Weihan Wang

Ph.D. Student at Stevens Insitute of Technology

I am a second-year Computer Sience Ph.D. student at Stevens Insitute of Technology, advised by Professor Philippos Mordohai.

Before that, I received my M.S. in Computer Science at Vanderbilt University, and my B.S. from University of Missouri-Columbia.

My current research interests cover various topics in visual inertial odometry, SLAM, and active vision.

Contact

E-mail: wwang103@stevens.edu


Experience


Research

2021

  • M. Xanthidis, B. Joshi, N. Karapetyan, M. Roznere, W. Wang, J. Johnson, A. Quattrini Li, J. Casana, P. Mordohai, S. Nelakuditi, I. Rekleitis, Towards multi-robot shipwreck mapping, presentation at ICRA 1st Advanced Marine Robotics TC Workshop: Active Perception, 2021.


Current Projects


Active Viewpoint Planning for 3D Model Acquisition

The objective of this project is to develop technologies for the 3D reconstruction of objects and scenes from passive cameras mounted on controllable robotic platforms.


The inputs to the system are a 3D bounding box and a tolerance value on the expected error of the 3D reconstruction. The output is a 3D model comprising a triangular mesh, texture maps and uncertainty estimates for the vertices that can be used for Virtual AND Augmented Reality.


Cooperative Underwater Structure Inspection and Mapping

This project aims to address the problem of mapping an underwater structure by a team of co-robots collaborating with a human operator.


The desired output is a 3D model of the underwater structure providing a high-resolution photo-realistic representation.


Previous Projects


Robothon 2021

In this competition, we developed robotic skills toward robots autonomously disassembling and sorting electronic waste.
The video shows our solution.
Robothon 2021.



Stereo Viusal-Inertial Fusion (Stereo-VIF) SLAM System

In this project, we propose a state-of-the-art Stereo Visual-Inertial SLAM system named Stereo Viusal-Inertial Fusion(Stereo-VIF), which is based on ORB-SLAM2 framework. The system includes Viusal-Inerial alignment, Viusal-Inertial system initialization and local window-based tightly-coupled Viusal-Inertial system optimization.
The video shows a simple demo of running Stereo-VIF system on Euroc dataset.
The open-source C++ code.



Apdative Cruise Control System

In this project, we propose a system which involves designing, building and testing an autonomous 1/10-scale model F1/10th racecar using NVIDIA Jetson TK1 platform for adaptive cruise control. We applied Reinforcement learning(RL) algorithms to train vehicles to drive for a safe distance to the human-controlled leading vehicle, and successfully implemented the whole system into a real F1/10th racecar.

Project Code are available.


Moving Object Detection and Tracking

In this project, we opt for color detection over object detection. The system consists of a Zed 2K Stereo Camera mounted on an autonomous vehicle(F1/10th Car Platform) for tracking a moving object. Both video processing, image processing algorithm and PID control algorithm are embedded on Nvidia TK1 board.

Proposal and Project Code are available.


WorldTrekker Application

WorldTrekker is a fitness and virtual travel app that allows wanderlusters to see the world with every step. WorldTrekker seeks to satisfy the needs of those wanderlusters who do not have the time, money or resources to do the amount of traveling they wish to do.

Slides and Project Code are available.