Zobrazeno 1 - 10
of 690
pro vyhledávání: '"Bajcsy, P."'
Visuomotor robot policies, increasingly pre-trained on large-scale datasets, promise significant advancements across robotics domains. However, aligning these policies with end-user preferences remains a challenge, particularly when the preferences a
Externí odkaz:
http://arxiv.org/abs/2412.04835
We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections. Different from prior works that rely on marker-based tracking and multiview cameras, ATS learns natural behav
Externí odkaz:
http://arxiv.org/abs/2410.16259
In interactive imitation learning (IL), uncertainty quantification offers a way for the learner (i.e. robot) to contend with distribution shifts encountered during deployment by actively seeking additional feedback from an expert (i.e. human) online.
Externí odkaz:
http://arxiv.org/abs/2410.08852
Robots must operate safely when deployed in novel and human-centered environments, like homes. Current safe control approaches typically assume that the safety constraints are known a priori, and thus, the robot can pre-compute a corresponding safety
Externí odkaz:
http://arxiv.org/abs/2409.14580
Robots can influence people to accomplish their tasks more efficiently: autonomous cars can inch forward at an intersection to pass through, and tabletop manipulators can go for an object on the table first. However, a robot's ability to influence ca
Externí odkaz:
http://arxiv.org/abs/2409.12153
Autor:
Jeong, Hyun Joe, Bajcsy, Andrea
Goal-conditioned policies, such as those learned via imitation learning, provide an easy way for humans to influence what tasks robots accomplish. However, these robot policies are not guaranteed to execute safely or to succeed when faced with out-of
Externí odkaz:
http://arxiv.org/abs/2409.09883
Publikováno v:
Proceedings Volume 12889, Integrated Optics: Devices, Materials, and Technologies XXVIII; 1288903 (2024)
We show the first demonstration of a hybrid external cavity diode laser (ECDL) using aluminum nitride (AlN) as the wave-guiding material. Two devices are presented, a near-infrared (NIR) laser using a 850 nm diode and a red laser using a 650 nm diode
Externí odkaz:
http://arxiv.org/abs/2408.06971
Assistive robotic arms often have more degrees-of-freedom than a human teleoperator can control with a low-dimensional input, like a joystick. To overcome this challenge, existing approaches use data-driven methods to learn a mapping from low-dimensi
Externí odkaz:
http://arxiv.org/abs/2406.07767
Autor:
Bajcsy, Peter, Bros, Maxime
This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for planting un
Externí odkaz:
http://arxiv.org/abs/2405.13217
Autor:
Bajcsy, Andrea, Fisac, Jaime F.
Artificial intelligence (AI) is interacting with people at an unprecedented scale, offering new avenues for immense positive impact, but also raising widespread concerns around the potential for individual and societal harm. Today, the predominant pa
Externí odkaz:
http://arxiv.org/abs/2405.09794