Autonomous Vehicle Trajectory Planning With Interaction Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle control systems fail to accurately predict collisions with dynamic obstacles, particularly other vehicles, due to the lack of consideration for interaction between the vehicle and proximate dynamic vehicles, leading to suboptimal behavior and potential collisions.
Innovation Solution
A data-driven prediction-based system for trajectory planning that utilizes sensors to collect data, a computing device, and a prediction module to forecast the trajectories of other vehicles and dynamic objects, adjusting the vehicle's path to avoid obstacles and ensure safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional autonomous vehicle control systems use polynomial expressions or mathematical functions to represent spatial information for trajectory planning, then the system complexity is reduced and ease of operation is improved, but the measurement precision of collision prediction with dynamic obstacles deteriorates
Solution Approach 1:
The patent introduces an intermediary prediction module that acts as a mediator between the simple polynomial trajectory planning and the complex dynamic obstacle behavior. This module uses learned interaction patterns to predict future positions of dynamic obstacles, bridging the gap between simple control operations and accurate collision prediction without requiring complex real-time calculations.
Solution Approach 2:
The system performs preliminary action by pre-learning interaction patterns between vehicles and dynamic obstacles during a training phase. These learned patterns are stored and later used to quickly predict obstacle behaviors during actual operation, allowing accurate collision prediction without complex real-time computation while maintaining simple polynomial trajectory planning.
2Device complexity
If conventional autonomous vehicle control systems do not consider interactions with proximate dynamic vehicles, then the device complexity is reduced and processing speed is improved, but the reliability of collision avoidance deteriorates
Solution Approach 1:
The patent segments the complex problem of collision avoidance into two independent parts: (1) simple polynomial trajectory planning for the autonomous vehicle, and (2) a separate prediction module that handles dynamic obstacle behavior prediction. This segmentation allows each module to remain simple while their combination achieves high reliability in collision avoidance by accounting for interactions with proximate dynamic vehicles.
3Measurement precision
If the system uses data-driven prediction to forecast trajectories of other vehicles and dynamic objects, then the measurement precision of collision prediction is improved, but the use of energy and computational resources increases
Solution Approach 1:
The patent merges the trajectory prediction function with the existing polynomial-based control system by integrating a relatively simple prediction module that uses pre-learned interaction patterns. This combination achieves high trajectory prediction accuracy while avoiding the need for complex energy-intensive simulations or real-time heavy computational models, as the prediction relies on stored learned behaviors rather than exhaustive real-time calculation.
Data Source
AI summary
A data-driven prediction-based system and method for trajectory planning of autonomous vehicles are disclosed. A particular embodiment includes: generating a first suggested trajectory for an autonomous vehicle; generating predicted resulting trajectories of proximate agents using a prediction module; scoring the first suggested trajectory based on the predicted resulting trajectories of the proximate agents; generating a second suggested trajectory for the autonomous vehicle and generating corresponding predicted resulting trajectories of proximate agents, if the score of the first suggested trajectory is below a minimum acceptable threshold; and outputting a suggested trajectory for the autonomous vehicle wherein the score corresponding to the suggested trajectory is at or above the minimum acceptable threshold.