Recursive Vehicle Trajectory Prediction Using Future Interaction Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle movement prediction techniques for autonomous driving rely solely on past information, leading to erroneous predictions due to the inability to infer future driver actions accurately.
Innovation Solution
An electronic device using a recursive network to predict vehicle movements by incorporating both past and future information, detecting input data and generating first and second prediction data through a preset recursive network configuration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only past information is used for prediction, then the prediction system is simple, but the prediction accuracy deteriorates due to inability to infer future driver actions
Solution Approach 1:
The system performs preliminary prediction of future vehicle states by recursively applying the motion model to predicted future positions, allowing the system to anticipate future driver actions before they occur. This preliminary action enables more accurate prediction by considering future interactions rather than only reacting to past events.
Solution Approach 2:
The recursive network uses feedback loops where predicted future states are fed back into the prediction process. The system recursively predicts future positions, evaluates interactions at those positions, and uses this information to refine subsequent predictions, creating a feedback mechanism that improves prediction accuracy while managing complexity.
2Measurement precision
If future information is incorporated into prediction, then prediction accuracy improves, but computational complexity increases
Solution Approach 1:
The system applies partial action by focusing computational resources on predicting and evaluating only the most relevant future states and interactions. Rather than exhaustively simulating all possible future scenarios, the recursive network selectively processes future positions that are most likely to impact the prediction outcome, reducing computational power requirements while maintaining improved accuracy.
3Reliability
If recursive prediction with future interactions is used, then reliability of autonomous driving improves, but processing time increases
Solution Approach 1:
The system implements periodic action by updating predictions at discrete time intervals rather than continuously. The recursive network processes future interactions at scheduled prediction points, allowing the system to maintain high reliability through regular updates while controlling processing time by avoiding continuous computation. This periodic approach balances reliability requirements with real-time processing constraints.
Data Source
AI summary
An electronic device and an operating method thereof may be configured to detect input data having a first time interval, detect first prediction data having a second time interval based on the input data using a preset recursive network, and detect second prediction data having a third time interval based on the input data and the first prediction data using the recursive network. The recursive network may include an encoder configured to detect each of a plurality of feature vectors based on at least one of the input data or the first prediction data, an attention module configured to calculate each of pieces of importance of the feature vectors by calculating the importance of each feature vector, and a decoder configured to output at least one of the first prediction data or the second prediction data using the feature vectors based on the pieces of importance.