Autonomous Vehicle Buffer-Based Multi-Objective Scenario Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face limitations in identifying and managing distinct vehicle operational scenarios due to limited resources and single-objective decision-making, which neglects risk, social acceptability, and passenger preferences.
Innovation Solution
A centralized shared scenario-specific operational control management system that uses a scenario-specific operational control evaluation module to identify multi-objective policies, considering safety, behavior preferences, and social acceptability, and selects vehicle control actions based on buffer values associated with these objectives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If single objective reasoning is used in decision making, then the decision making process is simple, but the decision making capability is limited and does not consider risk, safety, social acceptability, or passenger preferences
Solution Approach 1:
The patent segments the decision-making process into multiple independent objective functions (safety objective, social acceptability objective, passenger preference objective, etc.), each evaluated separately by dedicated evaluation modules. This allows the system to maintain relatively simple individual evaluation processes while achieving comprehensive multi-objective decision-making capability through the aggregation of segmented evaluations.
2Adaptability or versatility
If multi-objective policy is implemented, then the decision making capability is enhanced to consider multiple objectives, but the computational resources required increase
Solution Approach 1:
The patent implements partial action by using buffer values to selectively adjust only certain objectives when safety concerns arise, rather than re-evaluating all objectives. The buffer mechanism allows the system to make targeted adjustments to specific control actions based on safety buffer thresholds, reducing unnecessary computational overhead while maintaining comprehensive multi-objective decision-making capability.
Solution Approach 2:
The system performs preliminary evaluation of multiple objectives and pre-calculates buffer values for each objective before final decision-making. This preliminary action allows the system to identify potential safety issues and prepare adjustment strategies in advance, reducing the computational burden during real-time decision-making when the vehicle must respond quickly to dynamic conditions.
3Measurement precision
If scenario-specific operational control evaluation is performed, then the control accuracy is improved, but the system complexity increases due to multiple evaluation modules
Solution Approach 1:
The patent implements scenario-specific operational control evaluation modules that can be universally applied across different driving scenarios. Each evaluation module is designed to handle multiple objectives (safety, social acceptability, passenger preferences) in a unified framework, allowing the same modular structure to serve diverse scenarios such as lane changes, intersections, and pedestrian crossings without requiring entirely separate systems for each scenario.
Data Source
AI summary
An autonomous vehicle traverses a vehicle transportation network using a multi-objective policy based on a model for specific scenarios. The multi-objective policy includes a topographical map that shows a relationship between at least two objectives. The autonomous vehicle receives a candidate vehicle control action associated with each of the at least two objectives. The autonomous vehicle selects a vehicle control action based on a buffer value that is associated with the at least two objectives. The autonomous vehicle traverses a portion of the vehicle transportation network in accordance with the selected vehicle control action.