Recent work in Topological Deep Learning (TDL) seeks to generalize graph learning's preeminent $message \ passing$ paradigm to more complex relational structures: simplicial complexes, cell complexes, hypergraphs, and combinations thereof. Many approaches to such ${higher\text{-}order \ message \ passing}$ (HOMP) admit formulation in terms of nonlinear diffusion with the Hodge (combinatorial) Laplacian, a graded operator which carries an inductive bias that dimension-$k$ data features correlate with dimension-$k$ topological features encoded in the (singular) cohomology of the underlying domain. For $k=0$ this recovers the graph Laplacian and its well-studied homophily bias. In higher gradings, however, the Hodge Laplacian's bias is more opaque and potentially even degenerate. In this essay, we position sheaf theory as a natural and principled formalism for modifying the Hodge Laplacian's diffusion-mediated interface between local and global descriptors toward more expressive message passing. The sheaf Laplacian's inductive bias correlates dimension-$k$ data features with dimension-$k$ $sheaf$ cohomology, a data-aware generalization of singular cohomology. We will contextualize and novelly extend prior theory on sheaf diffusion in graph learning ($k=0$) in such a light -- and explore how it fails to generalize to $k>0$ -- before developing novel theory and practice for the higher-order setting. Our exposition is accompanied by a self-contained introduction shepherding sheaves from the abstract to the applied.

While 2D image datasets are abundant, they fail to capture essential structural details such as leaf architecture, plant volume, and spatial arrangements that 3D data provide. To address this limitation, we present AgriField3D (website), a curated dataset of 3D point clouds of field-grown maize plants from a diverse genetic panel, designed to be AI-ready for advancing agricultural research. Our dataset comprises over 1,000 high-quality point clouds collected using a Terrestrial Laser Scanner, complemented by procedural models that provide structured, parametric representations of maize plants. These procedural models, generated using Non-Uniform Rational B-Splines (NURBS) and optimized via a two-step process combining Particle Swarm Optimization (PSO) and differentiable programming, enable precise, scalable reconstructions of leaf surfaces and plant architectures. To enhance usability, we performed graph-based segmentation to isolate individual leaves and stalks, ensuring consistent labeling across all samples. We also conducted rigorous manual quality control on all datasets, correcting errors in segmentation, ensuring accurate leaf ordering, and validating metadata annotations. The dataset further includes metadata detailing plant morphology and quality, alongside multi-resolution subsampled versions (100k, 50k, 10k points) optimized for various computational needs. By integrating point cloud data of field grown plants with high-fidelity procedural models and ensuring meticulous manual validation, AgriField3D provides a comprehensive foundation for AI-driven phenotyping, plant structural analysis, and 3D applications in agricultural research.

The Multi-Agent Path Finding (MAPF) problem aims to determine the shortest and collision-free paths for multiple agents in a known, potentially obstacle-ridden environment. It is the core challenge for robotic deployments in large-scale logistics and transportation. Decentralized learning-based approaches have shown great potential for addressing the MAPF problems, offering more reactive and scalable solutions. However, existing learning-based MAPF methods usually rely on agents making decisions based on a limited field of view (FOV), resulting in short-sighted policies and inefficient cooperation in complex scenarios. There, a critical challenge is to achieve consensus on potential movements between agents based on limited observations and communications. To tackle this challenge, we introduce a new framework that applies sheaf theory to decentralized deep reinforcement learning, enabling agents to learn geometric cross-dependencies between each other through local consensus and utilize them for tightly cooperative decision-making. In particular, sheaf theory provides a mathematical proof of conditions for achieving global consensus through local observation. Inspired by this, we incorporate a neural network to approximately model the consensus in latent space based on sheaf theory and train it through self-supervised learning. During the task, in addition to normal features for MAPF as in previous works, each agent distributedly reasons about a learned consensus feature, leading to efficient cooperation on pathfinding and collision avoidance. As a result, our proposed method demonstrates significant improvements over state-of-the-art learning-based MAPF planners, especially in relatively large and complex scenarios, demonstrating its superiority over baselines in various simulations and real-world robot experiments.

The aim of this paper is to propose a novel framework to infer the sheaf Laplacian, including the topology of a graph and the restriction maps, from a set of data observed over the nodes of a graph. The proposed method is based on sheaf theory, which represents an important generalization of graph signal processing. The learning problem aims to find the sheaf Laplacian that minimizes the total variation of the observed data, where the variation over each edge is also locally minimized by optimizing the associated restriction maps. Compared to alternative methods based on semidefinite programming, our solution is significantly more numerically efficient, as all its fundamental steps are resolved in closed form. The method is numerically tested on data consisting of vectors defined over subspaces of varying dimensions at each node. We demonstrate how the resulting graph is influenced by two key factors: the cross-correlation and the dimensionality difference of the data residing on the graph's nodes.

