Automated Driving Trajectory Planning Using Path Feasibility Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated driving systems lack the ability to generate trajectories that consider the feasibility of predicted paths of mobile objects, leading to inefficient and potentially unsafe navigation.
Innovation Solution
An automated driving trajectory generating device that calculates predicted accelerations for each path based on the position and speed of mobile objects, identifies a target path using acceleration thresholds, and generates trajectories that account for the feasibility of these paths, including considerations for lateral and longitudinal accelerations, priorities, and direction indications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple predicted paths are calculated for mobile objects based on position and map information, then the coverage of possible trajectories is improved, but the computational complexity and processing time increase
Solution Approach 1:
The patent segments the trajectory generation process into distinct modules: mobile object recognition, path calculation, predicted acceleration calculation, target path identification, and trajectory generation. Each module handles a specific aspect of the problem, allowing for independent optimization and reducing overall computational complexity while maintaining comprehensive trajectory coverage.
Solution Approach 2:
The patent performs preliminary calculations of predicted accelerations for all possible paths before final trajectory selection. By pre-calculating acceleration characteristics and comparing them against threshold values, the system filters out infeasible paths early in the process, reducing the computational burden on subsequent trajectory generation steps.
2Speed
If predicted paths with low feasibility are used to generate trajectories, then the responsiveness of the automated driving system is improved, but the safety and appropriateness of navigation decrease
Solution Approach 1:
The patent introduces acceleration threshold values as a critical parameter to evaluate the feasibility of predicted paths. By calculating predicted accelerations and comparing them against predefined thresholds, the system objectively determines which paths are physically realizable and safe, filtering out infeasible trajectories while maintaining rapid response capability.
Solution Approach 2:
The system implements a feedback mechanism where predicted accelerations are continuously calculated and compared against threshold values to validate path feasibility. This feedback loop ensures that only trajectories meeting safety and physical constraints are selected, improving navigation reliability without sacrificing responsiveness.
3Measurement precision
If acceleration threshold comparison is performed for each predicted path, then the precision of path feasibility evaluation is improved, but the processing time increases
Solution Approach 1:
The patent extracts the critical evaluation criterion (acceleration threshold comparison) from the overall path selection process and applies it systematically to each predicted path. By focusing computational resources on this single, decisive metric rather than evaluating multiple complex factors, the system achieves high precision in feasibility evaluation with minimal processing time.
Data Source
AI summary
An automated driving trajectory generating device is configured to: recognize a mobile object which is located near a vehicle; calculate a host vehicle path for automated driving of the vehicle and a plurality of predicted paths of the mobile object based on a position of the vehicle on a map, a position of the mobile object on the map, and map information; calculate a predicted acceleration which is generated in the mobile object moving along a predicted path for each predicted path based on the plurality of predicted paths and a vehicle speed of the mobile object; identify a target path which is a predicted path used to generate the trajectory out of the plurality of predicted paths based on a result of comparison between the predicted acceleration and an acceleration threshold value; and generate the trajectory based on the host vehicle path and the target path.