mlautomotivehackathon

Road Entertainment System - Hack Dearborn Winner

ML-powered in-cabin recommendation system with 89% accuracy, winner of Hack Dearborn 2023 Automotive Track & ZF Challenge.

View Source Code

The Problem

In-car entertainment systems lacked personalized, intelligent recommendations based on trip context and user preferences.

The Solution

Built ML-powered system using trip ETA, age detection, and user genres to suggest media, integrated with Google Maps API and hand gesture controls.

Impact & Results

89% recommendation accuracy with gesture controls for collaboration tools and volume adjustments

89% recommendation accuracy

Winner of Hack Dearborn 2023

Integrated with Google Maps API

Hand gesture controls for collaboration

Tech Stack

Machine LearningGoogle Maps APIGesture RecognitionPython

Links

Source Code

Other Projects

Undergraduate Co-op Thesis - LLM based In-Cabin Comfort System

Scalable local LLM-based reasoning system for real-time in-cabin comfort prediction and entertainment suggestions using multi-modal sensor data.

aiautomotive

REC-IT Recreation Center App

Full-stack web app for Kettering University's Rec Center with in-app check-in, equipment checkouts, and events scheduling.

webfull-stack

Back to Projects