feat: add presentation demo mode
This commit is contained in:
@@ -1,41 +1,61 @@
|
||||
# Jury Q&A
|
||||
|
||||
## 1. Why 2D, Not 3D?
|
||||
## 1. Why Is This Not Just An Animation?
|
||||
|
||||
The animation is driven by a deterministic state machine, classifier, sensor state, actuator state, metrics and event log. The scene visualizes domain state instead of playing a decorative timeline.
|
||||
|
||||
## 2. How Is Classification Connected To The Actuator?
|
||||
|
||||
`classifyItem` returns B/C/D. The simulation maps that category to `ROUTE_TO_B`, `ROUTE_TO_C` or `ROUTE_TO_D`, which changes gate and pusher states and draws the physical route.
|
||||
|
||||
## 3. How Do You Prove The Route Was Correct?
|
||||
|
||||
The decision tree shows thresholds and PASS/FAIL, the scene shows the selected command and route arrow, and Event Log records state, command/category and item id.
|
||||
|
||||
## 4. Where Are OZON Rules Reflected?
|
||||
|
||||
The rules are explicit in classification limits: min/max dimensions, roundness threshold and C priority. Criteria Coverage maps these rules to scenarios and docs.
|
||||
|
||||
## 5. How Does The Operator Safely Stop The System?
|
||||
|
||||
The `emergency_stop` scenario enters `EMERGENCY_STOP`, stops conveyor target speed and requires Reset. In Presentation Mode, Safe Demo requires confirmation before fault scenarios.
|
||||
|
||||
## 6. What Happens On Sensor Failure Or Low Confidence?
|
||||
|
||||
Low confidence is logged as a warning. The system still applies deterministic dimensions/roundness rules as a fallback and shows this in the panel.
|
||||
|
||||
## 7. Why 2D, Not 3D?
|
||||
|
||||
2D is enough for MVP validation: it shows geometry, timing, sensor positions, routes and state transitions without spending effort on heavy rendering.
|
||||
|
||||
## 2. Where Is Computer Vision?
|
||||
## 8. What Is Needed For A Physical Prototype?
|
||||
|
||||
Replace pseudo-CV with a real CV service, connect PLC/robot telemetry, calibrate sensor latencies, add hardware interlocks and persist event logs.
|
||||
|
||||
## 9. Where Is Computer Vision?
|
||||
|
||||
The MVP uses pseudo-CV: bbox, dimensions, confidence and latency are derived from mock items. The architecture keeps CV output separate from classification, so a real CV service can replace it later.
|
||||
|
||||
## 3. How Is Classification Correctness Proven?
|
||||
## 10. How Is Classification Correctness Proven?
|
||||
|
||||
The decision tree shows PASS/FAIL for dimensions and roundness, actual values, thresholds and final category. Tests cover key boundary cases.
|
||||
|
||||
## 4. How Are Dimensions And Circular Section Handled?
|
||||
## 11. How Are Dimensions And Circular Section Handled?
|
||||
|
||||
Dimensions are checked first against min/max width, depth and height. If they pass, roundness is checked against threshold 0.8.
|
||||
|
||||
## 5. Why Does C Have Priority Over D?
|
||||
## 12. Why Does C Have Priority Over D?
|
||||
|
||||
Oversized or undersized items are operationally unsafe for the main line and must be diverted first. Therefore dimensions check precedes roundness.
|
||||
|
||||
## 6. How Is Synchronization Shown?
|
||||
## 13. How Is Synchronization Shown?
|
||||
|
||||
Cycle timeline shows state order, simulated timestamps, durations and status: done, active, pending or skipped.
|
||||
|
||||
## 7. How Does The Actuator Part Work?
|
||||
## 14. How Does The Actuator Part Work?
|
||||
|
||||
The stop-gate fixes the item. B opens the gate, C extends pusher C, D extends pusher D, then mechanisms return home.
|
||||
|
||||
## 8. What Happens On Jam?
|
||||
## 15. What Happens On Jam?
|
||||
|
||||
The system enters FAULT, conveyor target speed becomes 0, actual speed decays toward 0, and Reset is required.
|
||||
|
||||
## 9. What Happens On Low CV Confidence?
|
||||
|
||||
A warning is logged, but the system still classifies by deterministic dimensions and roundness rules.
|
||||
|
||||
## 10. How To Scale This To A Real Hardware-Software System?
|
||||
|
||||
Replace pseudo-CV with a CV service, connect PLC/robot telemetry via backend/WebSocket, persist event logs, calibrate sensor latencies and add recovery policies.
|
||||
|
||||
Reference in New Issue
Block a user