Available for engineering opportunities

Abel Mendoza

Robotics Software &
Autonomous Systems Engineer

I build and verify autonomous robots, UAV software, perception pipelines, and embedded systems using ROS 2, PX4, C++, Python, and NVIDIA Jetson.

Explore my work View robotics résumé

Southern California · US Citizen · Open to relocation

When I’m not coding, I like aggressively cuddling others on the jiu-jitsu mat, reading, and educating myself.

Abel Mendoza at his engineering workstation
450ROS-enabled Python tests
<100msRobot video latency
641Telemetry samples verified
3Robotics compute platforms

Skills & Technologies

Core autonomous systems competencies, tooling, and embedded platforms.

Python C++ C Go Bash Git Docker QGroundControl ROS2 PX4 Gazebo MAVLink MAVSDK OpenCV RealSense Jetson Raspberry Pi Arduino Ubuntu Linux Cursor ChatGPT Claude AI Grok Gemini Antigravity Muse
1. Robotic Systems Engineer-Resume 2. UAV Field Engineer-Resume 3. Electronics Technician-Resume 4. Fullstack Software Engineer-Resume

Featured Work

Omega-1 robot project showcase video thumbnail

Project Showcase

In this video, I'm showcasing my Ω1 robot. Check out my YouTube channel for more robotics videos.

Projects

Selected work in robotics, autonomy, and systems engineering.

RobotForge logo — a rover inside a CAD wireframe cube

RobotForge — Acceptance Gate for Robot Models

Building nowMeta AI Developer Hackathon · Oct 26 – Nov 4, 2026

GitHub repo created Oct 26, 2026 · Last worked on Oct 28, 2026

Current focus: hackathon build — live site, Robodex, and build-planning chat shipped

An acceptance gate for robot models. Describe a robot in plain words, from a photo, or from a parts list: Muse Spark drafts a structured spec (never the robot files themselves), deterministic code builds the digital twin, and a headless Gazebo gate grades its motion against ground truth at locked thresholds — PASS at ≤ 5% distance error and ≤ 5° heading error — and issues a measured evidence report. Built solo under Darkstar Robotics for the Meta Global AI Developer Hackathon.

⚖️ Locked-Threshold Gate 🤖 Robodex · 11 Robots 🧩 Parts Catalogue + Starter Kinds 💬 Forge Guide Chat 🖨️ Take-Apart 3D Kits
Engineering details
  • Pipeline: words / photo / parts list → spec → static validation checks → URDF/SDF twin → headless Gazebo run → odometry vs ground-truth verdict (PASS / MARGINAL / FAIL), with the suspect spec field named on failure
  • Fix-my-spec loop: a failing gate proposes a measured repair (e.g. a corrected wheel diameter) and re-runs to a pass in one command
  • Specimens: real robots decomposed part by part from their official open-source assets — the TurtleBot3 Burger from ROBOTIS's own URDF and meshes, licenses carried
  • Electrical harness checks over the wiring graph: voltage drop, ampacity, logic levels, rail budgets, connector match — counts and named gaps, never a blanket pass
  • Forge Guide chat answers questions and plans builds (starter kinds, reference BOMs, have-vs-need diffs) from the recorded catalogue data only — when the data doesn't say, it says so
  • Stack: Python · Gazebo Sim · ROS 2 · URDF/SDF · Muse Spark (Meta Model API) · SAM 3 · Three.js · Next.js · TypeScript · Vercel
  • Status: solo Indie-track entry, Meta Global AI Developer Hackathon (Cerebral Valley) — submission due Nov 4, 2026
Live Site See Code
PX4 / ROS 2 Autonomy and Verification Platform

PX4 / ROS 2 Autonomy & Verification Platform

Active developmentUpdated Oct 20, 2026

GitHub repo created Mar 18, 2026 · Last worked on Oct 23, 2026

Current focus: RobotForge acceptance gate — Meta hackathon, Oct 26 – Nov 4

Autonomous UAV development and verification platform built with PX4, ROS 2 Humble, Gazebo Harmonic, MAVSDK, MAVLink, Python, and C++. Features autonomous navigation, cooperative multi-UAV missions, fault injection, sensor integration, and requirements-based verification. Includes an interactive 3D flight replay application built with Three.js.

