Autonomous Driving Mode Transfer Using Scenario Safety Concepts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in efficiently processing and storing vast amounts of sensed information for obstacle detection, requiring substantial memory and processing resources.
Innovation Solution
A method involving the generation of sparse multidimensional signatures through iterative dimension expansion and merge operations, where irrelevant spanning elements are powered down to conserve energy, and hybrid processes using convolutional neural networks for object detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vast amounts of sensed information are processed and stored for obstacle detection, then detection accuracy is improved, but memory and processing resources are substantially consumed
Solution Approach 1:
The patent extracts only the essential and relevant features from sensed information rather than processing and storing complete data sets. By identifying and retaining only critical obstacle-related features, the system achieves accurate obstacle detection while significantly reducing memory resource consumption.
Solution Approach 2:
The patent creates simplified representations or models of obstacle information rather than storing complete sensed data. These compressed representations capture essential obstacle characteristics enabling accurate detection with minimal memory storage requirements.
2Reliability
If complete sensed information is processed for obstacle detection, then detection reliability is improved, but processing resources are substantially consumed
Solution Approach 1:
The patent extracts only the critical features necessary for reliable obstacle detection from complete sensed information. By processing and retaining only essential features rather than all sensed data, the system maintains detection reliability while substantially reducing processing resource consumption.
Solution Approach 2:
The patent applies partial processing to sensed information, focusing computational resources only on extracting and analyzing features that are critical for obstacle detection. This selective processing approach ensures reliable detection while avoiding the excessive resource consumption that would result from processing complete information sets.
3Measurement precision
If high accuracy object identification is achieved through detailed processing, then detection robustness is improved, but power consumption increases
Solution Approach 1:
The patent extracts only the essential features required for accurate object identification rather than performing detailed processing of complete sensed information. This feature extraction approach maintains high identification accuracy while significantly reducing the power consumption associated with processing all available data.
Data Source
AI summary
A method for safe transfer between manned and autonomous driving modes, the method may include detecting, based on first sensed information sensed during a first period, a situation related to an environment of the autonomous vehicle; searching for one or more matching concepts of a group of reference concepts, to which the situation belongs, each reference concept of the group represents a plurality of situations and has a reference concept safety level; wherein for each reference concept of at least a sub-group of the group of reference concepts the safety level of the reference concept is based on a tested success level of at only some of the plurality of scenarios represented by the reference concept; and determining, based on an outcome of the searching, whether the vehicle is capable to safely autonomously drive through the environment.