Radar Frame-of-Reference Detection via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Integrating a radar system within a moving electronic device, such as a mobile or wearable device, is challenging due to uncertainty about the radar's frame of reference, making it difficult to differentiate between stationary and moving situations, and requiring additional motion sensors that increase power consumption and cost.
Innovation Solution
A smart-device-based radar system uses a frame-of-reference machine-learned module trained with machine learning to analyze complex radar data from reflected signals, determining whether the radar system's frame of reference is stationary or moving without relying on non-radar-based sensors like gyroscopes or accelerometers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If additional motion sensors (gyroscopes, accelerometers) are integrated into the radar system to detect frame-of-reference changes, then the reliability of motion detection improves, but the power consumption and device complexity increase
Solution Approach 1:
The radar system uses its own transmitted signals and received reflections to detect frame-of-reference changes, eliminating the need for separate motion sensors. The machine learning module analyzes radar data patterns to determine when the radar is moving versus when objects are moving, making the radar system self-sufficient for motion detection.
Solution Approach 2:
The radar system performs multiple functions: it detects objects, tracks their motion, and simultaneously determines frame-of-reference changes. The same hardware components (transmitter, receiver, processor) are used for both traditional radar detection and motion state determination, eliminating the need for dedicated motion sensors.
2Reliability
If additional motion sensors (gyroscopes, accelerometers) are integrated into the radar system to detect frame-of-reference changes, then the reliability of motion detection improves, but the device complexity increases
Solution Approach 1:
The radar system uses its own transmitted signals and received reflections to detect frame-of-reference changes, eliminating the need for separate motion sensors. The machine learning module analyzes radar data patterns to determine when the radar is moving versus when objects are moving, making the radar system self-sufficient for motion detection.
Solution Approach 2:
The radar system performs multiple functions: it detects objects, tracks their motion, and simultaneously determines frame-of-reference changes. The same hardware components (transmitter, receiver, processor) are used for both traditional radar detection and motion state determination, eliminating the need for dedicated motion sensors.
3Speed
If the radar system uses traditional signal processing methods without machine learning, then the computational speed improves, but the ability to detect subtle motion patterns and differentiate frame-of-reference changes deteriorates
Solution Approach 1:
The patent replaces traditional mechanical signal processing methods with a machine learning-based system. The machine learning module is trained to recognize patterns in radar data that indicate frame-of-reference changes, enabling more precise motion detection and differentiation between radar motion and object motion compared to conventional processing techniques.
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
This approach allows the radar system to accurately determine gestures and compensate for its own motion, reducing the need for additional sensors and conserving power, while effectively operating in space-constrained devices.
Implementation Method 1
A radar system includes a frame-of-reference machine-learned module, which is trained to operate as a motion sensor. The frame-of-reference machine-learned module uses machine learning to recognize whether or not the radar system's frame of reference changes. In particular, the frame-of-reference machine-learned module analyzes complex radar data generated from at least one chirp of a reflected radar signal
Implementation Method 2
the frame-of-reference machine-learned module analyzes complex radar data generated from at least one chirp of a reflected radar signal to identify subtle patterns in a relative motion of at least one object over time
Data Source
AI summary
Techniques and apparatuses are described that implement a smart-device-based radar system capable of detecting a frame-of-reference change. In particular, a radar system includes a frame-of-reference machine-learned module trained to recognize whether or not the radar system's frame of reference changes. The frame-of-reference machine-learned module analyzes complex radar data generated from at least one chirp of a reflected radar signal to analyze a relative motion of at least one object over time. By analyzing the complex radar data directly using machine learning, the radar system can operate as a motion sensor without relying on non-radar-based sensors, such as gyroscopes, inertial sensors, or accelerometers. With knowledge of whether the frame-of-reference is stationary or moving, the radar system can determine whether or not a gesture is likely to occur and, in some cases, compensate for the relative motion of the radar system itself.