Anthony Angeles | Projects

RobotBallet GoogleDeepmind

My attempt at replicating the research presented by GoogleDeepmind in MuJoCo.

Project Overview

This project focuses on replicating the groundbreaking robotics research from GoogleDeepmind, specifically their work on creating ballet-like movements in robotic systems using advanced motion planning and control algorithms.

Technologies Used

MuJoCo Physics Simulation
Python for control algorithms
XML configuration for robot models
Advanced motion planning techniques

Key Features

Smooth trajectory generation for robotic ballet movements
Physics-based simulation environment
Real-time motion control and feedback
Integration with research findings from Science Robotics

Implementation Details

The implementation uses MuJoCo's advanced physics engine to create realistic robotic movements that mirror the grace and precision of ballet. The system incorporates complex trajectory planning algorithms to ensure smooth, flowing motions while maintaining physical constraints and stability.

Reinforcement Learning using Isaac Lab and Sim

code video

Using reinforcement learning we teach the manipulator to reach an end goal pose matching the end goal orientation.

Project Overview

This project leverages NVIDIA Isaac Lab and Isaac Sim to create a reinforcement learning environment where robotic manipulators learn complex reaching tasks. The system trains robots to achieve precise pose and orientation targets through trial and learning.

Technologies Used

NVIDIA Isaac Lab framework
Isaac Sim physics simulation
PyTorch for RL algorithms
GPU-accelerated training
Advanced reward shaping techniques

Key Features

End-to-end RL training pipeline
Precise pose and orientation control
Real-time simulation environment
Scalable training across multiple environments

Path Planning Simulation

code

Particle Fluid Simulation that demonstrates path planning in dynamic environments.

Project Overview

This project explores path planning algorithms in dynamic environments that can be agitated through user interaction.

Technologies Used

Particle physics simulation
Path planning algorithms
Interactive visualization

Key Features

SPH based fluid simulation
A* path planning
Euler fluid simulation
Interactive visualization

Implementation Details

Uses both SPH and Euler fluid simulation to create a dynamic environment that can be agitated through user interaction. This simulation uses both methods to create the particle behavior that then assigns two random particles to find the most optimal path between them while the environment changes.

Game AI

video

Agentic AI that follows player interacting with the world environment to achieve its goal.

Project Overview

An intelligent game AI system that creates autonomous agents capable of understanding and interacting with complex game environments. The AI agents can observe player behavior and adapt their strategies dynamically.

Technologies Used

Machine Learning frameworks
Behavioral tree systems
Real-time decision making algorithms
Environmental state analysis

Key Features

Adaptive AI behavior based on player actions
Dynamic goal-oriented decision making
Real-time environmental awareness
Interactive gameplay demonstrations

A* Path Planning

code video

A demonstration of A* path planning algorithm that dynamically renders its shortest path avoiding obstacles.

Project Overview

An interactive implementation of the A* pathfinding algorithm that visualizes the search process in real-time. The system demonstrates optimal path calculation while dynamically avoiding obstacles in a grid-based environment.

Technologies Used

A* search algorithm implementation
Real-time visualization libraries
Interactive grid-based interface
Dynamic obstacle placement system

Key Features

Real-time pathfinding visualization
Dynamic obstacle avoidance
Interactive start/end point selection
Step-by-step algorithm demonstration

Object Detection for VR

code Publication

A pipeline that gathers images from google maps API and converts them into VR friendly formats that runs an objection detection model that I labled for flammable objects within the picture.

Project Overview

An innovative VR application that combines Google Maps imagery with YOLOv8 object detection to identify flammable objects in real-world environments. This project creates immersive safety assessment tools for virtual reality platforms.

Technologies Used

YOLOv8 object detection framework
Google Maps API integration
VR-compatible image processing
Custom dataset labeling and training

Key Features

Real-world imagery integration in VR
Custom-trained flammable object detection
Interactive VR safety assessment
Academic research publication

Particle Fluid Simulation

code video

Simulation of fluid dynamics using particles written in C++.

Project Overview

A high-performance particle-based fluid dynamics simulation built from scratch in C++. The system accurately models fluid behavior using computational physics principles and provides real-time visualization of complex fluid interactions.

Technologies Used

C++ for performance-critical computation
Particle-based physics simulation
Real-time rendering systems
Advanced mathematical modeling

Key Features

Real-time fluid particle simulation
Physics-accurate fluid dynamics
High-performance C++ implementation
Interactive parameter adjustment

Computer Vision Projects

code

Various projects dealing with computer vision that I am working on. Currently I have a facial detection script available for use.

Project Overview

A comprehensive collection of computer vision projects showcasing various techniques in image processing and pattern recognition. The repository includes facial detection systems and other advanced CV applications.

Technologies Used

OpenCV computer vision library
Python for rapid prototyping
Machine learning frameworks
Real-time image processing

Key Features

Real-time facial detection and recognition
Modular CV pipeline architecture
Multiple detection algorithms
Extensible project framework