Ambarella. has been granted a patent for an apparatus that utilizes a processor and interface to process pixel and sensor data from vehicles. The system employs a trained neural network to generate actuator commands based on dynamic set-points and visual odometry, enhancing vehicle navigation and control. GlobalData’s report on Ambarella gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Ambarella, Cloud gaming was a key innovation area identified from patents. Ambarella's grant share as of June 2024 was 90%. Grant share is based on the ratio of number of grants to total number of patents.
Vehicle control using neural network and sensor data
The patent US12037001B1 describes an advanced apparatus designed for vehicle control, integrating a trained neural network model to process sensor and pixel data. The system receives pixel data from the vehicle's surroundings and sensor data, which includes environmental information such as the vehicle's pitch angle and speed. The processor executes a neural network model that generates real actuator commands based on this data, desired dynamic set-points from a path planning application, and inferences made by the model. The neural network is trained through computer vision operations to detect features in video frames and apply visual odometry to determine dynamic set-points, which are essential for controlling vehicle functions like acceleration, steering, and braking.
Additionally, the apparatus includes a method for real-time updating of the neural network's weights to adapt to changing vehicle dynamics, road conditions, and weather. This involves comparing predicted actuator commands from a second neural network model with real actuator commands from the first model, allowing for continuous refinement of the system's performance. The architecture of both neural networks is similar, and updates occur when discrepancies between predicted and real commands exceed a predefined threshold. This innovative approach aims to enhance vehicle responsiveness and safety by leveraging machine learning and real-time data processing.
To know more about GlobalData’s detailed insights on Ambarella, buy the report here.
Data 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, 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.
