Autonomous Vehicle Trajectory Selection Using Perceived Risk Costs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles navigating complex environments face challenges in selecting trajectories that balance objective safety with perceived risk, leading to potential passenger discomfort and increased likelihood of human intervention.
Innovation Solution
The system determines a trajectory for an autonomous vehicle based on perceived risk by optimizing an overall cost function that includes risk components, allowing the vehicle to choose a path that minimizes perceived risk while maintaining objective safety standards.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles select trajectories based only on objective safety constraints, then safety is ensured, but passenger comfort and perceived safety deteriorate
Solution Approach 1:
The system changes the parameters of trajectory evaluation by introducing perceived risk cost components alongside traditional safety constraints. The cost function includes parameters for perceived safety, comfort, and natural driving behavior, allowing the vehicle to select trajectories that optimize both objective safety and passenger experience by adjusting weightings of different cost components.
2Ease of operation
If autonomous vehicles prioritize perceived risk minimization, then passenger comfort improves, but navigation efficiency may deteriorate
Solution Approach 1:
The system adjusts parameters in the cost function to balance perceived risk and navigation efficiency. By modifying the weighting of perceived safety costs versus time and distance costs, the vehicle can adapt its behavior to achieve acceptable passenger comfort while maintaining reasonable navigation efficiency through optimized parameter selection.
3Reliability
If autonomous vehicles use complex cost functions with multiple risk components, then trajectory optimization improves, but computational complexity increases
Solution Approach 1:
The system segments the complex cost function into distinct, manageable components: safety constraint costs, perceived risk costs, and efficiency costs. Each component can be calculated and optimized independently, then combined to form the overall trajectory selection criterion, reducing computational complexity while maintaining comprehensive optimization.
Data Source
AI summary
Systems and methods for selecting a trajectory for an autonomous vehicle based on perceived risk are provided. A trajectory is selected that satisfies objective safety constraints and minimizes an overall cost based at least in part on cost components representing the perceived risk of the trajectory. The vehicle is navigated according to the selected (e.g., optimized) trajectory.