Current Research (To Be Completed...)
Set-theoretic Localization for Mobile Robots with Infrastructure-based Sensing [Github, arXiv]
In Collaboration with Dr. Yutong Li, Advisor: Prof. Anouck Girard Prof. Ilya Kolmanovsky
The proposed method computes sets that over-bound the robot body and orientation under an assumption of known noise bounds on the sensor and robot motion model. We establish theoretical properties and computational approaches for this set-theoretic localization approach and illustrate its application to an automated valet parking example in simulations and to omnidirectional robot localization problems in real-world experiments.
SeanNet: Semantic Understanding Network for Localization Under Object Dynamics [Github，arXiv]
In Collaboration with Yidong Du and Dr. Zhen Zeng, Advisor: Prof. Chad Jenkins
This research work proposes a scene graph enhanced deep neuron network for localization under visual uncertainties using Pytorch. The proposed network is provided to have a better performance in visual navigation tasks under object dynamics compared to those using CNN benchmark architectures.
Dynamic Scene Graph and Visual Navigation
In Collaboration with Yidong Du and Dr. Zhen Zeng, Advisor: Prof. Chad Jenkins
This research work develops a cognitive map representation that enables a dynamic memory of scene set-ups for autonomous agents. Image and scene graph-based Neuron Network is designed for localization with uncertainties using Pytorch. This research work ultimately enables the domestic robot for intelligent service tasks facing object-level visual uncertainties.
Independed Study
Test Platform for Autonomous Driving Functionalities [Github]
ME 590 Independent Study in Collaboration with Dr. Yutong Li, Advisor: Prof. Ilya Kolmanovsky, Prof. Bogdan Epureanu
Develope software and hardware RC-Car platform for validate autonomous parking application. (i.e. path planning, control, and visual-based localization)
