Touching Grass with Local AI: Building Waypoint Autopilot

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

What I Built

Waypoint Autopilot is a mobile-first, privacy-centric Progressive Web App (PWA) designed to get you off the screen and into the real world. It generates autonomous, context-aware pedestrian exploration missions through your city or local parks without requiring you to constantly stare at a map.

It is built for urban explorers, mindful walkers, and anyone looking to discover hidden gems (like quiet greenways, historic landmarks, or vibrant pedestrian alleys) in their vicinity. By using an "Eyes Up, Phone Away" philosophy, the app calculates a deterministic route using open geographic data, delivers a locally-generated AI mission briefing before you leave, and then lets you cache the entire mission offline. While walking, it uses subtle audio and haptic cues to guide you from waypoint to waypoint, ensuring you remain present in your surroundings.

Demo

Since this application relies on a local AI model for mission preparation and heavily utilizes device-native features (like GPS and IndexedDB for offline storage), the best way to experience it is to run it locally!

journey
    title A Typical Waypoint Mission
    section Preparation
      Set anchor & radius: 5: User
      Select exploration style: 5: User
      Local AI generates brief: 4: AI
      Cache for offline use: 5: User
    section The Walk
      Put phone in pocket: 5: User
      Walk to Waypoint 1: 4: User
      Audio chime on arrival: 5: System
      Glance to confirm: 5: User
    section Completion
      Return to start: 4: User
      View mission summary: 5: User

Code

Joydeep2005Banik / waypoint

Waypoint Autopilot

Waypoint Autopilot is a mobile-first, installable web application (PWA) that guides a person through an ordered sequence of real-world geographic waypoints for pedestrian exploration of cities and parks.

It is designed around an "Eyes Up, Phone Away" philosophy: alerting walkers with distinct audio and glanceable waypoint cues upon arrival so they can keep their phones in their pockets.

---

Technical Stack & Architecture

• Frontend & App Framework: Next.js 14 (App Router), React 18, TypeScript (strict).
• Styling & Design System: Tailwind CSS with outdoor-optimized high-contrast palettes and 48px+ touch targets.
• Mapping & Geometry: Leaflet and React-Leaflet with OpenStreetMap tiles and pedestrian topology.
• Navigation State Machine: Pure TypeScript finite state machine with noisy GPS filters, arrival dwell confirmation, and route deviation detection.
• Local Persistence & Privacy: Local storage & IndexedDB for mission storage, waypoint logs, and offline tile caching. Zero remote tracking or telemetry.
• Open-Weight AI…

View on GitHub

How I Built It

Waypoint Autopilot is built using Next.js 14, React, Leaflet, and TailwindCSS for a sleek, highly-responsive mobile UI.

The Open-Source AI Integration:
The project uses Ollama running locally (specifically recommending the qwen2.5:1.5b open-weight model) to act as your personal "Mission Commander." Before you embark on your walk, the application queries the local LLM with the deterministic waypoints it gathered. The AI generates a rich, contextual pre-departure briefing—adding narrative flavor and context to the route based on the POIs.

Crucially, the AI is strictly sandboxed to the preparation phase. Pathfinding, obstacle avoidance, and waypoint progression are governed entirely by deterministic spatial algorithms (OSRM and OpenStreetMap Overpass API) to ensure pedestrian safety. The AI never hallucinates navigation instructions or routing.

Offline-First & Privacy Architecture:
Once the mission is prepared, the entire payload (route geometry, AI briefing, map data) is serialized into IndexedDB. A PWA Service Worker caches the application shell. You can completely disconnect from the internet and cellular data, and the app will continue to track your progress using offline device GPS. Furthermore, there is zero remote telemetry—no accounts, no analytics, and no continuous location tracking sent to any servers.

Why Does Open Innovation Matter?

Open innovation is the core enabler of Waypoint Autopilot.

If this app were built on closed APIs, it would be impossible to guarantee the absolute privacy of the user's location data. By using OpenStreetMap (ODbL) for POI discovery and routing, we bypass proprietary mapping ecosystems that monetize location history. By using Ollama and open-weight models running strictly on localhost:11434, the user's contextual data and starting location never leave their device to hit a corporate inference endpoint.

Open innovation makes it possible to build an application that genuinely respects the user's peace, privacy, and physical safety while still delivering a highly personalized, AI-enhanced experience.