Autonomous Vehicle Trajectory Planning With Dynamic Obstacle Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle control systems fail to accurately predict interactions with dynamic obstacles, particularly other vehicles, leading to potential collisions due to the inability to account for their unexpected behaviors.
Innovation Solution
A data-driven prediction-based system that utilizes sensors and a computing device to collect data, generate initial trajectory options, and predict the reactions of nearby vehicles and objects using a prediction module, refining the trajectory planning process through iterative data collection and prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional autonomous vehicle control systems use polynomial expressions or mathematical functions to represent spatial information of the driving path, then the vehicle can avoid stationary obstacles, but the system cannot accurately predict collisions with dynamic obstacles such as other vehicles
Solution Approach 1:
The system transitions from static polynomial path representation to dynamic trajectory prediction that adapts to moving obstacles. The prediction module continuously updates predicted trajectories of dynamic obstacles based on their current motion states, enabling the system to respond to changing environmental conditions rather than relying on fixed mathematical path representations.
Solution Approach 2:
The patent introduces a prediction module as an intermediary component between the perception system and the control system. This module specifically predicts the future trajectories of dynamic obstacles, serving as a bridge that translates current obstacle states into future position predictions, which then inform the trajectory planning and control decisions.
2Device complexity
If the autonomous vehicle does not consider interaction with proximate dynamic vehicles, then the control system is simpler, but the vehicle cannot achieve optimal behavior and may collide with dynamic obstacles
Solution Approach 1:
The control system is segmented into distinct functional modules: a prediction module that specifically handles dynamic obstacle trajectory prediction, a trajectory planning module that generates candidate paths, and a control module that executes maneuvers. This segmentation allows the system to incorporate complex interaction modeling without overwhelming the entire control architecture, maintaining manageability while improving safety.
Solution Approach 2:
The prediction module performs preliminary action by forecasting the future positions and trajectories of dynamic obstacles before the vehicle makes control decisions. This advance prediction allows the trajectory planning module to proactively adjust the vehicle's path to avoid predicted collisions, rather than reacting to obstacles after they are detected.
3Measurement precision
If the system uses iterative data collection and prediction to refine trajectory options, then the trajectory planning accuracy improves, but the computational time increases
Solution Approach 1:
The system applies partial action by focusing computational resources on predicting and planning for the most relevant dynamic obstacles in the vehicle's vicinity rather than all objects in the environment. The prediction module prioritizes proximate dynamic vehicles that pose the greatest collision risk, performing iterative refinement only for these critical targets, thus balancing accuracy with computational efficiency.
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.