Abstract

Understanding how we grasp objects with our hands has important applications in areas like robotics and mixed re ality. However, this challenging problem requires accurate modeling of the contact between hands and objects. To capture grasps, existing methods use skeletons, meshes, or parametric models that does not represent hand shape accu rately resulting in inaccurate contacts. We present MANUS, amethodforMarkerlessHand-ObjectGraspCaptureusing Articulated 3D Gaussians. We build a novel articulated 3D Gaussians representation that extends 3D Gaussian splatting [33] for high-fidelity representation of articulat ing hands. Since our representation uses Gaussian primi tives optimized from the multi-view pixel-aligned losses, it enables us to efficiently and accurately estimate contacts between the hand and the object.

Abstract

Advances in neural fields are enabling high-fidelity capture of the shape and appearance of dynamic 3D scenes. However, their capabilities lag behind those offered by conventional representations such as 2D videos because of algorithmic challenges and the lack of large-scale multi-view real-world datasets. We address the dataset limitation with DiVa-360, a real-world 360◦ dynamic visual dataset that contains synchronized high-resolution and long-duration multi-view video sequences of table-scale scenes captured using a customized low-cost system with 53 cameras. It contains 21 object-centric sequences categorized by different motion types, 25 intricate hand-object interaction sequences, and 8 long-duration sequences for a total of 17.4 M image frames. In addition, we provide foreground-background segmentation masks, synchronized audio, and text descriptions. We benchmark the state-of-the-art dynamic neural field methods on DiVa-360 and provide insights about existing methods and future challenges on long-duration neural field capture

Abstract

This research paper presents a novel low computational approach for navigating a micro UAV (Unmanned Aerial Vehicle) through narrow passages using only its onboard camera feed and a PID control system. The proposed method uses edge detection and homography techniques to extract the key features of the passage from the camera feed, and then employs a tuned PID controller to guide the UAV through and out of the passage while avoiding collisions with the walls. To evaluate the effectiveness of the proposed approach, a series of experiments were conducted using a micro-UAV navigating in and out of a custom-built test environment (constrained rectangular box). The results demonstrate that the system is able to successfully guide the UAV through the passages while avoiding collisions with the walls

Abstract

Computing binding affinities is of great importance in drug discovery pipeline and its prediction using advanced machine learning methods still remains a major challenge as the existing datasets and models do not consider the dynamic features of protein-ligand interactions. To this end, we have developed PLAS-20k dataset, an extension of previously developed PLAS-5k, with 97,500 independent simulations on a total of 19,500 different protein-ligand complexes. Our results show good correlation with the available experimental values, performing better than docking scores. This holds true even for a subset of ligands that follows Lipinski’s rule, and for diverse clusters of complex structures, thereby highlighting the importance of PLAS-20k dataset in developing new ML models. Along with this, our dataset is also beneficial in classifying strong and weak binders compared to docking. Further, OnionNet model has been retrained on PLAS-20k dataset and is provided as a baseline for the prediction of binding affinities. We believe that large-scale MD-based datasets along with trajectories will form new synergy, paving the way for accelerating drug discovery.

Abstract

Quantum states least affected by interactions with environment play a pivotal role in both foundations and applications of quantum mechanics. Known as pointer states, they surprisingly lacked a systematic description. Working within the Born-Markov approximation, we combine methods of group theory and open quantum systems and derive general conditions describing pointer states. Contrary to common expectations, they are in general different from coherent states. Thus the two notions of being “closest to the classical”—one defined by the uncertainty relations and the other by the interaction with the environment—are in general different. As an example, we study spin-spin and spin-boson models with an arbitrary central spin J.

Abstract

This work introduces Talk2BEV, a large vision-language model (LVLM) interface for bird’s-eye view (BEV) maps in autonomous driving contexts. While existing perception systems for autonomous driving scenarios have largely focused on a pre-defined (closed) set of object categories and driving scenarios, Talk2BEV blends recent advances in general-purpose language and vision models with BEV-structured map representations, eliminating the need for task-specific models. This enables a single system to cater to a variety of autonomous driving tasks encompassing visual and spatial reasoning, predicting the intents of traffic actors, and decision-making based on visual cues. We extensively evaluate Talk2BEV on a large number of scene understanding tasks that rely on both the ability to interpret free-form natural language queries and in grounding these queries to the visual context embedded into the language-enhanced BEV map. To enable further research in LVLMs for autonomous driving scenarios, we develop and release Talk2BEV-Bench, a benchmark encompassing 1000 human-annotated BEV scenarios, with more than 20,000 questions and ground-truth responses from the NuScenes dataset.

