Search

Autonomous system navigation is a well-researched and evolving field. Recent advancements in improving robot navigation have sparked increased interest among researchers and practitioners, especially in the use of sensing data. However, this heightened focus has also raised significant privacy concerns, particularly for robots that rely on cameras and LiDAR for navigation. Our innovative concept of Radio Frequency (RF) map generation through ray-tracing (RT) within digital twin environments effectively addresses these concerns. In this paper, we propose DT-RaDaR, a robust privacy-preserving, deep reinforcement learning-based framework for robot navigation that leverages RF ray-tracing in both static and dynamic indoor scenarios as well as in smart cities. We introduce a streamlined framework for generating RF digital twins using open-source tools like Blender and NVIDIA's Sionna RT. This approach allows for high-fidelity replication of real-world environments and RF propagation models, optimized for service robot navigation. Several experimental validations and results demonstrate the feasibility of the proposed framework in indoor environments and smart cities, positioning our work as a significant advancement toward the practical implementation of robot navigation using ray-tracing-generated data., Comment: 15 pages, 25 figures, 7 tables, under review to IEEE transactions

Agricultural landscapes are quite complex, especially in the Global South where fields are smaller, and agricultural practices are more varied. In this paper we report on our progress in digitizing the agricultural landscape (natural and man-made) in our study region of India. We use high resolution imagery and a UNet style segmentation model to generate the first of its kind national-scale multi-class panoptic segmentation output. Through this work we have been able to identify individual fields across 151.7M hectares, and delineating key features such as water resources and vegetation. We share how this output was validated by our team and externally by downstream users, including some sample use cases that can lead to targeted data driven decision making. We believe this dataset will contribute towards digitizing agriculture by generating the foundational baselayer., Comment: 34 pages, 7 tables, 15 figs

Careful robot manipulation in every-day cluttered environments requires an accurate understanding of the 3D scene, in order to grasp and place objects stably and reliably and to avoid mistakenly colliding with other objects. In general, we must construct such a 3D interpretation of a complex scene based on limited input, such as a single RGB-D image. We describe SceneComplete, a system for constructing a complete, segmented, 3D model of a scene from a single view. It provides a novel pipeline for composing general-purpose pretrained perception modules (vision-language, segmentation, image-inpainting, image-to-3D, and pose-estimation) to obtain high-accuracy results. We demonstrate its accuracy and effectiveness with respect to ground-truth models in a large benchmark dataset and show that its accurate whole-object reconstruction enables robust grasp proposal generation, including for a dexterous hand. Project website - https://scenecomplete.github.io/

Dual-arm manipulation is an area of growing interest in the robotics community. Enabling robots to perform tasks that require the coordinated use of two arms, is essential for complex manipulation tasks such as handling large objects, assembling components, and performing human-like interactions. However, achieving effective dual-arm manipulation is challenging due to the need for precise coordination, dynamic adaptability, and the ability to manage interaction forces between the arms and the objects being manipulated. We propose a novel pipeline that combines the advantages of policy learning based on environment feedback and gradient-based optimization to learn controller gains required for the control outputs. This allows the robotic system to dynamically modulate its impedance in response to task demands, ensuring stability and dexterity in dual-arm operations. We evaluate our pipeline on a trajectory-tracking task involving a variety of large, complex objects with different masses and geometries. The performance is then compared to three other established methods for controlling dual-arm robots, demonstrating superior results.

AI Infrastructure plays a key role in the speed and cost-competitiveness of developing and deploying advanced AI models. The current demand for powerful AI infrastructure for model training is driven by the emergence of generative AI and foundational models, where on occasion thousands of GPUs must cooperate on a single training job for the model to be trained in a reasonable time. Delivering efficient and high-performing AI training requires an end-to-end solution that combines hardware, software and holistic telemetry to cater for multiple types of AI workloads. In this report, we describe IBM's hybrid cloud infrastructure that powers our generative AI model development. This infrastructure includes (1) Vela: an AI-optimized supercomputing capability directly integrated into the IBM Cloud, delivering scalable, dynamic, multi-tenant and geographically distributed infrastructure for large-scale model training and other AI workflow steps and (2) Blue Vela: a large-scale, purpose-built, on-premises hosting environment that is optimized to support our largest and most ambitious AI model training tasks. Vela provides IBM with the dual benefit of high performance for internal use along with the flexibility to adapt to an evolving commercial landscape. Blue Vela provides us with the benefits of rapid development of our largest and most ambitious models, as well as future-proofing against the evolving model landscape in the industry. Taken together, they provide IBM with the ability to rapidly innovate in the development of both AI models and commercial offerings., Comment: Corresponding Authors: Talia Gershon, Seetharami Seelam,Brian Belgodere, Milton Bonilla

