no code implementations • 4 Oct 2023 • Meghna Gummadi, Cassandra Kent, Karl Schmeckpeper, Eric Eaton
Despite outstanding semantic scene segmentation in closed-worlds, deep neural networks segment novel instances poorly, which is required for autonomous agents acting in an open world.
Out-of-Distribution Detection Out of Distribution (OOD) Detection +2
no code implementations • CVPR 2023 • Jiahui Lei, Congyue Deng, Karl Schmeckpeper, Leonidas Guibas, Kostas Daniilidis
First, we introduce equivariant shape representations to this problem to eliminate the complexity induced by the variation in object configuration.
1 code implementation • 12 Apr 2022 • Karl Schmeckpeper, Philip R. Osteen, Yufu Wang, Georgios Pavlakos, Kenneth Chaney, Wyatt Jordan, Xiaowei Zhou, Konstantinos G. Derpanis, Kostas Daniilidis
Empirically, we show that our approach can accurately recover the 6-DoF object pose for both instance- and class-based scenarios even against a cluttered background.
1 code implementation • CVPR 2022 • Georgios Georgakis, Karl Schmeckpeper, Karan Wanchoo, Soham Dan, Eleni Miltsakaki, Dan Roth, Kostas Daniilidis
We consider the problem of Vision-and-Language Navigation (VLN).
1 code implementation • 24 Feb 2022 • Georgios Georgakis, Bernadette Bucher, Anton Arapin, Karl Schmeckpeper, Nikolai Matni, Kostas Daniilidis
We consider the problems of exploration and point-goal navigation in previously unseen environments, where the spatial complexity of indoor scenes and partial observability constitute these tasks challenging.
2 code implementations • 27 Sep 2021 • Frederik Ebert, Yanlai Yang, Karl Schmeckpeper, Bernadette Bucher, Georgios Georgakis, Kostas Daniilidis, Chelsea Finn, Sergey Levine
Robot learning holds the promise of learning policies that generalize broadly.
2 code implementations • ICLR 2022 • Georgios Georgakis, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Kostas Daniilidis
We consider the problem of object goal navigation in unseen environments.
1 code implementation • 6 May 2021 • Karl Schmeckpeper, Georgios Georgakis, Kostas Daniilidis
Object-centric video prediction offers a solution to these problems by taking advantage of the simple prior that the world is made of objects and by providing a more natural interface for control.
1 code implementation • 26 Mar 2021 • Wenbo Zhang, Karl Schmeckpeper, Pratik Chaudhari, Kostas Daniilidis
We empirically demonstrate that our approach can predict the rope state accurately up to ten steps into the future and that our algorithm can find the optimal action given an initial state and a goal state.
1 code implementation • 12 Nov 2020 • Karl Schmeckpeper, Oleh Rybkin, Kostas Daniilidis, Sergey Levine, Chelsea Finn
In this paper, we consider the question: can we perform reinforcement learning directly on experience collected by humans?
1 code implementation • 13 Mar 2020 • Bernadette Bucher, Karl Schmeckpeper, Nikolai Matni, Kostas Daniilidis
Model-based curiosity combines active learning approaches to optimal sampling with the information gain based incentives for exploration presented in the curiosity literature.
2 code implementations • 20 Feb 2020 • Vasileios Vasilopoulos, Georgios Pavlakos, Karl Schmeckpeper, Kostas Daniilidis, Daniel E. Koditschek
This paper solves the planar navigation problem by recourse to an online reactive scheme that exploits recent advances in SLAM and visual object recognition to recast prior geometric knowledge in terms of an offline catalogue of familiar objects.
Robotics
no code implementations • ECCV 2020 • Karl Schmeckpeper, Annie Xie, Oleh Rybkin, Stephen Tian, Kostas Daniilidis, Sergey Levine, Chelsea Finn
Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes.
no code implementations • 24 Oct 2019 • Sudeep Dasari, Frederik Ebert, Stephen Tian, Suraj Nair, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Sergey Levine, Chelsea Finn
This leads to a frequent tension in robotic learning: how can we learn generalizable robotic controllers without having to collect impractically large amounts of data for each separate experiment?