Gaussian process (GP) models that combine both categorical and continuous input variables have found use in longitudinal data analysis of and computer experiments. However, standard inference for these models has the typical cubic scaling, and common scalable approximation schemes for GPs cannot be applied since the covariance function is non-continuous. In this work, we derive a basis function approximation scheme for mixed-domain covariance functions, which scales linearly with respect to the number of observations and total number of basis functions. The proposed approach is naturally applicable to also Bayesian GP regression with discrete observation models. We demonstrate the scalability of the approach and compare model reduction techniques for additive GP models in a longitudinal data context. We confirm that we can approximate the exact GP model accurately in a fraction of the runtime compared to fitting the corresponding exact model. In addition, we demonstrate a scalable model reduction workflow for obtaining smaller and more interpretable models when dealing with a large number of candidate predictors.

GPR models can also incorporate prior knowledge through selecting an appropriate kernel function. GPR commonly assumes a homoscedastic Gaussian distribution for observation noise because this yields an analytical form for the posterior predictive prediction. However, Bayesian inference based on Gaussian noise distributions is known to be sensitive to outliers which are defined as observations that strongly deviate from model assumptions. In regression, outliers can arise from relevant inputs being absent from the model, measurement error, and other unknown sources. These outliers are associated with unconsidered sources of variation that affect the target variable sporadically. In this case, the observation model is unable to distinguish between random noise and systematic effects not captured by the model. In the context of GPR under Gaussian noise, outliers can heavily influence the posterior predictive distribution, resulting in a biased estimate of the mean function and overly confident prediction intervals. Therefore, robust observation models are desired in the presence of potential outliers.

Caves and lava tubes on the Moon and Mars are sites of geological and astrobiological interest but consist of terrain that is inaccessible with traditional robot locomotion. To support the exploration of these sites, we present ReachBot, a robot that uses extendable booms as appendages to manipulate itself with respect to irregular rock surfaces. The booms terminate in grippers equipped with microspines and provide ReachBot with a large workspace, allowing it to achieve force closure in enclosed spaces such as the walls of a lava tube. To propel ReachBot, we present a contact-before-motion planner for non-gaited legged locomotion that utilizes internal force control, similar to a multi-fingered hand, to keep its long, slender booms in tension. Motion planning also depends on finding and executing secure grips on rock features. We use a Monte Carlo simulation to inform gripper design and predict grasp strength and variability. Additionally, we use a two-step perception system to identify possible grasp locations. To validate our approach and mechanisms under realistic conditions, we deployed a single ReachBot arm and gripper in a lava tube in the Mojave Desert. The field test confirmed that ReachBot will find many targets for secure grasps with the proposed kinematic design.

Machine learning practitioners often face significant challenges in formally integrating their prior knowledge and beliefs into predictive models, limiting the potential for nuanced and context-aware analyses. Moreover, the expertise needed to integrate this prior knowledge into probabilistic modeling typically limits the application of these models to specialists. Our goal is to build a regression model that can process numerical data and make probabilistic predictions at arbitrary locations, guided by natural language text which describes a user's prior knowledge. Large Language Models (LLMs) provide a useful starting point for designing such a tool since they 1) provide an interface where users can incorporate expert insights in natural language and 2) provide an opportunity for leveraging latent problem-relevant knowledge encoded in LLMs that users may not have themselves. We start by exploring strategies for eliciting explicit, coherent numerical predictive distributions from LLMs. We examine these joint predictive distributions, which we call LLM Processes, over arbitrarily-many quantities in settings such as forecasting, multi-dimensional regression, black-box optimization, and image modeling. We investigate the practical details of prompting to elicit coherent predictive distributions, and demonstrate their effectiveness at regression. Finally, we demonstrate the ability to usefully incorporate text into numerical predictions, improving predictive performance and giving quantitative structure that reflects qualitative descriptions. This lets us begin to explore the rich, grounded hypothesis space that LLMs implicitly encode.

