The best way to develop safe and reliable machine perception systems

Realistic sensor simulation to diagnose, test, train, and monitor perception systems at scale

High-fidelity simulation API:

Render camera, lidar, and radar from script-driven scenarios in dynamic virtual environments or real-world scans (PD Replica)

Challenges with Drone Perception Development

Safe, Reliable Autonomous Performance

Edge Cases – Unique scenarios are critical for model accuracy and safety, but rarely seen in the real-world and often unsafe or impossible to capture

Observability – Changes to a perception model can have unintended consequences that are not observable until tested in the real-world 

Safety – Crashes can lead to litigation, regulatory scrutiny, and diminish brand perception

Solution – Continuously evaluate both standard and edge-case scenarios in a virtual world designed to mimic the real-world

Time, and Cost

New drone sensor rigs, and sensor types require recapturing sensor data, labeling, curation, and QA 

Entering new geographic markets requires new data and overcoming regulatory hurdles 

Regulation is constantly changing and evolving requiring rework to perception models

Solution – Generate the scenarios, test suites, and datasets you need in days, not months

Scalability across regions and hardware

New drone sensor rigs, and sensor types require recapturing sensor data, labeling, curation, and QA 

Entering new geographic markets requires new data and overcoming regulatory hurdles 

Regulation is constantly changing and evolving requiring rework to perception models

Solution – Simulate new camera configurations, enviornments, and scenarios by updating code, not recapturing data

Simulated drone sensor data

Parallel Domain Solutions

Evaluate

  • Observability - Nightly regression testing to monitor perception performance changes
  • Near validation testing in real-world location scans (PD Replica)
  • Software-in-the-loop, Closed-loop, and open-loop testing integration
  • Perception unit testing (edge cases, weather, lighting, regional differences)

Analyze

  • Benchmark against pre-defined or custom scenarios and sensor rigs, covering new regulations, accident data, locations, etc.
  • Explore sensor rig selection, rig configurations, model selection

Train

  • Scaled data generation for building or augmenting training data sets
  • Simulate in real-world location scans (PD Replica)
  • Build data sets covering infinite variations of edge cases, weather, geographic differences, lighting, sensor noise, etc

PD Replica - Closing the sim-to-real gap with real environments

Incorporate real-world scans as fully annotated, simulation-ready environments seamlessly integrated into Parallel Domain’s Data Lab API. Experience unparalleled variety and realism for model testing, training, and validation

Addressing Industry Challenges

Benefits

Save time and money while operating at scale

Simulate perfectly annotated sensor data in weeks rather than capturing, labeling, curating, and QAing real-world data that takes months. Run infinite variations of new scenario simulations with just a few lines of code.

Access new geographic regions and hardware configurations

Enter new markets more quickly by updating simulation assets and environments to match new needs. No need to recapture data when hardware changes, it is just a few small tweaks to our simulation sensor configurations.

Develop safe and reliable AI-driven systems

Ensuring safety and reliability comes from routinely testing your AI system against critical, rare, and exhaustive scenarios. Doing this across thousands of variations, in real or procedural environments provides additional assurance of systems performing as designed.

Schedule a Demo