Perception and localization

Use simulation, re-simulation, and synthetic data to inform advanced driver-assistance systems (ADAS) and automated driving (AD) decision-making.

See the workflow

“We use the most powerful and flexible simulation platforms in the self-driving industry.”

Mike Carter

Founding Engineer

Customer challenge

Testing ADAS and AD perception and localization systems in the real world is time-consuming and often difficult to execute and repeat at scale.

Real-world operations don’t capture all situations

One situation has many edge cases and variations

Certain events are dangerous to test in the real world

Collecting and labeling real datasets is costly

Applied Intuition’s solution

Applied Intuition’s solution allows teams to test ADAS and AD perception and localization systems at scale, identify edge cases, and ensure high-quality code.

Re-simulate failures found in the field

Generate synthetic datasets to train perception models using both classical and generative sensor simulation

Utilize sensor simulation to iterate rapidly

Develop high-performing perception and localization systems

01

Identify issues found in field testing

Search real-world logs using both structured queries and natural language to identify segments that challenged your ADAS or AD stack, including issues like driver interventions.

Data Explorer

02

Perform root cause analysis

Re-simulate the identified real-world logs to understand your ADAS or AD stack’s performance and determine necessary adjustments.

Data Explorer Log Sim

03

Improve and test perception modules

Modify perception modules or re-train machine learning (ML) models with synthetic data generated with both classical and generative sensor simulation to address the identified issues. Iteratively run sensor simulations to monitor progress across purpose-built test cases, and introduce variations across behaviors, weather, and lighting to ensure robustness.

Sensor Sim Synthetic Datasets

04

Scale testing to ensure safety

Execute a full test suite before merging changes or deploying a new stack version in the field to prevent regressions. Generate new test cases with natural language and parameter-based approaches to scale coverage across your ODD.

Sensor Sim Log Sim Validation Toolset Cloud Engine