activity
20162022
most citedLearning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

224 citations · 708 across the 24 of their papers we have counts for

collaborators
Showing 2018Show all

11 papers · 1 filter

cs.RO2018

Learning with Training Wheels: Speeding up Training with a Simple Controller for Deep Reinforcement Learning

Linhai Xie, Sen Wang, Stefano Rosa +2

Deep Reinforcement Learning (DRL) has been applied successfully to many robotic applications. However, the large number of trials needed for training is a key issue. Most of existi…

cs.RO2018

Learning with Stochastic Guidance for Navigation

Linhai Xie, Yishu Miao, Sen Wang +5

Due to the sparse rewards and high degree of environment variation, reinforcement learning approaches such as Deep Deterministic Policy Gradient (DDPG) are plagued by issues of hig…

cs.LG2018

Transferring Physical Motion Between Domains for Neural Inertial Tracking

Changhao Chen, Yishu Miao, Chris Xiaoxuan Lu +3

Inertial information processing plays a pivotal role in ego-motion awareness for mobile agents, as inertial measurements are entirely egocentric and not environment dependent. Howe…

cs.RO2018

OxIOD: The Dataset for Deep Inertial Odometry

Changhao Chen, Peijun Zhao, Chris Xiaoxuan Lu +3

Advances in micro-electro-mechanical (MEMS) techniques enable inertial measurements units (IMUs) to be small, cheap, energy efficient, and widely used in smartphones, robots, and d…

cs.NE2018

Neural Allocentric Intuitive Physics Prediction from Real Videos

Zhihua Wang, Stefano Rosa, Yishu Miao +4

Humans are able to make rich predictions about the future dynamics of physical objects from a glance. On the other hand, most existing computer vision approaches require strong ass…

cs.LG2018

GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks

Yasin Almalioglu, Muhamad Risqi U. Saputra, Pedro P. B. de Gusmao +2

In the last decade, supervised deep learning approaches have been extensively employed in visual odometry (VO) applications, which is not feasible in environments where labelled da…