Dimitrios Chatziparaschis

I'm a graduate student in the ECE Department of the University of California, Riverside, working towards my PhD in EE under Konstantinos Karydis. Prior to that, I completed my MSc in Computer Science and Engineering and my Diploma in Electrical and Computer Engineering at the Technical University of Crete in Chania, Greece. In both my MSc and Diploma programs, I was honored to work with Prof. Michail G. Lagoudakis.

Email  /  Google Scholar  /  GitHub  /  LinkedIn

Research

My work lies at the intersection of computer vision, machine learning, and robotics. Main topics of my research include 3D perception, multi-modal sensing, landmark detection, and localization in outdoor and dynamic settings. In the past I focused on fully autonomous robotic applications for Search-and-Rescue, applying aerial and ground robot relative localization, vision-based object of interest detection, and decision making.

Development of algorithm framework to perform real-time tree landmark detection and global association based on an underlying Kalman Filter for tree state estimation and employed criteria in canditate matching based on association uncertainty (entropy).

Demonstration of a fully autonomous robotic platform for stem water potential (SWP) measurements in avocado fields, based on Gaussian Processes (GPs) for modeling sampling area uncertainty and onboard leaf detection to perform 6D pose estimation and leaf cutting.

A lightweight keypoint detector based on a centroid point distance criterion, coupled with a multi-modal Non-Maximum Suppression (NMS) algorithm, to obtain salient and repeatable points in both colored and uncolored 3D point clouds.

Development of a robust semi-autonomous mobile robot solution to conduct soil apparent conductivity measurements in large fields, achieving high linearity with more than 90% in Pearson Correlation Coefficient (r) compared with groundtruth.

Development of a novel surveying approach using a custom-equipped UAV model, incorporating a gimbal with a camera and a single-dimensional rangefinder. The developed UAV behavior presented a multilateration target coordinate estimation, enforced spatial criteria, real-time detection, and ranging, and was evaluated in simulation showcasing high applicability under different environments and flight scenarios.

Development of a fully autonomous UAV behavior in Search-and-Rescue, utilizing machine learning approaches in both perception and control. The UAV's control and decision making part was based on a Deep Reinforcement Learning (DRL) and Deep Deterministic Policy Gradient (DDPG) model, designed and tested in a custom-crafted OpenAI Gym environment. On the perception side, object-of-interest detection was based on a proposed, designed, and trained feed-forward deconvolutional neural network to perform pixel-wise classification and segmentation.

Proposal of UAV system to assist surveys in GNSS-denied areas, due to the clear-sky visibility of GNSS satellites. This study demonstrated the feasibility of this application by presenting background information, proposing system architecture, and conducting a positioning error analysis for theoretical evaluation.

Demonstration of an aerial-ground robot collaboration in Search-and-Rescue scenarios in unknown environments. Considering the humanoid robot as "sensor blind" for localization, we demonstrate UAV-assisted in relative localization by employing onboard Hector SLAM and Adaptive Monte Carlo localization (AMCL), from above, to provide the humanoid's pose. At the same time, the humanoid robot used a YOLOV2 model trained on the PASCAL VOC dataset to detect individuals in need and approached them by using the FootStep planner based on R* search.