(video) LeddarVision™ LVP H – Automated Parking and Parking Assist Overview

LVP-H is a comprehensive fusion and perception software stack supporting premium ADAS L2/L2+ automated parking and parking assist applications, including intelligent parking assist (IPA), remote parking assist (RPA) and maneuver assist (MA). Based on LeddarVision™ low-level fusion (LLF) and perception technology, sensor modalities are optimally combined, pushing performance and reliability envelope beyond legacy solutions, for safer and more comfortable stress-free parking experience. LVP-H enhances valid parking detection probability to over 95% with low false detections in challenging ODDs and environments and provides superior dynamic and static object detection for enhanced safety, including support to advanced NHTSA IPA safety scenarios.

Features and Benefits
LVP-H utilizes a 4V4R sensor configuration, having four fish-eye cameras with 190° FoV, 1.3 Mpx resolution and four short-range corner radars with support to extension of up to 12 ultrasonic sensors. Sensor configuration and stack are designed to support a comprehensive stand-alone parking assistance application. Implementation on a domain controller with access to all sensor modalities allows to maximize the benefit of low-level fusion for increased performance and reliability.

LVP-H implements a complete stack handling sensors’ interface, calibration and synchronization, sensor fusion, dynamic and static object detection and classification, valid parking space detection, accurate 3D static environment modeling, continuous filtering and stabilization of objects and static environment, parking attributes detection, visual and vehicle odometry interface and ego-motion localization, providing a comprehensive environmental model and HMI visualization API to parking applications.

Product Family
LVP-H is part of the LeddarVision product family supporting ADAS evolution with a comprehensive product roadmap and growing features support. Targeting premium L2/L2+ automated parking and parking assist, LVP-H supports advanced applications including trained parking assist (TPA), garage parking assist (GPA) and reverse assist (RA). Extended perception and positioning include advanced localization and mapping, extended ODD operation and enhanced driving HMI to support the special needs of low-speed automated driving applications. Future LeddarVision Unified (LVU) product will provide unified support to ADAS and parking applications, combining the Surround (LVS) and Parking (LVP) product families to maximize the advantage of E/E architecture centralization trend, extending convergence of centralized processing into a single and unified environmental model for better applications development scalability and costs.

Hardware Platform

Sensor configuration: 4V4R + 12 USS (optional)
Fish Eye Cameras: Four fish-eye 1.3 Mpx, 190° x 150° FoV (Ficosa ADAEX eE or similar)
Corner radars: Four short-range corner radars (Continental SRR520 or similar)
Ultrasonic sensors: 8 to 12 sensor system (sensor type: TBD)
SoC/memory: TBD
ECU: TBD
Target Applications

High-performance multimodal parking perception solutions.
Safety: AEB VRU & AEB triggering (by static obstacles detection and USS sensors in low-speed environment).
Driving: L2/L2+ parking assist, including IPA (outdoor/indoor support and parallel/perpendicular/diagonal parking), MA, RPA, driver HMI (bird’s-eye view visual layer with perception data overlay).