TY - JOUR
T1 - Characterizing the Complexity of Social Robot Navigation Scenarios
AU - Stratton, Andrew
AU - Hauser, Kris
AU - Mavrogiannis, Christoforos
N1 - Manuscript received: May, 18, 2024; Revised August, 21, 2024; Accepted October, 28, 2024. This paper was recommended for publication by Editor Gentiane Venture upon evaluation of the Associate Editor and Reviewers\u2019 comments. A. Stratton was partially funded by NSF Grant # NRI-2025782. 1Andrew Stratton and Christoforos Mavrogiannis are with the Department of Robotics, University of Michigan, Ann Arbor, USA. {arstr, cmavro}@umich.edu. 2Kris Hauser is with the Department of Computer Science, University of Illinois at Urbana-Champaign. [email protected]. Digital Object Identifier (DOI): see top of this page.
PY - 2025
Y1 - 2025
N2 - Social robot navigation algorithms are often demonstrated in overly simplified scenarios, prohibiting the extraction of practical insights about their relevance to real-world domains. Our key insight is that an understanding of the inherent complexity of a social robot navigation scenario could help characterize the limitations of existing navigation algorithms and provide actionable directions for improvement. Through an exploration of recent literature, we identify a series of factors contributing to the complexity of a scenario, disambiguating between contextual and robot-related ones. We then conduct a simulation study investigating how manipulations of contextual factors impact the performance of a variety of navigation algorithms. We find that dense and narrow environments correlate most strongly with performance drops, while the heterogeneity of agent policies and directionality of interactions have a less pronounced effect. Our findings motivate a shift towards developing and testing algorithms under higher-complexity settings.
AB - Social robot navigation algorithms are often demonstrated in overly simplified scenarios, prohibiting the extraction of practical insights about their relevance to real-world domains. Our key insight is that an understanding of the inherent complexity of a social robot navigation scenario could help characterize the limitations of existing navigation algorithms and provide actionable directions for improvement. Through an exploration of recent literature, we identify a series of factors contributing to the complexity of a scenario, disambiguating between contextual and robot-related ones. We then conduct a simulation study investigating how manipulations of contextual factors impact the performance of a variety of navigation algorithms. We find that dense and narrow environments correlate most strongly with performance drops, while the heterogeneity of agent policies and directionality of interactions have a less pronounced effect. Our findings motivate a shift towards developing and testing algorithms under higher-complexity settings.
KW - Autonomous vehicle navigation
KW - human-aware motion planning
KW - human-centered robotics
UR - http://www.scopus.com/inward/record.url?scp=85204548224&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85204548224&partnerID=8YFLogxK
U2 - 10.1109/LRA.2024.3502060
DO - 10.1109/LRA.2024.3502060
M3 - Article
AN - SCOPUS:85204548224
SN - 2377-3766
VL - 10
SP - 184
EP - 191
JO - IEEE Robotics and Automation Letters
JF - IEEE Robotics and Automation Letters
IS - 1
ER -