// selected work

Projects

Robotics, simulation, applied data, and hackathon builds. Each one links to a deeper write-up with background, features, and outcomes.

Self-Hosted Agentic LLM Framework
2026 Thesis

Self-Hosted Agentic LLM Framework

Multi-agentic systems via local LLMs, with typed outputs, deterministic verification, and a self-correction loop, producing auditable results.

Pydantic AIOllamaMulti-AgentText-to-SQLPython
Real Time Visual Localization and Mapping of Mobile Robot in Dynamic Environment
2020 Final Year

Real Time Visual Localization and Mapping of Mobile Robot in Dynamic Environment

Visual SLAM based project to localize and navigate the mobile robot in a dynamic environment. Fine-tuned a semantic segmentation model (ICNet) to detect humans as dynamic obstacles so the robot does not treat them as valid landmarks while localizing itself.

Visual SLAMOpenVSLAMROSICNetPyTorchSemantic Segmentation
Precision Livestock Farming
2019 Winner

Precision Livestock Farming

Precision Livestock Farming (PLF) uses advanced technologies to monitor and understand animal behavior and optimize their contribution to the livestock. The prototype monitors broiler chickens using a camera, microphone, and environmental sensors to examine feeding, mobility and distribution, correlated to the well-being and health of the broiler variety.

YOLOSORTSound AnalysisIoTMobile AppAutomation
Vehicle Traffic Management and Analysis
2019

Vehicle Traffic Management and Analysis

The project addresses traffic jams in Kathmandu Valley, particularly at major intersections like Koteshwor, Jadibuti and Lokanthali, where fixed-timing traffic lights cause delays, deadlocks and higher fuel consumption. The goal was an intelligent system that detects traffic flow, analyzes data, and optimizes traffic light sequences for efficient management.

PythonFlaskJavaScriptAJAX / jQueryPTV VissimData CollectionSimulationData Modeling
2019

ABU Robocon 2019 Simulator

A graphics project to simulate the ABU Robocon 2019 robots and stage, used to experiment with and build the best robot configuration for the competition. Focused on camera calibration, lighting effects and model rendering.

C++OpenGLCamera CalibrationLighting EffectsModel Rendering