Service Overview

System Test AI

FPT Automotive's system-test-ai automates system-level validation, HIL/SIL loop simulation, and ISO 26262 functional safety compliance. Integrates AUTOSAR, CANoe, and MATLAB/Simulink into Jenkins/GitLab pipelines and SDV DevOps environments with virtualized SILS boards. Automatically generates test cases, validates edge models through a 3-stage validation pipeline (AI Model → Hardware → Vehicle Loop), and analyzes vision-based inspections to cut execution time by 75%.

ISO 26262Test AutomationAUTOSARFunctional Safety

75%

Test execution time cut

ISO 26262

Functional safety compliance

18.7×

Inference speedup on hardware

99.7%

Vision inspection accuracy

3 stages

Model/Hardware/Vehicle loop

Capabilities

Key capabilities

End-to-End Test Automation

Comprehensive system-level testing from requirements to validation.

HIL/SIL Support

Full support for Hardware-in-the-Loop and Software-in-the-Loop testing environments.

Traceability Matrix

Complete traceability from requirements to test cases to results.

Automated Test Generation

AI generates system test scenarios based on requirements and specifications.

Performance Optimization

75% reduction in test execution time through intelligent test scheduling.

Technology

Technology stack

System Test AI architecture diagram
Component Technology
Test Framework AUTOSAR, CANoe
Simulation MATLAB/Simulink, CarMaker
Test Generation LLM, AI models
Traceability Requirements management tools
CI/CD Jenkins, GitLab CI

Use cases

Real-world applications

Documented outcomes from actual deployments.

1

AI Model Validation Pipeline

Three-stage validation pipeline (AI Model Loop → Hardware Loop → Vehicle Loop) to validate AI models for automotive applications within tight production timelines, ensuring both performance targets and functional safety are met.

Before

No structured pipeline to validate AI models against rigorous automotive performance criteria

After

Both AI models deployed and exceeded production targets on schedule

5.99% accuracy improvement
18.7× inference speedup
2

Vision AI Door Inspection — 2s at 99.7% Accuracy

Automated computer-vision inspection system for door-panel screw verification. System evaluates each unit in real time and returns an immediate pass/fail decision — replacing manual visual checks with an AI-driven test running at production speed.

Before

3-minute manual visual check per door; bottleneck worsened with throughput growth and still missed defects under pressure

After

AI inspection at 99.7% accuracy in 2 seconds; operators only intervene on flagged items

99.7% inspection accuracy
2s vs 3 min manual
$200K annual savings

How we work

Implementation approach

1

Phase 1: Requirements Analysis

  • Analyze system requirements and specifications
  • Define test scenarios and acceptance criteria
  • Plan HIL/SIL test environment setup
2

Phase 2: Test Generation & Automation

  • Generate system test cases from requirements
  • Automate test execution in HIL/SIL environments
  • Create traceability matrix
3

Phase 3: Validation & Optimization

  • Execute tests and validate results
  • Optimize test execution order and scheduling
  • Ensure comprehensive requirement coverage
4

Phase 4: Continuous Integration

  • Integrate with CI/CD pipeline
  • Automate regression testing
  • Monitor test results and quality metrics

Explore more

Related services