Humans cannot always be treated as oracles for collaborative sensing. Robots thus need to maintain beliefs over unknown world states when receiving semantic data from humans, as well as account for possible discrepancies between human-provided data and these beliefs. To this end, this paper introduces the problem of semantic data association (SDA) in relation to conventional data association problems for sensor fusion. It then develops a novel probabilistic semantic data association (PSDA) algorithm to rigorously address SDA in general settings, unlike previous work on semantic data fusion which developed heuristic techniques for specific settings. PSDA is further incorporated into a recursive hybrid Bayesian data fusion scheme which uses Gaussian mixture priors for object states and softmax functions for semantic human sensor data likelihoods. Simulations of a multi-object search task show that PSDA enables robust collaborative state estimation under a wide range of conditions where semantic human sensor data can be erroneous or contain significant reference ambiguities.

NASA has marked the Curiosity rover's ninth anniversary on Mars by unveiling a new panoramic image of the Martian landscape, a locale that may explain why the Red Planet became dry. The panoramic image, which was put together on July 3 by stitching 129 individual images together, shows Curiosity's current home, Mount Sharp, a 5-mile-tall mountain inside Mars' Gale Crater. NASA marked the Curiosity rover's ninth anniversary on Mars by unveiling a new panoramic image. The image was created by the rover's Mast Camera, or Mastcam. Upon arrival at Mount Sharp in 2014, Curiosity has been traveling up the rock formation for the past several years.

At first glance at this image, you'd be forgiven for mistaking it as a still from the latest science fiction blockbuster. But the photo is very much real, and was snapped by NASA's Curiosity Mars rover this week. The selfie shows the rover alongside a rock formation dubbed'Mont Mercou', a nickname taken from a mountain in France. And while the photo is impressive on its own, it was actually taken to celebrate Curiosity's 30th sample to date, after the rover drilled a hole at a nearby rock sample nicknamed'Nontron.' The selfie shows the rover alongside a rock formation dubbed'Mont Mercou', a nickname taken from a mountain in France So far 2021 has been the'year of Mars' with three spaceships from Earth arriving at the Red Planet.

A renowned photographer has captured the highest resolution shots of snowflakes ever using a homemade prototype described as one part microscope and one part camera. Nathan Myhrvold, an American scientist, inventor, photographer and ex-chief technology officer of Microsoft, took 18 months to build the 100 megapixel camera capable of capturing a snowflake's microscopic detail. Using the camera, which he describes as the'highest resolution snowflake camera in the world', he took 100 frames of each snowflake in quick succession then stacked them for the whole image to be in focus. The results show the lush variety of snowflakes measuring only a few tens of millimetres in diameter, captured when Myhrvold was in Alaska and Canada. Pictured, stellar dendrite captured in Yellowknife, Canada.

These 26 holes represent each of the rock samples NASA's Curiosity Mars rover has collected as of early July 2020. A map in the upper left shows where the holes were drilled along the rover's route, along with where it scooped six samples of soil Two sizes of ripples are evident in this December 13, 2015, view of a top of a Martian sand dune, from NASA's Curiosity Mars rover Here you can see clouds in the Martian sky captured by NASA's Curiosity rover. Mount Sharp is one of the images shared by NASA to mark the anniversary of Curiosity landing on Mars - the image is actually 44 pictures stitched together. Curiosity will never venture to the upper portion of the mountain; instead, it's exploring the many layers found lower down. Each has a different story to tell about how Mars, which was once more like Earth (warmer and wetter), changed over time and will reach the next layer in 2021.

NASA is asking people to explore Mars using images taken of the Red Planet by its Curiosity Rover and help to label rocks and other surface features. The project, known as AI4Mars, is designed to improve an artificial intelligence algorithm that will help future Martian rovers move across the planet's surface. The simulation was designed by a team from NASAs Jet Propulsion Laboratory as a way to help future rovers spot potential obstacles and avoid getting stuck. The projected is hosted on the citizen science site Zooniverse and involves volunteers labelling terrain features in thousands of pictures of the Red Planet. NASA hopes that having a more effective algorithm - similar to the ones used in self driving cars - will prevent future rovers suffering the same fate as Spirit which got stuck in a sand pit that ended its mission after seven years.