Shichao Yang

Learn More
Most visual odometry algorithm for a monocular camera focuses on points, either by feature matching, or direct alignment of pixel intensity, while ignoring a common but important geometry entity: edges. In this paper, we propose an odometry algorithm that combines points and edges to benefit from the advantages of both direct and feature based methods. It(More)
Semantic 3D mapping can be used for many applications such as robot navigation and virtual interaction. In recent years, there has been great progress in semantic segmentation and geometric 3D mapping. However, it is still challenging to combine these two tasks for accurate and largescale semantic mapping from images. In the paper, we propose an incremental(More)
We consider the problem of understanding the 3D layout of indoor corridor scenes from a single image in real time. Identifying obstacles such as walls is essential for robot navigation, but also challenging due to the diversity in structure, appearance and illumination of real-world corridor scenes. Many current single-image methods make Manhattan-world(More)
This paper addresses the problem of autonomous navigation of a micro aerial vehicle (MAV) inside a constrained shipboard environment for inspection and damage assessment, which might be perilous or inaccessible for humans especially in emergency scenarios. The environment is GPS-denied and visually degraded, containing narrow passageways, doorways and small(More)
Existing simultaneous localization and mapping (SLAM) algorithm is not robust in challenging low-texture environments because of few salient features. The resulting sparse or semi-dense map also conveys little information for motion planning. Though some work utilize plane or scene layout for dense map regularization, they require decent state estimation(More)
Zheng Fang State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, Liaoning 110819, China Shichao Yang, Sezal Jain, and Geetesh Dubey Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213 e-mail: shichaoy@andrew.cmu.edu, sezal@andrew.cmu.edu, gdubey@andrew.cmu.edu Stephan Roth(More)
Obstacle avoidance from monocular images is a challenging problem for robots. Though multi-view structurefrom-motion could build 3D maps, it is not robust in textureless environments. Some learning based methods exploit human demonstration to predict a steering command directly from a single image. However, this method is usually biased towards certain(More)
Existing simultaneous localization and mapping (SLAM) algorithms are not robust in challenging low-texture environments because there are only few salient features. The resulting sparse or semi-dense map also conveys little information for motion planning. Though some work utilize plane or scene layout for dense map regularization, they require decent state(More)
This paper addresses the problem of autonomous navigation of a micro aerial vehicle (MAV) inside of a constrained shipboard environment to aid in fire control, which might be perilous or inaccessible for humans. The environment is GPS-denied and visually degraded, containing narrow passageways, doorways and small objects protruding from the wall, which(More)
In this paper, an optimized central pattern generator (CPG) network is proposed for humanoid walking control. The CPG controller targets three joints (hip, knee and ankle) of each leg including 4 degrees of freedom (DOFs). The connections for CPG units of related joints are simplified and optimized hierarchically. The total number of CPG parameters is(More)