🚁 Autonomous Navigation 🤖 Multi-UAV Coordination 🛡️ Fault Injection & Recovery 🧪 Verification & CI/CD 🌐 Interactive 3D Replay
Engineering details
  • ROS 2 mission state machines, A* path planning, LiDAR-based reactive obstacle avoidance, geofencing, failsafe handling, and resource-aware mission control
  • Cooperative two-UAV missions with task allocation, route reservations, separation monitoring, watchdogs, and automatic task reassignment after confirmed vehicle failure
  • Requirements-based verification: a 26-requirement catalog, independent telemetry analysis, fault injection, regression testing, and PASS/FAIL/SKIP reporting
  • 450 ROS-enabled Python tests, 27 browser tests, and 41 C++ checks, with GitHub Actions CI/CD and reproducible evidence reports
  • Stereo visual odometry, IMU fusion, velocity PID control, ArUco precision landing, and simulated GPS-aiding-loss handling
  • MAVLink v2 communication utilities, vehicle abstraction interfaces, and telemetry pipelines for simulated and hardware-facing integration
  • Two-UAV fault-recovery mission verified across 641 telemetry samples, two task reassignments, and 8.095 m minimum sampled horizontal separation against a 2.5 m requirement
  • Mission-completion defects found and corrected through independent verification, with the failing evidence kept as regression tests
  • Browser-based Three.js flight replay that visualizes recorded missions and fault recovery without a local PX4/Gazebo install
  • Stack: PX4 v1.15+ · ROS 2 Humble · Gazebo Harmonic · Python · C++ · MAVSDK · MAVLink · Micro XRCE-DDS · OpenCV · Three.js · GitHub Actions
Live Demo See Code
Omega-1 Robotics Platform

Omega-1 — Remote-Controlled Robotics Platform

Offline for maintenanceUpdated Apr 2026

GitHub repo created Jun 1, 2024 · Last worked on Oct 20, 2026

A fully operational remote-controlled robot running on Raspberry Pi 4B — driven from a custom web dashboard with Xbox controller support, live sensor feeds, and a mission control map, while it streams live video and tracks its own position in real time. Autonomy is in development and being worked on in simulation.

Built as a distributed system across three machines: the Pi handles real-time motor control and sensor fusion, a web UI runs on any laptop with no robot software installed, and an NVIDIA Jetson Orin handles GPU-accelerated object detection — all communicating over a VPN-secured network.

🤖 Manual Remote Control 📷 Live Video Streaming 📍 Real-Time Localization 📡 Multi-Machine Network
Engineering details
  • Obstacle avoidance is in development in simulation — an ultrasonic sensor triggers deceleration, pivot, and heading recovery without stopping abruptly; the real robot is driven manually today
  • Estimates its own position using a Kalman filter that fuses dead-reckoning (motor commands) with visual landmark corrections (ArUco markers) — no GPS required
  • Streams live camera video to the browser with under 100 ms latency via a custom MJPEG proxy
  • Runs a full software simulation mode: the robot's physics and sensor geometry are modeled so the entire stack can be developed and tested without hardware
  • Detects objects with YOLOv8 on the Jetson Orin and relays results back to the Pi in real time over a compressed image stream (~500 KB/s vs 9 MB/s raw)
  • Solved a hardware bug where the motor driver corrupted servo signals at power-on — traced to a shared PWM clock; fixed with register verification and hard pulse clamping on every write
  • Eliminated ~240 unnecessary HTTP requests/minute from the frontend by introducing circuit breakers, shared polling contexts, and WebSocket health checks
  • Stack: Python · Go · TypeScript · React · Next.js · FastAPI · ROS2 · OpenCV · WebSockets · Docker · TailwindCSS
  • Status: Operational prototype, currently offline for maintenance — live teleoperation, sensor streaming, localization, and multi-machine communication all verified when last run; a hardware failure is pending replacement parts.
Live Demo See Code
Darkstar Robotics — robotics for every platform

Darkstar Robotics — Robotics Control Center for Mac

Prototypev0.4.0 released Oct 24, 2026

GitHub repo created Oct 23, 2026 · Last worked on Oct 24, 2026

Current focus: live simulation viewer proof

A native macOS app (Swift + SwiftUI) that gives budding roboticists one friendly place for robotics development: pick a validated Ubuntu + ROS 2 + Gazebo environment, pass a pre-flight prerequisite check, add hardware by photo, fly PX4 missions in simulation, and verify the evidence — while a managed Linux runtime does the heavy lifting underneath. No terminal, no version matrix, no install guides.

