Zheyuan Brian Zhang

Ann Arbor, MI

Greetings!

My name is Zheyuan (Brian) Zhang (张喆元 in chinese). I am a master student at the University of Michigan pursuing Robotics MS in the Robotics Institute and Cognitive Science Graduate Certificate in the Weinberg Institute for Cognitive Science. Currently, I am a research assistant at the Situated Language and Embodied Dialogue (SLED) lab, advised by Professor Joyce Chai. Prior to UMich, I received my undergraduate degree in Computer Science (B.S.) from UMass Amherst, College of Information & Computer Sciences.

Click to view my latest Curriculum Vitae.

My research interests lie in the intersection of artificial intelligence and cognitive science because I am particularly curious about how the brain works and how we understand the world. To this end, I want to incorporate ideas from cognitive psychology and neuroscience into the creation of computational AI models. Currently, my research focuses on Deep Learning, Natural Language Reasoning, Multimodal Learning, Continual Learning and Embodied Intelligence.

selected papers

UNPUB

Bot Lab: Autonomous Ground Vehicle from Low-level Control, SLAM to Planning and Exploration

Zheyuan Zhang, Yu Zhu, Manu Aatitya Raajan Priyadharshini, and Thirumalaesh Ashokkumar

2022

Abs PDF

The MBot mobile robotics project aims to develop an autonomous ground vehicle to navigate in the unknown environment. There are four key components of the project. Low-level control executes commands from high-level system to drive the robot based on velocity models and kinematics with a PID controller. Simultaneous Localization and Mapping (SLAM) is at the core of MBot project which allows the robot to use LiDAR to build a map of the environment and localize in that map at the same time. We developed mapping module, particle filter with action model and sensor model. Additionally, we implemented AStar (A*) heuristic search with pruning algorithm for path planning and frontier-guided algorithm for exploration. We present the theory and detailed imple- mentation with experimental results for the project in this report.
INSAI

Low-cost Solution for Vision-based Robotic Grasping

Zheyuan Zhang, and Huiliang Shang

In International Conference on Networking Systems of AI (IEEE INSAI) 2021

Abs IEEE Xplore

Robotic grasping is a fundamental task for many robots to interact with the outside world, and it is still challenging. There are at least three tasks for robot grasping: object localization, grasp pose estimation, and motion planning. This paper presents a low-cost machine vision solution for robotic grasping based on template matching, including comparisons between different approaches, including state-of-the-art YOLOv4 object detection and edge-based geometric shape detection. The robotic grasping solution presented in this paper shows a high pick-and-place success rate. An improvement for template matching is implemented in this paper as well. This paper also provides detailed analysis, algorithms, and experiments.