We show that this laziness directly relates to volume comparison results from Riemannian geometry. We then extend this scalar curvature notion to an entire quadratic form using neural network estimations based on the diffusion map of point-clouddata.

We propose a novel segmentation-based explainable artificial intelligence (XAI) method for neural networks working on point cloud classification. As one building block of this method, we propose a novel point-shifting mechanism to introduce perturbations in point cloud data. Recently, AI has seen an exponential growth. Hence, it is important to understand the decision-making process of AI algorithms when they are applied in critical areas. Our work focuses on explaining AI algorithms that classify point cloud data. An important aspect of the methods used for explaining AI algorithms is their ability to produce explanations that are easy for humans to understand. This allows them to analyze the AI algorithms better and make appropriate decisions based on that analysis. Therefore, in this work, we intend to generate meaningful explanations that can be easily interpreted by humans. The point cloud data we consider represents 3D objects such as cars, guitars, and laptops. We make use of point cloud segmentation models to generate explanations for the working of classification models. The segments are used to introduce perturbations into the input point cloud data and generate saliency maps. The perturbations are introduced using the novel point-shifting mechanism proposed in this work which ensures that the shifted points no longer influence the output of the classification algorithm. In contrast to previous methods, the segments used by our method are meaningful, i.e. humans can easily interpret the meaning of the segments. Thus, the benefit of our method over other methods is its ability to produce more meaningful saliency maps. We compare our method with the use of classical clustering algorithms to generate explanations. We also analyze the saliency maps generated for example inputs using our method to demonstrate the usefulness of the method in generating meaningful explanations.

-- High-definition (HD) semantic mapping of complex intersections poses significant challenges for traditional vehicle-based approaches due to occlusions and limited perspectives. This paper introduces a novel camera-LiDAR fusion framework that leverages elevated intelligent roadside units (IRUs). Additionally, we present RS-seq, a comprehensive dataset developed through the systematic enhancement and annotation of the V2X-Seq dataset. RS-seq includes precisely labelled camera imagery and LiDAR point clouds collected from roadside installations, along with vectorized maps for seven intersections annotated with detailed features such as lane dividers, pedestrian crossings, and stop lines. The proposed fusion framework employs a two-stage process that integrates modality-specific feature extraction and cross-modal semantic integration, capitalizing on camera high-resolution texture and precise geometric data from LiDAR. Quantitative evaluations using the RS-seq dataset demonstrate that our multimodal approach consistently surpasses unimodal methods. Specifically, compared to unimodal baselines evaluated on the RS-seq dataset, the multimodal approach improves the mean Intersection-over-Union (mIoU) for semantic segmentation by 4% over the image-only results and 18% over the point cloud-only results. This study establishes a baseline methodology for IRU-based HD semantic mapping and provides a valuable dataset for future research in infrastructure-assisted autonomous driving systems. Semantic HD maps are essential for autonomous driving, as they provide precise road location details through semantic features such as lane dividers, stop lines, and pedestrian crossings.

Time series foundation models (FMs) have emerged as a popular paradigm for zero-shot multi-domain forecasting. FMs are trained on numerous diverse datasets and claim to be effective forecasters across multiple different time series domains, including cloud data. In this work we investigate this claim, exploring the effectiveness of FMs on cloud data. We demonstrate that many well-known FMs fail to generate meaningful or accurate zero-shot forecasts in this setting. We support this claim empirically, showing that FMs are outperformed consistently by simple linear baselines. We also illustrate a number of interesting pathologies, including instances where FMs suddenly output seemingly erratic, random-looking forecasts. Our results suggest a widespread failure of FMs to model cloud data.

This paper presents a 6-DoF range-based Monte Carlo localization method with a GPU-accelerated Stein particle filter. To update a massive amount of particles, we propose a Gauss-Newton-based Stein variational gradient descent (SVGD) with iterative neighbor particle search. This method uses SVGD to collectively update particle states with gradient and neighborhood information, which provides efficient particle sampling. For an efficient neighbor particle search, it uses locality sensitive hashing and iteratively updates the neighbor list of each particle over time. The neighbor list is then used to propagate the posterior probabilities of particles over the neighbor particle graph. The proposed method is capable of evaluating one million particles in real-time on a single GPU and enables robust pose initialization and re-localization without an initial pose estimate. In experiments, the proposed method showed an extreme robustness to complete sensor occlusion (i.e., kidnapping), and enabled pinpoint sensor localization without any prior information.

