Perception-Based Parking Assistance for Dynamic Rule Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for autonomous vehicles struggle with accurately determining permitted parking locations due to static and outdated information in location-based traffic management databases, and the complexity of interpreting temporary changes in parking rules.
Innovation Solution
A perception-based parking assistance system that uses on-board sensors to capture and parse data, generating virtual parking strips and associating them with parking rules based on perceived features and the tracked motion of the vehicle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If location-based traffic management databases are used to determine parking locations, then vehicle navigation assistance is provided, but the information becomes obsolete over time leading to inaccurate parking location data
Solution Approach 1:
The system transitions from static database information to dynamic real-time perception. The autonomous vehicle uses onboard sensors (cameras, LIDAR) to continuously detect and update parking strip geometry and parking signs in the current environment, ensuring the information reflects the actual current state rather than outdated database records.
Solution Approach 2:
The vehicle performs self-updating of parking location information by using its own sensors to perceive and interpret parking signs and strip markings in real-time. The system independently validates and updates its understanding of parking rules without relying on external database updates, making the information current through self-observation.
2Adaptability or versatility
If traditional database systems are used for parking information, then navigation assistance is provided, but temporary changes to parking rules are not captured
Solution Approach 1:
The system continuously perceives the environment through onboard sensors and compares detected parking signs with the current path of travel. When temporary changes such as covered signs or new markings are detected, the system immediately updates its understanding of parking rules, providing real-time feedback about current parking permissions rather than relying on stale database information.
Solution Approach 2:
The system proactively detects and interprets parking signs and strip geometry before the vehicle reaches the relevant location. By preliminarily identifying temporary changes in parking rules through real-time perception, the system can prepare appropriate navigation decisions in advance rather than reacting to outdated information.
3Measurement precision
If perception-based systems are used to detect parking signs, then real-time parking information is obtained, but the complexity of processing sensor data increases
Solution Approach 1:
The system extracts only the relevant parking information from sensor data by filtering for specific features such as parking signs, strip markings, and geometric characteristics of parking areas. Rather than processing all sensor data, the system selectively extracts parking-related features, reducing computational complexity while maintaining detection precision.
Solution Approach 2:
The parking detection system segments the complex sensor data into distinct components: detection of parking signs, identification of strip geometry, interpretation of markings, and validation against the path of travel. This segmentation allows each component to be processed independently with specialized algorithms, managing overall system complexity.
Data Source
AI summary
In various examples, perception-based parking assistance systems and methods for an ego-machine are presented. Example embodiments may determine a location of a real-world parking strip relative to an ego-machine and an associated parking rule for the parking strip. A virtual parking strip and one or more virtual parking signs may be generated based at least in part on one or more detected features in an environment of the ego-machine and a tracked motion of the ego machine, and the virtual parking strip may be used to track parking strip locations and associated parking rules. The virtual parking strips and associated rules may be relied upon by an ego-machine to determine parking locations and/or to navigate into a suitable parking spot.