We present NavACL, a method of automatic curriculum learning tailored to the navigation task. NavACL is simple to train and efficiently selects relevant tasks using geometric features. In our experiments, deep reinforcement learning agents trained using NavACL in collision-free environments significantly outperform state-of-the-art agents trained with uniform sampling -the current standard. Furthermore, our agents are able to navigate through unknown cluttered indoor environments to semantically-specified targets using only RGB images. Collision avoidance policies and frozen feature networks support transfer to unseen real-world environments, without any modification or retraining requirements. We evaluate our policies in simulation, and in the real world on a ground robot and a quadrotor drone. Videos of real-world results are available in the supplementary material. 1
International audienceIn this paper, a general framework based on fractional-order partial differential equations allows to solve image reconstruction problems. The algorithm presented in this work combines two previous notions: a fractional derivative implementation by Discrete Fourier Transform and the edge detection by topological gradient. The purpose of the paper is to extend some existing results in image denoising problem with fractional-order diffusion equations and presents new results in image inpainting. The results emphasize the importance of particular fractional-orders
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.