Maozhen Wang

PhD Student

Northeastern University

Welcome! 你好!

I’m a current PhD student in the Mechanical Engineering-Mechatronics program at Northeatern University. I’m doing research at the interface between Robotics and Control, under the supervison of Dr. Taskin Padir. Specifically, my research is application oriented with interactive navigation and manipulation as the main targets, and using optimal control theory and data-driven methods as the primary tools.

Before this, I received my BS degree in Mechanical Enginnering from the joint program between Beijing Jiaotong University and Oakland University. During my time at Oakland, I worked on the design and manufacturing of the racing car’s steering system in the school’s Formula SAE team, Grizzlies Racing.

Interests

Robotics
Optimal Control
Machine Learning

Education

PhD in Mechatronics, 2015-Present

Northeastern University
BSc in Mechanical Engineering, 2011-2015

Beijing Jiaotong University/Oakland University

Work Experience

Robotics Engineer Intern

BITO Robotics

May 2019 – Aug 2019 Pittsburgh, PA

Worked on motion planning and control for autonomous forklift:

Optimized the Bézier curve based path planning algorithm to ensure the generated path never exceeds the forklifts’ angular and linear speed limitations.
Responsible for realization of a model predictive controller for trajectory tracking using C++. Achieved smooth motions on the hardware with a goal tracking error within 10 cm.
Awarded Outstanding Internship Prize.

Robotics R&D Intern

Arçelik

Jun 2018 – Dec 2018 Istanbul, Turkey

Performed research and development for a service robot prototype:

Conducted a systematic review on state-of-the-art researches regarding elder caring robotics and smart home. Proposed a technology road map from the review results for future product design and development.
Wrote a planner for the service robot prototype to pick up objects designated by user.

Projects

Feedback controller for Non-prehensile Manipulation

In this project, a feedback controller is developed for planar pushing manipulations. Realtime control is achived by using nonlienar optimization in a Model Predictive Control setting. Straight line tracking without feedback control: Straight line tracking with feedback control: Controller recovers the trajectory from external perturbation: Circular tracking: Circular tracking with external perturbations:

Affordance-Based Interactive Navigation Among Movable Obstacles

In this project, we proposed a navigation and manipulation algorithm based on the concept of affordance and trajectory optimization method, that will enable a mobile manipulator to remove unexpected obstacles on the way to destination and have the capability to decide whether to pick or push items.

SLAM with Object Recognition

Turtlebot SLAM with object recognition and localization. Specified objects (office chair) are detected and their locations are marked on the fianl map. RTAB-Map and YOLO Object Detection are used in this project.

Publications

Affordance-Based Mobile Robot Navigation Among Movable Obstacles

Avoiding obstacles in the perceived world has been the classical approach to autonomous mobile robot navigation. However, this usually …

Maozhen Wang, Rui Luo, ‪Aykut Özgün Önol and Taskin Padir

Project