navbot_ppo
Mapless mobile-robot navigation: deep-RL motion planners — PPO, DDPG, SAC and TD3 — that drive a TurtleBot to a goal from sparse LiDAR and the target pose, with no SLAM and no map.
Research, perception, and systems work — built, trained, and shipped. Filter by theme; star counts are pulled live from GitHub.
Mapless mobile-robot navigation: deep-RL motion planners — PPO, DDPG, SAC and TD3 — that drive a TurtleBot to a goal from sparse LiDAR and the target pose, with no SLAM and no map.
From-scratch reimplementations of PointNet, PointNet++, DGCNN and PointMLP for point-cloud classification and part segmentation.
An end-to-end 3D object-detection pipeline on RGB-D data, comparing a from-scratch model against a fine-tuned EfficientNet-B3 backbone under a small-data regime.
A Vision-Transformer autoencoder for industrial inspection: reconstruct the image, then localize defects from patch-wise reconstruction error.
A real-time object-detection pipeline built with YOLOv3 and non-max suppression on the COCO dataset.
A from-scratch ray tracer in C (miniLibX): ray–object intersections, Phong shading, and an .rt scene parser producing photorealistic renders.
A minimal neural-network framework written from scratch in NumPy, with multiple activation functions and MSE loss, supporting classification and regression.
Predictive-maintenance fault detection for rotating machinery using Deep Stack Autoencoders.
A complete set of modern C++ exercises building up the language fundamentals through practical, meaningful projects.
A complete HTTP/1.1 web server written from scratch in modern C++: non-blocking I/O, GET/POST/DELETE, CGI, file upload and multiple concurrent clients.