We propose to forecast future hand-object interactions given an egocentric video. Instead of predicting action labels or pixels, we directly predict the hand motion trajectory and the …
Everyday tasks of long-horizon and comprising a sequence of multiple implicit subtasks still impose a major challenge in offline robot control. While a number of prior methods aimed to …
Recognizing and generating object-state compositions has been a challenging task, especially when generalizing to unseen compositions. In this paper, we study the task of …
O Makansi, E Ilg, O Cicek… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Future prediction is a fundamental principle of intelligence that helps plan actions and avoid possible dangers. As the future is uncertain to a large extent, modeling the uncertainty and …
S Nair, C Finn - arXiv preprint arXiv:1909.05829, 2019 - arxiv.org
Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision …
Robotic reinforcement learning (RL) holds the promise of enabling robots to learn complex behaviors through experience. However, realizing this promise for long-horizon tasks in the …
KR Allen, KA Smith… - Proceedings of the …, 2020 - National Acad Sciences
Many animals, and an increasing number of artificial agents, display sophisticated capabilities to perceive and manipulate objects. But human beings remain distinctive in their …
Learning how to interact with objects is an important step towards embodied visual intelligence, but existing techniques suffer from heavy supervision or sensing requirements …
Imitation learning is an effective and safe technique to train robot policies in the real world because it does not depend on an expensive random exploration process. However, due to …