The integration of Light Detection and Ranging (LiDAR) and Internet of Things (IoT) technologies offers transformative opportunities for public health informatics in urban safety and pedestrian well-being. This paper proposes a novel framework utilizing these technologies for enhanced 3D object detection and activity classification in urban traffic scenarios. By employing elevated LiDAR, we obtain detailed 3D point cloud data, enabling precise pedestrian activity monitoring. To overcome urban data scarcity, we create a specialized dataset through simulated traffic environments in Blender, facilitating targeted model training. Our approach employs a modified Point Voxel-Region-based Convolutional Neural Network (PV-RCNN) for robust 3D detection and PointNet for classifying pedestrian activities, significantly benefiting urban traffic management and public health by offering insights into pedestrian behavior and promoting safer urban environments. Our dual-model approach not only enhances urban traffic management but also contributes significantly to public health by providing insights into pedestrian behavior and promoting safer urban environment.

This story was originally published by Yale E360 and is reproduced here as part of the Climate Desk collaboration. Two months after its release in November 2022, OpenAI's ChatGPT had 100 million active users, and suddenly tech corporations were racing to offer the public more "generative AI" Pundits compared the new technology's impact to the Internet, or electrification, or the Industrial Revolution--or the discovery of fire. Time will sort hype from reality, but one consequence of the explosion of artificial intelligence is clear: this technology's environmental footprint is large and growing. AI use is directly responsible for carbon emissions from non-renewable electricity and for the consumption of millions of gallons of fresh water, and it indirectly boosts impacts from building and maintaining the power-hungry equipment on which AI runs. As tech companies seek to embed high-intensity AI into everything from resume-writing to kidney transplant medicine and from choosing dog food to climate modeling, they cite many ways AI could help reduce humanity's environmental footprint.

With the increasing prevalence of drones in various industries, the navigation and tracking of unmanned aerial vehicles (UAVs) in challenging environments, particularly GNSS-denied areas, have become crucial concerns. To address this need, we present a novel multi-LiDAR dataset specifically designed for UAV tracking. Our dataset includes data from a spinning LiDAR, two solid-state LiDARs with different Field of View (FoV) and scan patterns, and an RGB-D camera. This diverse sensor suite allows for research on new challenges in the field, including limited FoV adaptability and multi-modality data processing. The dataset facilitates the evaluation of existing algorithms and the development of new ones, paving the way for advances in UAV tracking techniques. Notably, we provide data in both indoor and outdoor environments. We also consider variable UAV sizes, from micro-aerial vehicles to more standard commercial UAV platforms. The outdoor trajectories are selected with close proximity to buildings, targeting research in UAV detection in urban areas, e.g., within counter-UAV systems or docking for UAV logistics. In addition to the dataset, we provide a baseline comparison with recent LiDAR-based UAV tracking algorithms, benchmarking the performance with different sensors, UAVs, and algorithms. Importantly, our dataset shows that current methods have shortcomings and are unable to track UAVs consistently across different scenarios.

This letter presents a continuous probabilistic modeling methodology for spatial point cloud data using finite Gaussian Mixture Models (GMMs) where the number of components are adapted based on the scene complexity. Few hierarchical and adaptive methods have been proposed to address the challenge of balancing model fidelity with size. Instead, state-of-the-art mapping approaches require tuning parameters for specific use cases, but do not generalize across diverse environments. To address this gap, we utilize a self-organizing principle from information-theoretic learning to automatically adapt the complexity of the GMM model based on the relevant information in the sensor data. The approach is evaluated against existing point cloud modeling techniques on real-world data with varying degrees of scene complexity.

The topic of AI is not new and each one of us is benefiting from AI every day, transforming many aspects of our lives. This trend is fueled by edge computing which is providing opportunities to move AI workloads from the Intelligent Cloud to the Intelligent Edge for improved response times and bandwidth savings. In combination with Digital Twins and IoT, there is a strong trend not only in manufacturing but also in other industries to leverage AI/ML analytics for getting better and faster insights for improved Predictive Maintenance and more. The benefit of edge deployments is especially strong when it comes to computer vision models that take large data streams like images or live video as input. With edge computing, these large data streams can now be processed locally at the device / client, eliminating the need for significant bandwidth or privacy concerns associated with streaming into a cloud data center. Edge video analytics systems can execute computer vision and deep-learning algorithms either directly integrated into the camera or with an attached edge computing system.