Roadmap

Current Status

We have the core hardware in hand — an ESP32-P4 module (Waveshare P4-NANO) for the submerged vision unit, Heltec Wireless Trackers for the smart buoy and base station. The software stack is open-source tooling: ESP-DL for on-device inference, ESP-IDF for firmware, LoRa for communications.

Dependency Graph

Not everything is sequential. The diagram below shows what actually blocks what — and where work can run in parallel.

flowchart LR
  subgraph hw["Hardware & Firmware"]
    direction LR
    CV["Core\nValidation"]
    WF["Waterproofing &\nField Trials"]
    RR["Ropeless\nRecovery"]
    EI["Energy\nIndependence"]
    CV --> WF --> RR --> EI
  end

  subgraph sw["Software & Intelligence"]
    direction LR
    HI["Harvest\nIntelligence"]
    DT["Deck\nTablet"]
    DP["Data\nPlatform"]
  end

  subgraph adv["Advanced Systems"]
    direction LR
    BD["Ballistic\nDeployment"]
    AD["Autonomous\nDeployment"]
  end

  CV -.->|BLE bridge| DT
  WF -->|real telemetry| DP
  WF -.->|training data| CV
  HI -.->|soak alerts| DT
  RR --> BD
  EI --> BD
  EI --> AD
  RR --> AD

  style CV fill:#0d3b3e,stroke:#1a8a8f,color:#5ec4c8
  style HI fill:#0d3b3e,stroke:#1a8a8f,color:#5ec4c8
  style WF fill:#1a2c2f,stroke:#4a6568,color:#8fa8ac
  style RR fill:#1a2c2f,stroke:#4a6568,color:#8fa8ac
  style EI fill:#1a2c2f,stroke:#4a6568,color:#8fa8ac
  style DT fill:#1a2c2f,stroke:#4a6568,color:#8fa8ac
  style DP fill:#0a1517,stroke:#2a3d40,color:#4a6568
  style BD fill:#0a1517,stroke:#2a3d40,color:#4a6568
  style AD fill:#0a1517,stroke:#2a3d40,color:#4a6568

Status Key

• Active — Currently in development
• Planned — Approved, starting when dependencies are met
• Future — Strategic vision, scope may evolve based on field testing

---

Hardware & Firmware Track

The physical system — from bench validation through self-sustaining ocean deployment.

Core Validation

Active

• Train and validate the species detection model on the ESP32-P4
• Build camera-only waterproof enclosure for underwater training data collection
• Build and test the servo door latch mechanism
• Integrate the submerged unit with the Heltec Tracker buoy over a wired tether
• Bench-test the full bidirectional command protocol
• Develop base station firmware with fleet management

Training Data Bootstrap

The species detection model needs real underwater images from the actual OV5647 NoIR sensor, but waterproofing the full system is a later milestone. Solution: build a camera-only waterproof enclosure now — PVC housing with an acrylic viewport, following the same approach described in the Waterproof Enclosure guide — and start collecting labeled images in parallel with bench validation. This decouples training data collection from the full waterproofing schedule.

Goal: Demonstrate end-to-end operation on the bench — catch event triggers classification, buoy relays result over LoRa, base station displays status and sends commands.

Waterproofing & Field Trials

Planned

Depends on: Core Validation

• Waterproof enclosure design for submerged unit
• Waterproof enclosure design for smart buoy
• Shallow-water field trials (dock-side, controlled environment)
• Open-water field trials with commercial crabbers
• Validate classification accuracy in real-world conditions
• Test LoRa range in maritime environment
• Battery life and solar charging validation

Goal: Prove the system works in real ocean conditions with real crabs.

Ropeless Recovery

Planned

Depends on: Waterproofing & Field Trials

• Design ballast release mechanism
• Integrate surface command with mechanical actuation
• Buoyancy testing and ascent rate characterization
• Safety validation (no hazard to boats, divers, or marine life during ascent)

Tether Resilience — see full design exploration: Tether Resilience & Subsea Autonomy

• Tether breakaway section design and force characterization
• Supercapacitor bank integration on submerged unit 5V rail
• Hardware watchdog latch prototype (RC timer + solenoid)
• Pre-wound spring mechanism for autonomous ballast release
• Combined failsafe bench testing (tether cut → supercap last gasp → watchdog → surface)

Recovery Hardware

• Standardized coupling point design (shared interface for drone and boat arm)
• RFID tag integration on pot/buoy for close-range identification
• Boat arm retrieval concept --- guided by base station GPS/telemetry data
• Spring-loaded hydrofoil fin mechanism (for drone tow --- separate from boat arm)

Goal: Eliminate the buoy line entirely. Pot surfaces on command from the base station. Breakaway tether and layered failsafes ensure the pot can survive and surface even after tether loss.

