Towards Employing FPGA and ASIP Acceleration to Enable Onboard AI/ML in Space Applications

Leon, Vasileios; Lentaris, George; Soudris, Dimitrios; Vellas, Simon; Bernou, Mathieu

doi:10.1109/vlsi-soc54400.2022.9939566

Cited by 9 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The newer generation satellites aim to use on-edge processing ie board processing, then transmit only the required data to the base stations. [101][102][103][104][105] The Phi-sat 1 is the first of its kind mission, that uses onboard technology for DL usage. The Phi-Sat 1 was used for remote sensing applications like cloud detection utilizing a specially designed onboard processor, Intel Movidius Myriad 2, which is a hardware AI accelerator.…”

Section: Onboard Enabling Technologiesmentioning

confidence: 99%

“…101,102 The Phi-Sat 1 system consists of eyes of things (EoT) system with the Myriad 2 vision processing unit along with a HyperScout 2, which is a miniaturized spectral camera, which can be used to capture data in the near-infrared and thermal infrared regions. The Myriad 2 vision processing unit is an SoC with integrated DRAM RISC-V processors, streaming hybrid architecture vector engines, and can compute with a steady voltage supply of 2 V. [101][102][103][104]106 The NN on the Phi-SAT-1 was trained using modified data from European Space Agency's Sentinal 2 archive. The modification was done to simulate the behavior of the HyperScout 2 system.…”

Section: Onboard Enabling Technologiesmentioning

confidence: 99%

“…This however used a lot of power and bandwidth resources of the satellite. The newer generation satellites aim to use on‐edge processing ie board processing, then transmit only the required data to the base stations 101–105 …”

Section: Enabling Technologiesmentioning

confidence: 99%

“…The FPGA implementation showed a 2.4 times improvement on the Myriad 2 vision processing unit at a cost of 1.8 times power usage, but per inference, power usage was reduced by 24%. Authors of Leon et al 104 the use of FGPA, vision processing units, tensor processing units, and AI accelerators for satellite task automation. They evaluate the use of components off the shelf FPGA and TPUs.…”

Section: Enabling Technologiesmentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning and Deep Learning powered satellite communications: Enabling technologies, applications, open challenges, and future research directions

Bhattacharyya

Nambiar

Ojha

et al. 2023

Satell Commun Network

View full text Add to dashboard Cite

SummaryThe recent wave of creating an interconnected world through satellites has renewed interest in satellite communications. Private and government‐funded space agencies are making advancements in the creation of satellite constellations, and the introduction of 5G has brought a new focus to a fully connected world. Satellites are the proposed solutions for establishing high throughput and low latency links to remote, hard‐to‐reach areas. This has caused the injection of many satellites in Earth's orbit, which has caused many discrepancies. There is a need to establish highly adaptive and flexible satellite systems to overcome this. Machine Learning (ML) and Deep Learning (DL) have gained much popularity when it comes to communication systems. This review extensively provides insight into ML and DL's utilization in satellite communications. This review covers how satellite communication subsystems and other satellite system applications can be implemented through Artificial Intelligence (AI) and the ongoing open challenges and future directions.

show abstract

Section: Onboard Enabling Technologiesmentioning

confidence: 99%

Section: Onboard Enabling Technologiesmentioning

confidence: 99%

Section: Enabling Technologiesmentioning

confidence: 99%

Section: Enabling Technologiesmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning and Deep Learning powered satellite communications: Enabling technologies, applications, open challenges, and future research directions

Bhattacharyya

Nambiar

Ojha

et al. 2023

Satell Commun Network

View full text Add to dashboard Cite

show abstract

“…Focusing on space applications, there are currently no available GPUs that are Radiation-Hardened-By-Design (RHBD). Radiation-tolerant GPU-based systems, also capable of addressing embedded AI tasks, are available [12] (e.g., S-A1760 Venus, based on the NVIDIA Jetson TX2i GPU, and the SpaceVPX GPU Single Board Computer (SBC) [13]); however, even though they have been shown to achieve high performance (∼TFLOPS) at a remarkable level of energy efficiency, their use is limited to shorter-duration LEO and NEO programs and other short-term missions, as they cannot sustain higher levels of radiation. Commercial GPUs have been tested for radiation as well; in particular, the National Aeronautics and Space Administration (NASA) has conducted several studies on AMD and NVIDIA GPUs [14], [15].…”

Section: A Gpusmentioning

confidence: 99%

Exploring Key Aspects of Soft GPGPU Computing for On-board Acceleration of Artificial Intelligence Algorithms in Space Applications

Monopoli,

Zulberti,

Nannipieri

et al. 2023

2023 European Data Handling &Amp; Data Processing Conference (EDHPC)

View full text Add to dashboard Cite

Intelligence has gained widespread adoption across different industrial sectors, serving as a versatile tool to carry out a diverse array of tasks, ranging from image classification and traffic forecasting to natural language processing and speech recognition. In the space domain, however, a special focus must be placed on area overhead, power consumption, and fault-tolerant solutions. In this particular scenario, soft General-Purpose Computing on Graphic Processing Units has the potential to revolutionise space-related activities. Indeed, by leveraging both Field Programmable Gate Array technology and Graphic Processing Unit computing, it becomes feasible to achieve highperformance capabilities without compromising neither power consumption nor radiation tolerance features. Moreover, the use of reconfigurable hardware can facilitate the acceleration of a wide range of Machine Learning algorithms, avoiding the drawbacks of excessive specialisation. This paper explores the State-of-the-Art in terms of hardware platforms for on-the-edge acceleration of Artificial Intelligence algorithms and compares it with a possible System-on-Chip implementation based on a soft-Graphic Processing Unit. Then, the attention is shifted towards the investigation of key aspects for future space missions, such as reliability and Dynamic Partial Reconfiguration. We point out the lack of European technological solutions, emphasising the promising potential offered by NanoXplore devices. We also discuss the importance of fault detection and mitigation techniques in space applications, covering the most commonly employed hardware methods for reliability enhancement and highlighting the lack of work in the field of General-Purpose Computing for Graphic Processing Units, especially in the space sector. Furthermore, we briefly examine the implementation of Dynamic Partial Reconfiguration over a System-on-Chip featuring a soft-Graphic Processing Unit IP. Finally, in the last section of the paper, we hint at future development of the project and conclude the work.

show abstract

Increasing the Fault Tolerance of COTS FPGAs in Space: SEU Mitigation Techniques on MPSoC

Pagonis,

Leon,

Soudris

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Towards Employing FPGA and ASIP Acceleration to Enable Onboard AI/ML in Space Applications

Cited by 9 publications

References 11 publications

Machine Learning and Deep Learning powered satellite communications: Enabling technologies, applications, open challenges, and future research directions

Machine Learning and Deep Learning powered satellite communications: Enabling technologies, applications, open challenges, and future research directions

Exploring Key Aspects of Soft GPGPU Computing for On-board Acceleration of Artificial Intelligence Algorithms in Space Applications

Increasing the Fault Tolerance of COTS FPGAs in Space: SEU Mitigation Techniques on MPSoC

Contact Info

Product

Resources

About