🍎 Native macOS · SwiftUI ✅ Preflight Checks 📷 Photo Hardware Intake 🐧 Managed Linux Runtime 🚁 PX4 + ROS 2
Engineering details
  • Live dashboard wired to real probes — UTM runtime state via utmctl, Tailscale link status, host summary — refreshed every few seconds
  • Preflight prerequisite checks (memory, disk, Xcode, UTM, VM state, Tailscale) with a one-click remedy on failures, plus a dependency-download manifest with sizes and sources
  • Environments are validated pairings — Ubuntu 24.04 + ROS 2 Jazzy + Gazebo Harmonic today, Ubuntu 22.04 + ROS 2 Humble next — so users never guess which versions belong together
  • Hardware intake by photo or scan: QR/serial decoding first, photo matching second, always confirm-before-configure (recognition engine in development)
  • Missions view built around a verified PX4 swarm-recovery demo — PASS, 8.095 m minimum separation vs 2.5 m required, 641 telemetry samples, 2 task reassignments
  • Managed-runtime prototype (Omega-Ubuntu VM) built and tuned end-to-end: 6-second boot, ROS 2 Jazzy + Gazebo Harmonic 8.15 verified headless
  • Stack: Swift · SwiftUI · macOS 14+ · UTM/QEMU · Ubuntu 24.04 · ROS 2 Jazzy · Gazebo Harmonic · PX4 · Micro XRCE-DDS · Tailscale
  • Status: v0.1 — first native build (Oct 2026); provisioning/download engine and golden-image packaging in progress.
Landing Page See Code

RealmForge XR — Hands-On World Builder

PrototypeUpdated Oct 19, 2026

GitHub repo created Oct 17, 2026 · Last worked on Oct 21, 2026

A desktop and Meta Quest WebXR editor where you shape a miniature environment with your hands, place a robot, and watch it re-route when you move a wall. Originally built by a team of four in 12 hours for the MOLTEN Hackathon’s Worldbuild track, then expanded with real property-scan workflows.

⏱️ 12-Hour Hackathon ✋ Hand Interaction 🤖 A* Re-routing 🏠 Property Scans
  • Direct hand grab, two-hand scale and rotation, gestures, controller input, voice commands, and a wrist-mounted VR menu
  • Grid-based A* robot navigation over obstacle footprints, including automatic re-planning when the world changes
  • Imports up to 24 named GLB scan sections for rooms, garages, and outdoor areas, with alignment, floor labeling, visibility, and ceiling controls
  • Portable property bundles carry the world and its mesh files between devices; world scale ranges from tabletop 1:60 to life-size 1:1
  • Real-room awareness on Quest, voice commands, preset environments, save/load, and undo/redo
  • Stack: React 19 · TypeScript · Three.js · React Three Fiber · WebXR · Zustand · GLB/glTF · Vite · Vitest
  • Status: Live and automated tests pass; physical Quest interaction and real-world Scaniverse exports still need hands-on validation
Live Demo See Code
Neon robot mascots coding with Claude and ChatGPT — Discord Agent Presence

Discord Agent Presence — Live AI Coding Status

Active developmentUpdated Oct 23, 2026

GitHub repo created Oct 21, 2026 · Last worked on Oct 28, 2026

Discord Rich Presence for AI coding tools. Like Discord's built-in "Playing Visual Studio Code" card, but for Claude, ChatGPT/Codex, Grok Build, Cursor and VS Code. Each card shows which projects you're working on, how many AI agents are running, and what they're doing right now.

🤖 5 AI Coding Apps ⚡ Live Agent Actions 🖼️ Mood-Based Images 🐍 Pure Python, 0 Deps
  • Reads Claude Code and Codex session transcripts to show what each agent is doing (editing, running tests, building, waiting for you) and counts agents across projects
  • Rotating status lines with git branch and diff stats, a commit streak, the model in use and GitHub CI status. Card images change with agent mood and the current action
  • Talks to Discord's local IPC socket directly, with one card per app. Uses /proc and X11 for app and window detection. One-line installer, a systemd user service and a doctor command
⬇ Mac ⬇ Windows See Code
Jetson RealSense Perception System project preview

Jetson RealSense Perception

PrototypeUpdated Mar 2026

GitHub repo created Mar 13, 2026 · Last worked on Oct 19, 2026

Embedded RGB-D perception toolkit for NVIDIA Jetson Orin Nano and Intel RealSense D455. Supports standalone pyrealsense2 workflows and ROS2 Humble integration, validated on Ubuntu 22.04 / JetPack L4T 36.4.7.

