Sensor Fusion Diagnostic Analyzer
Diagnose sensor fusion failures and validate multi-modal ADAS/AV perception alignment
What You Can Do
You can pinpoint the exact source of sensor fusion failures—whether they stem from misaligned camera/LiDAR/radar extrinsic calibration, timestamp desynchronization, data validation gaps, or algorithmic issues. This skill decomposes multi-modal perception errors into sensor-specific contributions and generates quantifiable diagnostic reports that directly guide calibration and testing teams toward fixes rather than blind troubleshooting.
Features
Cross-checks camera, LiDAR, and radar spatial alignment consistency to identify offset or rotation misalignments
Detects timestamp desynchronization patterns that cause positional discrepancies between sensor modalities
Decomposes multi-modal perception failures into individual sensor contributions for targeted diagnostics
Validates sensor data integrity, missing values, and outlier patterns that indicate upstream data pipeline issues
Maps detection failures to specific environmental conditions (rain, night, low-contrast) to isolate modality-dependent sensitivities
Produces structured root-cause analyses with quantifiable metrics and prioritized remediation recommendations
Compares pre/post-calibration update behavior to confirm whether changes resolved or introduced fusion failures
Prioritizes failures across sensor firmware, extrinsic calibration, and fusion algorithm domains for production issue response
Example Output
Example 1: Extrinsic Calibration Mismatch
Fusion Diagnostic Report
─────────────────────────
Failure Mode: Lateral offset in camera-LiDAR detections
Detected Root Cause: Extrinsic calibration (camera → vehicle frame)
Findings:
• Camera detections laterally offset +0.23m vs. LiDAR ground truth
• Rotation error around Z-axis: +2.1° (exceeds 0.5° threshold)
• Timestamp alignment: ✓ Within 40ms tolerance
• Data quality: ✓ No missing frames or outliers
Recommendation: Re-run camera extrinsic calibration using checkerboard/object targets. Prioritize rotation correction before lateral adjustment.
Example 2: Timestamp Desynchronization
Detected Root Cause: Temporal synchronization (LiDAR → CAN bus)
Findings:
• LiDAR frame timestamps drift +120ms relative to camera sync pulse
• Failure occurs predictably when vehicle speed >40 km/h (increased motion sensitivity)
• Pattern: ~100ms lag grows to ~150ms under acceleration
• Extrinsic calibration: ✓ Validated (within tolerance)
Recommendation: Check LiDAR PPS (pulse-per-second) synchronization to CAN/RTC clock source. Firmware update may be required.
What's Included
- SKILL.md instruction file with sensor fusion diagnostic methodology:
- Extrinsic Calibration Validation Checklist: step-by-step camera/LiDAR/radar alignment verification
- Temporal Synchronization Diagnostic Template: timestamp correlation analysis and drift detection
- Root-Cause Attribution Worksheet: structured decision tree to isolate calibration vs. algorithmic failures
- Perception Failure Condition Classifier: environmental mapping and modality-specific sensitivity matrix
- Diagnostic Report Template: production-ready format with quantified findings and remediation priority
Who It's For
- ADAS/AV Perception Engineers — diagnosing and validating multi-modal sensor fusion stack failures in development and production
- Sensor Calibration Specialists — root-cause analysis to determine whether extrinsic calibration updates are required
- OTA Software Engineers — triaging production perception issues and prioritizing firmware/calibration vs. algorithm fixes
- Test & Validation Engineers — correlating test log failures to specific sensor modality misalignments
- Systems Integration Leads — determining impact scope of sensor or fusion algorithm changes across the perception pipeline
Best For
- Troubleshooting spatial inconsistencies between camera and LiDAR detections (offset positions, rotation errors)
- Validating extrinsic calibration after hardware replacement, maintenance, or calibration updates
- Identifying temporal synchronization failures causing detection dropout or false positives in specific speed ranges
- Mapping perception failures to environmental conditions to isolate modality-dependent issues (weather, lighting, contrast)
- Prioritizing production OTA issues between sensor firmware, extrinsic calibration, and fusion algorithm domains
You might also like
You can systematically analyze suspension geometry, load paths, and component interactions to validate design decisions and identify optimization opportunities. Claude acts as your collaborative design partner to map force distributions, explore how geometry changes affect performance characteristics, compare suspension architectures, and reconcile conflicting engineering constraints in independent double-wishbone, multi-link, and other suspension systems.
You can transform vague customer NVH complaints into actionable diagnostic protocols by systematically mapping vibration sources, transfer paths, and receiver responses. The framework guides you through symptom normalization, operational condition analysis, and isolation strategy development—reducing diagnostic iteration cycles and accelerating root cause identification across powertrain, chassis, interior, and aerodynamic domains.
You can decode SAE J2012 standard CAN diagnostic trouble codes (P, B, C, and U codes) with manufacturer-specific extensions, analyze multi-frame fault sequences and temporal patterns across multiple modules, and generate structured diagnostic hypotheses that differentiate between electrical, communication, and algorithmic failures. This skill transforms raw DTC data into actionable investigation vectors, reducing diagnostic analysis cycles from hours to minutes while improving root cause accuracy.
You can quantify sensor fusion performance across object detection, classification, tracking, and localization using standardized metrics. The framework helps you identify systematic failure modes in diverse environmental conditions, document safety-critical gaps, and generate structured evidence packages for ISO 26262 and SOTIF compliance. This enables you to benchmark sensor configurations, define perception KPIs, and support regulatory submissions with rigorous performance documentation.
You can systematically investigate NVH complaints, conduct root cause analysis using transfer path analysis methodologies, plan and interpret diagnostic testing data, and develop evidence-based solutions across the full vehicle lifecycle. This framework guides you through multidisciplinary analysis—covering acoustics, mechanical dynamics, materials, and manufacturing variability—enabling faster problem resolution and more effective cross-functional communication with design, manufacturing, and supplier teams.
You can create multi-phase OTA rollout campaigns tailored to automotive safety constraints, hardware heterogeneity, and regulatory requirements. This skill helps you design canary deployments (2%, 5%, 20%, 100% increments), establish automated rollback thresholds, coordinate dependencies across ECUs, and communicate deployment risks to cross-functional stakeholders—transforming reactive firefighting into proactive, data-driven fleet management.
This skill systematically validates your OTA update architecture across five critical dimensions: partition and storage allocation for A/B slots and recovery images, safety and rollback mechanisms including atomic commit strategies, delta compression efficiency for cellular bandwidth optimization, regulatory compliance mapping against ISO 26262 and UN R156, and deployment risk identification including version conflicts and single points of failure. You identify architectural gaps before they cause field failures or fleet immobilization.
You can transform raw accelerometer data, sound pressure measurements, and frequency spectra into structured diagnostic insights. Claude helps you organize test data, interpret Campbell diagrams and waterfall plots, quantify source contributions through transfer path analysis, and correlate physical measurements with customer complaints. This systematic approach replaces intuitive troubleshooting with hypothesis-driven test plans and targeted solutions.