Mars has long captivated the human imagination as a potential destination for settlement and scientific exploration. After deploying individual rovers, the next step in our journey to Mars is the autonomous exploration of the Red Planet using a collaborative swarm of rovers, drones, and satellites. This concept paper envisions a sustainable Mars exploration scenario featuring energy-aware, collaborative, and autonomous vehicles, including rovers, drones, and satellites, operating around Mars. The proposed framework is designed to address key challenges in energy management, edge intelligence, communication, sensing, resource-aware task scheduling, and radiation hardening. This work not only identifies these critical areas of research but also proposes novel technological solutions drawn from terrestrial advancements to extend their application to extraterrestrial exploration.

Hyperdimensional Computing (HDC) is an emerging AI algorithm, touted to be an efficient, neuro-inspired and reliable alternative to neural networks for Edge AI. HDC utilizes hypervectors with several thousand elements; the number of elements in these hypervectors denotes the HDC dimension. This dimension can be optimized for improving the efficiency and reliability of HDC inference against errors such as bit-flips, which can be caused by environmental radiation-induced soft errors. We hypothesize that, by reducing the runtime chip area and execution time utilized by HDC inference through lowering dimensionality, both efficiency and reliability against soft error-induced bit-flips can be simultaneously improved while trading off a negligible amount of accuracy and error threshold. We tested our hypothesis by executing an HDC inference algorithm with two different dimension values, 10000 (10k) and 1024, on a commercially available, low-power, bare-metal ARM platform with a Cortex-M4 processor. We conducted the efficiency analysis by measuring the CPU cycles and energy required for executing the algorithm, and the reliability analysis using real-world atmospheric-like neutron radiation from the ChipIr facility in Oxfordshire, UK. Analyses revealed that, by lowering the HDC dimension from 10k to 1024, the reliability of HDC inference against soft error-induced bit-flips was 3.5 times better and efficiency improved by more than 16 times. This innovative observation contrasts the prevailing understanding in the community that increasing the HDC dimension always improves robustness or reliability. To the best of our knowledge, our work is the first to study the reliability of HDC inference using real-world radiation.

Artificial intelligence (AI) algorithms bring autonomy to many applications including safety-critical ones involving automotive, aviation, satellites, medical instruments, in- terplanetary rovers, the Internet of things, etc. Noise introduced inside the AI model can undermine this autonomy by unintentionally altering its internal parameters such as the weights of neural networks or the hypervectors of hyperdimensional computing AI algorithms. This internal noise introduces unreliability in the AI inferences, a pro- cess crucial in many AI-enabled safety-critical applications, for example, self-driving and navigation deployed on the edges of the network. Here, anything that disturbs the data or parameters used by an algorithm for computation is considered as noise. AI computed at the network edges, i.e., Edge AI, by nature of their application, are placed close to the data source and cannot be ideally protected from environmental factors, for instance, the radiation at space and terrestrial levels. This radiation produces internal noise in the form of soft errors leading to inadvertent bit-flips. Edge AI often has limited power sources and cannot employ power-hungry algorithms or techniques to protect from such errors. While hardware techniques exist, they can be costly to realize and often cannot be extended to existing architectures and commercially available off- the-shelf (COTS) devices. Hence, this book focuses on software techniques to improve efficiency and to at least maintain or improve the reliability of Edge AI algorithms such as Neural Networks (NN) and Hyperdimensional computing (HDC) under radiation such as neutron rays. The key uniqueness of my research work is the focus on a new branch of techniques where reliability and efficiency optimizations coexist for Edge AI, unlike many other works which trade some efficiency for reliability. Such techniques presented in this book might have tradeoffs in terms of the AI model accuracy due to changes in the data representation used by the model or might be only applicable to AI models with certain level of sparsity. However, the associated benefits are of interest for various low-power Edge AI applications with limited power budget and high reliability requirements.