Probabilistic circuits (PCs) offer a promising avenue to perform embedded reasoning under uncertainty. They support efficient and exact computation of various probabilistic inference tasks by design. Hence, hardware-efficient computation of PCs is highly interesting for edge computing applications. As computations in PCs are based on arithmetic with probability values, they are typically performed in the log domain to avoid underflow. Unfortunately, performing the log operation on hardware is costly. Hence, prior work has focused on computations in the linear domain, resulting in high resolution and energy requirements. This work proposes the first dedicated approximate computing framework for PCs that allows for low-resolution logarithm computations. We leverage Addition As Int, resulting in linear PC computation with simple hardware elements. Further, we provide a theoretical approximation error analysis and present an error compensation mechanism. Empirically, our method obtains up to 357x and 649x energy reduction on custom hardware for evidence and MAP queries respectively with little or no computational error.

This paper explores the seamless integration of Generative AI (GenAI) and Evolutionary Algorithms (EAs) within the domain of large-scale multi-objective optimization. Focusing on the transformative role of Large Language Models (LLMs), our study investigates the potential of LLM-Assisted Inference to automate and enhance decision-making processes. Specifically, we highlight its effectiveness in illuminating key decision variables in evolutionarily optimized solutions while articulating contextual trade-offs. Tailored to address the challenges inherent in inferring complex multi-objective optimization solutions at scale, our approach emphasizes the adaptive nature of LLMs, allowing them to provide nuanced explanations and align their language with diverse stakeholder expertise levels and domain preferences. Empirical studies underscore the practical applicability and impact of LLM-Assisted Inference in real-world decision-making scenarios., Comment: Accepted IJCNN

In this study, we present the construction of a new proper motion catalog utilizing the photometric data from the Sloan Digital Sky Survey (SDSS) and Dark Energy Spectroscopic Instrument (DESI) imaging surveys, with a median time baseline of about 13 years. To mitigate systematic errors, the DESI galaxy positions are employed to establish a reference frame and to correct the position-, magnitude-, and color-dependent discrepancies between SDSS and DESI imaging datasets. Spanning 12,589 square degrees, the catalog encompasses about 206.6 million non-Gaia objects down to $m_r \sim$ 23. Based on 734k quasars, the assessment of the global systematic errors in DESI-SDSS proper motion catalog yields values of 0.14 mas yr$^{-1}$ for $\mu_{\alpha *}$ and 0.11 mas yr$^{-1}$ for $\mu_{\delta}$. The catalog exhibits a precision surpassing 3.7 mas yr$^{-1}$, albeit varying with position, color, and magnitude. An additional evaluation employing approximately 5,300 distant star samples yields an overall precision of approximately 3.0 and 2.9 mas yr$^{-1}$ for $\mu_{\alpha *}$ and $\mu_{\delta}$, respectively. Further comparisons with proper motions from SDSS Stripe 82 reveal a strong consistency between the two datasets. As a practical application, we utilize fainter non-Gaia objects in our catalog to update the proper motions of 17 star clusters. The resulting proper motions for these clusters exhibit excellent consistency with those derived from Gaia data. Our proper motion measurements, characterized by a deeper limiting magnitude, stands as a valuable complement to the Gaia dataset. The catalog is publicly available at \url{https://www.scidb.cn/s/YzaIv2}.

