49 citations · 275 across the 31 of their papers we have counts for
5 papers · 1 filter
gradSLAM: Automagically differentiable SLAM
Krishna Murthy Jatavallabhula, Soroush Saryazdi, Ganesh Iyer +1
Blending representation learning approaches with simultaneous localization and mapping (SLAM) systems is an open question, because of their highly modular and complex nature. Funct…
Perceptual Generative Autoencoders
Zijun Zhang, Ruixiang Zhang, Zongpeng Li +2
Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dim…
Active Domain Randomization
Bhairav Mehta, Manfred Diaz, Florian Golemo +2
Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training…
The AI Driving Olympics at NeurIPS 2018
Julian Zilly, Jacopo Tani, Breandan Considine +14
Despite recent breakthroughs, the ability of deep learning and reinforcement learning to outperform traditional approaches to control physically embodied robotic agents remains lar…
Deep Active Localization
Sai Krishna, Keehong Seo, Dhaivat Bhatt +3
Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an inform…