Shaownak Shahriar

• Developed real-time underwater image enhancement systems using GAN-based image translation.
• Managed sensor interfaces and integrated Jetson Orin Nano, Pixhawk, and Raspberry Pi for onboard inference and control.
• Optimized model performance for embedded inference using TensorRT and TorchScript.
• Built robust control software for autonomous underwater vehicles.

• Designed vision pipelines for underwater robotics using YOLO, SAM, SSD, Mask-RCNN, and U2-Net.
• Trained, fine-tuned, and deployed models for real-time vision inference directly on Nvidia Jetson Nano edge devices.
• Led vision and control system development for autonomous underwater vehicle operations.

• Developed terrain-aware SLAM and mapping systems using LiDAR, IMU, and GPS data.
• Integrated ROS-based autonomy and motor control on embedded platforms for real-time navigation.
• Trained custom object detection models (YOLOv5, Faster R-CNN, SSD) specifically for Mars-like terrain autonomy.

• Currently pursuing advanced coursework focusing on Data Science, machine learning algorithms, and advanced computing infrastructure.

• Thesis: Point-Cloud-based 3D Object Detection for Autonomous Navigation (Awarded Best Thesis of the Year 2024).
• Research Interests: Computer Vision, Rover Autonomy.
• Notable Courses: Quantum Computing, Artificial Intelligence, Neural Networks, Robotics, Pattern Recognition, Software Engineering, System Design.
• Mentorship: Mentored 4 undergraduate thesis groups on applied Computer Vision research (including Driver Safety, Breast Cancer Detection, and Underwater Waste Detection).
• Competitions: Represented BRAC University in multiple International Robotics Championships (UGV, AUV, UAS), national robotics competitions, and Intra-University Programming Contests (IUPC).
• Key Involvement: Co-Founder of RaptorX, Senior Engineer at Mongol-Tori, and Sub-Team Lead at BRACU Duburi.

• Proposed a hybrid GLENetVR + SE-SSD model combining voxel-based and point-based learning for LIDAR object detection.
• Implemented 3D bounding box regression with spatial attention to enhance accuracy and reduce inference latency.
• Recognized as Best Thesis of the Year 2024 by the Department of Computer Science.
• Submitted to the CVPR 2026

Designed scalable asynchronous microservices for automated CV analysis and LLM-based ranking. Built a robust NLP platform using Transformers for intelligent semantic matching, with a backend infrastructure engineered to handle asynchronous tasks and API rate limiting.

Integrated Retrieval-Augmented Generation (RAG) into a full-stack blogging platform to provide AI-driven dynamic content summarization and intelligent semantic search capabilities.

Developed a secure, end-to-end encrypted messaging platform featuring robust user authentication and cryptographic message hashing to prioritize data privacy.

Built comprehensive Enterprise Resource Planning software tailored for e-commerce operations, focusing on scalable database management and robust backend services.

Built a centralized university web application allowing students to easily report and track lost items securely across campus.

Engineered a congestion simulation system using GIS road networks with interactive scenario visualization. Utilized OSMnx data and predictive models to simulate infrastructure changes for urban traffic flow optimization.

Fine-tuned YOLOv11 and successfully deployed it directly onboard a drone's embedded edge device for real-time drone-to-drone tracking and visual identification.

Developed a real-time driver monitoring and road perception system integrating lane detection, drowsiness detection, and monocular depth estimation to support safe driving and scene understanding.

Designed and evaluated multiple deep learning architectures including LSTM, BERT, GRU, and Conv1D for advanced natural language processing and robust sentiment classification.

Engineered an accurate real estate valuation tool by fine-tuning XGBoost and custom Neural Networks to predict housing prices based on multifaceted property data.

Engineered an embedded C++ system using Arduino to fuse MPU6050 accelerometer and gyroscope data through a Kalman Filter, significantly improving noise reduction and orientation accuracy.

Designed an intelligent IoT hardware system for continuous environmental monitoring, featuring automatic gas detection and emergency shut-off mechanisms.

Designed and built a disaster-response robot prototype featuring onboard computer vision and autonomous navigation for hazardous environments.