Radar Occupancy Grid Parking Spot Selection in Crowded Lots
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parking systems rely on infrastructure sensors or vision sensors that struggle to identify and confirm parking spot availability and dimensions, especially in crowded environments where spots are occluded, limiting the ability to perform natural and practical front-in perpendicular parking.
Innovation Solution
A radar-centric occupancy grid (RCOG) map system using vehicle-mounted sensors to identify and select parking spots based on characteristics such as width, turning radius, and longitudinal distance, enabling autonomous parking without passing the spot.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vision sensors (cameras) are used to identify parking spots, then the system can detect parking spot availability and dimensions, but the system fails in crowded environments where spots are occluded by parked vehicles
Solution Approach 1:
The patent combines multiple sensor types (radar, LIDAR, ultrasonic sensors, and vision sensors) into a unified sensing system. The radar-centric occupancy grid map integrates data from these different sensors to create a comprehensive environmental model that works effectively in both open and crowded parking environments, overcoming the limitations of vision-only systems.
Solution Approach 2:
The patent introduces radar as an intermediary sensing modality that can penetrate occlusions and detect objects behind parked vehicles. The radar occupancy grid serves as a mediator that fills in gaps where vision sensors fail, enabling the system to detect parking spots and obstacles that are not visible to cameras.
2Reliability
If infrastructure sensors are used to identify parking spots, then the system can reliably detect available spots, but the system is limited to specific parking lots and parking garages
Solution Approach 1:
The patent enables the vehicle to detect and identify parking spots using its own onboard sensors (radar, LIDAR, ultrasonic sensors, cameras) rather than relying on external infrastructure sensors. The vehicle independently creates its own occupancy grid map and identifies parking opportunities, making the system universally applicable to any parking environment without requiring specialized infrastructure.
Solution Approach 2:
The multi-sensor system with radar-centric occupancy grid mapping is designed to be universally applicable across different parking environments (open lots, crowded garages, structured parking). The system performs multiple functions including obstacle detection, parking spot identification, and navigation planning, making it adaptable to various conditions without infrastructure dependencies.
3Measurement precision
If the system needs to pass a parking spot to confirm its availability, then the system can verify spot characteristics, but the system cannot perform natural front-in perpendicular parking
Solution Approach 1:
The patent performs preliminary detection and verification of parking spot characteristics (availability, dimensions, obstacles) using radar and other sensors before the vehicle begins its parking maneuver. The occupancy grid map is created in advance, allowing the system to identify suitable spots and plan the front-in parking path without needing to pass by the spot first.
Solution Approach 2:
The patent replaces the mechanical requirement to physically pass by a parking spot (which vision systems need to verify characteristics) with a radar-based detection system. The radar can detect spot characteristics and obstacles from a distance and through occlusions, eliminating the need for the vehicle to maneuver past each potential spot to confirm its suitability.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables efficient identification and selection of parking spots in crowded environments, allowing vehicles to perform natural front-in parking maneuvers autonomously, without the need for infrastructure sensors or passing the spot.
Implementation Method 1
identifying, using sensor data obtained from one or more sensors of a host vehicle, one or more available parking spots near the host vehicle in a parking environment, the one or more sensors including a radar system and the sensor data including a radar occupancy grid (ROG) map
Data Source
AI summary
This document describes techniques and systems for identifying and selecting a parking spot using radar-centric occupancy grid (RCOG) maps. An example system includes a processor that can identify available parking spots near a host vehicle using sensor data, including a radar occupancy grid (ROG) map. Parking-spot characteristics of each available parking spot are also determined using the sensor data. The processor can then determine a selected parking spot based on the parking-spot characteristics. The processor or another processor can then control operation of the host vehicle to park in the selected parking spot using an assisted-driving or autonomous-driving system and based on the parking-spot characteristics. In this way, the described system can identify, select, and navigate to a parking spot using a RCOG map without having to rely on infrastructure sensors or pass by open spots.