"One of the dreams I had as a kid was about the first day of school, and being able to build and be creative, and it was the happiest day of my life. And at MIT, I felt like that dream became reality," says Ballesteros. Growing up in the suburban town of Spring, Texas, just outside of Houston, Erik Ballesteros couldn't help but be drawn in by the possibilities for humans in space. It was the early 2000s, and NASA's space shuttle program was the main transport for astronauts to the International Space Station (ISS). Ballesteros' hometown was less than an hour from Johnson Space Center (JSC), where NASA's mission control center and astronaut training facility are based.

NASA's Cooperative Autonomous Distributed Robotic Exploration (CADRE) mission, slated for flight to the Moon's Reiner Gamma region in 2025/2026, is designed to demonstrate multi-agent autonomous exploration of the Lunar surface and sub-surface. A team of three robots and a base station will autonomously explore a region near the lander, collecting the data required for 3D reconstruction of the surface with no human input; and then autonomously perform distributed sensing with multi-static ground penetrating radars (GPR), driving in formation while performing coordinated radar soundings to create a map of the subsurface. At the core of CADRE's software architecture is a novel autonomous, distributed planning, scheduling, and execution (PS&E) system. The system coordinates the robots' activities, planning and executing tasks that require multiple robots' participation while ensuring that each individual robot's thermal and power resources stay within prescribed bounds, and respecting ground-prescribed sleep-wake cycles. The system uses a centralized-planning, distributed-execution paradigm, and a leader election mechanism ensures robustness to failures of individual agents. In this paper, we describe the architecture of CADRE's PS&E system; discuss its design rationale; and report on verification and validation (V&V) testing of the system on CADRE's hardware in preparation for deployment on the Moon.

The exploration of ocean worlds stands as a pivotal element in humanity's exploration of our solar system, encompassing critical research objectives including the quest for potential signs of life and the comprehensive understanding of conditions fostering habitability [1], [2], [3]. Robotic exploration missions are essential for the exploration of potentially habitable ocean worlds. Past lander and rover missions including the Mars exploration program [4] and the Perseverance rover mission [5] are human-in-the-loop systems with expert teams on Earth supervising the terrain sampling process and controlling them based on the collected data. However, unlike Mars missions, many of the ocean world missions, including the Europa Lander mission concept [6], are anticipated to have short durations, on the order of tens of days, due to the intensity of the radiation environment, adverse thermal conditions, low availability of solar energy, and using battery as the sole power source. The limited mission duration combined with the long communication delays between Earth and the ocean worlds necessitates a high degree of autonomy for the lander's success [7]. The Europa lander's primary objectives include collecting terrain samples for in situ analysis of surface and sub-surface materials. Autonomy in terrain sampling missions is challenging due to the high degree of uncertainty in the surface topology at the landing site, terrain material properties, composition, and appearance. Constraints on the number of samples that can be analyzed in-situ, coupled with the risk of system failures, further limits the extent of exploration [8].

Asteroid restructuring uses robotics, self replication, and mechanical automatons to autonomously restructure an asteroid into a large rotating space station. The restructuring process makes structures from asteroid oxide materials; uses productive self-replication to make replicators, helpers, and products; and creates a multiple floor station to support a large population. In an example simulation, it takes 12 years to autonomously restructure a large asteroid into the space station. This is accomplished with a single rocket launch. The single payload contains a base station, 4 robots (spiders), and a modest set of supplies. Our simulation creates 3000 spiders and over 23,500 other pieces of equipment. Only the base station and spiders (replicators) have advanced microprocessors and algorithms. These represent 21st century technologies created and trans-ported from Earth. The equipment and tools are built using in-situ materials and represent 18th or 19th century technologies. The equipment and tools (helpers) have simple mechanical programs to perform repetitive tasks. The resulting example station would be a rotating framework almost 5 kilometers in diameter. Once completed, it could support a population of over 700,000 people. Many researchers identify the high launch costs, the harsh space environment, and the lack of gravity as the key obstacles hindering the development of space stations. The single probe addresses the high launch cost. The autonomous construction eliminates the harsh space environment for construction crews. The completed rotating station provides radiation protection and centripetal gravity for the first work crews and colonists.

If there is extraterrestrial life in our solar system, experts have long thought it could be hiding beneath Mars' surface, in Venus' clouds or in the icy oceans of Jupiter and Saturn's moons. NASA scientists say Uranus' moons Titania and Oberon may also have oceans warm enough to support life, suggesting that we should look there too in our hunt for aliens close to home. They made their discovery after re-analysing data from Voyager 2's close flybys of Uranus in the 1980s, as well as using computer modelling to look for signs of water on five of the planet's largest icy moons. It is the first piece of research to establish how the interior makeup and structure has evolved on Ariel, Umbriel, Titania, Oberon, and Miranda. Distant ice worlds: NASA scientists say Uranus' moons Titania and Oberon may have oceans warm enough to support life.

