Skip to main content
Back to challenges
Challenge

Design Urban Air Mobility Flight Routing using Google ADK and Qwen 3

Urban air taxis like the ePlane face dynamic airspace constraints and micro-weather shifts during intra-city transit. Build a flight dispatch routing agent using Google Agent Development Kit (ADK) and Qwen 3 model runtime to continuously recalculate safe air corridors. Achieve 100% violation-free path clearance on simulated flight corridors.

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 autonomous flight dispatch planner using Google ADK and Qwen 3 models to resolve spatial airspace conflicts for eVTOL aircraft.

Delivery guide

How work is evaluated

Evaluation

Tests flight plan generation against dynamic spatial restricted zones and weather events.

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_violation_check

Ensures path intersects zero active restricted zones

Binary check

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

Dimension 2

route_safety_score

Percentage of waypoints maintaining mandatory safety buffer • 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

  • Utilize Google ADK agent architecture for spatio-temporal route planning

  • Integrate Qwen 3 vision and reasoning capabilities for processing dynamic radar overlays

  • Implement real-time airspace boundary checking and conflict detection

  • Ensure compliance with Director General of Civil Aviation (DGCA) drone/eVTOL corridor rules

Resources and assets

Reference links and supporting material

Dataset notes

GeoJSON terrain coordinates, weather threat overlays, and simulated urban airspace traffic streams.

Challenge setup

Tests flight plan generation against dynamic spatial restricted zones and weather events.

Challenge input

JSON object with start/end coordinates and no-fly zones

Google ADK

Offers agent abstractions for tool calling and context handling.

Qwen 3

Provides spatial reasoning and geometric computation support.

Evaluated output

JSON array of flight waypoints with clearance flags

Evaluation checks
  • Ensures path intersects zero active restricted zones
  • Percentage of waypoints maintaining mandatory safety buffer • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: Spatial Path Clearance Benchmark
  • Route Safety Score 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
  • Google · Required
  • Google ADK · Optional
Policy Serving
  • Qwen 3 · Optional

Evaluation contract

  • zero_violation_check · Weight 1
  • route_safety_score · Weight 1

Metrics

  • route_safety_score · Target 1

Benchmarks

  • Spatial Path Clearance Benchmark
  • robotics

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with start/end coordinates and no-fly zones

    Output: JSON array of flight waypoints with clearance flags

    Execution harness: Python

Evaluation tools

  • Google ADK · Agent Development Kit
  • Qwen 3 · Multimodal Model

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Design Urban Air Mobility Flight Routing using Google ADK and Qwen 3