Autonomous Driving Computer System Detecting Environmental Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating environments where prior stored maps become outdated or inaccurate due to changes such as construction or accidents, which can lead to unsafe operation if they rely solely on outdated map data.
Innovation Solution
An autonomous driving computer system that compares stored location information of key objects with real-time sensor data to determine discrepancies, using metrics like maximum deviation, average deviation, and signed deviation to assess changes in the environment and adjust navigation accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle relies on prior stored map data for navigation, then the navigation system can operate efficiently using pre-collected information, but the system becomes unreliable when the environment changes (construction, accidents, lane shifts)
Solution Approach 1:
The system continuously compares real-time sensor detections of map objects (lane markings, barriers, signs) with the prior stored electronic map representation. This feedback mechanism detects discrepancies between expected and actual object locations, enabling the system to identify when the environment has changed and the stored map is no longer accurate, thus maintaining navigation reliability despite environmental changes
Solution Approach 2:
The system performs preliminary comparison of detected objects with stored map data before relying on the map for navigation decisions. By proactively detecting discrepancies in object locations, shapes, or characteristics, the system can switch from map-based navigation to sensor-based navigation before the outdated map causes navigation errors
2Measurement precision
If the autonomous vehicle uses multiple sensors (lasers, sonar, radar, cameras) to detect objects, then the detection accuracy and environmental awareness improve, but the system complexity and computational requirements increase
Solution Approach 1:
The system segments the sensor data processing by identifying and tracking specific map-related objects (lane markings, barriers, signs, curbs) separately from other objects. Each object type can be detected and compared with the stored map independently, reducing the computational complexity of processing all sensor data while maintaining high detection accuracy for navigation-critical objects
Solution Approach 2:
The sensor system is designed to perform multiple functions: detecting objects for navigation, comparing with stored map data, identifying environmental changes, and providing feedback for map updates. This multi-functionality reduces the need for separate specialized systems, managing complexity while maintaining detection precision
3Adaptability or versatility
If the autonomous vehicle continuously monitors and compares real-time sensor data with stored map information to detect environmental changes, then the system can adapt to changes and maintain safety, but the computational load and processing time increase
Solution Approach 1:
The system extracts only the critical map objects (lane markings, barriers, signs, curbs) from the complete stored map representation for comparison with real-time sensor data. By focusing computational resources on these essential navigation elements rather than processing the entire map, the system achieves environmental adaptability with reduced processing time and computational load
Data Source
AI summary
A autonomous driving computer system determines whether a driving environment has changed. One or more objects and/or object types in the driving environment may be identified as primary objects. The autonomous driving computer system may be configured to detect the primary objects and/or object types, and compare the detected objects and/or object types with the previous known location of the detected object and/or object types. The autonomous driving computer system may obtain several different metrics to facilitate the comparison. A confidence probability obtained from the comparison may indicate the degree of confidence that the autonomous driving computer system has in determining that the driving environment has actually changed.