Efficiently generating grasp poses tailored to specific regions of an object is vital for various robotic manipulation tasks, especially in a dual-arm setup. This scenario presents a significant challenge due to the complex geometries involved, requiring a deep understanding of the local geometry to generate grasps efficiently on the specified constrained regions. Existing methods only explore settings involving table-top/small objects and require augmented datasets to train, limiting their performance on complex objects. We propose CGDF: Constrained Grasp Diffusion Fields, a diffusion-based grasp generative model that generalizes to objects with arbitrary geometries, as well as generates dense grasps on the target regions. CGDF uses a part-guided diffusion approach that enables it to get high sample efficiency in constrained grasping without explicitly training on massive constraint-augmented datasets. We provide qualitative and quantitative comparisons using analytical metrics and in simulation, in both unconstrained and constrained settings to show that our method can generalize to generate stable grasps on complex objects, especially useful for dual-arm manipulation settings, while existing methods struggle to do so., Comment: Project Page: https://constrained-grasp-diffusion.github.io/

Neural Radiance Fields (NeRF) have become an increasingly popular representation to capture high-quality appearance and shape of scenes and objects. However, learning generalizable NeRF priors over categories of scenes or objects has been challenging due to the high dimensionality of network weight space. To address the limitations of existing work on generalization, multi-view consistency and to improve quality, we propose HyP-NeRF, a latent conditioning method for learning generalizable category-level NeRF priors using hypernetworks. Rather than using hypernetworks to estimate only the weights of a NeRF, we estimate both the weights and the multi-resolution hash encodings resulting in significant quality gains. To improve quality even further, we incorporate a denoise and finetune strategy that denoises images rendered from NeRFs estimated by the hypernetwork and finetunes it while retaining multiview consistency. These improvements enable us to use HyP-NeRF as a generalizable prior for multiple downstream tasks including NeRF reconstruction from single-view or cluttered scenes and text-to-NeRF. We provide qualitative comparisons and evaluate HyP-NeRF on three tasks: generalization, compression, and retrieval, demonstrating our state-of-the-art results., Comment: Project Page: https://hyp-nerf.github.io

Power quality (PQ) events are recorded by PQ meters whenever anomalous events are detected on the power grid. Using neural networks with machine learning can aid in accurately classifying the recorded waveforms and help power system engineers diagnose and rectify the root causes of problems. However, many of the waveforms captured during a disturbance in the power system need to be labeled for supervised learning, leaving a large number of data recordings for engineers to process manually or go unseen. This paper presents an autoencoder and K-means clustering-based unsupervised technique that can be used to cluster PQ events into categories like sag, interruption, transients, normal, and harmonic distortion to enable filtering of anomalous waveforms from recurring or normal waveforms. The method is demonstrated using three-phase, field-obtained voltage waveforms recorded in a distribution grid. First, a convolutional autoencoder compresses the input signals into a set of lower feature dimensions which, after further processing, is passed to the K-means algorithm to identify data clusters. Using a small, labeled dataset, numerical labels are then assigned to events based on a cosine similarity analysis. Finally, the study analyzes the clusters using the t-distributed stochastic neighbor embedding (t-SNE) visualization tool, demonstrating that the technique can help investigate a large number of captured events in a quick manner.

In this work, we present the first dataset, MailEx, for performing event extraction from conversational email threads. To this end, we first proposed a new taxonomy covering 10 event types and 76 arguments in the email domain. Our final dataset includes 1.5K email threads and ~4K emails, which are annotated with totally ~8K event instances. To understand the task challenges, we conducted a series of experiments comparing three types of approaches, i.e., fine-tuned sequence labeling, fine-tuned generative extraction, and few-shot in-context learning. Our results showed that the task of email event extraction is far from being addressed, due to challenges lying in, e.g., extracting non-continuous, shared trigger spans, extracting non-named entity arguments, and modeling the email conversational history. Our work thus suggests more future investigations in this domain-specific event extraction task., Comment: Accepted at EMNLP 2023