Energy Independence

Planned

Depends on: Ropeless Recovery

• Wave energy harvester prototype (linear electromagnetic generator)
• Hybrid solar + wave power management
• Extended deployment testing (weeks without maintenance)
• Ultra-low-power firmware optimization

Pneumatic Self-Sufficiency --- see Pneumatic Architecture

• Pneumatic frame-as-tank feasibility study (tube diameter, pressure rating, weld/braze integrity)
• Tesla turbine prototype for intermittent burst-charge power generation
• Pneumatic surfacing mechanism prototype (solenoid valve + buoyancy bladder)
• Data-only tether prototype (2-wire, ultra-thin, for v2 intermediate step)
• Rechargeable air system testing (fill time, cycle life, regulator reliability)

Goal: Self-sustaining buoy that operates indefinitely without battery swaps. Pneumatic architecture provides a path to full tether elimination --- compressed air powers electronics and enables self-surfacing from the pot frame itself.

---

Software & Intelligence Track

Data, analysis, and user-facing tools. Harvest Intelligence has no hardware dependency — it’s already underway.

Harvest Intelligence

Active

The system tells you when to pull — not your gut. Tidal awareness identifies the productive window. Soak time awareness prevents catch quality degradation. Together, they answer the only question that matters: which pots to pull right now, and in what order.

Tidal Phase:

• Tablet GPS → NOAA CO-OPS tide table lookup for deployment location
• Flood/ebb tide alerts (productive window opening and closing)
• Catch rate correlation with tidal phase (per-pot, per-location)
• Safe-to-soak confirmation for leaving pots across tidal cycles

Soak Time:

• Per-crab entry timestamp tracking (guest duration)
• Longest-guest-duration alert (configurable threshold)
• Bait effectiveness decay model (temperature-adjusted, configurable bait type)
• Catch rate decay detection (idle while pot has catch)
• Water temperature factor in soak recommendations
• Configurable regulatory soak limit with hard alert

Fleet Alerts:

• “Pot full” threshold alerts based on keeper count
• Idle pot detection (no catch events over configurable window)
• Soak quality score: composite 0–100 metric (guest duration + temperature + catch rate trend)
• Priority pull ranking: which pots to pull first based on combined intelligence

Tooling Available

The mcnoaa-tides MCP server already implements the NOAA CO-OPS integration needed here — including tidal phase classification, deployment briefings, and catch-tidal correlation. See Tools Reference.

Soak Time Biology

Soak time optimization is grounded in real fisheries biology — bait decay curves, in-pot cannibalism rates, and species-specific stress thresholds. See Soak Time Biology for the research basis behind these features.

Deck Tablet

Planned

Depends on: Core Validation (BLE bridge from base station)

Commercial crabbing happens in salt spray, diesel fumes, and direct sun. The operator interface needs to survive that environment and be usable with wet or gloved hands.

Hardware Requirements:

Requirement	Specification
Environmental rating	IP68 or MIL-STD-810H (salt fog, vibration, drop)
Display	10”+ IPS, 1000+ nits sunlight-readable
Connectivity	Bluetooth 5.0+ (BLE to base station), Wi-Fi (NOAA API, data sync)
Touch	Capacitive with wet-finger and glove mode
Mounting	RAM mount or AMPS-compatible for helm/console installation

Software:

• BLE connection from base station to tablet
• Fleet dashboard with map view (pot locations, status, drift alerts)
• Harvest intelligence alert UI (tidal window + soak time + pull priority)
• Command interface with confirmation dialogs (glove-compatible large touch targets)
• Catch data export and visualization
• Browser-based PWA — no app store dependency, works on any tablet meeting the hardware spec

Goal: The operator’s tablet becomes the primary command interface — live fleet map, one-tap commands, harvest intelligence alerts, and catch analytics at the helm. No specific tablet model is mandated; any device meeting the requirements above works.

Data Platform

Future

Depends on: Waterproofing & Field Trials (needs real telemetry data)

• Cloud ingestion pipeline for fleet telemetry
• Web dashboard for fleet-wide analytics
• Aggregated catch data API for fisheries managers
• Catch-per-tidal-cycle analysis and deployment optimization
• Seasonal pattern analysis across locations and conditions
• Regulatory compliance reporting

Goal: Move from per-boat operations to fishery-wide intelligence. Catch data correlated with tidal phase, location, season, and conditions creates optimization insights that used to take a lifetime on the water to develop — and gives fisheries managers real-time stock data instead of delayed survey estimates.

---

Advanced Systems Track

Long-horizon research that builds on the proven base system.

Ballistic Deployment

Future

Depends on: Ropeless Recovery, Energy Independence

• Collapsible hydrodynamic fairing design
• Pneumatic launch rail prototype
• Fairing-to-trap unfolding mechanism at depth
• Integration with ropeless recovery for full no-rope workflow

Goal: A crabber never handles rope at all — deploy by launch, recover by command. Dramatically faster deployment cycles, smaller deck footprint.

Autonomous Deployment

Future — Research

Depends on: Ropeless Recovery, Energy Independence

The logical endpoint of SmartPot: the cage is the vehicle. Each pot propels itself from the dock, navigates to a GPS waypoint, submerges, fishes, and either surfaces for pickup or returns home under its own power. This is speculative R&D that builds on the ballast and power systems from the hardware track.

See the full design exploration: Autonomous Deployment

Goal: No boat, no rope, no fuel, no empty pulls. A fleet of pots deploys itself from a dock pier and comes home full.