A neural network assisted vehicle adaptive autonomous navigation method
By using a neural network-assisted multi-parameter parallel prediction LSTM model and variational Bayesian filtering, the error accumulation problem of vehicle inertial navigation in environments without satellite signals was solved, achieving fully autonomous and high-precision navigation for vehicles.
Patent Information
- Application Number
- CN202411867627.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-18
- Publication Date
- 2026-01-09
- Estimated Expiration
- 2044-12-18
AI Technical Summary
Existing vehicle-mounted inertial navigation systems suffer from severe error accumulation in environments without satellite signals, making it difficult to achieve high-precision autonomous navigation.
A neural network-assisted multi-parameter parallel prediction LSTM model, combined with variational Bayesian filtering, is used to achieve adaptive integrated navigation of inertial navigation data. The trained model can perform high-precision prediction of vehicle attitude and speed when GNSS is ineffective.
It enables fully autonomous, high-precision navigation of vehicles in the absence of GNSS, significantly reducing the accumulation of inertial navigation errors, and is suitable for scenarios where satellite signals fail, such as tunnels and building obstructions.