Monitoring growth behavior of maize plants such as the development of ears can give key insights into the plant's health and development. Traditionally, the measurement of the angle of ears is performed manually, which can be time-consuming and prone to human error. To address these challenges, this paper presents a computer vision-based system for detecting and tracking ears of corn in an image sequence. The proposed system could accurately detect, track, and predict the ear's orientation, which can be useful in monitoring their growth behavior. This can significantly save time compared to manual measurement and enables additional areas of ear orientation research and potential increase in efficiencies for maize production. Using an object detector with keypoint detection, the algorithm proposed could detect 90 percent of all ears. The cardinal estimation had a mean absolute error (MAE) of 18 degrees, compared to a mean 15 degree difference between two people measuring by hand. These results demonstrate the feasibility of using computer vision techniques for monitoring maize growth and can lead to further research in this area.

Abstract-- We present a contact-based phenotyping robot platform that can autonomously insert nitrate sensors into cornstalks to proactively monitor macronutrient levels in crops. This task is challenging because inserting such sensors requires sub-centimeter precision in an environment which contains high levels of clutter, lighting variation, and occlusion. To address these challenges, we develop a robust perceptionaction pipeline to detect and grasp stalks, and create a custom robot gripper which mechanically aligns the sensor before inserting it into the stalk. Through experimental validation on 48 unique stalks in a cornfield in Iowa, we demonstrate our platform's capability of detecting a stalk with 94% success, grasping a stalk with 90% success, and inserting a sensor with 60% success. In addition to developing an autonomous phenotyping research platform, we share key challenges and insights obtained from deployment in the field. With the development of artificial intelligence in computer vision and robotics, the agricultural sector is poised to implement precision agriculture methods to enhance crop production efficiency and minimize environmental footprint [1]. Figure 1: Robot inserting sensors into cornstalks to monitor plant nitrate concentration in Curtiss Farm, Iowa.

The ability to adapt and conform to angular and uneven surfaces improves the suction cup's performance in grasping and manipulation. However, in most cases, the adaptation costs lack of required stiffness for manipulation after surface attachment; thus, the ideal scenario is to have compliance during adaptation and stiffness after attachment to the surface. Nevertheless, most stiffness modulation techniques in suction cups require additional actuation. This article presents a new stiffness tunable suction cup that adapts to steep angular surfaces. Using granular jamming as a vacuum driven stiffness modulation provides a sensorless for activating the mechanism. Thus, the design is composed of a conventional active suction pad connected to a granular stalk, emulating a hinge behavior that is compliant during adaptation and has high stiffness after attachment is ensured. During the experiment, the suction cup can adapt to angles up to 85 degrees with force lower than 0.5 N. We also investigated the effect of granular stalk's length on the adaptation and how this design performs compared to passive adaptation without stiffness modulation.

Facebook Inc. announced today that it is integrating its virtual assistant "M" into Messenger to offer suggestions for features that users might want to access during their conversations. In a new blog post, Facebook Product Managers Laurent Landowski and Kemal El Moujahid said that the company has been steadily improving M behind the scenes, and now Facebook believes that M is ready to take on a more active role on the social network. "When we announced M over a year ago, it was a small AI experiment powered by humans that could fulfill almost any request," Landowski and El Moujahid said. "We learned a lot and these interactions have enabled us to build a completely automated version of M that suggests helpful actions in your chat, exposing features people may not have known were available right in Messenger." M will now track conversations in Messenger and offer suggested features based on what users are talking about.

With strawberry picking season well under way - but migrant labour in short supply in several countries - we look at the various robots being developed around the world to help producers harvest this most popular fruit. Next time you buy strawberries take a look a good look in the punnet. Do the berries still have the stem attached or has it been plucked off leaving only the green hat of leaves called the calyx? You may not think that matters, but it's a key consideration for growers as they contemplate the merits of a range of robotic prototypes that promise to pick strawberries as fast and as carefully as humans. Whether the berry is plucked or whether the stalk is snipped through and kept attached is one critical difference between the concepts that Spanish, Belgian, British and US engineers are testing, ready to roll out in fields as soon as next year.

April 12, 2018 --Visit this online directory of the nearly 200 faculty members at Hampshire College and you'll find that, listed between a professor of communications and a visiting professor of video and film, is a petri dish of yellow schmutz. The schmutz is a plasmodial slime mold, Physarum polycephalum, a glob of living cells that exhibits decidedly non-schmutzlike behavior, such as solving mazes and anticipating periodic events – so much so that in 2017 Hampshire, a private liberal arts school in Amherst, Mass., awarded it a position of "visiting non-human scholar." The abilities of non-animals to remember events, recognize patterns, and solve problems are prompting scientists and philosophers to rethink what thinking is. In the 20th century, science demolished the notion that humans are the only animals to exhibit complex thinking; in the 21st, biologists are beginning to see cognition in other biological kingdoms – not just slime molds, but also plants. This shift in thought could not only help scientists better understand cognition's workings and its origins, but it could also help in the search for intelligence beyond Earth.