Timezone: »
Learning-based methods for training embodied agents typically require a large number of high-quality scenes that contain realistic layouts and support meaningful interactions. However, current simulators for Embodied AI (EAI) challenges only provide simulated indoor scenes with a limited number of layouts. This paper presents LUMINOUS, the first research framework that employs state-of-the-art indoor scene synthesis algorithms to generate large-scale simulated scenes for Embodied AI challenges. Further, we automatically and quantitatively evaluate the quality of generated indoor scenes via their ability to support complex household tasks. LUMINOUS incorporates a novel scene generation algorithm (Constrained Stochastic Scene Generation (CSSG)), which achieves competitive performance with human-designed scenes. Within LUMINOUS, the EAI task executor, task instruction generation module, and video rendering toolkit can collectively generate a massive multimodal dataset of new scenes for the training and evaluation of Embodied AI agents. Extensive experimental results demonstrate the effectiveness of the data generated by LUMINOUS, enabling the comprehensive assessment of embodied agents on generalization and robustness.
Author Information
Yizhou Zhao (UCLA)
Kaixiang Lin (Amazon)
Zhiwei Jia (University of California, San Diego)
Qiaozi Gao (Amazon)
Govindarajan Thattai (Amazon)
Jesse Thomason (University of Southern California)
Gaurav Sukhatme (USC)
More from the Same Authors
-
2020 : Poster #16 »
Feiyang Niu · Govindarajan Thattai -
2021 : ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations »
Tongzhou Mu · Zhan Ling · Fanbo Xiang · Derek Yang · Xuanlin Li · Stone Tao · Zhiao Huang · Zhiwei Jia · Hao Su -
2022 : Towards Reasoning-Aware Explainable VQA »
Rakesh Vaideeswaran · Feng Gao · ABHINAV MATHUR · Govindarajan Thattai -
2020 : Panel »
Maxine Eskenazi · Ankur Parikh · Govindarajan Thattai · Alexander Rudnicky · Jason E Weston -
2020 : Poster Session Presentations »
Nalin Chhibber · Weiyi Lu · Lina Rojas-Barahona · Katherine Stasaski · Dookun Park · Govindarajan Thattai · Alexandry Augustin · Mathilde Veron · Sahisnu Mazumder · Evgeny Krivosheev · Alessandro Bozzon -
2020 Poster: Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals »
Tongzhou Mu · Jiayuan Gu · Zhiwei Jia · Hao Tang · Hao Su -
2017 Poster: Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets »
Karol Hausman · Yevgen Chebotar · Stefan Schaal · Gaurav Sukhatme · Joseph Lim