The development, integration, and maintenance of geospatial databases rely heavily on efficient and accurate matching procedures of Geospatial Entity Resolution (ER). While resolution of points-of-interest (POIs) has been widely addressed, resolution of entities with diverse geometries has been largely overlooked. This is partly due to the lack of a uniform technique for embedding heterogeneous geometries seamlessly into a neural network framework. Existing neural approaches simplify complex geometries to a single point, resulting in significant loss of spatial information. To address this limitation, we propose Omni, a geospatial ER model featuring an omni-geometry encoder. This encoder is capable of embedding point, line, polyline, polygon, and multi-polygon geometries, enabling the model to capture the complex geospatial intricacies of the places being compared. Furthermore, Omni leverages transformer-based pre-trained language models over individual textual attributes of place records in an Attribute Affinity mechanism. The model is rigorously tested on existing point-only datasets and a new diverse-geometry geospatial ER dataset. Omni produces up to 12% (F1) improvement over existing methods. Furthermore, we test the potential of Large Language Models (LLMs) to conduct geospatial ER, experimenting with prompting strategies and learning scenarios, comparing the results of pre-trained language model-based methods with LLMs. Results indicate that LLMs show competitive results.

Prime Day came and went in a blur. It isn't until the post-haze deliveries start showing up that you realize you spent far too much on silly trinkets and toiletries instead of investment purchases. A hot dog toaster or a cute nightlight can't take chores off your plate, but this 3-in-1 robotic vacuum and mop can. And thankfully, there's still time to grab it for 68 percent off. The ECOVACS DEEBOT T20 Omni is your secret weapon for a squeaky clean home--with minimal intervention required from you.

--This paper presents a real-time trajectory planning scheme for a heterogeneous multi-robot system (consisting of a quadrotor and a ground mobile robot) for a cooperative landing task, where the landing position, landing time, and coordination between the robots are determined autonomously under the consideration of feasibility and user specifications. The proposed framework leverages the potential of the complementarity constraint as a decision-maker and an indicator for diverse cooperative tasks and extends it to the collaborative landing scenario. In a potential application of the proposed methodology, a ground mobile robot may serve as a mobile charging station and coordinates in real-time with a quadrotor to be charged, facilitating a safe and efficient rendezvous and landing. We verified the generated trajectories in simulation and real-world applications, demonstrating the real-time capabilities of the proposed landing planning framework. I. INTRODUCTION Heterogeneous multi-robot collaboration combines the advantages of different robot domains, providing wide-area coverage and high environmental adaptability. This cross-domain cooperation, where aerial and ground robots are usually involved, has been developed and utilized in various applications, such as search and rescue, logistics and delivery, and infrastructure inspection [1].

Theoretical and empirical evidence suggests that joint graph embedding algorithms induce correlation across the networks in the embedding space. In the Omnibus joint graph embedding framework, previous results explicitly delineated the dual effects of the algorithm-induced and model-inherent correlations on the correlation across the embedded networks. Accounting for and mitigating the algorithm-induced correlation is key to subsequent inference, as sub-optimal Omnibus matrix constructions have been demonstrated to lead to loss in inference fidelity. This work presents the first efforts to automate the Omnibus construction in order to address two key questions in this joint embedding framework: the correlation-to-OMNI problem and the flat correlation problem. In the flat correlation problem, we seek to understand the minimum algorithm-induced flat correlation (i.e., the same across all graph pairs) produced by a generalized Omnibus embedding. Working in a subspace of the fully general Omnibus matrices, we prove both a lower bound for this flat correlation and that the classical Omnibus construction induces the maximal flat correlation. In the correlation-to-OMNI problem, we present an algorithm -- named corr2Omni -- that, from a given matrix of estimated pairwise graph correlations, estimates the matrix of generalized Omnibus weights that induces optimal correlation in the embedding space. Moreover, in both simulated and real data settings, we demonstrate the increased effectiveness of our corr2Omni algorithm versus the classical Omnibus construction.

Open-ended algorithms aim to learn new, interesting behaviors forever. That requires a vast environment search space, but there are thus infinitely many possible tasks. Even after filtering for tasks the current agent can learn (i.e., learning progress), countless learnable yet uninteresting tasks remain (e.g., minor variations of previously learned tasks). An Achilles Heel of open-endedness research is the inability to quantify (and thus prioritize) tasks that are not just learnable, but also $\textit{interesting}$ (e.g., worthwhile and novel). We propose solving this problem by $\textit{Open-endedness via Models of human Notions of Interestingness}$ (OMNI). The insight is that we can utilize large (language) models (LMs) as a model of interestingness (MoI), because they $\textit{already}$ internalize human concepts of interestingness from training on vast amounts of human-generated data, where humans naturally write about what they find interesting or boring. We show that LM-based MoIs improve open-ended learning by focusing on tasks that are both learnable $\textit{and interesting}$, outperforming baselines based on uniform task sampling or learning progress alone. This approach has the potential to dramatically advance the ability to intelligently select which tasks to focus on next (i.e., auto-curricula), and could be seen as AI selecting its own next task to learn, facilitating self-improving AI and AI-Generating Algorithms. View website at https://www.jennyzhangzt.com/omni/

Last year, I reviewed Ecovacs' Deebot (6/10, WIRED Review). It was an expensive and massive mopping robot vacuum that came with a ton of extra functions that, to be quite honest, didn't make much practical sense. My 8-year-old, for example, is used to her mother occasionally doing strange things around the house. She accepted when her mother was talking to her through that robot vacuum's walkie-talkie, but she didn't exactly like it. That's why, this year, it made more sense for me to try the Deebot T9, which at $800 is the midrange model in Deebot's 2023 line.

With unique styling and a motorized, rotatable camera the 70mai Dash Cam Omni both looks good in your vehicle and takes detailed captures in any direction. I don't want to saddle the 70mai Dash Cam Omni with the adjective cute, though the onboard and app graphics animations push that aesthetic somewhat. Clever and unique are far better terms to describe the unit with its motorized, rotatable camera. More than that, the Omni is an effective dash cam that takes detailed video from any direction you point it at--day or night. Note that all images are showing the Omni resting its mount.

Cleaning robot maker Ecovacs is launching three new Deebot vacuum / mop models. The company says the Deebot N10 Plus, T9 and T10 Omni "have 3x the suction power of most robotic vac mops" while bringing some premium features from the $1,549 X1 Omni to (somewhat) lower price points. The three cleaning machines are available in the US starting today. The Deebot T10 Omni is the most expensive of the three new models at $1,300. However, it tries to justify its price with a four-stage cleaning system that has 5,000Pa suction power.

People from underrepresented communities are strongly encouraged to apply.

"Bite the dust" is one of those rare phrases you can use on your archnemesis and your robot vacuum. We can't make up for the mayhem your enemies have caused, but we can help you find a robot vacuum that will reduce the mayhem in your home. For Prime Day, some of our favorites are on sale. They not only suck up dust, but can also dump it out, map their path, and even mop up. The WIRED Gear team tests products year-round, and we sorted through hundreds of thousands of deals by hand to make these picks.