Abstract

We focus on the problem of LiDAR point cloud based loop detection (or Finding) and closure (LDC) for mobile robots. State-of-the-art (SOTA) methods directly generate learned embeddings from a given point cloud, require large data augmentation, and are not robust to wide viewpoint variations in 6 Degrees-of-Freedom (DOF). Moreover, the absence of strong priors in an unstructured point cloud leads to highly inaccurate LDC. In this original approach, we propose independent roll and pitch canonicalization of point clouds using a common dominant ground plane. We discretize the canonicalized point clouds along the axis perpendicular to the ground plane leads to images simi- lar to digital elevation maps (DEMs), which expose strong spatial priors in the scene. Our experiments show that LDC based on learnt embeddings from such DEMs is not only data efficient but also significantly more robust, and generalizable than the current SOTA. We report an (aver- age precision for loop detection, mean absolute transla- tion/rotation error) improvement of (8.4, 16.7/5.43)% on the KITTI08 sequence, and (11.0, 34.0/25.4)% on GPR10 sequence, over the current SOTA. To further test the ro- bustness of our technique on point clouds in 6-DOF motion we create and opensource a custom dataset called Lidar- UrbanFly Dataset (LUF) which consists of point clouds ob- tained from a LiDAR mounted on a quadrotor. More details on our website https://gsc2001.github.io/FinderNet/

Abstract

Coastal waters are complex, dynamic, and sensitive, and any change in the system impacts the marine environment and life. Coastal water quality has been decreasing due to the incursion of anthropogenic derived waste and toxins into the ocean. This study investigates water quality along the Kollam coast of Kerala State, India, using Sentinel-2 Multispectral Imager (MSI) data for the period of 2019–2022. Four key water quality parameters, chlorophyll (Chl-a), total suspended matter (TSM), turbidity, and coloured dissolved organic matter (CDOM), were analysed for seasonal variations and driving factors. The study highlights the potential of web-based platforms like Google Earth Engine for facilitating large-scale water quality assessments. The results reveal a distinct seasonal pattern in all parameters, primarily influenced by monsoonal riverine discharge and anthropogenic activities as contributing factors to water quality degradation. Overall, the study emphasises the need for comprehensive monitoring and management strate- gies to ensure the long-term sustainability of the coastal ecosystem.

Abstract

Sugarcane holds a critical position in global agriculture, serving as a basis for the sugar and bioenergy sectors. The integration of remote sensing technologies and sophisticated machine learning approaches and related models has revolutionized sugarcane research. These tools ofer efcient, noninvasive, and large-scale assessment methods. This review highlights the utilization of satellite imagery and sensor data, encompassing RGB, multispectral, hyperspectral, and unmanned aerial vehicles (UAVs) in sugarcane agriculture. It addresses crop identifcation, pest and disease management, yield and acreage estimation, modeling, phenotypic measurement, and their impact on empowering farmers with insights for optimal irrigation, fertilizer application, and overall crop management. These advancements signifcantly increase productivity and foster environmental sustainability. The review had dual aims: (1) consolidate RS data applications in India’s sugarcane research and development, and (2) examine the pros and cons of RS and AI methods in sugarcane farming. The review employed prominent bibliographic databases—google scholar, scopus, researchgate, and web of science—along with pertinent research articles on RS and AI applications in sugarcane, and comprehensive data on sensors and UAVs retrieved from these databases. The study concludes that AI-driven crop RS stands as an efective method for monitoring and managing sugarcane, contributing signifcantly to improving yield and quality, while simultaneously ofering substantial benefts in social, economic, and environmental realms. However, challenges in the sugar industry, such as adapting technology, high initial costs, climate impact, communication, policy, and regulation, must be addressed.

Abstract

This paper presents the design and implementation of a hardware system for real-time object detection and range estimation utilizing Frequency-Modulated Continuous Wave (FMCW) millimeter wave radar signals, which are commonly used in Advance Driver Assistance Systems (ADAS) and robotic applications. The proposed system utilizes the Fast Fourier Transform (FFT) algorithm to process the FMCW radar signal for estimating the range of an object. For developing a resource-efficient and low latency range-estimation hardware, this paper also presents a comparative analysis for the implementation of three popular FFT architectures (iterative Radix-2, iterative Radix-4, and pipelined Radix-2) on FPGA. Based on the presented analysis the lowest latency range-estimation architecture has been chosen for FFT implementation and a system prototype is developed as a proof-of-concept by integrating the commercially available Texas Instruments' 77 GHz AWR1642BOOST FMCW radar module with a FPGA to host the chosen FFT architecture. Measurement results of the proposed system hardware are also presented in this paper, which shows >99.21% range-estimation accuracy.