Skip to main content
Back to challenges
Challenge

Build an AutoGen Urban Air Mobility & Vertiport Dispatch System

Emerging Electric Vertical Takeoff and Landing (eVTOL) mobility startups demand automated airspace and vertiport scheduling systems. Build an AutoGen multi-agent system where Flight Operations Agents and Vertiport Controller Agents negotiate flight paths while maintaining zero collision conflicts.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Develop an AutoGen agent conversation system managing airspace corridors and vertiport landing slots for urban air mobility vehicles.

Delivery guide

How work is evaluated

Evaluation

Evaluates collision-free flight scheduling and battery clearance constraint compliance.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

zero_conflict_check

Ensures scheduled flight slots have zero spatial conflicts

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

scheduled_ratio

Ratio of validly assigned flights to total flight requests • target: 1 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Build multi-agent AutoGen routing environments for electric aircraft dispatch

  • Implement flight path conflict resolution algorithms between autonomous agents

  • Manage battery state-of-charge constraints during route calculation

  • Output verified flight plan manifests in airspace regulatory formats

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic airspace routing telemetry and vertiport landing slot schedules.

Challenge setup

Evaluates collision-free flight scheduling and battery clearance constraint compliance.

Challenge input

JSON flight dispatch request array with battery state and desired slot

AutoGen

Multi-agent negotiation framework

Evaluated output

JSON flight schedule manifest with conflict_count

Evaluation checks
  • Ensures scheduled flight slots have zero spatial conflicts
  • Ratio of validly assigned flights to total flight requests • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: Autonomous Mobility Scheduling Benchmark
  • Scheduled Ratio target: 1
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • AutoGen · Required
  • ZenML · Optional
  • All Hands AI · Optional

Evaluation contract

  • zero_conflict_check · Weight 1
  • scheduled_ratio · Weight 1

Metrics

  • scheduled_ratio · Target 1

Benchmarks

  • Autonomous Mobility Scheduling Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON flight dispatch request array with battery state and desired slot

    Output: JSON flight schedule manifest with conflict_count

    Execution harness: Python

Evaluation tools

  • AutoGen · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build an AutoGen Urban Air Mobility & Vertiport Dispatch System