Zobrazeno 1 - 10
of 156
pro vyhledávání: '"Eustice, Ryan M."'
This work reports on developing a deep inverse reinforcement learning method for legged robots terrain traversability modeling that incorporates both exteroceptive and proprioceptive sensory data. Existing works use robot-agnostic exteroceptive envir
Externí odkaz:
http://arxiv.org/abs/2207.03034
Autor:
Gan, Lu, Kim, Youngji, Grizzle, Jessy W., Walls, Jeffrey M., Kim, Ayoung, Eustice, Ryan M., Ghaffari, Maani
This article presents a novel and flexible multitask multilayer Bayesian mapping framework with readily extendable attribute layers. The proposed framework goes beyond modern metric-semantic maps to provide even richer environmental information for r
Externí odkaz:
http://arxiv.org/abs/2106.14986
Autor:
Zhang, Ray, Lin, Tzu-Yuan, Lin, Chien Erh, Parkison, Steven A., Clark, William, Grizzle, Jessy W., Eustice, Ryan M., Ghaffari, Maani
This paper reports on a novel nonparametric rigid point cloud registration framework that jointly integrates geometric and semantic measurements such as color or semantic labels into the alignment process and does not require explicit data associatio
Externí odkaz:
http://arxiv.org/abs/2012.03683
Autor:
Zhu, Minghan, Ghaffari, Maani, Zhong, Yuanxin, Lu, Pingping, Cao, Zhong, Eustice, Ryan M., Peng, Huei
This paper reports a new continuous 3D loss function for learning depth from monocular images. The dense depth prediction from a monocular image is supervised using sparse LIDAR points, which enables us to leverage available open source datasets with
Externí odkaz:
http://arxiv.org/abs/2003.09763
WiFi technology has been used pervasively in fine-grained indoor localization, gesture recognition, and adaptive communication. Achieving better performance in these tasks generally boils down to differentiating Line-Of-Sight (LOS) from Non-Line-Of-S
Externí odkaz:
http://arxiv.org/abs/2002.00484
This paper reports on a robust RGB-D SLAM system that performs well in scarcely textured and structured environments. We present a novel keyframe-based continuous visual odometry that builds on the recently developed continuous sensor registration fr
Externí odkaz:
http://arxiv.org/abs/1912.01064
Autor:
Lin, Tzu-Yuan, Clark, William, Eustice, Ryan M., Grizzle, Jessy W., Bloch, Anthony, Ghaffari, Maani
In this paper, we extend the recently developed continuous visual odometry framework for RGB-D cameras to an adaptive framework via online hyperparameter learning. We focus on the case of isotropic kernels with a scalar as the length-scale. In practi
Externí odkaz:
http://arxiv.org/abs/1910.00713
This paper develops a Bayesian continuous 3D semantic occupancy map from noisy point clouds by generalizing the Bayesian kernel inference model for building occupancy maps, a binary problem, to semantic maps, a multi-class problem. The proposed metho
Externí odkaz:
http://arxiv.org/abs/1909.04631
An accurate characterization of pose uncertainty is essential for safe autonomous navigation. Early pose uncertainty characterization methods proposed by Smith, Self, and Cheeseman (SCC), used coordinate-based first-order methods to propagate uncerta
Externí odkaz:
http://arxiv.org/abs/1906.07795
Legged robots require knowledge of pose and velocity in order to maintain stability and execute walking paths. Current solutions either rely on vision data, which is susceptible to environmental and lighting conditions, or fusion of kinematic and con
Externí odkaz:
http://arxiv.org/abs/1904.09251