Výsledky vyhledávání - "Chang, Eric T."

Report

R$\times$R: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training

Autor: Khandate, Gagan, Saidi, Tristan L., Shang, Siqi, Chang, Eric T., Liu, Yang, Dennis, Seth, Adams, Johnson, Ciocarlie, Matei

We present a method for enabling Reinforcement Learning of motor control policies for complex skills such as dexterous manipulation. We posit that a key difficulty for training such policies is the difficulty of exploring the problem state space, as

Externí odkaz: http://arxiv.org/abs/2401.15484

Zobrazit plný text záznamu

Report

An Investigation of Multi-feature Extraction and Super-resolution with Fast Microphone Arrays

Autor: Chang, Eric T., Wang, Runsheng, Ballentine, Peter, Xu, Jingxi, Smith, Trey, Coltin, Brian, Kymissis, Ioannis, Ciocarlie, Matei

In this work, we use MEMS microphones as vibration sensors to simultaneously classify texture and estimate contact position and velocity. Vibration sensors are an important facet of both human and robotic tactile sensing, providing fast detection of

Externí odkaz: http://arxiv.org/abs/2310.00206

Zobrazit plný text záznamu

Report

Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation

Autor: Khandate, Gagan, Shang, Siqi, Chang, Eric T., Saidi, Tristan Luca, Liu, Yang, Dennis, Seth Matthew, Adams, Johnson, Ciocarlie, Matei

In this paper, we present a novel method for achieving dexterous manipulation of complex objects, while simultaneously securing the object without the use of passive support surfaces. We posit that a key difficulty for training such policies in a Rei

Externí odkaz: http://arxiv.org/abs/2303.03486

Zobrazit plný text záznamu