Automotive Radar Modeling for Virtual Simulation Based on Mixture Density Network

Li, Hexuan; Tarik, Kanuric; Eichberger, Arno

doi:10.1109/jsen.2022.3223765

Cited by 6 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This advantage over standard neural networks makes the MDN suitable for use in optimization problems, which may include non-unique solutions for different parameters [19]. This has led to the application of MDN to parameter estimation for inverse problems [20][21][22] and to simulation of physical processes [23].…”

Section: Background and Related Workmentioning

confidence: 99%

“…In a related domain, the MDN was applied to the estimation of direction of arrival for acoustic signals also within an AWGN environment, and was shown to capture an accurate model of the uncertainty due to the channel [22]. In the radar domain, the MDN is demonstrated as an effective data-driven method to approximate radar sensor measurements for distance, velocity, and orientation of a moving vehicle [23]. In this scenario, a transmitted chirp signal is distorted by channel perturbations and noise as well as fading and the Doppler effect [23].…”

Section: Background and Related Workmentioning

confidence: 99%

“…In the radar domain, the MDN is demonstrated as an effective data-driven method to approximate radar sensor measurements for distance, velocity, and orientation of a moving vehicle [23]. In this scenario, a transmitted chirp signal is distorted by channel perturbations and noise as well as fading and the Doppler effect [23].…”

Section: Background and Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning Based Over-the-Air Training of Wireless Communication Systems without Feedback

Davey,

Shakeel,

Deo

et al. 2024

Sensors

View full text Add to dashboard Cite

In trainable wireless communications systems, the use of deep learning for over-the-air training aims to address the discontinuity in backpropagation learning caused by the channel environment. The primary methods supporting this learning procedure either directly approximate the backpropagation gradients using techniques derived from reinforcement learning, or explicitly model the channel environment by training a generative channel model. In both cases, over-the-air training of transmitter and receiver requires a feedback channel to sound the channel environment and obtain measurements of the learning objective. The use of continuous feedback not only demands extra system resources but also makes the training process more susceptible to adversarial attacks. Conversely, opting for a feedback-free approach to train the models over the forward link, exclusively on the receiver side, could pose challenges to reliably end the training process without intermittent testing over the actual channel environment. In this article, we propose a novel method for the over-the-air training of wireless communication systems that does not require a feedback channel to train the transmitter and receiver. Random samples are transmitted through the channel environment to train a mixture density network to approximate the channel distribution on the receiver side of the network. The transmitter and receiver models are trained with the resulting channel model, and the transmitter can be deployed after training. We show that the block error rate measurements obtained with the simulated channel are suitable for monitoring as a stopping criterion during the training process. The resulting method is demonstrated to have equivalent performance to the end-to-end autoencoder training on small message sequences.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Section: Background and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Based Over-the-Air Training of Wireless Communication Systems without Feedback

Davey,

Shakeel,

Deo

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…The right front wheel load for the three different vehicle types was assessed on the drum test bench, and figure 6 displays the test process. The ratio ߤ of unsprung mass to sprung mass typically falls within the range of 3.5 to 7.0 [7]. A value of ߤ = 6 has been calculated using the load distribution and unsprung mass measurement.…”

Section: /4 Vertical Vibration Model Of Vehiclementioning

confidence: 99%

Parameter Optimization of Passive Suspension Based on MATLAB Simulation

Deng,

Gao,

et al. 2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

With the development of the automobile industry and economy, the automobile penetration rate is increasing. Most people are more concerned about the driving comfort of a vehicle, and the quality of suspension system directly affects the stability of a car. Although active suspension offers better control, its complexity and high cost limit its use to premium cars. And most regular saloons, the mainstay of the market, employ passive suspension. Therefore, the optimisation of passive suspensions remains important and marketable. In this paper, Matlab/Simulink is used to model the suspension as it relates to road inputs and the vertical vibration of a 1/4 vehicle with a dual mass. A three-factor, four-level orthogonal test was carried out on various models and road surfaces. The damping coefficient of the shock absorber, spring stiffness, and tyre stiffness were predicted by plotting line graphs, observing the pattern, and carrying out ANOVA using statistic package for social science (SPSS). The simulation results demonstrate that, while maintaining the stability of the suspension structure, a large damping coefficient, as well as small tyre and spring stiffness, effectively reduces the root mean square (RMS) value of body acceleration, suspension dynamic deflection, and RMS value of wheel dynamic load. This achieves a smooth and safe ride. Finally, it has been confirmed through a real vehicle test that reduced stiffness in the small tyre effectively lowers the body acceleration.

show abstract

“…Several solutions to represent different sensing tasks can be found in the literature. Stochastic [ 22 ], phenomenological [ 10 ], data-driven [ 23 ], and semi-physical [ 24 ] modelling methods are the most commonly used. The authors in [ 25 , 26 ] show that with a non-parametric modelling approach, sensor detection range, occlusions, latencies, ghost objects, and object loss can be modelled in a realistic way without explicit programming and can be simulated efficiently in real time.…”

Section: Related Workmentioning

confidence: 99%

A Novel Approach for Simulation of Automotive Radar Sensors Designed for Systematic Support of Vehicle Development

Magosi

Eichberger

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Despite the progress in driving automation, the market introduction of higher-level automation has not yet been achieved. One of the main reasons for this is the effort in safety validation to prove functional safety to the customer. However, virtual testing may compromise this challenge, but the modelling of machine perception and proving its validity has not been solved completely. The present research focuses on a novel modelling approach for automotive radar sensors. Due to the complex high-frequency physics of radars, sensor models for vehicle development are challenging. The presented approach employs a semi-physical modelling approach based on experiments. The selected commercial automotive radar was applied in on-road tests where the ground truth was recorded with a precise measurement system installed in ego and target vehicles. High-frequency phenomena were observed and reproduced in the model on the one hand by using physically based equations such as antenna characteristics and the radar equation. On the other hand, high-frequency effects were statistically modelled using adequate error models derived from the measurements. The model was evaluated with performance metrics developed in previous works and compared to a commercial radar sensor model. Results show that, while keeping real-time performance necessary for X-in-the-loop applications, the model is able to achieve a remarkable fidelity as assessed by probability density functions of the radar point clouds and using the Jensen–Shannon divergence. The model delivers values of radar cross-section for the radar point clouds that correlate well with measurements comparable with the Euro NCAP Global Vehicle Target Validation process. The model outperforms a comparable commercial sensor model.

show abstract

Automotive Radar Modeling for Virtual Simulation Based on Mixture Density Network

Cited by 6 publications

References 29 publications

Deep Learning Based Over-the-Air Training of Wireless Communication Systems without Feedback

Deep Learning Based Over-the-Air Training of Wireless Communication Systems without Feedback

Parameter Optimization of Passive Suspension Based on MATLAB Simulation

A Novel Approach for Simulation of Automotive Radar Sensors Designed for Systematic Support of Vehicle Development

Contact Info

Product

Resources

About