Skip to contentSkip to content
Verified credentials. On-chain. Forever.Learn more
Cover image for Train an Object Detector for an Autonomous-Forklift Robotics Startup
Code

Train an Object Detector for an Autonomous-Forklift Robotics Startup

FreeVerified credential3 weeksAdvanced

Overview

What this challenge is about.

You receive 12,000 labeled warehouse images (pallets, pedestrians, forklifts) plus a 1,500-image safety-test set heavy on pedestrian edge cases. Train an object detector (YOLOv8 or RT-DETR are good baselines) and tune for pedestrian recall above 0.99 at the operating point while keeping mAP above 0.7 across all classes. Profile latency on Jetson Orin (or a documented x86 proxy if hardware is unavailable). Write a 3-page safety-case appendix documenting the operating point, edge-case failures, and recommended mitigations.

CredentialBlockchain-anchored
ShareableLinkedIn-ready
LanguageEnglish
PaceSelf-paced

The Brief

What you'll do, and what you'll demonstrate.

Train a real-time pallet-and-pedestrian detector with pedestrian recall above 0.99 at the chosen operating point and on-device latency under 35 ms per frame.

Earning criteria — what you'll demonstrate

  • Train modern object detectors on domain-specific data
  • Select operating points under hard safety constraints
  • Profile and budget on-device inference latency
  • Communicate model behavior to a safety-officer audience

Program Fit

Where this fits in your program.

Sharpens the same skills your degree expects you to demonstrate.

Skills

Skills you'll demonstrate.

Each one shows up on your verified credential.

Careers

Roles this prepares you for.

Real titles. Real skill bridges. Pick the one closest to your trajectory.

Computer Vision Engineer

Shipping a safety-critical detector with on-device latency budgets is exactly the work CV engineers do at robotics companies.

This challenge sharpens

  • object-detection
  • yolo
  • edge-deployment

Machine Learning Engineer

Profiling on-device inference and selecting operating points is core MLE work on edge-AI teams.

This challenge sharpens

  • edge-deployment
  • operating-point-selection
  • pytorch

AI Safety Researcher

Writing the safety-case appendix and documenting pedestrian failure modes is a stepping stone into AI safety research roles for safety-critical systems.

This challenge sharpens

  • safety-evaluation
  • operating-point-selection
  • object-detection

One more thing

You can put a credential on your CV by Friday.