We report the discovery of four blue lurkers with low and extremely low-mass white dwarf (ELM WDs) companions in the Galactic globular cluster NGC 362 using AstroSat Ultra Violet Imaging Telescope (UVIT). We analyzed the multi-wavelength spectral energy distribution (SED) of FUV-bright MS stars using data from the UVIT, UVOT, GAIA EDR3, and 2.2m ESO/MPI telescopes. Two each of low-mass WDs and ELM WDs are found as companions for the four blue lurkers by the fitting of two-component SED models. The effective temperatures, radii, luminosities, and masses of two low-mass WDs are (35000, 23000) K, (0.04, 0.05) Rsun , (1.45, 0.22) Lsun , and (0.2, 0.2) Msun, while the two ELM WDs are (14750, 14750) K, (0.09, 0.10) Rsun, (0.34, 0.40) Lsun, and (0.18, 0.18) Msun. The position of blue lurkers within the cluster shows that they originated via the Case A/B mass-transfer mechanism in a low-density environment. This is the first detection of blue lurkers with low-mass WDs and ELM WDs as companions in a globular cluster. The companion cooling age is less than 4 Myr, which suggests that they were just recently formed. These binary systems might have originated due to the cluster recent core collapse., Comment: 6 pages, 3 figures, 1 table

Recovering full 3D shapes from partial observations is a challenging task that has been extensively addressed in the computer vision community. Many deep learning methods tackle this problem by training 3D shape generation networks to learn a prior over the full 3D shapes. In this training regime, the methods expect the inputs to be in a fixed canonical form, without which they fail to learn a valid prior over the 3D shapes. We propose SCARP, a model that performs Shape Completion in ARbitrary Poses. Given a partial pointcloud of an object, SCARP learns a disentangled feature representation of pose and shape by relying on rotationally equivariant pose features and geometric shape features trained using a multi-tasking objective. Unlike existing methods that depend on an external canonicalization, SCARP performs canonicalization, pose estimation, and shape completion in a single network, improving the performance by 45% over the existing baselines. In this work, we use SCARP for improving grasp proposals on tabletop objects. By completing partial tabletop objects directly in their observed poses, SCARP enables a SOTA grasp proposal network improve their proposals by 71.2% on partial shapes. Project page: https://bipashasen.github.io/scarp, Comment: Accepted at ICRA 2023

We report the discovery of extremely low-mass white dwarfs (ELM WDs) as a companion of blue straggler stars (BSSs) in the Galactic globular cluster NGC 362 using images from AstroSats Ultra Violet Imaging Telescope (UVIT). Spectral Energy Distributions (SEDs) for 26 FUV bright member BSSs are created using data from the UVIT, UVOT, Gaia EDR3, and the 2.2 m ESO/MPI telescope. A single SED is fitted to 14 BSSs, whereas double-SED fits revealed ELM WDs as binary companions in 12 of the 26 BSSs studied. The effective temperature, radius, luminosity and mass of the 12 ELM WDs are found to have a range (Teff = 9750-18000 K, R = 0.1-0.4 Rsun, L = 0.4-3.3 Lsun, and M =0.16-0.20 Msun). These suggest that 12 BSSs are post-mass-transfer systems formed through Case A/B mass transfer pathway. To the best of our knowledge, this is the first finding of ELM WDs as companions to BSS in globular clusters. This cluster is known to have a binary BSS sequence and the 12 binary and 14 single BSSs (as classified by the SEDs) follow the mass transfer and collisional sequence of BSS in the colour-magnitude diagram. The cooling ages of 9 of the ELM WDs are found to be younger than 500 Myr. Though the binary BSSs may have formed during the core-collapse (approx 200 Myr) or as part of the dynamical evolution of the cluster, they provide new insights on the dynamics of this cluster., Comment: 16 pages, 10 figures, accepted for publication in ApJ

Determining accurate bird's eye view (BEV) positions of objects and tracks in a scene is vital for various perception tasks including object interactions mapping, scenario extraction etc., however, the level of supervision required to accomplish that is extremely challenging to procure. We propose a light-weight, weakly supervised method to estimate 3D position of objects by jointly learning to regress the 2D object detections and scene's depth prediction in a single feed-forward pass of a network. Our proposed method extends a center-point based single-shot object detector, and introduces a novel object representation where each object is modeled as a BEV point spatio-temporally, without the need of any 3D or BEV annotations for training and LiDAR data at query time. The approach leverages readily available 2D object supervision along with LiDAR point clouds (used only during training) to jointly train a single network, that learns to predict 2D object detection alongside the whole scene's depth, to spatio-temporally model object tracks as points in BEV. The proposed method is computationally over $\sim$10x efficient compared to recent SOTA approaches while achieving comparable accuracies on KITTI tracking benchmark.