Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Allshire, Arthur"'
Autor:
Lum, Tyler Ga Wei, Matak, Martin, Makoviychuk, Viktor, Handa, Ankur, Allshire, Arthur, Hermans, Tucker, Ratliff, Nathan D., Van Wyk, Karl
A pivotal challenge in robotics is achieving fast, safe, and robust dexterous grasping across a diverse range of objects, an important goal within industrial applications. However, existing methods often have very limited speed, dexterity, and genera
Externí odkaz:
http://arxiv.org/abs/2407.02274
Autor:
Van Wyk, Karl, Handa, Ankur, Makoviychuk, Viktor, Guo, Yijie, Allshire, Arthur, Ratliff, Nathan D.
Robotics policies are always subjected to complex, second order dynamics that entangle their actions with resulting states. In reinforcement learning (RL) contexts, policies have the burden of deciphering these complicated interactions over massive a
Externí odkaz:
http://arxiv.org/abs/2405.02250
Symmetry is a fundamental aspect of many real-world robotic tasks. However, current deep reinforcement learning (DRL) approaches can seldom harness and exploit symmetry effectively. Often, the learned behaviors fail to achieve the desired transformat
Externí odkaz:
http://arxiv.org/abs/2403.04359
Autor:
Gürtler, Nico, Widmaier, Felix, Sancaktar, Cansu, Blaes, Sebastian, Kolev, Pavel, Bauer, Stefan, Wüthrich, Manuel, Wulfmeier, Markus, Riedmiller, Martin, Allshire, Arthur, Wang, Qiang, McCarthy, Robert, Kim, Hangyeol, Baek, Jongchan, Kwon, Wookyong, Qian, Shanliang, Toshimitsu, Yasunori, Michelis, Mike Yan, Kazemipour, Amirhossein, Raayatsanati, Arman, Zheng, Hehui, Cangan, Barnabas Gavin, Schölkopf, Bernhard, Martius, Georg
Experimentation on real robots is demanding in terms of time and costs. For this reason, a large part of the reinforcement learning (RL) community uses simulators to develop and benchmark algorithms. However, insights gained in simulation do not nece
Externí odkaz:
http://arxiv.org/abs/2308.07741
In this work, we propose algorithms and methods that enable learning dexterous object manipulation using simulated one- or two-armed robots equipped with multi-fingered hand end-effectors. Using a parallel GPU-accelerated physics simulator (Isaac Gym
Externí odkaz:
http://arxiv.org/abs/2305.12127
Autor:
Handa, Ankur, Allshire, Arthur, Makoviychuk, Viktor, Petrenko, Aleksei, Singh, Ritvik, Liu, Jingzhou, Makoviichuk, Denys, Van Wyk, Karl, Zhurkevich, Alexander, Sundaralingam, Balakumar, Narang, Yashraj, Lafleche, Jean-Francois, Fox, Dieter, State, Gavriel
Recent work has demonstrated the ability of deep reinforcement learning (RL) algorithms to learn complex robotic behaviours in simulation, including in the domain of multi-fingered manipulation. However, such models can be challenging to transfer to
Externí odkaz:
http://arxiv.org/abs/2210.13702
Autor:
Bauer, Stefan, Widmaier, Felix, Wüthrich, Manuel, Buchholz, Annika, Stark, Sebastian, Goyal, Anirudh, Steinbrenner, Thomas, Akpo, Joel, Joshi, Shruti, Berenz, Vincent, Agrawal, Vaibhav, Funk, Niklas, De Jesus, Julen Urain, Peters, Jan, Watson, Joe, Chen, Claire, Srinivasan, Krishnan, Zhang, Junwu, Zhang, Jeffrey, Walter, Matthew R., Madan, Rishabh, Schaff, Charles, Maeda, Takahiro, Yoneda, Takuma, Yarats, Denis, Allshire, Arthur, Gordon, Ethan K., Bhattacharjee, Tapomayukh, Srinivasa, Siddhartha S., Garg, Animesh, Sikchi, Harshit, Wang, Jilong, Yao, Qingfeng, Yang, Shuyu, McCarthy, Robert, Sanchez, Francisco Roldan, Wang, Qiang, Bulens, David Cordova, McGuinness, Kevin, O'Connor, Noel, Redmond, Stephen J., Schölkopf, Bernhard
Dexterous manipulation remains an open problem in robotics. To coordinate efforts of the research community towards tackling this problem, we propose a shared benchmark. We designed and built robotic platforms that are hosted at MPI for Intelligent S
Externí odkaz:
http://arxiv.org/abs/2109.10957
Autor:
Makoviychuk, Viktor, Wawrzyniak, Lukasz, Guo, Yunrong, Lu, Michelle, Storey, Kier, Macklin, Miles, Hoeller, David, Rudin, Nikita, Allshire, Arthur, Handa, Ankur, State, Gavriel
Isaac Gym offers a high performance learning platform to train policies for wide variety of robotics tasks directly on GPU. Both physics simulation and the neural network policy training reside on GPU and communicate by directly passing data from phy
Externí odkaz:
http://arxiv.org/abs/2108.10470
Autor:
Allshire, Arthur, Mittal, Mayank, Lodaya, Varun, Makoviychuk, Viktor, Makoviichuk, Denys, Widmaier, Felix, Wüthrich, Manuel, Bauer, Stefan, Handa, Ankur, Garg, Animesh
We present a system for learning a challenging dexterous manipulation task involving moving a cube to an arbitrary 6-DoF pose with only 3-fingers trained with NVIDIA's IsaacGym simulator. We show empirical benefits, both in simulation and sim-to-real
Externí odkaz:
http://arxiv.org/abs/2108.09779
Autor:
Allshire, Arthur, Martín-Martín, Roberto, Lin, Charles, Manuel, Shawn, Savarese, Silvio, Garg, Animesh
The process of learning a manipulation task depends strongly on the action space used for exploration: posed in the incorrect action space, solving a task with reinforcement learning can be drastically inefficient. Additionally, similar tasks or inst
Externí odkaz:
http://arxiv.org/abs/2103.15793