Autonomous Vehicle Trajectory Costing With Safety-First Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in prioritizing roadway safety while navigating through dynamic environments, as existing motion planning systems often compromise safety for passenger comfort and other factors, leading to potential accidents and inefficiencies.
Innovation Solution
A computer-implemented method and system that generates and evaluates trajectories for autonomous vehicles by prioritizing safety costs over total costs, using sub-cost functions and relational propositions to ensure safe navigation, incorporating sensor data and dynamic adjustments to optimize motion planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing motion planning systems prioritize passenger comfort and other factors over safety, then passenger comfort and operational efficiency are improved, but roadway safety deteriorates leading to potential accidents
Solution Approach 1:
The cost function is segmented into multiple independent sub-cost functions, each evaluating a specific motion planning criterion (safety, comfort, efficiency). This segmentation allows the system to independently optimize safety without compromising other factors, as each sub-cost can be weighted and adjusted separately in the total cost calculation.
Solution Approach 2:
The system dynamically changes parameters by adjusting the weights of different sub-cost functions based on situational context. When safety risks are detected, the safety sub-cost weight is increased, automatically reparameterizing the optimization problem to prioritize safety over comfort or efficiency in critical situations.
2Productivity
If motion planning systems use complex cost functions to evaluate multiple criteria, then navigation efficiency and decision-making accuracy are improved, but computational complexity increases
Solution Approach 1:
The complex cost function is divided into modular sub-cost functions that can be independently computed and evaluated. This segmentation reduces computational complexity by allowing parallel evaluation of different criteria and enabling selective computation based on situational relevance.
Solution Approach 2:
Different sub-cost functions are activated or emphasized based on local environmental conditions. For example, safety sub-costs are prioritized in high-risk zones while efficiency sub-costs dominate in safe conditions, creating a locally optimized cost evaluation that reduces overall computational burden.
3Measurement precision
If the system generates and evaluates multiple trajectories with different cost functions, then trajectory selection accuracy and safety are improved, but processing time and computational resources increase
Solution Approach 1:
The system evaluates multiple trajectories but uses partial evaluation strategies where not all sub-cost functions are computed for all trajectories. Instead, trajectories are preliminarily filtered using critical safety sub-costs, and only promising candidates undergo full evaluation, reducing processing time while maintaining accuracy.
Solution Approach 2:
The system dynamically adjusts the number of trajectories evaluated and the depth of cost function evaluation based on situational urgency. In time-critical situations, fewer trajectories are evaluated with simplified cost functions, while in less urgent situations, more comprehensive evaluation is performed.
Data Source
AI summary
Systems and methods for autonomous vehicle motion planning are provided. Sensor data describing an environment of an autonomous vehicle and an initial travel path for the autonomous vehicle through the environment can be obtained. A number of trajectories for the autonomous vehicle are generated based on the sensor data and the initial travel path. The trajectories can be evaluated by generating a number of costs for each trajectory. The costs can include a safety cost and a total cost. Each cost is generated by a cost function created in accordance with a number of relational propositions defining desired relationships between the number of costs. A subset of trajectories can be determined from the trajectories based on the safety cost and an optimal trajectory can be determined from the subset of trajectories based on the total cost. The autonomous vehicle can control its motion in accordance with the optimal trajectory.