Predicting Unused Parking Duration for Automated Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing presence of automated self-driving vehicles on the road necessitates efficient parking solutions, as vehicles often pay for more time than used, leading to unused parking durations and potential penalties, which can be avoided by transferring these durations between vehicles.
Innovation Solution
A system and method utilizing an artificial neural network to predict and transfer unused parking durations between vehicles, considering contextual situations, behavior factors, geographical location, and events, with the ability to store payments as blockchain nodes, facilitating efficient parking continuity and incentives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If vehicles pay for more parking time than used, then the possibility of avoiding penalties or fines is improved, but unused parking duration is wasted
Solution Approach 1:
The system recovers unused parking duration from vehicles that leave early and transfers it to other vehicles needing parking, converting what would be wasted time into a useful resource for others through the neural network prediction and matching system
Solution Approach 2:
The system uses neural networks to continuously learn from parking patterns, vehicle behaviors, and transfer outcomes to improve predictions of unused duration availability and optimize transfer affinity calculations, creating a feedback loop that enhances system efficiency
2Productivity
If parking duration is transferred between vehicles, then parking usage efficiency is improved, but system complexity increases
Solution Approach 1:
The system introduces an intermediary platform with neural networks that mediates between vehicles with unused parking duration and vehicles needing parking, managing the complex matching, prediction, and transfer coordination through a centralized intelligent system
Solution Approach 2:
The system dynamically changes parameters such as transfer affinity scores, prediction confidence levels, and contextual weights based on real-time conditions, allowing flexible optimization of parking transfers without rigid complex rules
3Measurement precision
If neural network predictions consider multiple factors, then prediction accuracy is improved, but computation time increases
Solution Approach 1:
The system performs preliminary actions by pre-processing contextual data, vehicle behavior patterns, and historical parking information before prediction is needed, storing processed features that can be quickly retrieved during actual prediction moments
Solution Approach 2:
The prediction system is segmented into multiple independent neural network components that process different aspects (vehicle behavior, contextual situation, geographical factors) separately and combine results, allowing parallel computation and reducing overall computation time
Data Source
AI summary
An artificial neural network trained to predict the availability of an unused duration of a parking space based on input features is executed. Input features may include at least a contextual situation associated with the second entity, a behavior factor associated with a first entity that has been using the parking space, geographical location and time, events occurring within a threshold distance from the parking space. The artificial neural network may be further trained to output a transfer affinity based on the predicted availability of an unused duration, the contextual situation associated with the second entity and the behavior factor associated with the first entity. Based at least on the transfer affinity, the second entity can be selected. The unused duration can be transferred to the second entity from the first entity. The transferring can also include storing a payment and associated computation as a blockchain node in a blockchain.