Automated parking development solution

Deploy safe and reliable automated parking systems (APS) up to 12x faster with our development solution.
See details

Customer challenge

While automated parking systems (APS) utilize technologies similar to advanced driver-assistance systems (ADAS), automotive engineering teams must overcome parking-specific challenges when bringing APS to production.
Parking operational design domains (ODDs) are incredibly diverse
Sensors must provide 360-degree coverage and detect nearby and farther-off objects
Perception must reliably detect and classify parking spots across diverse ODDs
Parking lots are often unstructured and unmapped

Applied Intuition’s solution

Applied Intuition’s automated parking development solution empowers automakers and Tier 1 suppliers to develop reliable APS by providing the following key features:
Pre-constructed ODD taxonomies, test suites, and maps
Re-simulation to test sensing and perception with drive logs
MLOps tools to curate training datasets by mining real logs and generating synthetic data
Object simulation with physics-based vehicle dynamics and behaviors

Develop and scale robust APS

Streamline the development and validation of APS with simulation and data tools that cover parking ODDs, multi-sensor suites, and test cases. 

Model and evaluate performance across an ODD

Kickstart development with pre-made ODD taxonomies, simulation maps, and test suites.

Adapt to the long tail of an ODD with tools to customize taxonomies, maps, 3D content, and test cases.

Scale simulation across an ODD with cloud orchestration.

Utilize multi-sensor perception and localization testing

Develop safer APS by accurately modeling parking systems with multi-sensor simulation of ultrasonics, fisheye and rectilinear cameras, radar, and lidar. 

Reliably develop, test, and validate sensing, perception, or the end-to-end APS stack by using log re-simulation or sensor SIL or HIL.

Efficiently develop ML-based perception using real and synthetic data

Efficiently curate training datasets from drive logs with data mining and auto-labeling tools.

Complement real datasets with targeted synthetic datasets that have annotations and diversity of parking spaces, signs, road markings, and beyond.

Tools to develop and test classical or ML-based planning, prediction, and controls

Object-level sensors mock out perception so teams can unit test planning, prediction, and controls.

Realistically test planning, prediction, and controls by utilizing vulnerable-road-user (VRU) and park-in/park-out behaviors, metrics for parking quality, and physically accurate vehicle dynamics.

Develop and scale robust APS

Streamline the development and validation of APS with simulation and data tools that cover parking ODDs, multi-sensor suites, and test cases.

Model and evaluate performance across an ODD

Kickstart development with pre-made ODD taxonomies, simulation maps, and test suites.

Adapt to the long tail of an ODD with tools to customize taxonomies, maps, 3D content, and test cases.

Scale simulation across an ODD with cloud orchestration.

Utilize multi-sensor perception and localization testing

Develop safer APS by accurately modeling parking systems with multi-sensor simulation
of ultrasonics, fisheye and rectilinear cameras, radar, and lidar.

Reliably develop, test, and validate sensing, perception, or the end-to-end APS stack by using log re-simulation or sensor SIL or HIL.

Efficiently develop ML-based perception using real and synthetic data

Efficiently curate training datasets from drive logs with data mining and auto-labeling tools.

Complement real datasets with targeted synthetic datasets that have annotations and diversity of parking spaces, signs, road markings, and beyond.

Tools to develop and test classical or ML-based planning, prediction, and controls

Object-level sensors mock out perception so teams can unit test planning, prediction, and controls.

Realistically test planning, prediction, and controls by utilizing vulnerable-road-user (VRU) and park-in/park-out behaviors, metrics for parking quality, and physically accurate vehicle dynamics.

Build reliable APS that improve safety and increase driver comfort

Validate performance, safety, and reliability

Powered by ML to increase APS reliability by shifting testing and validation left from the real world into simulation.

Customize as your program matures

Directly customizable maps, scenarios, and more to extend simulation results to the long tail of the parking ODD.

Accelerate development up to 12x and reduce cloud costs by up to 70%

Highly accurate pre-built parking ODD taxonomies, maps, and test suites. Efficient cloud simulation to optimize speed and cost.

Get started with our automated parking development solution

Learn how Applied Intuition can help your team develop reliable APS.
Contact us