Build a Volumetric Inspection Coverage Planner
Parse optical bounding box dimensions from initial inspection logs to coordinate robotic multi-camera volumetric scans. Synthesize secondary camera poses with MoveIt to eliminate occlusion zones.
What you are building
The core problem, expected build, and operating context for this challenge.
Parse optical bounding box dimensions from initial inspection logs to coordinate robotic multi-camera volumetric scans. Synthesize secondary camera poses with MoveIt to eliminate occlusion zones.
Robotics Vision Engineer
Parse initial optical inspection defect coordinates and bounding volume from telemetry logs.
Calculate occlusion zones and coverage deficits based on cell geometry and robot arm reach limits.
Generate secondary camera pose waypoints to achieve complete volumetric inspection coverage.
Compile an automated inspection sequence trajectory for the robot controller to execute.
Terminal console outputting a trajectory plan and 3D coordinate visualizations for secondary camera sweeps.
Mock JSON test fixtures containing initial optical defect viewpoints, bounding box limits, and occlusion ratios. These are explicitly simplified synthetic app records, not complete official schema files. Starter examples below are synthetic. They are not downloaded records.
MoveIt robotics Uses MoveIt kinematic reachability envelope principles from Source 1 to ensure secondary camera poses are valid within the robotic cell.
mastra-ai, pydantic, numpy. Mastra AI provides deterministic workflow state handling to orchestrate occlusion detection and secondary pose generation steps. Local model to categorize inspection states and evaluate spatial coverage heuristics.
Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.
Calculates secondary poses correctly: if occlusion_ratio < 0.6, generates two offset poses by adding/subtracting 20 from x/y and adding 15 to z. Otherwise, requires manual inspection.
Fails safely when requested camera poses exceed normalized robotic cell reach maximums.
Outputs valid JSON with generated pose coordinates or manual inspection flags.
```json [ { "input": { "assembly_id": "WELD-01", "initial_view": { "x": 210, "y": 140, "z": 45 }, "occlusion_ratio": 0.4 }, "expected_output": { "assembly_id": "WELD-01", "action": "GENERATE_POSES", "new_poses": [ { "x": 230, "y": 120, "z": 60 }, { "x": 190, "y": 160, "z": 60 } ], "coverage_achieved": true } }, { "input": { "assembly_id": "WELD-02", "initial_view": { "x": 620, "y": 140, "z": 45 }, "occlusion_ratio": 0.8 }, "expected_output": { "assembly_id": "WELD-02", "action": "MANUAL_INSPECTION_REQUIRED", "new_poses": [], "coverage_achieved": false } } ] ```
Outputs are limited to recommended camera pose trajectories and require human confirmation before sending commands to actual robot controllers. Use mock external writes. Require human review before any real deployment.
Participation guide
Outputs are limited to recommended camera pose trajectories and require human confirmation before sending commands to actual robot controllers. Use mock external writes and human review.
How work is evaluated
Calculates secondary poses correctly: if occlusion_ratio < 0.6, generates two offset poses by adding/subtracting 20 from x/y and adding 15 to z. Otherwise, requires manual inspection. Fails safely when requested camera poses exceed normalized robotic cell reach maximums. Outputs valid JSON with generated pose coordinates or manual inspection flags.
Runnable source, pinned dependencies, setup commands, working interface, example outputs, recorded demo, tests, and action logs.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
Complete workflow
Parse initial optical inspection defect coordinates and bounding volume from telemetry logs. Calculate occlusion zones and coverage deficits based on cell geometry and robot arm reach limits. Generate secondary camera pose waypoints to achieve complete volumetric inspection coverage. Compile an automated inspection sequence trajectory for the robot controller to execute.
Missing or incorrect.
Partly complete, with documented gaps.
Complete, with reproducible evidence.
Correctness and evidence
Calculates secondary poses correctly: if occlusion_ratio < 0.6, generates two offset poses by adding/subtracting 20 from x/y and adding 15 to z. Otherwise, requires manual inspection. Fails safely when requested camera poses exceed normalized robotic cell reach maximums. Outputs valid JSON with generated pose coordinates or manual inspection flags.
Missing or incorrect.
Partly complete, with documented gaps.
Complete, with reproducible evidence.
Review interface
Terminal console outputting a trajectory plan and 3D coordinate visualizations for secondary camera sweeps.
Missing or incorrect.
Partly complete, with documented gaps.
Complete, with reproducible evidence.
Safe execution
Outputs are limited to recommended camera pose trajectories and require human confirmation before sending commands to actual robot controllers.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Parse initial optical inspection defect coordinates and bounding volume from telemetry logs.
Calculate occlusion zones and coverage deficits based on cell geometry and robot arm reach limits.
Generate secondary camera pose waypoints to achieve complete volumetric inspection coverage.
Compile an automated inspection sequence trajectory for the robot controller to execute.
Reference links and supporting material
Mock JSON test fixtures containing initial optical defect viewpoints, bounding box limits, and occlusion ratios. These are explicitly simplified synthetic app records, not complete official schema files. Supplied starter examples are synthetic, not source extracts.
Challenge setup
Configuration summary for this challenge.
Challenge input
Input details are not configured.
Mastra AI
TypeScript agent framework.
Evaluated output
No output checks are configured.
- Parse initial optical inspection defect coordinates and bounding volume from telemetry logs. Calculate occl...
- Calculates secondary poses correctly: if occlusion_ratio < 0.6, generates two offset poses by adding/subtra...
- Terminal console outputting a trajectory plan and 3D coordinate visualizations for secondary camera sweeps.
- 2 public reference cases
- 2 configured tools
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
- Mastra AI · Optional
- Mastra AI · Optional
Evaluation contract
- Complete workflow · Weight 40
- Correctness and evidence · Weight 30
- Review interface · Weight 20
- Safe execution · Weight 10
Reference cases
- 2 public reference cases
Workflow tasks
No workflow tasks are configured.
Recipe freeze marker
No recipe freeze time is recorded.