Unknown Organization (20240265681). SYSTEM AND METHOD FOR DATA HARVESTING FROM ROBOTIC OPERATIONS FOR CONTINUOUS LEARNING OF AUTONOMOUS ROBOTIC MODELS simplified abstract
SYSTEM AND METHOD FOR DATA HARVESTING FROM ROBOTIC OPERATIONS FOR CONTINUOUS LEARNING OF AUTONOMOUS ROBOTIC MODELS
Organization Name
Inventor(s)
Andrés Felipe Chavez Cortes of El Cerrito CA (US)
Carlos Andres Alvarez Restrepo of Medellín (CO)
Rafael Rincon of Medellín (CO)
SYSTEM AND METHOD FOR DATA HARVESTING FROM ROBOTIC OPERATIONS FOR CONTINUOUS LEARNING OF AUTONOMOUS ROBOTIC MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240265681 titled 'SYSTEM AND METHOD FOR DATA HARVESTING FROM ROBOTIC OPERATIONS FOR CONTINUOUS LEARNING OF AUTONOMOUS ROBOTIC MODELS
Simplified Explanation:
The patent application describes a system and method for detecting trigger events in an autonomous ground vehicle, generating event sequence data, communicating data to cloud storage and databases, normalizing data, identifying true trigger events, and updating the vehicle's navigational control system using machine learning.
- The system detects trigger events during the operation of an autonomous ground vehicle.
- Event sequence data is generated from primary sensor data, secondary sensor data, spatiotemporal data, and telemetry data.
- The data is communicated to cloud storage and raw data to a streaming database.
- Raw data is transformed into normalized data stored in a relational database.
- A curation system identifies true trigger events and extracts training data.
- A machine learning model generates a model update from aggregate training data.
- The navigational control system is reconfigured with the model update from the active learning pipeline.
Key Features and Innovation:
- Detection of trigger events in autonomous ground vehicles.
- Generation of event sequence data from multiple sources.
- Communication of data to cloud storage and databases.
- Normalization of raw data for storage in a relational database.
- Identification of true trigger events and extraction of training data.
- Utilization of machine learning for model updates in an active learning pipeline.
- Reconfiguration of the navigational control system based on model updates.
Potential Applications:
The technology can be applied in autonomous vehicles, transportation systems, logistics, and fleet management.
Problems Solved:
The system addresses the need for efficient detection of trigger events, accurate data processing, and continuous improvement of autonomous vehicle navigation.
Benefits:
The technology enhances the safety, reliability, and efficiency of autonomous ground vehicles. It enables real-time decision-making and adaptive control based on machine learning.
Commercial Applications:
The system can be used in autonomous vehicle companies, transportation agencies, logistics companies, and research institutions to improve vehicle performance and operational capabilities.
Prior Art:
Readers can explore prior research in the fields of autonomous vehicles, machine learning, and sensor data processing for related technologies.
Frequently Updated Research:
Stay informed about advancements in machine learning algorithms, sensor technologies, and autonomous vehicle navigation systems for potential improvements in the described technology.
Questions about Autonomous Ground Vehicle Technology: 1. How does the system differentiate between true trigger events and false alarms? 2. What are the potential challenges in implementing machine learning models for updating the navigational control system?
Original Abstract Submitted
a system and method involves detecting a trigger event during operation of an autonomous ground vehicle traveling between two physical locations; generating event sequence data from primary sensor data, secondary sensor data, spatiotemporal data, and telemetry data through operation of a reporter; communicating the event sequence data to cloud storage and raw data to a streaming database; transforming the raw data into normalized data stored in a relational database through operation of a normalizer; operating a curation system to identify true trigger events from the normalized data and extract training data by way of a discriminator; operating a machine learning model within an active learning pipeline to generate a model update from aggregate training data generated from the training data by an aggregator; and reconfiguring the navigational control system with the model update communicated from the active learning pipeline to the autonomous ground vehicle.
