Autonomous Driving Safety Rule Generation for Complex Route Scenarios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving safety rule formulations, such as Responsibility-Sensitive Safety (RSS), are limited to simple scenarios and struggle to handle complex driving operations, failing to ensure both safety conditions and postconditions are met.
Innovation Solution
A safety rule generation device that pre-stores general-purpose scenarios and safety rules, using goal-aware RSS to divide complex routes into segments, assign scenarios, and generate overall safety rules that guarantee both safety and postconditions are satisfied.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If Responsibility-Sensitive Safety (RSS) is used for safety rule formulation, then safety conditions can be mathematically proven, but complex driving scenarios cannot be handled
Solution Approach 1:
The patent divides complex driving scenarios into multiple sub-scenarios and further segments them into atomic scenarios. Each atomic scenario is handled by specific safety rules, allowing the system to manage complexity while maintaining comprehensive coverage. The route is also segmented into route segments, with general-purpose scenarios assigned to each segment.
Solution Approach 2:
The patent creates general-purpose scenarios that can be universally applied to multiple route segments. These general-purpose scenarios serve multiple functions: they can be assigned to different route segments, connected in sequences, and reused across various driving contexts, enhancing adaptability without sacrificing safety guarantees.
2Ease of operation
If simple collision avoidance rules are applied, then same-lane same-direction scenarios are handled, but complex multi-scenario routes cannot be managed
Solution Approach 1:
The patent segments complex routes into multiple route segments and further divides scenarios into hierarchical levels (general-purpose scenarios into sub-scenarios into atomic scenarios). This segmentation allows simple rules to be applied to each segment while collectively handling complex multi-scenario routes through systematic composition.
Solution Approach 2:
The patent implements a nested structure where general-purpose scenarios contain sub-scenarios, which in turn contain atomic scenarios. Similarly, overall safety rules are generated by connecting multiple general-purpose safety rules in sequences. This nesting enables simple atomic rules to be composed into complex route-level safety guarantees.
Data Source
AI summary
A safety rule generation device includes a memory and a processor coupled to the memory. The memory stores a plurality of general-purpose scenarios for an autonomously-operable moving body to execute a predetermined driving operation, and a plurality of general-purpose safety rules previously calculated so as to complete the general-purpose scenarios while satisfying a predetermined safety condition. The processor receives an input of route information in which a route of travel from a starting position to a target position is divided into a plurality of route segments, assigns the general-purpose scenarios to the respective route segments, and generates an overall safety rule in which the general-purpose safety rules corresponding to the general-purpose scenarios are connected according to an order of the route segments.


