Autonomous Rail Vehicle Dynamic Scheduling and Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current railway systems lack the flexibility and efficiency in managing autonomous vehicles, as they are often constrained by fixed schedules and traditional sensor technologies that struggle with dynamic detection and response to real-time environmental changes.
Innovation Solution
A method and system utilizing a combination of active and passive sensors, including LiDAR and radar systems, coupled with artificial intelligence to dynamically detect and respond to events on the railway track, allowing autonomous vehicles to adjust their movement based on real-time data and create demand schedules rather than fixed ones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional fixed schedules are used in railway systems, then operational simplicity is maintained, but flexibility and adaptability to real-time conditions deteriorate
Solution Approach 1:
The patent implements dynamic scheduling where the railway system transitions from fixed, predetermined schedules to adaptive, real-time schedule generation. The central controller continuously receives sensor data from multiple vehicles and environmental sensors, then dynamically generates and updates schedules based on current conditions, vehicle positions, and detected events, enabling the system to adapt flexibly while managing complexity through centralized intelligence.
Solution Approach 2:
The system incorporates continuous feedback loops where sensor data from vehicles and the environment is constantly monitored, processed, and used to adjust schedules in real-time. The central controller receives feedback about vehicle positions, detected events, and environmental conditions, then generates updated schedules that reflect current system state, creating a closed-loop control system that balances flexibility with manageable complexity.
2Measurement precision
If traditional sensor technologies are used, then system simplicity is maintained, but detection precision and response to dynamic events deteriorate
Solution Approach 1:
The patent combines multiple active sensor systems (LiDAR, radar) and passive sensor systems (cameras, acoustic sensors) into an integrated sensor array on each vehicle, plus environmental sensors along the track. This merging of diverse sensor types creates a comprehensive detection network that achieves high measurement precision while managing complexity through unified sensor arrays and centralized processing.
Solution Approach 2:
The sensor systems are designed with multi-functionality, where the same sensor array serves multiple detection purposes: detecting other vehicles, identifying environmental events, monitoring track conditions, and tracking rider positions. This universal sensor platform achieves comprehensive detection precision without proportionally increasing system complexity, as one sensor system performs multiple functions.
3Adaptability or versatility
If mechanical coupling between vehicles is used, then system stability is maintained, but operational flexibility and individual vehicle autonomy deteriorate
Solution Approach 1:
The patent introduces a communication network as an intermediary between vehicles, replacing direct mechanical coupling. The central controller and vehicle-to-vehicle communication systems serve as mediators that coordinate vehicle movements, maintain system stability, and enable flexible autonomous operation. This communication-based coordination achieves operational flexibility while maintaining reliability through continuous digital coordination rather than rigid mechanical connections.
4Adaptability or versatility
If demand-based scheduling is implemented, then service flexibility is improved, but computational complexity and processing requirements increase
Solution Approach 1:
The patent segments the computational workload by distributing sensor data collection to individual vehicles (each vehicle independently collects and preprocesses its own sensor data) while centralizing the complex schedule generation and optimization functions in a central controller. This segmentation reduces the computational complexity at any single point while maintaining overall service flexibility through coordinated demand-based scheduling.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables autonomous vehicles to operate safely and efficiently by dynamically adjusting their movement in response to environmental changes and anomalies, providing a flexible and reliable service that adapts to real-time conditions, enhancing safety and operational efficiency.
Implementation Method 1
a light-detection and ranging (LiDAR) system...configured to output at least one output sensor configuration to identify the event using the detected reflectance of the event
Implementation Method 2
a plurality of active sensor systems...such as electromagnetic signal ranging and detection systems (e.g., radar and LiDAR systems)
Data Source
AI summary
An autonomous vehicle (“AV”) is configured on a railway system. The AV can be configured among the other vehicles and railway to communicate with a rider on a peer to peer basis to pick up the rider on demand, rather than the rider being held hostage to a fixed railway schedule. The rider can have an application on his/her cell phone, which tracks each of the AVs, and contact them using the application on the cell phone.