Skip to main content
Back to challenges
Challenge

Drone Logistics Dispatch Multi-Agent System with CrewAI

Urban aerial delivery networks require real-time corridor monitoring and dynamic airspace re-routing under severe weather conditions. Build a collaborative drone fleet dispatch system using CrewAI to coordinate weather, airspace, and payload agents with zero corridor collisions.

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.

Orchestrate a role-playing multi-agent team for low-altitude urban air mobility dispatch using CrewAI.

Delivery guide

How work is evaluated

Evaluation

Evaluates dynamic drone corridor allocation accuracy under severe wind and airspace restriction scenarios.

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

check_no_redzone_penetration

Validates that approved corridor never intersects prohibited DGCA red zones

Binary check

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

Dimension 2

dispatch_safety_score

Composite safety score based on battery margins and clearance compliance • target: 0.95 • 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

  • Design role-playing agents using CrewAI Agent, Task, and Crew primitives

  • Implement inter-agent collaboration patterns (delegation, consensus)

  • Process DGCA DigitalSky airspace geo-fencing constraints in real-time

  • Optimize drone battery consumption vs delivery speed trade-offs

Resources and assets

Reference links and supporting material

Dataset notes

Simulated urban low-altitude airspace telemetry, weather radar overlays, and DGCA DigitalSky restricted zone coordinates.

Challenge setup

Evaluates dynamic drone corridor allocation accuracy under severe wind and airspace restriction scenarios.

Challenge input

JSON containing payload_weight_kg, start_coords, end_coords, and active_redzones

CrewAI

Role-playing multi-agent orchestration framework.

Evaluated output

JSON with corridor_waypoints, flight_approval, and projected_battery_used_pct

Evaluation checks
  • Validates that approved corridor never intersects prohibited DGCA red zones
  • Composite safety score based on battery margins and clearance compliance • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: Urban Air Mobility Flight Dispatch Benchmark
  • Dispatch Safety Score target: 0.95
  • 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
  • CrewAI · Required
  • crewAI · Optional
  • Ray Tune · Optional

Evaluation contract

  • check_no_redzone_penetration · Weight 1
  • dispatch_safety_score · Weight 1

Metrics

  • dispatch_safety_score · Target 0.95

Benchmarks

  • Urban Air Mobility Flight Dispatch Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing payload_weight_kg, start_coords, end_coords, and active_redzones

    Output: JSON with corridor_waypoints, flight_approval, and projected_battery_used_pct

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Orchestration Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Drone Logistics Dispatch Multi-Agent System with CrewAI