🟦 NVIDIA Jetson Orin Nano 📷 Intel RealSense D455 🛠️ librealsense 2.0 (RSUSB) 🐢 ROS2 Humble
  • Standalone scripts: capture, camera info probe, obstacle detection, point clouds, IMU, occupancy mapping
  • ROS2 wrapper validation: realsense2_camera launch, topic sanity, camera_info intrinsics, topic publishers
  • Documentation + onboarding: hardware setup, software setup, ROS2 setup, troubleshooting, validation checklist
  • Full validation: rs-enumerate-devices and check_realsense.py; depth/color streaming capture; ROS2 topic and intrinsics checks
See Code
Titan Rover Autonomous Navigation project

Titan Rover — Autonomous Navigation

CompletedUniversity team project

Group project with the Titan Rover university club — a team of Cal State Fullerton engineering students. Built and contributed to an autonomous rover using ROS, OpenCV, and sensor fusion for real-world terrain navigation and obstacle avoidance.

🤖 ROS 👁️ OpenCV 📡 Sensor Fusion 🗺️ Autonomous Navigation
  • Autonomous terrain navigation with real-time obstacle detection using OpenCV
  • Sensor fusion pipeline integrating camera, IMU, and encoder data
  • ROS-based architecture with custom nodes for perception and motion planning
▶ Watch Video Titan Rover Club
LoreBook — AI Life Engine

LoreBook — AI Life Engine

LiveIn production · Updated Sep 2026

GitHub repo created Nov 14, 2025 · Last worked on Oct 28, 2026

A full-stack AI platform that transforms journals, conversations, and memories into a continuously evolving knowledge base of a person's life. LoreBook automatically builds timelines, biographies, relationship intelligence, life arcs, and evidence-backed personal knowledge from unstructured entries.

🧠 Autobiographical Memory 📖 Biography Generation 🔎 Hybrid Retrieval ⚙️ 30+ Analysis Engines
  • Autobiographical Memory System — converts journal entries into structured events, timelines, relationships, and life arcs that persist over time
  • Knowledge Crystallization Engine — detects recurring behavioral patterns and converts them into evidence-backed knowledge claims with confidence scoring and traceable supporting evidence
  • Continuity Intelligence — identifies contradictions, identity drift, abandoned goals, emotional arcs, and recurring behavioral patterns across a user's history
  • Relationship Intelligence System — tracks relationship evolution, influence, interaction patterns, drift, and autobiographical impact across a user's life story
  • Hybrid Retrieval Architecture — combines vector search (pgvector), BM25 keyword search, entity-aware retrieval, temporal weighting, and MMR reranking for context-aware memory retrieval
  • Temporal Reasoning Engine — builds causal chains, life arcs, chronology graphs, and hierarchical timelines from years of journaled experiences
  • Custom orchestration framework: 30+ specialized analysis engines with dependency-aware scheduling, parallel execution, 10–100× caching improvements, and eliminated N+1 bottlenecks
  • Stack: TypeScript · React · Node.js · Supabase/PostgreSQL · pgvector · OpenAI · Stripe · GitHub Actions
Live Demo See Code

CERBERUS — The Guardian Security Suite

Active developmentUpdated Oct 14, 2026

GitHub repo created Oct 14, 2026 · Last worked on Oct 25, 2026

An open-source security monitoring and system hardening ecosystem for Windows, Linux, and macOS. Three separate Guardian desktop apps — one for each platform — share one landing page: integrity checks, security posture, network exposure, threat detection, and remediation that stays dry-run until the operator confirms a change.

🖥️ Windows · Linux · macOS 🛡️ Threat Detection 🔒 System Hardening 📖 Open Source
  • Three desktop Guardians — Windows (WinUI 3 / .NET 8), Linux, and macOS — each in its own repository
  • System integrity, security posture, network monitoring, and threat detection on every platform
  • Controlled remediation: dry-run or confirmation-gated until the operator approves a change
  • React landing page that documents what each public Guardian repository actually ships
  • Stack: TypeScript · React · Vite · Tailwind CSS · .NET · Python · Shell
Live Demo See Code

Contact

Open to UAV, robotics, electronics, aerospace, and defense roles. Based in Southern California — open to relocation. US Citizen.

abelxmendoza@gmail.com
X GitHub LinkedIn YouTube