Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Gandhi, Dhiraj"'
Autor:
Pratik, Anurag, Chintala, Soumith, Srinet, Kavya, Gandhi, Dhiraj, Qian, Rebecca, Sun, Yuxuan, Drew, Ryan, Elkafrawy, Sara, Tiwari, Anoushka, Hart, Tucker, Williamson, Mary, Gupta, Abhinav, Szlam, Arthur
In recent years, there have been significant advances in building end-to-end Machine Learning (ML) systems that learn at scale. But most of these systems are: (a) isolated (perception, speech, or language only); (b) trained on static datasets. On the
Externí odkaz:
http://arxiv.org/abs/2101.10384
Autor:
Young, Sarah, Gandhi, Dhiraj, Tulsiani, Shubham, Gupta, Abhinav, Abbeel, Pieter, Pinto, Lerrel
Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching or teleoperation prohibitively restrict our ability
Externí odkaz:
http://arxiv.org/abs/2008.04899
Truly intelligent agents need to capture the interplay of all their senses to build a rich physical understanding of their world. In robotics, we have seen tremendous progress in using visual and tactile perception; however, we have often ignored a k
Externí odkaz:
http://arxiv.org/abs/2007.01851
This work studies the problem of object goal navigation which involves navigating to an instance of the given object category in unseen environments. End-to-end learning-based navigation methods struggle at this task as they are ineffective at explor
Externí odkaz:
http://arxiv.org/abs/2007.00643
Autor:
Chaplot, Devendra Singh, Gandhi, Dhiraj, Gupta, Saurabh, Gupta, Abhinav, Salakhutdinov, Ruslan
This work presents a modular and hierarchical approach to learn policies for exploring 3D environments, called `Active Neural SLAM'. Our approach leverages the strengths of both classical and learning-based methods, by using analytical path planners
Externí odkaz:
http://arxiv.org/abs/2004.05155
We present an approach to learn an object-centric forward model, and show that this allows us to plan for sequences of actions to achieve distant desired goals. We propose to model a scene as a collection of objects, each with an explicit spatial loc
Externí odkaz:
http://arxiv.org/abs/1910.03568
Autor:
Murali, Adithyavairavan, Chen, Tao, Alwala, Kalyan Vasudev, Gandhi, Dhiraj, Pinto, Lerrel, Gupta, Saurabh, Gupta, Abhinav
This paper introduces PyRobot, an open-source robotics framework for research and benchmarking. PyRobot is a light-weight, high-level interface on top of ROS that provides a consistent set of hardware independent mid-level APIs to control different r
Externí odkaz:
http://arxiv.org/abs/1906.08236
Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck in environ
Externí odkaz:
http://arxiv.org/abs/1906.04161
Data-driven approaches to solving robotic tasks have gained a lot of traction in recent years. However, most existing policies are trained on large-scale datasets collected in curated lab settings. If we aim to deploy these models in unstructured vis
Externí odkaz:
http://arxiv.org/abs/1807.07049
Can a robot grasp an unknown object without seeing it? In this paper, we present a tactile-sensing based approach to this challenging problem of grasping novel objects without prior knowledge of their location or physical properties. Our key idea is
Externí odkaz:
http://arxiv.org/abs/1805.04201