Abstract
Realistic household simulation must capture not only diverse environments but also the lived-in object arrangements and spatial constraints that shape robot motion and interaction. Existing resources often trade off scale, real-world correspondence, and interaction readiness, leaving a gap in faithful, interactive replicas of how real homes are actually arranged. To this end, we introduce LIVIN, a benchmark for spatial and embodied intelligence built on digital twins of 30 diverse lived-in homes. These replicas preserve observed room layouts, furniture configurations, and everyday belongings. To construct them, we design a human-in-the-loop workflow comprising instance recognition, architectural reconstruction, and object generation and placement, with intermediate results reviewed and corrected by humans against the source observations at each stage. We evaluate four tasks in LIVIN: 3D detection, 3D reconstruction, navigation, and loco-manipulation. Our evaluations show that current methods remain challenged by the dense object arrangements, occlusions, limited free space, and constrained interaction regions found in realistic lived-in homes. We hope LIVIN will help advance embodied AI in real-world homes, from spatial understanding to robotic interaction, and ultimately bring embodied intelligence into everyday home environments.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Xu, P., Nie, C., He, Y., Bai, Y., Liu, J., Shao, K., Jiao, Y., Xia, K., Zhu, J., Yang, Z., Zhang, Y., Tan, T., Di, S., Xu, J., Yu, J., & Gu, J. (2026). LIVIN: Benchmarking Spatial and Embodied Intelligence in Digital Twins of Lived-In Homes. https://omanscience.com/en/articles/livin-benchmarking-spatial-and-embodied-intelligence-in-digital-twins-of-lived-in-homes
MLA 9
Xu, Peijun, et al. "LIVIN: Benchmarking Spatial and Embodied Intelligence in Digital Twins of Lived-In Homes." https://omanscience.com/en/articles/livin-benchmarking-spatial-and-embodied-intelligence-in-digital-twins-of-lived-in-homes.
Chicago (author–date)
Xu, Peijun, Chuansen Nie, Yiyang He, Yinuo Bai, Jingyang Liu, Kuixiang Shao, Yuyang Jiao, Kuanhao Xia, Jiayi Zhu, Zitian Yang, Yanqi Zhang, Tianye Tan, Shuwei Di, Junyi Xu, Jingyi Yu, and Jiayuan Gu. 2026. "LIVIN: Benchmarking Spatial and Embodied Intelligence in Digital Twins of Lived-In Homes." https://omanscience.com/en/articles/livin-benchmarking-spatial-and-embodied-intelligence-in-digital-twins-of-lived-in-homes.
Harvard
Xu, P., Nie, C., He, Y., Bai, Y., Liu, J., Shao, K., Jiao, Y., Xia, K., Zhu, J., Yang, Z., Zhang, Y., Tan, T., Di, S., Xu, J., Yu, J. and Gu, J. (2026) 'LIVIN: Benchmarking Spatial and Embodied Intelligence in Digital Twins of Lived-In Homes', Available at: https://omanscience.com/en/articles/livin-benchmarking-spatial-and-embodied-intelligence-in-digital-twins-of-lived-in-homes.
Vancouver
Xu P, Nie C, He Y, Bai Y, Liu J, Shao K, et al. LIVIN: Benchmarking Spatial and Embodied Intelligence in Digital Twins of Lived-In Homes. https://omanscience.com/en/articles/livin-benchmarking-spatial-and-embodied-intelligence-in-digital-twins-of-lived-in-homes
IEEE
P. Xu, C. Nie, Y. He, Y. Bai, J. Liu, K. Shao, Y. Jiao, K. Xia, J. Zhu, Z. Yang, Y. Zhang, T. Tan, S. Di, J. Xu, J. Yu, and J. Gu, "LIVIN: Benchmarking Spatial and Embodied Intelligence in Digital Twins of Lived-In Homes," https://omanscience.com/en/articles/livin-benchmarking-spatial-and-embodied-intelligence-in-digital-twins-of-lived-in-homes.