Control System For Railway Yard And Related Methods
Patent No. US12217183 (titled "Control System For Railway Yard And Related Methods") was filed by All Terminal Services Llc on May 31, 2024.
What is this patent about?
’183 is related to the field of railway yard management, specifically systems for monitoring and controlling the movement of railcars within a railyard. The background involves the increasing complexity of railyards due to intermodal shipping, making it difficult to track and manage containers as they are switched between trains or offloaded for truck transport. Existing methods struggle to efficiently monitor the status and location of containers, and to ensure adherence to safety protocols.
The underlying idea behind ’183 is to automate the process of tracking and positioning railcars within a railyard using a combination of sensors, remote-controlled locomotives (RCLs), and a central server. The system uses railyard sensor data , including image data, to identify railcars and their characteristics, and then uses this information to selectively control the RCLs to position the railcars on the tracks. This aims to improve efficiency, safety, and reduce operational costs.
The claims of ’183 focus on a control system comprising RCLs, railyard sensors, and a server. The server generates a database of railcars based on sensor data and selectively controls the RCLs to position the railcars. A key element is the use of an image sensor as a railyard sensor, enabling the server to identify individual railcars based on the image data.
In practice, the system uses image sensors to capture images of the railcars, and the server then processes this data using techniques like optical character recognition (OCR) and machine learning to identify the railcar type, logo, and classification. This information is stored in a database, which is then used to optimize the positioning of railcars within the yard. The server communicates with the RCLs via wireless transceivers, sending commands to control their movement and position the railcars according to the optimized plan.
This approach differs from traditional methods that rely on manual tracking and control of railcars. By automating the process of identification and positioning, the system can significantly improve efficiency and reduce the risk of human error. The use of machine learning allows the system to adapt to changing conditions and improve its accuracy over time, while the remote control of locomotives eliminates the need for human operators in the yard, further enhancing safety and reducing operational costs. The system can also monitor for safety violations, such as speeding or illegal parking, providing an additional layer of safety.
How does this patent fit in bigger picture?
Technical landscape at the time
In the late 2010s when ’183 was filed, systems commonly relied on image sensors and proximity sensors for object detection and monitoring, at a time when machine learning models such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) were increasingly used for image analysis and optical character recognition (OCR).
Novelty and Inventive Step
The examiner allowed the claims because the prior art, specifically Ferencz, does not teach a plurality of railyard sensors configured to generate railyard sensor data and a server in communication with the railyard sensors. Also, Raez utilizes RFID to identify the railcars of a train rather than a visual identification of each railcar. Modifying Ferencz to include an image sensor and server configured to identify each railcar based on image data would require an improper amount of hindsight reasoning and a redesign of Raez.
Claims
This patent contains 30 claims, with independent claims numbered 1, 16, and 29. The independent claims are directed to a control system, a server, and a method for operating a control system, respectively, all for use in a railway yard. The dependent claims generally elaborate on and refine the features and functionalities described in the independent claims.
Key Claim Terms New
Definitions of key terms used in the patent claims.
Litigation Cases New
US Latest litigation cases involving this patent.
Patent Family
File Wrapper
The dossier documents provide a comprehensive record of the patent's prosecution history - including filings, correspondence, and decisions made by patent offices - and are crucial for understanding the patent's legal journey and any challenges it may have faced during examination.
Date
Description
Get instant alerts for new documents
US12217183
- Application Number
- US18731207
- Filing Date
- May 31, 2024
- Status
- Granted
- Expiry Date
- Nov 18, 2040
- External Links
- Slate, USPTO, Google Patents