RTX had 24 patents in artificial intelligence during Q3 2023. One patent describes a system that manipulates vehicle trajectories to achieve a desired track density profile. Another patent involves using AI/ML models to demodulate signals and generate symbol estimates. There is also a patent for a system that monitors vehicle-borne probes and predicts their remaining useful life and failure. Additionally, there is a patent for an AI/ML system for aircraft that processes inputs from sensors and information systems. Lastly, there is a patent for a method that uses machine learning to detect incipient compressor surge events in cabin air compressors and implement corrective actions. GlobalData’s report on RTX gives a 360-degreee view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData

Report-cover

Premium Insights Raytheon Technologies Corp - Company Profile

Buy the Report

Premium Insights

The gold standard of business intelligence.

Find out more

RTX grant share with artificial intelligence as a theme is 50% in Q3 2023. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Spatio-temporal track density shaping (Patent ID: US20230267844A1)

The patent filed by RTX Corp. describes a system and process for manipulating vehicle trajectories to achieve a desired vehicle track density profile. The system includes a first dataset of vehicle trajectories, a desired vehicle track density profile, a spatio-temporal coverage metric, and a track model. The track model consists of Heaviside functions that encode track time origins and durations for individual vehicle tracks, as well as their locations. The Heaviside functions are approximated and minimized based on the spatio-temporal coverage metric. The first dataset of vehicle trajectories is then optimized to satisfy the desired track density profile by shifting each individual vehicle track, resulting in a second dataset of vehicle trajectories with a different track density. The second dataset is used to train a vehicle resources machine learning algorithm.

The process involves receiving the first dataset of vehicle trajectories, the vehicle track density profile, the spatio-temporal coverage metric, and the track model into a computer processor. The Heaviside functions are approximated and minimized based on the spatio-temporal coverage metric. The first dataset of vehicle trajectories is then optimized based on the vehicle track density profile and the minimized approximation of the Heaviside functions. This optimization generates start times and start locations for each individual vehicle track. The individual vehicle tracks are shifted as a result of the optimization, creating the second dataset of vehicle trajectories with a different track density. Finally, the second dataset is used to train a vehicle resources machine learning algorithm.

The patent also mentions various aspects and features of the system and process. The optimization can involve minimizing the deviation from a predetermined value of the spatio-temporal metric, and it can be performed using a sequential least-squares optimizing method. The first dataset of vehicle trajectories can be based on real or synthetic track datasets. The vehicle track density profile can include spatial and temporal profiles, as well as track identifications, start times, durations, and coordinates. The shifting of individual vehicle tracks can involve temporal and spatial shifts. Additionally, the patent mentions the application of the system and process to aircraft trajectories, where the individual vehicle tracks are aircraft tracks, and the vehicle resources machine learning algorithm is an aircraft resources machine learning algorithm.

In summary, the patent filed by RTX Corp. describes a system and process for manipulating vehicle trajectories to achieve a desired track density profile. The system includes a first dataset of vehicle trajectories, a desired track density profile, a spatio-temporal coverage metric, and a track model. The process involves approximating and minimizing Heaviside functions based on the spatio-temporal coverage metric, optimizing the first dataset of vehicle trajectories based on the track density profile and minimized approximation of the Heaviside functions, shifting individual vehicle tracks, and training a vehicle resources machine learning algorithm using the resulting dataset. Various aspects and features of the system and process are also mentioned, including optimization methods, dataset types, and application to aircraft trajectories.

To know more about GlobalData’s detailed insights on RTX, buy the report here.

Premium Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.