18060049. REAL-TIME CONTROL SELECTION AND CALIBRATION USING NEURAL NETWORK simplified abstract (GM Global Technology Operations LLC)
Contents
- 1 REAL-TIME CONTROL SELECTION AND CALIBRATION USING NEURAL NETWORK
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 REAL-TIME CONTROL SELECTION AND CALIBRATION USING NEURAL NETWORK - 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
REAL-TIME CONTROL SELECTION AND CALIBRATION USING NEURAL NETWORK
Organization Name
GM Global Technology Operations LLC
Inventor(s)
Shuqing Zeng of Sterling Heights MI (US)
Yubiao Zhang of Sterling Heights MI (US)
Bakhtiar B. Litkouhi of Washington MI (US)
REAL-TIME CONTROL SELECTION AND CALIBRATION USING NEURAL NETWORK - A simplified explanation of the abstract
This abstract first appeared for US patent application 18060049 titled 'REAL-TIME CONTROL SELECTION AND CALIBRATION USING NEURAL NETWORK
Simplified Explanation
The abstract describes a system for real-time control selection and calibration in a vehicle using a deep-Q network (DQN). The system includes sensors and actuators on the vehicle, a control module with a processor, memory, and I/O ports, and program code portions that utilize vehicle dynamics and road surface estimation information to generate a vehicle dynamical context. The system decides on a calibration based on the vehicle dynamical context and generates commands to the actuators accordingly while the vehicle is in operation.
- The system utilizes sensors and actuators to obtain vehicle dynamics and road surface estimation information.
- It uses this information to generate a vehicle dynamical context and select an appropriate calibration.
- Commands are then generated based on the selected calibration and continuously executed while the vehicle is being operated.
Potential Applications
The technology can be applied in autonomous vehicles, advanced driver assistance systems, and vehicle stability control systems.
Problems Solved
This technology helps in improving vehicle control and stability by selecting and applying the appropriate calibration in real-time based on the vehicle's dynamics and road conditions.
Benefits
The system enhances vehicle safety, performance, and efficiency by dynamically adjusting control parameters according to the current driving conditions.
Potential Commercial Applications
Potential commercial applications include automotive industry suppliers, vehicle manufacturers, and companies developing autonomous driving technologies.
Possible Prior Art
One possible prior art could be the use of traditional control systems in vehicles that do not utilize deep learning algorithms like DQN for real-time calibration and selection.
Unanswered Questions
How does this technology impact vehicle maintenance costs?
This article does not address the potential impact of this technology on vehicle maintenance costs. Implementing a real-time control selection and calibration system using a deep-Q network may require specialized maintenance procedures or components, which could affect overall maintenance costs.
What are the cybersecurity implications of implementing this technology in vehicles?
The article does not discuss the cybersecurity implications of integrating a deep-Q network-based system for control selection and calibration in vehicles. Ensuring the security of the system against cyber threats and potential vulnerabilities is crucial, especially in connected and autonomous vehicles.
Original Abstract Submitted
A system for real-time control selection and calibration in a vehicle using a deep-Q network (DQN) includes sensors and actuators disposed on the vehicle. A control module has a processor, memory, and input/output (I/O) ports in communication with the one or more sensors and the one or more actuators. The processor executes program code portions that cause the sensors actuators to obtain vehicle dynamics and road surface estimation information and utilize the vehicle dynamics information and road surface estimation information to generate a vehicle dynamical context. The system decides which one of a plurality of predefined calibrations is appropriate for the vehicle dynamical context, generates a command to the actuators based on a selected calibration. The system continuously and recursively causes the program code portions to execute while the vehicle is being operated.