A Hybrid Reinforcement Learning Approach With a Spiking Actor Network for Efficient Robotic Arm Target Reaching

Oikonomou, Katerina Maria; Kansizoglou, Ioannis; Γαστεράτος, Αντώνιος

doi:10.1109/lra.2023.3264836

Cited by 8 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During training, a batch size of 32 has been adopted, thereby training the model for a total of 200 epochs. After the training procedure, the best model was obtained and exploited for testing according to the recent literature [ 68 ]. The experiments were conducted on a computer device with an i5 CPU processor and an Nvidia GeForce 1060, 6 GB GPU.…”

Section: Resultsmentioning

confidence: 99%

A Deep Learning Approach for Autonomous Compression Damage Identification in Fiber-Reinforced Concrete Using Piezoelectric Lead Zirconate Titanate Transducers

Sapidis,

Kansizoglou,

Naoum

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

Effective damage identification is paramount to evaluating safety conditions and preventing catastrophic failures of concrete structures. Although various methods have been introduced in the literature, developing robust and reliable structural health monitoring (SHM) procedures remains an open research challenge. This study proposes a new approach utilizing a 1-D convolution neural network to identify the formation of cracks from the raw electromechanical impedance (EMI) signature of externally bonded piezoelectric lead zirconate titanate (PZT) transducers. Externally bonded PZT transducers were used to determine the EMI signature of fiber-reinforced concrete specimens subjected to monotonous and repeatable compression loading. A leave-one-specimen-out cross-validation scenario was adopted for the proposed SHM approach for a stricter and more realistic validation procedure. The experimental study and the obtained results clearly demonstrate the capacity of the introduced approach to provide autonomous and reliable damage identification in a PZT-enabled SHM system, with a mean accuracy of 95.24% and a standard deviation of 5.64%.

show abstract

Section: Resultsmentioning

confidence: 99%

A Deep Learning Approach for Autonomous Compression Damage Identification in Fiber-Reinforced Concrete Using Piezoelectric Lead Zirconate Titanate Transducers

Sapidis,

Kansizoglou,

Naoum

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The format FXP(a,b) indicates a-1 integer bits, b fraction bits, and one sign bit are used to represent the number using fixed-point. As per the methodology presented in 25,26 , the input range of P is assumed to be P ∈ 10 −6 , 10 6 and N ∈ [2,1002] . For comparison purposes, 27 bits are used to represent the fractional part of the input number P. The maximum value of P is 10 6 , which can be represented using 20 integer bits.…”

Section: Datawidth Analysismentioning

confidence: 99%

Radix-4 CORDIC algorithm based low-latency and hardware efficient VLSI architecture for Nth root and Nth power computations

Changela,

Kumar,

Woźniak

et al. 2023

Sci Rep

View full text Add to dashboard Cite

In this article, a low-complexity VLSI architecture based on a radix-4 hyperbolic COordinate Rotion DIgital Computer (CORDIC) is proposed to compute the $$N{{\rm th}}$$ N th root and $$N{{\rm th}}$$ N th power of a fixed-point number. The most recent techniques use the radix-2 CORDIC algorithm to compute the root and power. The high computation latency of radix-2 CORDIC is the primary concern for the designers. $$N{{\rm th}}$$ N th root and $$N{{\rm th}}$$ N th power computations are divided into three phases, and each phase is performed by a different class of the proposed modified radix-4 CORDIC algorithms in the proposed architecture. Although radix-4 CORDIC can converge faster with fewer recurrences, it demands more hardware resources and computational steps due to its intricate angle selection logic and variable scale factor. We have employed the modified radix-4 hyperbolic vectoring (R4HV) CORDIC to compute logarithms, radix-4 linear vectoring (R4LV) to perform division, and the modified scaling-free radix-4 hyperbolic rotation (R4HR) CORDIC to compute exponential. The criteria to select the amount of rotation in R4HV CORDIC is complicated and depends on the coordinates $$X^j$$ X j and $$Y^j$$ Y j of the rotating vector. In the proposed modified R4HV CORDIC, we have derived the simple selection criteria based on the fact that the inputs to R4HV CORDIC are related. The proposed criteria only depend on the coordinate $$Y^j$$ Y j that reduces the hardware complexity of the R4HV CORDIC. The R4HR CORDIC shows the complex scale factor, and compensation of such scale factor necessitates the complex hardware. The complexity of R4HR CORDIC is reduced by pre-computing the scale factor for initial iterations and by employing scaling-free rotations for later iterations. Quantitative hardware analysis suggests better hardware utilization than the recent approaches. The proposed architecture is implemented on a Virtex-6 FPGA, and FPGA implementation demonstrates $$19\%$$ 19 % less hardware utilization with better error performance than the approach with the radix-2 CORDIC algorithm.

show abstract

“…The authors provide a comparison between SNN and convolutional neural networks and show that SNN is much more energy efficient and, at the same time, demonstrates higher accuracy. Oikonomou et al [15] successfully applied SNN in combination with deep learning in a robotic arm target-reach task. The authors of [16] used a probabilistic spiking response model (PSRM) with a multi-layer structure to classify bearing vibration data: the model was proven to be an effective tool for fault diagnosis.…”

Section: First Generationmentioning

confidence: 99%

Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection Tasks

Druzhina

Vatnik

Kulagin

et al. 2023

BDCC

View full text Add to dashboard Cite

For the last two decades, artificial neural networks (ANNs) of the third generation, also known as spiking neural networks (SNN), have remained a subject of interest for researchers. A significant difficulty for the practical application of SNNs is their poor suitability for von Neumann computer architecture, so many researchers are currently focusing on the development of alternative hardware. Nevertheless, today several experimental libraries implementing SNNs for conventional computers are available. In this paper, using the RCNet library, we compare the performance of reservoir computing architectures based on artificial and spiking neural networks. We explicitly show that, despite the higher execution time, SNNs can demonstrate outstanding classification accuracy in the case of complicated datasets, such as data from industrial sensors used for the fault detection of bearings and gears. For one of the test problems, namely, ball bearing diagnosis using an accelerometer, the accuracy of the classification using reservoir SNN almost reached 100%, while the reservoir ANN was able to achieve recognition accuracy up to only 61%. The results of the study clearly demonstrate the superiority and benefits of SNN classificators.

show abstract

A Hybrid Reinforcement Learning Approach With a Spiking Actor Network for Efficient Robotic Arm Target Reaching

Cited by 8 publications

References 29 publications

A Deep Learning Approach for Autonomous Compression Damage Identification in Fiber-Reinforced Concrete Using Piezoelectric Lead Zirconate Titanate Transducers

A Deep Learning Approach for Autonomous Compression Damage Identification in Fiber-Reinforced Concrete Using Piezoelectric Lead Zirconate Titanate Transducers

Radix-4 CORDIC algorithm based low-latency and hardware efficient VLSI architecture for Nth root and Nth power computations

Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection Tasks

Contact Info

Product

Resources

About