18182195. TRAJECTORY IMPUTATION AND PREDICTION simplified abstract (HONDA MOTOR CO., LTD.)
Contents
TRAJECTORY IMPUTATION AND PREDICTION
Organization Name
Inventor(s)
Armin Bazarjani of Los Angeles CA (US)
Hyung-gun Chi of West Lafayette IN (US)
Chiho Choi of San Jose CA (US)
TRAJECTORY IMPUTATION AND PREDICTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18182195 titled 'TRAJECTORY IMPUTATION AND PREDICTION
Simplified Explanation
The patent application describes systems and methods for trajectory imputation and prediction. Here is a simplified explanation of the abstract:
- Generating spatial missing patterns in trajectory data
- Extracting spatial features from the missing patterns
- Encoding spatial features into latent variables
- Modeling temporal dependency and decay
- Imputing trajectories based on latent variables and temporal patterns
- Predicting future trajectories for multiple agents
---
- Potential Applications
This technology could be applied in various fields such as transportation, logistics, and urban planning to predict and optimize trajectories of multiple agents.
- Problems Solved
This technology addresses the challenge of missing trajectory data and provides a method to impute and predict future trajectories accurately.
- Benefits
- Improved accuracy in trajectory prediction - Optimization of agent trajectories - Enhanced decision-making in dynamic environments
- Potential Commercial Applications
"Trajectory Imputation and Prediction Technology for Enhanced Logistics and Transportation Efficiency"
- Possible Prior Art
There may be prior art related to trajectory prediction algorithms and missing data imputation methods in the fields of machine learning and data analysis.
---
- Unanswered Questions
- How does this technology handle real-time trajectory updates?
The patent application focuses on imputing and predicting trajectories based on historical data. It does not specify how real-time trajectory updates are incorporated into the system.
- What is the computational complexity of the proposed method?
The abstract does not provide information on the computational resources required to implement the trajectory imputation and prediction method. Understanding the computational complexity is crucial for assessing the scalability of the technology.
Original Abstract Submitted
Systems and methods for trajectory imputation and prediction are provided. In one embodiment, a method includes generating a spatial missing pattern in an imputation stream by applying a binary mask to an observational dataset over a number of past timesteps. The method includes extracting spatial features from the spatial missing pattern for the number of past time steps. The method includes encoding the spatial features of the observational dataset into imputation latent variables in a latent space based on the spatial missing pattern. The method includes generating a temporal missing pattern by modeling temporal dependency as temporal decay from the past time to the first time based on the latent space. The method includes determining imputation trajectories based on the imputation latent variables and the temporal missing pattern. The method includes predicting future trajectories for the number of agents for a number of future timesteps based temporal missing pattern.
