Mountain View, Calif., March 18, 2024 — Applied Intuition, an autonomous vehicle software company which develops AI-powered software that helps companies build, test, and deploy safe autonomous vehicles, announced its new automated parking development solution for advanced driver-assistance systems (ADAS) and automated driving (AD). The solution will allow ADAS and AD development teams to develop, test, and deploy ML-based or classical automated parking systems (APS) up to 12 times faster with improved safety and reliability. The solution aims to optimize parking spaces for vehicles with these features, making it easier and safer for drivers to park their cars.
APS enable vehicles to self-park, increasing safety and comfort for drivers, but they are traditionally difficult to develop. Automotive original equipment manufacturers (OEMs) and Tier 1 suppliers face numerous challenges when developing APS. These challenges include diverse operational design domains (ODDs), unpredictable vehicle and pedestrian movement in parking lots, and nonlinear vehicle dynamics. Furthermore, the need for highly accurate 360-degree sensor and perception coverage often demands advanced machine learning (ML) techniques. Moreover, examples include birds-eye-view (BEV) perception or occupancy networks.
Applied Intuition’s automated parking development solution addresses the key challenges of engineering an APS. It enables ADAS and AD development teams to enhance APS safety and reliability while reducing time to market. The solution includes:
- Pre-constructed ODD taxonomies, test suites, and maps, allowing development teams to customize simulations to their program needs
- 360-degree sensing and perception testing with multi-sensor software-in-the-loop (SIL) and hardware-in-the-loop (HIL) simulation is conducted. This simulation models APS sensors such as ultrasonics and fisheye cameras.
- Data mining and curation to optimize data-driven AI/ML development by rapidly assembling new training datasets that target specific model weaknesses
- Synthetic parking datasets to train ML-based perception, targeting specific edge cases and data gaps identified in model testing and dataset curation
- Realistic simulated vehicle dynamics and behaviors accurately model low-velocity and high-steering-angle vehicle behavior in unstructured parking lots. Moreover, this enables the testing of all planners and training of ML-based planners.
- Cloud orchestration to ensure simulation tests can be executed at scale across an ODD
These capabilities enable ADAS and AD development teams to develop safe and efficient APS up to 12x faster. They also reduce cloud simulation costs by up to 70% and improve the performance of ML-based perception on target edge cases by up to 3x.
“Safe and reliable APS can have a huge impact on driving comfort and convenience. Automated parking should be a smooth everyday experience. However, it’s hard to get right and most existing systems don’t work well outside the dealer lot demo,” said Peter Ludwig, CTO and Co-Founder of Applied Intuition. “Applied Intuition is empowering OEMs and Tier 1 suppliers to develop next-generation APS. These systems work outstandingly well anywhere a vehicle can park and offer the best possible experience for drivers and passengers.”
News related to Applied Intuition –
