Hongyu Li, Wanjia Fu, Xiaoyan Cong, Zekun Li, Binghao Huang, Hanxiao Jiang, Xintong He, Yiqing Liang, Rao Fu, Tao Lu, Srinath Sridhar, Kevin A. Smith, George Konidaris, Yunzhu Li
The Deform360 dataset provides a large-scale visuotactile dataset for deformable world models, featuring 198 daily-life objects and over 215 hours of observations. This dataset enables the evaluation of current state-of-the-art world models and provides insights into their strengths and limitations. It has applications in robotic manipulation and deformable object-centric world modeling.
The Deform360 dataset has practical significance in robotic manipulation, as it can improve the ability of robots to predict and interact with deformable objects. This can lead to advancements in fields such as manufacturing, healthcare, and service robotics. The dataset can also facilitate the development of more generalizable and scalable world models.
Thank you to arXiv for use of its open access interoperability. arxiv.org. aibrief.ai is not affiliated with or endorsed by arXiv.