Thomas Fuchs, the Dean of Artificial Intelligence and Human Health at Mount Sinai in NYC, said AI will be needed to retain the standard of care in the U.S. Artificial intelligence (AI) is helping physicians to diagnose cancer more accurately at much faster rates and at a lower cost than previously possible, according to a scientist working in computational pathology. Dr. Thomas J. Fuchs, the Dean of Artificial Intelligence and Human Health at Mount Sinai in New York City, also works as the chief scientific officer at Paige AI, a company using AI to detect and treat cancer. The latest study from the company tasked 16 pathologists with the review of 610 whole-slide images prepared at multiple institutions globally. They reviewed the slides once without assistance, and then again with assistance from the Pathology Artificial Intelligence Guidance Engine (Paige AI). When Paige AI was used, diagnostic errors reduced by 70%.

There has been an increase in interest in missions that drive significantly longer distances per day than what has currently been performed. Further, some of these proposed missions require autonomous driving and absolute localization in darkness. For example, the Endurance A mission proposes to drive 1200km of its total traverse at night. The lack of natural light available during such missions limits what can be used as visual landmarks and the range at which landmarks can be observed. In order for planetary rovers to traverse long ranges, onboard absolute localization is critical to the ability of the rover to maintain its planned trajectory and avoid known hazardous regions. Currently, to accomplish absolute localization, a ground in the loop (GITL) operation is performed wherein a human operator matches local maps or images from onboard with orbital images and maps. This GITL operation limits the distance that can be driven in a day to a few hundred meters, which is the distance that the rover can maintain acceptable localization error via relative methods. Previous work has shown that using craters as landmarks is a promising approach for performing absolute localization on the moon during the day. In this work we present a method of absolute localization that utilizes craters as landmarks and matches detected crater edges on the surface with known craters in orbital maps. We focus on a localization method based on a perception system which has an external illuminator and a stereo camera. We evaluate (1) both monocular and stereo based surface crater edge detection techniques, (2) methods of scoring the crater edge matches for optimal localization, and (3) localization performance on simulated Lunar surface imagery at night. We demonstrate that this technique shows promise for maintaining absolute localization error of less than 10m required for most planetary rover missions.

Robots are increasingly entering our lives: cleaning robots are in our homes, (partly) automated vehicles bring us to work where we cooperate with service robots, industrial robots, or agricultural robots. Successfully engineering robots demands the interdisciplinary collaboration of experts from, e.g., electrical engineering, mechanical engineering, artificial intelligence, and software engineering. Consequently, integrating modules contributed by respective experts is a key challenge in engineering software-centric robots, yet it is only one of the cross-cutting software concerns crucial to robotics. Hence, most of the added value contributed by domain experts, as well as the glue between the individual experts' contributions in modern robots, is software.

The Far-side Array for Radio Science Investigations of the Dark ages and Exoplanets (FARSIDE) is a proposed mission concept to the lunar far side that seeks to deploy and operate an array of 128 dual-polarization, dipole antennas over a region of 100 square kilometers. The resulting interferometric radio telescope would provide unprecedented radio images of distant star systems, allowing for the investigation of faint radio signatures of coronal mass ejections and energetic particle events and could also lead to the detection of magnetospheres around exoplanets within their parent star's habitable zone. Simultaneously, FARSIDE would also measure the "Dark Ages" of the early Universe at a global 21-cm signal across a range of red shifts (z approximately 50-100). Each discrete antenna node in the array is connected to a central hub (located at the lander) via a communication and power tether. Nodes are driven by cold=operable electronics that continuously monitor an extremely wide-band of frequencies (200 kHz to 40 MHz), which surpass the capabilities of Earth-based telescopes by two orders of magnitude. Achieving this ground-breaking capability requires a robust deployment strategy on the lunar surface, which is feasible with existing, high TRL technologies (demonstrated or under active development) and is capable of delivery to the surface on next-generation commercial landers, such as Blue Origin's Blue Moon Lander. This paper presents an antenna packaging, placement, and surface deployment trade study that leverages recent advances in tethered mobile robots under development at NASA's Jet Propulsion Laboratory, which are used to deploy a flat, antenna-embedded, tape tether with optical communication and power transmission capabilities.

Navigating off-road with a fast autonomous vehicle depends on a robust perception system that differentiates traversable from non-traversable terrain. Typically, this depends on a semantic understanding which is based on supervised learning from images annotated by a human expert. This requires a significant investment in human time, assumes correct expert classification, and small details can lead to misclassification. To address these challenges, we propose a method for predicting high- and low-risk terrains from only past vehicle experience in a self-supervised fashion. First, we develop a tool that projects the vehicle trajectory into the front camera image. Second, occlusions in the 3D representation of the terrain are filtered out. Third, an autoencoder trained on masked vehicle trajectory regions identifies low- and high-risk terrains based on the reconstruction error. We evaluated our approach with two models and different bottleneck sizes with two different training and testing sites with a fourwheeled off-road vehicle. Comparison with two independent test sets of semantic labels from similar terrain as training sites demonstrates the ability to separate the ground as low-risk and the vegetation as high-risk with 81.1% and 85.1% accuracy.