Skip to content

Mode Virtual (V) — Overview

Design, simulate, and control a virtual drilling system using standardized interfaces. Mode Virtual (V) emphasizes closed-loop control, data semantics, and clear reporting over hardware.

Cases (2025.1)

  • Connect through D‑WIS to the OpenLab Drilling Simulator and implement detection/response for a simulated influx (kick).
  • Focus on reliable signal handling, thresholds/logic for detection, appropriate automated actions, and clear operator feedback.
  • Validate against provided test cases; document assumptions, limits, and performance.
  • Build a virtual drilling system model and controller that adapts to changing lithology to maximize ROP under constraints.
  • Incorporate realistic constraints (e.g., slide/rotate modes, dogleg limits), virtual measurements with uncertainty, and automatic re-planning based on as-drilled surveys.
  • Produce trajectory data (Minimum Curvature) and plan-vs-actual plots; log surveys and controller decisions for review.
  • Reach TD with low torsional oscillations; demonstrate dysfunction detection/mitigation while meeting constraints.
  • Emphasize robust control design and monitoring; present time-aligned evidence from logs and plots.

New team? Start here

Most first-time teams are successful by starting with the OpenLab Drilling Simulator and focusing on the control system and data handling, rather than building a simulator from scratch.

Tooling & Interfaces

  • D‑WIS semantics: standardized names/metadata for setpoints and measurements. See the D‑WIS Vocabulary Index.
  • OpenLab simulator: the plant used for Mode Virtual (V) scenarios. See the OpenLab website.
  • Connectivity and discovery, expected signals, and example flows are described in Technical Specs.

Technical Specs

Edge‑deployable models

  • Expectation: focus your effort on generating/fine-tuning data and optimizing compact multimodal models.
  • Inference‑only, offline, JSON outputs (e.g., Explain‑This‑Event or Rig‑State Textualizer).
  • Small‑model, edge‑deployable focus: teams may prototype with larger cloud‑hosted models during development, but final deliverables and performance are evaluated using locally run or on‑rig small models under limited inference hardware.
  • Suggested caps: ≤2 vCPU or ≤20 W GPU, ≤4–8 GB RAM (non‑LLM) and ≤8 vCPU or ≤1,150 W GPU, ≤16–64 GB RAM (LLM); ≤15 min total inference runtime. Rig compute otherwise open. All AI runs must be offline during judging; no PLC/actuator writes.
  • Custom task option: teams may propose a custom offline JSON task with objective ground truth and the same interface for pre‑approval (recommended deadline: 2026‑02‑01). Approved tasks use the same AI sub‑rubric and scale to +10.

Design for discovery

On competition day, endpoints and available signals may change. Your software must discover available D‑WIS signals and adapt accordingly.

Phases & Timing

  • Phase I — Design: monthly updates plus a design report and optional short video.
  • Phase II — Implementation & testing: enhance the model and controllers; final test occurs at the end of the cycle.

Dates vary each year. See the living schedule for what’s open now.

Timeline & Milestones Upcoming Dates

What You Submit

  • Monthly updates, Phase I design report (and optional video), and a Phase II package with data, plots, and a short presentation.
  • Directional option: Minimum Curvature trajectory, plan-vs-actual plots, survey logs with acceptance flags, and controller rationale.
  • Well control option: detection and control logic description, test results, and logs.

Full details and file naming live on the Deliverables page.

Deliverables

How You’re Judged

  • Directional option: drilling system model realism, control scheme quality, app robustness/UX, and performance vs. objectives.
  • Well control option: performance, app robustness/UX, and control scheme quality.

Weights and rubrics are on the Judging page.

Judging

Overview Technical Specs Deliverables Judging

Getting Started Checklist

  • Confirm your team is registered (registration closed 2025-12-31); if you missed the window, contact the committee at competition@Drillbotics.com
  • Review the Technical Specs for D‑WIS and OpenLab expectations.
  • Review the three Mode V cases and pick your initial target.
  • Stand up a minimal data flow: connect, discover signals, and log data.
  • Implement a basic control loop with clear state display and logging.
  • Build required plots/reports incrementally as you test.

References