17936655. METHOD AND SYSTEM FOR PERSONALIZED CAR FOLLOWING WITH TRANSFORMERS AND RNNS simplified abstract (TOYOTA JIDOSHA KABUSHIKI KAISHA)
Contents
- 1 METHOD AND SYSTEM FOR PERSONALIZED CAR FOLLOWING WITH TRANSFORMERS AND RNNS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHOD AND SYSTEM FOR PERSONALIZED CAR FOLLOWING WITH TRANSFORMERS AND RNNS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
METHOD AND SYSTEM FOR PERSONALIZED CAR FOLLOWING WITH TRANSFORMERS AND RNNS
Organization Name
TOYOTA JIDOSHA KABUSHIKI KAISHA
Inventor(s)
Ziran Wang of San Jose CA (US)
Kyungtae Han of Palo Alto CA (US)
Rohit Gupta of Santa Clara CA (US)
METHOD AND SYSTEM FOR PERSONALIZED CAR FOLLOWING WITH TRANSFORMERS AND RNNS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17936655 titled 'METHOD AND SYSTEM FOR PERSONALIZED CAR FOLLOWING WITH TRANSFORMERS AND RNNS
Simplified Explanation
The patent application describes a method for predicting the gap between an ego vehicle and lead vehicles using a Transformer-RNN model. Here are some key points to explain the innovation:
- Receiving training data with time series of gaps between vehicles
- Embedding the training data into a fixed-length sequence
- Inputting the sequence into a Transformer-RNN model
- Transformer component applies attention to each data point based on previous inputs
- Training the model to output predicted gap at future time steps
Potential Applications
This technology could be applied in autonomous driving systems to improve safety and efficiency by predicting gaps between vehicles on the road.
Problems Solved
This technology addresses the challenge of accurately predicting the distance between vehicles in real-time, which is crucial for safe and efficient driving.
Benefits
The benefits of this technology include enhanced safety on the roads, improved traffic flow, and potentially reducing accidents caused by sudden changes in vehicle gaps.
Potential Commercial Applications
A potential commercial application of this technology could be integrating it into autonomous vehicles to enhance their decision-making capabilities on the road.
Possible Prior Art
One possible prior art could be the use of traditional machine learning models to predict vehicle gaps, but the innovation of using a Transformer-RNN model sets this technology apart.
Unanswered Questions
How does this technology handle variations in vehicle speed and behavior?
The article does not delve into how the model accounts for different driving conditions and behaviors that may affect vehicle gaps.
What kind of data preprocessing is required before inputting it into the Transformer-RNN model?
The article does not provide details on the specific data preprocessing steps needed to prepare the training data for the model.
Original Abstract Submitted
A method may include receiving training data comprising a time series of gaps between an ego vehicle and one or more lead vehicles at a plurality of time steps, embedding the training data into a fixed-length sequence, inputting the fixed-length sequence into a Transformer-RNN model comprising a Transformer component and an RNN component, wherein the transformer component applies attention to each data point of the fixed-length sequence based on a fixed number of previous inputs, and training the Transformer-RNN model, using the training data, to output a predicted gap at a future time step based on an input sequence of gaps.