
• RQ4 What are the major evaluation and validation gaps in current social navigation research?
• RQ5 What future directions can drive progress in the next decade of social robot navigation?

Key findings

• Brings a holistic taxonomy of planning, behavioral, and evaluation challenges.
• Highlights the trade-offs and non-convexity in coupled multiagent navigation problems.
• Shows the limitations of treating humans as dynamic obstacles without coupling predictions.
• Documents the role of proxemics, intention inference, and group formations in social navigation.
• Identifies context and environment geometry as underexplored yet crucial factors.
• Offers constructive directions to address open problems in modeling interaction, behavior, and evaluation.