Parallel Domain launched PD Forma, a software platform that converts raw real-world capture data into validated, simulation-ready environments in hours using advanced 4D reconstruction technology, helping autonomy teams accelerate testing and deployment.
- PD Forma combines 4D reconstruction, quality assessment, and scenario extraction into a single integrated pipeline for faster simulation workflows
- Teams can convert raw capture logs to simulation-ready environments in just hours without sacrificing fidelity or requiring extensive engineering resources
- The platform includes quality reports that compare rendered output to original capture data before publishing to simulation
- Customer usage has increased 19 times in six months, demonstrating strong market demand for the solution
- Supports multiple use cases including drone delivery, robotics, and autonomous vehicle testing across various environmental conditions
Parallel Domain launched PD Forma, software that transforms raw, real-world capture data into validated, simulation-ready environments in hours.
Powered by the firm's 4D Geometric Foundation Model, PD Forma is designed to help autonomy teams move faster, detect and solve failures early and simulate the complexity of the real world with confidence.
“With PD Forma, teams can move from real-world logs to validated, simulation-ready environments in just hours without sacrificing fidelity," says Zack Novak, Parallel Domain CEO. "We're helping customers accelerate their time to market by making program scale simulation more accessible and efficient. And we've seen demand explode; customer usage has increased 19 times over the past six months."
Key takeaways:
· Building on its PD Replica and PD Sim products, PD Forma is the end-to-end platform that brings reconstruction, quality assessment and scenario extraction into one pipeline. With PD Forma, autonomy teams scale their simulation workflows faster and without the engineering bandwidth traditionally required.
· PD Forma gives teams the full workflow to build replicas on their own through a web app, CLI or API. Teams validate and curate raw logs before upload, then process them in batches using pre-sets for driving, drone and indoor scenes. When a run fails, stage logs show what broke, and teams restart from that stage instead of starting over.
· Every replica comes with a quality report that compares the rendered output to the original capture, which can be reviewed before publishing the replica to PD Sim for camera, lidar and radar simulation.
· PD Forma streamlines the process of converting raw capture data into high-quality, simulation-ready environments and does so with 4D capabilities, allowing reconstruction of not only the static environment but also dynamic agents and behaviors within it.
· PD Forma is built to support a broad range of simulation needs, including:
Drone delivery: Turn flight logs into replicas of the neighborhoods a drone serves, then test every approach and drop-off at dawn, at dusk, in rain or in snow.
Robotics: Recreate the warehouses and facilities robots work in so teams can test around people and equipment before they deploy.
