no code implementations • 3 Sep 2023 • Haimin Hu, Zixu Zhang, Kensuke Nakamura, Andrea Bajcsy, Jaime F. Fisac
An outstanding challenge for the widespread deployment of robotic systems like autonomous vehicles is ensuring safe interaction with humans without sacrificing performance.
1 code implementation • 5 Apr 2023 • Haimin Hu, Kensuke Nakamura, Kai-Chieh Hsu, Naomi Ehrich Leonard, Jaime Fernández Fisac
We present a multi-agent decision-making framework for the emergent coordination of autonomous agents whose intents are initially undecided.
1 code implementation • 2 Oct 2021 • Haimin Hu, Kensuke Nakamura, Jaime F. Fisac
Leveraging recent work on Bayesian human motion prediction, the resulting robot policy proactively balances nominal performance with the risk of high-cost emergency maneuvers triggered by low-probability human behaviors.
no code implementations • 1 May 2021 • Kensuke Nakamura, Simon Korman, Byung-Woo Hong
Based on these observations, we propose a data representation for the GAN training, called noisy scale-space (NSS), that recursively applies the smoothing with a balanced noise to data in order to replace the high-frequency information by random data, leading to a coarse-to-fine training of GANs.
no code implementations • 21 Dec 2020 • Kensuke Nakamura, Bong-Soo Sohn, Kyoung-Jae Won, Byung-Woo Hong
The quantitative analysis is performed by comparing the behavior of the label noise, the example trimming, and the proposed algorithm.
no code implementations • 14 Apr 2020 • Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong
We propose a first-order stochastic optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework.
no code implementations • 21 Jul 2019 • Kensuke Nakamura, Byung-Woo Hong
Regularization in the optimization of deep neural networks is often critical to avoid undesirable over-fitting leading to better generalization of model.
no code implementations • 20 Nov 2017 • Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong
We present a stochastic first-order optimization algorithm, named BCSC, that adds a cyclic constraint to stochastic block-coordinate descent.