Self-directed project
Amazon Robotics - Black-Friday Fleet Coordination
Software Engineering · September 2026
A ProoV case study · educational project, not employment
Built an end-to-end warehouse fleet coordination solution for a Black-Friday-scale fulfillment center: framed the bottleneck as aisle congestion and dock contention, implemented optimal single-agent A*, extended it to cooperative A* with centralized vertex-and-edge reservations, and validated staggered charging plus dispersed idle parking in simulation. The final pitch tied the policy to zero-collision operation, reduced wait time, and a concrete single-zone pilot ask.
Graded against
- Problem framing & operational stakes20%
- Algorithmic depth - A* and cooperative coordination30%
- Coordination policy realism - deadlock, charging, idle25%
- Throughput trade-off analysis15%
- Executive pitch to leadership10%
Passed · pass mark 55/100
What stood out6
- Implemented A* with Manhattan heuristic on a 4-connected grid and showed it expanded fewer nodes than Dijkstra while preserving optimality.
- Built a reservation table keyed by (cell, tick) and explicitly blocked head-on swaps with edge reservations.
- Chose a realistic coordination policy: centralized control, priority/watchdog deadlock handling, staggered charging, and dispersed perimeter idle parking.
- Used simulator outputs to identify a concave throughput curve and locked onto a concrete fleet-size operating point.
- Leakage-Free Multi-Agent Coordination
- Honest Search and Simulation Evaluation
The work I submitted20 tasks
12 tasks · 6.8k characters · Python · 8 written answers · 198 words
- Role And Mission115 characters
- Amazon Robotics Context459 characters
- Program Overview133 characters
- Grid World Theory104 characters
- State Representation Task341 characters
- State Representation Task ValidatorPython · 1.8k characters
- Phase1 Recap348 characters
- Astar Theory124 characters
- Astar Implementation Cell2.6k characters
- Astar Solution Correct4 characters
- Single Unit Challenge465 characters
- Phase2 Recap374 characters
- Role And Mission1 word
- Amazon Robotics Context37 words
- Program Overview1 word
- Grid World Theory1 word
- State Representation Task1 word
- State Representation Task Validator133 words
- Phase1 Recap23 words
- Astar Theory1 word
Summarised on purpose — the submitted code and writing stay private so this page cannot be reused as an answer key. The full submission sits behind the verified certificate.