2020 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT) 2020
DOI: 10.1109/dft50435.2020.9250908
|View full text |Cite
|
Sign up to set email alerts
|

AI in space: applications examples and challenges

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
12
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
4

Relationship

1
7

Authors

Journals

citations
Cited by 23 publications
(12 citation statements)
references
References 8 publications
0
12
0
Order By: Relevance
“…In recent years, S-CPS and onboard processors in space have been striving for more performance, fueled by more advanced mission requirements and higher expectations for onboard electronics resulting from the advancement of commercial technology [17,36]. However, reliability and dependability [9,50] remain key concerns in the space domain because, with high levels of cosmic rays, errors are more frequent than at ground level and occur too often for a system to perform its intended mission reliably.…”
Section: Design Trends For Cps In Spacementioning
confidence: 99%
See 1 more Smart Citation
“…In recent years, S-CPS and onboard processors in space have been striving for more performance, fueled by more advanced mission requirements and higher expectations for onboard electronics resulting from the advancement of commercial technology [17,36]. However, reliability and dependability [9,50] remain key concerns in the space domain because, with high levels of cosmic rays, errors are more frequent than at ground level and occur too often for a system to perform its intended mission reliably.…”
Section: Design Trends For Cps In Spacementioning
confidence: 99%
“…New Space missions with smaller, more cost-effective satellites tend to rely more on Commercial Off-the-Shelf (COTS) electronics to design the spacecraft [43]. These components offer significantly more performance at a lower cost, sacrificing reliability, which can be tolerated for non-critical applications, such as in CubeSats [43] or for non-critical machine learning workloads [17]. However, even for these satellite missions, certain aspects, such as communication and control, still require some radiation tolerance in COTS solutions, often guaranteed with watchdog timers.…”
Section: Design Trends For Cps In Spacementioning
confidence: 99%
“…Introducing additional noise into already noisy data will not significantly degrade the result. These computationally intensive and noise-tolerant applications however could greatly benefit from higher processing power [7].…”
Section: Introductionmentioning
confidence: 99%
“…In recent years, research in the space community has shown a growing interest in the application of Artificial Intelligence (AI), and in particular Deep Learning (DL), on board spacecrafts in view of its potential advantages [1][2][3][4][5]. One main reason is due to the high potential demonstrated by Deep Neural Network (DNN) models for many different space applications, such as object-detection [3] and recognition, image scene classification [6,7], super-resolution [8], agricultural-crop detection [9], and change detection [10], outperforming classical approaches both in terms of performance and time to design.…”
Section: Introductionmentioning
confidence: 99%
“…The deployment of DNNs on board spacecraft might also mitigate the problem of the increasing number of sensor data that must be downloaded to ground [1,5,11]. Indeed, less usable data, like cloud-covered images, can be identified, tagged, pre-filtered, discarded, or selectively compressed [2,3].…”
Section: Introductionmentioning
confidence: 99%