analiza aiqbench
This paper introduces the ACME dataset, a significant resource for advancing social robot navigation policies through diverse cross-cultural scenarios involving seven distinct robot embodiments across five countries. By explicitly capturing goal-driven interactions via robot speech alongside standard sensor data and trajectory labels, it addresses critical gaps in existing benchmarks regarding cultural and geographical diversity in human-robot shared spaces. This work directly supports the development of more robust machine learning models capable of predicting pedestrian behavior in complex, real-world social environments.
ACME: A Multi-Cultural, Multi-Embodiment Social-Navigation Dataset
arXiv:2607.21964v1 Announce Type: cross Abstract: Understanding how robots and humans move in shared spaces is essential for designing effective social robot navigation policies and predicting human behavior. However, existing datasets often lack the diversity needed to capture differences in culture, geography, and human-robot interaction-factors that strongly shape appropriate social behavior. To address this gap, we introduce ACME: A Cross-cultural, Multi-Embodiment dataset for social navigation. A large-scale data collection effort across 8 sites in 5 countries, using 7 robot embodiments, ACME is a large and diverse multi-modal dataset aimed at advancing social navigation research, providing 29.35 hours of onboard robot data and 43.5 hours of overhead pedestrian tracking data. Unlike prior datasets, it focuses on capturing goal-driven social navigation behavior in complex social scenarios with explicit robot-crowd interaction through robot speech. To facilitate learning navigation policies and predicting pedestrian trajectories, ACME provides 3D and 2D scene features, odometry, interaction information, and human-annotated pedestrian trajectory labels. We make ACME easy to use by providing both human-readable data for each sensor modality as well as raw binary data. Our qualitative and quantitative analyses show that our dataset captures more challenging scenarios and a broader distribution of pedestrian behavior than previous datasets.
Authors:Shashank Rao Marpally, Allan Wang, Atharva Ghotavadekar, Renato Alexandre Ribeiro, Nhat Le, Pilar Bachiller-Burgos, Pranav Goyal, Subham Agrawal, Yasuhiro Nitta, Howard Ziyu Han, Daeun Song, Masaki Kuribayashi, Kohei Uehara, Xiyue Wang, Yangzhe Kong, Duc M. Nguyen, Amirreza Payandeh, Gerardo Pérez-González, Alejandro Torrejón-Harto, Jeeho Ahn, Tisha Jain, Andrew Stratton, Elvin Yang, Jorge de Heuvel, Nico Ostermann-Myrau, Sai Anudeep Sajja, Mithilya Raj, Daisuke Sato, Gaston Rouquette, Nikolas Martelaro, Maki Sugimoto, Hironobu Takagi, Chieko Asakawa, Maren Bennewitz, Aaron Steinfeld, Xuesu Xiao, Christoforos Mavrogiannis, Harold Soh
Abstract:Understanding how robots and humans move in shared spaces is essential for designing effective social robot navigation policies and predicting human behavior. However, existing datasets often lack the diversity needed to capture differences in culture, geography, and human-robot interaction-factors that strongly shape appropriate social behavior. To address this gap, we introduce ACME: A Cross-cultural, Multi-Embodiment dataset for social navigation. A large-scale data collection effort across 8 sites in 5 countries, using 7 robot embodiments, ACME is a large and diverse multi-modal dataset aimed at advancing social navigation research, providing 29.35 hours of onboard robot data and 43.5 hours of overhead pedestrian tracking data. Unlike prior datasets, it focuses on capturing goal-driven social navigation behavior in complex social scenarios with explicit robot-crowd interaction through robot speech. To facilitate learning navigation policies and predicting pedestrian trajectories, ACME provides 3D and 2D scene features, odometry, interaction information, and human-annotated pedestrian trajectory labels. We make ACME easy to use by providing both human-readable data for each sensor modality as well as raw binary data. Our qualitative and quantitative analyses show that our dataset captures more challenging scenarios and a broader distribution of pedestrian behavior than previous datasets.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2607.21964 [cs.RO]
(or arXiv:2607.21964v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.21964 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 295 cuvinte
Subiecte conexe
ERQA-Plus: A Diagnostic Benchmark for Reasoning in Embodied AI
arXiv · 17 iun. 2026
Google DeepMind Ships Three Physical AI Models For Whole Body Control, Dexterity And Multi Robot Collaboration
MarkTechPost · 30 iul. 2026
How to Train a Cross-Embodiment Robot Navigation Policy with AI Agents
NVIDIA · 26 aug. 2026
10 Ways AI Helps You Build What Your Business Needs
AppDirect · 15 mai 2026