[ZJU Robotics Project] DWA and Astar algorithms for wheeled-robot path planning

Heavy rainfall intensity as a function of duration and return period is defined according to DWA-A 531 (2012). This program reads rainfall measurement data and calculates the distribution of design rainfall as a function of both return period and duration, for durations up to 12 hours (and beyond) and return periods in the range 0.5 a ≤ Tₙ ≤ 100 a.

This work investigates automatic hyperparameter tuning for planners such as DWA and TEB, and our navigation framework LE-Nav can be used to adjust hyperparameters of any optimization-based planner.

Simulation for DWA (Dynamic Window Approach) and modified DWA algorithms

Complete ROS2 navigation and exploration system with multiple advanced algorithms: - Bidirectional A* path planning - DWA local planner for real-time obstacle avoidance - RRT exploration strategy - PID motion control - Comprehensive English documentation - Performance optimization guidelines - GitHub-ready project structure

Multi-Task Learning for Accelerated MR Reconstruction

Multi-task learning with adapted torchvision models (SSD, FasterRCNN, DeepLabv3) using Lightning-AI

Comparative benchmark of 14 representative path-planning algorithms with multi-scenario visualization and GIF demos in Python.

This project represents my dissertation project. It implements a multi robot control system that uses Yahboom Transbot robots.

Custom ROS2 DWA local planner with real-time trajectory sampling, obstacle avoidance, recovery logic, and RViz visualization — built from scratch without Nav2, for semi-structured real-world environments.

Planificación de trayectorias y control autónomo en F1TENTH usando el circuito Oschersleben. Integra Theta*, RRT y Spline Catmull–Rom para generar rutas suaves, junto con un controlador DWA para navegación autónoma, evitando obstáculos y siguiendo la ruta planificada.

robot planning algorithms