Autonomous Vehicle Path Planning via Target Acceleration Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in planning safe paths while navigating through environments with moving and non-moving objects, as existing technologies struggle to accurately account for the dynamic accelerations of other vehicles and pedestrians, leading to potential collisions or near-collisions.
Innovation Solution
A method and system that determine a planned acceleration for an autonomous vehicle by predicting the optimal acceleration of targets, such as pedestrians or other vehicles, and revising this acceleration based on actual acceleration differences, using a filter to adjust safety thresholds and ensure safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses a static path planning method, then the computational complexity is reduced, but the vehicle cannot respond to dynamic changes in target acceleration, leading to potential collisions
Solution Approach 1:
The path planning system transitions from static to dynamic by continuously monitoring target acceleration and adjusting the vehicle's path in real-time. The system detects changes in target acceleration and dynamically modifies planning parameters, allowing the vehicle to adapt to moving objects while maintaining computational efficiency through targeted updates rather than complete replanning.
Solution Approach 2:
The system implements feedback by continuously monitoring the actual acceleration of detected objects and comparing it against predicted acceleration values. When deviations are detected, the system feeds this information back into the path planning algorithm to adjust the vehicle's trajectory, ensuring collision avoidance while responding to dynamic environmental changes.
2Reliability
If the autonomous vehicle continuously monitors and adjusts path based on target acceleration, then collision avoidance is improved, but the computational load and processing time increase
Solution Approach 1:
The system performs preliminary actions by pre-calculating potential path adjustments and maintaining a buffer of computed trajectories. When target acceleration changes are detected, the system can quickly switch to pre-computed paths rather than performing full replanning, significantly reducing the time required to respond to dynamic changes while maintaining safety.
3Productivity
If the autonomous vehicle uses simplified acceleration assumptions, then the computational processing is faster, but the measurement precision of target motion prediction deteriorates
Solution Approach 1:
The system dynamically changes parameters based on the detected motion characteristics of targets. When targets exhibit complex acceleration patterns, the system switches to more sophisticated prediction models with higher precision. For targets with simple motion patterns, the system uses simplified assumptions, thereby maintaining high processing speed while achieving accurate predictions when necessary.
Data Source
AI summary
A planned acceleration of a vehicle and a predicted optimal acceleration of a target is determined. Upon determining that an actual acceleration of the target differs from the predicted optimal acceleration, the planned acceleration of the vehicle is revised based on the actual acceleration of the target. The foregoing steps can be implemented by a vehicle computer according to program instructions stored in a memory of the vehicle computer. The vehicle can include sensors, actuators, and/or controllers in communication with the computer via a vehicle communication network.