DANAE++: A Smart Approach for Denoising Underwater Attitude Estimation.
Paolo Russo1, Fabiana Di Ciaccio2, Salvatore Troisi2
1Department of Computer, Control and Management Engineering "Antonio Rubert", University of Rome La Sapienza, Via Ariosto 25, 00185 Rome, Italy.
Sensors (Basel, Switzerland)
|March 6, 2021
Summary
DANAE++ enhances underwater robot navigation by accurately estimating vehicle orientation. This deep learning model effectively removes noise from sensor data, improving positioning for autonomous systems.
Area of Science:
- Robotics
- Artificial Intelligence
- Signal Processing
Background:
- Accurate vehicle positioning is critical for underwater robot navigation.
- Orientation estimation is heavily influenced by sensor and environmental noise.
- Existing filtering algorithms require time-consuming configuration for noise reduction.
Purpose of the Study:
- To introduce DANAE++, an improved deep learning model for denoising orientation estimations.
- To enhance the robustness and performance of attitude estimation in noisy underwater environments.
- To develop a method capable of handling diverse noise types without manual tuning.
Main Methods:
- Utilizing a deep denoising autoencoder architecture (DANAE++).
- Applying the model to recover orientation estimations from Kalman Filter (KF) IMU/AHRS data.
- Simultaneously denoising pitch, roll, and yaw angles.
Main Results:
- DANAE++ demonstrates significant improvements in denoising results and performance over its predecessor.
- The model effectively recovers orientation estimations corrupted by various noise typologies.
- Simultaneous denoising of attitude angles is achieved and verified with extended KF estimations.
Conclusions:
- DANAE++ offers a robust and reliable solution for attitude estimation in underwater navigation.
- The enhanced deep learning approach effectively mitigates noise impact on orientation data.
- DANAE++ shows potential for real-time applications in autonomous underwater vehicle navigation.
Related Concept Videos
01:18Uniform Depth Channel Flow: Problem Solving
220
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
220
01:20Deconvolution
403
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
403
01:20Downsampling
421
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
421
01:26Linear Approximation in Frequency Domain
239
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
239
01:21Linear Approximation in Time Domain
197
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
197