Zobrazeno 1 - 10
of 2 119
pro vyhledávání: '"Schwager, P."'
We present FAST-Splat for fast, ambiguity-free semantic Gaussian Splatting, which seeks to address the main limitations of existing semantic Gaussian Splatting methods, namely: slow training and rendering speeds; high memory usage; and ambiguous sema
Externí odkaz:
http://arxiv.org/abs/2411.13753
Autor:
Lum, Tyler Ga Wei, Li, Albert H., Culbertson, Preston, Srinivasan, Krishnan, Ames, Aaron D., Schwager, Mac, Bohg, Jeannette
This work explores conditions under which multi-finger grasping algorithms can attain robust sim-to-real transfer. While numerous large datasets facilitate learning generative models for multi-finger grasping at scale, reliable real-world dexterous g
Externí odkaz:
http://arxiv.org/abs/2410.23701
We present DisCo, a distributed algorithm for contact-rich, multi-robot tasks. DisCo is a distributed contact-implicit trajectory optimization algorithm, which allows a group of robots to optimize a time sequence of forces to objects and to their env
Externí odkaz:
http://arxiv.org/abs/2410.23283
Autor:
Sun, Jiankai, Curtis, Aidan, You, Yang, Xu, Yan, Koehle, Michael, Guibas, Leonidas, Chitta, Sachin, Schwager, Mac, Li, Hui
Generalizable long-horizon robotic assembly requires reasoning at multiple levels of abstraction. End-to-end imitation learning (IL) has been proven a promising approach, but it requires a large amount of demonstration data for training and often fai
Externí odkaz:
http://arxiv.org/abs/2409.16451
Autor:
Kim, Chan, Kim, Keonwoo, Oh, Mintaek, Baek, Hanbi, Lee, Jiyang, Jung, Donghwi, Woo, Soojin, Woo, Younkyung, Tucker, John, Firoozi, Roya, Seo, Seung-Woo, Schwager, Mac, Kim, Seong-Woo
Large language models (LLMs) have shown significant potential in guiding embodied agents to execute language instructions across a range of tasks, including robotic manipulation and navigation. However, existing methods are primarily designed for sta
Externí odkaz:
http://arxiv.org/abs/2409.10027
Autor:
Chen, Timothy, Swann, Aiden, Yu, Javier, Shorinwa, Ola, Murai, Riku, Kennedy III, Monroe, Schwager, Mac
SAFER-Splat (Simultaneous Action Filtering and Environment Reconstruction) is a real-time, scalable, and minimally invasive action filter, based on control barrier functions, for safe robotic navigation in a detailed map constructed at runtime using
Externí odkaz:
http://arxiv.org/abs/2409.09868
Autor:
Plou, Carlos, Pueyo, Pablo, Martinez-Cantin, Ruben, Schwager, Mac, Murillo, Ana C., Montijano, Eduardo
Gen-Swarms is an innovative method that leverages and combines the capabilities of deep generative models with reactive navigation algorithms to automate the creation of drone shows. Advancements in deep generative models, particularly diffusion mode
Externí odkaz:
http://arxiv.org/abs/2408.15899
We present SODA-MPC, a Safe, Out-of-Distribution-Adaptive Model Predictive Control algorithm, which uses an ensemble of learned models for prediction, with a runtime monitor to flag unreliable out-of-distribution (OOD) predictions. When an OOD situat
Externí odkaz:
http://arxiv.org/abs/2406.02436
Autor:
Vincent, Joseph A., Nishimura, Haruki, Itkina, Masha, Shah, Paarth, Schwager, Mac, Kollar, Thomas
With the rise of stochastic generative models in robot policy learning, end-to-end visuomotor policies are increasingly successful at solving complex tasks by learning from human demonstrations. Nevertheless, since real-world evaluation costs afford
Externí odkaz:
http://arxiv.org/abs/2405.05439
Autor:
Shorinwa, Ola, Tucker, Johnathan, Smith, Aliyah, Swann, Aiden, Chen, Timothy, Firoozi, Roya, Kennedy III, Monroe, Schwager, Mac
We present Splat-MOVER, a modular robotics stack for open-vocabulary robotic manipulation, which leverages the editability of Gaussian Splatting (GSplat) scene representations to enable multi-stage manipulation tasks. Splat-MOVER consists of: (i) ASK
Externí odkaz:
http://arxiv.org/abs/2405.04378