Navigation is a fundamental capacity for mobile robots, enabling them to operate autonomously in complex and dynamic environments. Conventional approaches use probabilistic models to localize robots and build maps simultaneously using sensor observations. Recent approaches employ human-inspired learning, such as imitation and reinforcement learning, to navigate robots more effectively. However, these methods suffer from high computational costs, global map inconsistency, and poor generalization to unseen environments. This paper presents a novel method inspired by how humans perceive and navigate themselves effectively in novel environments. Specifically, we first build local frames that mimic how humans represent essential spatial information in the short term. Points in local frames are hybrid representations, including spatial information and learned features, so-called spatial-implicit local frames. Then, we integrate spatial-implicit local frames into the global topological map represented as a factor graph. Lastly, we developed a novel navigation algorithm based on Rapid-Exploring Random Tree Star (RRT*) that leverages spatial-implicit local frames and the topological map to navigate effectively in environments. To validate our approach, we conduct extensive experiments in real-world datasets and in-lab environments. We open our source code at https://github.com/tuantdang/simn}{https://github.com/tuantdang/simn.

Semantic understanding plays a crucial role in Dense Simultaneous Localization and Mapping (SLAM), facilitating comprehensive scene interpretation. Recent advancements that integrate Gaussian Splatting into SLAM systems have demonstrated its effectiveness in generating high-quality renderings through the use of explicit 3D Gaussian representations. Building on this progress, we propose SGS-SLAM, the first semantic dense visual SLAM system grounded in 3D Gaussians, which provides precise 3D semantic segmentation alongside high-fidelity reconstructions. Specifically, we propose to employ multi-channel optimization during the mapping process, integrating appearance, geometric, and semantic constraints with key-frame optimization to enhance reconstruction quality. Extensive experiments demonstrate that SGS-SLAM delivers state-of-the-art performance in camera pose estimation, map reconstruction, and semantic segmentation, outperforming existing methods meanwhile preserving real-time rendering ability.

In this work, we present a dense tracking and mapping system named Vox-Fusion, which seamlessly fuses neural implicit representations with traditional volumetric fusion methods. Our approach is inspired by the recently developed implicit mapping and positioning system and further extends the idea so that it can be freely applied to practical scenarios. Specifically, we leverage a voxel-based neural implicit surface representation to encode and optimize the scene inside each voxel. Furthermore, we adopt an octree-based structure to divide the scene and support dynamic expansion, enabling our system to track and map arbitrary scenes without knowing the environment like in previous works. Moreover, we proposed a high-performance multi-process framework to speed up the method, thus supporting some applications that require real-time performance. The evaluation results show that our methods can achieve better accuracy and completeness than previous methods. We also show that our Vox-Fusion can be used in augmented reality and virtual reality applications. Our source code is publicly available at https://github.com/zju3dv/Vox-Fusion.

In this paper, we propose a novel object-level mapping system that can simultaneously segment, track, and reconstruct objects in dynamic scenes. It can further predict and complete their full geometries by conditioning on reconstructions from depth inputs and a category-level shape prior with the aim that completed object geometry leads to better object reconstruction and tracking accuracy. For each incoming RGB-D frame, we perform instance segmentation to detect objects and build data associations between the detection and the existing object maps. A new object map will be created for each unmatched detection. For each matched object, we jointly optimise its pose and latent geometry representations using geometric residual and differential rendering residual towards its shape prior and completed geometry. Our approach shows better tracking and reconstruction performance compared to methods using traditional volumetric mapping or learned shape prior approaches. We evaluate its effectiveness by quantitatively and qualitatively testing it in both synthetic and real-world sequences.

The robotic process automation (RPA) market has heated up as enterprises increasingly look to RPA bots to achieve their long-term automation ambitions. Meanwhile the RPA tools market has been rapidly evolving as new vendors enter the market, mature vendors add new features, and RPA use cases expand beyond traditional applications in response to the platforms adding cognitive and AI capabilities. However welcome these new capabilities may be, they muddy the waters for enterprises that are evaluating RPA tools. TechBeacon talked to top experts and analysts to provide some clarity. Here are the variables to consider as you shop for the right RPA tools for your organization.

Simultaneous localization and mapping (SLAM) is the computational problem of constructing or updating a map of an unknown environment while simultaneously keeping track of a robot's location within it. SLAM is being gradually developed towards Spatial AI, the common sense spatial reasoning that will enable robots and other artificial devices to operate in general ways in their environments. This will enable robots to not just localize and build geometric maps, but actually interact intelligently with scenes and objects. A key technology that is helping this progress is deep learning, which has enabled many recent breakthroughs in computer vision and other areas of AI. In the context of Spatial AI, deep learning has most obviously had a big impact on bringing semantic meaning to geometric maps of the world.

IMAGE: Brian Davison, Associate Professor of Computer Science Engineering at Lehigh University, is principal investigator of an NSF-backed project to develop a search engine intended to help scientists and others locate... view more There was a time--not that long ago--when the phrases "Google it" or "check Yahoo" would have been interpreted as sneezes, or a perhaps symptoms of an oncoming seizure, rather than as coherent thoughts. Today, these are key to answering all of life's questions. It's one thing to use the Web to keep up with a Kardashian, shop for ironic T-shirts, argue with our in-laws about politics, or any of the other myriad ways we use the Web in today's world. But if you are a serious researcher looking for real data that can help you advance your ideas, how useful are the underlying technologies that support the search engines we've all come to take for granted? "Not very," says Brian Davison, associate professor of computer science at Lehigh University.

Forget lightning speed calculations, technological superiority and machine-like precision. Thanks to the efforts of some researchers, artificial intelligence can now create magic. "We've done a number of different tricks involving artificial intelligence," says Peter McOwan, a computer science professor at Queen Mary University of London. McOwan and his coauthor, Howard Williams, recently published a study in PLOS ONE on using search algorithms to scour the internet to find the hidden mental associations magicians can use to astound their spectators. "A piece of software is like a magic trick in that it has something that seems amazing," McOwan says.

Computer vision is ready for its next big test: seeing in 3D. The ImageNet Challenge, which has boosted the development of image-recognition algorithms, will be replaced by a new competition next year that aims to help robots see the world in all its depth. Since 2010, researchers have trained image recognition algorithms on the ImageNet database, a go-to set of more than 14 million images hand-labelled with information about the objects they depict. The algorithms learn to classify the objects in the photos into different categories, such as house, steak or Alsatian. Almost all computer vision systems are trained like this before being fine-tuned on a more specific set of images for different tasks.

Sir James Dyson is taking on the might of Google by investing £5m in a British university to develop a new generation of "intelligent domestic robots". His company, best known for its vacuum cleaners, is putting the money into a laboratory at Imperial College London, which has begun hiring up to 15 scientists who will work on developing robot vision systems that could be used in devices such as robot-controlled vacuums – a longstanding ambition of Dyson himself. The inventor said the plan was to create "practical everyday technologies that will make our lives easier". The move could put Dyson into a position where it is directly challenging Google, which has recently acquired eight robotics companies, including Boston Dynamics, which has made self-controlling robots for the US military. In January it spent £400m acquiring DeepMind Technologies, a London-based startup focusing on artificial intelligence.