Search arXiv⌕ Search

arXiv subjects

Prashant Kumar

Publications and source records attributed to Prashant Kumar.

At least 19 recordsLinked to original sources

PACT: Pose-Robust Actuation Co-Design for Tendon-Driven Robotic Hands

Humanoid robotic hands must provide sufficient force, speed, and backdrivability within a human-scale envelope. Tendon-driven transmissions address this challenge by relocating actuators to the palm and forearm, but routing paths, moment arms, and capstan dimensions jointly determine both force capability and joint speed, so selecting them sequentially satisfies one requirement at the expense of the other. This paper presents a pose-robust actuation co-design for tendon-driven robot hands (PACT) framework that optimizes tendon routing, moment arms, and capstan dimensions under pose-dependent force requirements and drivetrain-bandwidth constraints. A feasible-force formulation enforces actuator bounds and equilibrium at all joints, while a max-min objective maximizes task-force coverage at the weakest pose. Applied to a four-degree-of-freedom finger, the framework produces an asymmetric N + 1 tendon topology using quasi-direct-drive actuators. Across eight poses, the design achieves task-force coverage of 0.88-1.00 and a predicted 5 Hz minimum isolated-joint flexion/extension bandwidth within a 70th-percentile human-size envelope. Prototype measurements deviate from predictions by up to 24.5%, primarily due to unmodeled transmission losses. These results indicate that co-designing routing with the drivetrain can meet pose-dependent force requirements without relaxing the bandwidth constraint, paving the way for human-sized robotic hands with human-level performance.

cs.RO↗

RCFormer: Reliability-aware Context Transformer for Occlusion-Robust Facial Landmark Detection

Facial landmark detection has advanced substantially under regular imaging conditions, yet occlusion, poor illumination, and large pose changes remain major sources of error because local facial evidence can become incomplete or misleading. Context-guided latent patch recovery offers a promising way to address this issue by inferring unreliable patch representations from surrounding facial context before heatmap prediction. However, the recovered context can itself be unreliable when it is weakly adapted to the input face, influenced by corrupted neighboring patches, or blended without preserving local spatial coherence. We propose RCFormer, a Reliability-aware Context Transformer for occlusion-robust facial landmark detection. RCFormer strengthens latent patch recovery with three reliability-oriented components: visible-context conditioning (VCC), which adapts the context representation using a visibility-weighted global facial summary; visibility-guided context aggregation (VGCA), which reduces the influence of unreliable source patches during attention; and spatial residual correction (SRC), which refines blended latent features using neighboring patch information. The recovered heatmaps are then used as reliability-aware structural cues for existing landmark detection networks. Experiments show that RCFormer improves heatmap recovery and achieves strong landmark localization results on the WFLW, COFW, and 300W datasets.

cs.CV↗

Benchmarking Model Compression Techniques Across Heterogeneous Edge Platforms: A Predictive Maintenance Use Case for Rotating Machinery

To enable Industry 5.0, where autonomous systems are widely adopted and integrated with people to promote sustainable development in industries, it is imperative to adapt complex deep learning models to operate efficiently on resource-constrained hardware for edge inference. However, adapting these models remains challenging due to the hardware heterogeneity of edge computing in industrial settings, performance degradation caused by model compression, and the lack of clear guidance on which compression techniques are practical and effective for applications such as predictive maintenance. To address these challenges, this paper presents a comprehensive comparative analysis of four state-of-the-art model compression techniques applied to a high-performance convolutional neural network for predictive maintenance using a real-world dataset of rotating machinery, equipment typically used in industry. The compressed models were evaluated across a heterogeneous set of nine computing platforms, ranging from highly constrained edge computing devices to general purpose and high-performance processors, reflecting the diversity and fragmentation typical of industrial edge environments. By jointly prioritizing classification performance, inference speed, and compression ratio, we found that compression using knowledge distillation emerged as the most effective approach. The model had more than 90% speedup across all devices while maintaining a 91.22% balanced F-score, with a very small drop in predictive performance relative to the uncompressed model, along with a 98.9% size reduction. Through successful deployment across multiple edge platforms and a systematic comparison of compression strategies, we demonstrated a clear path to achieving Industry 5.0 targets, drastically cutting computational costs and, consequently, energy consumption without sacrificing predictive performance.

cs.LG↗

An Annealing-based Quantum Neural Network with Discrete Wavelet Transforms for Enhanced Air Pollution Nowcasting

Air pollution poses a significant threat to public health, exacerbated by the rapid industrialization and urbanization of modern society. While traditional deep learning offers predictive capabilities, recent advancements in quantum machine learning (QML) present a compelling alternative. Here, we introduce a scalable hybrid framework that integrates variational quantum circuits with quantum annealing. Leveraging a neuromorphic quantum computing platform to transcend the qubit limitations of the NISQ era, we model particulate matter (PM$_{2.5}$) dynamics using high-density urban data from the UK. We demonstrate that our Quantum Neural Networks (QNNs) exhibit an intrinsic resilience to input volatility, significantly outperforming classical baselines (MLP and LSTM) on raw, high-entropy environmental data. Furthermore, we successfully scaled the model to 172 qubits, observing a synergistic enhancement when coupled with wavelet decomposition that achieves state-of-the-art predictive fidelity. These findings establish a critical benchmark for quantum utility, proving that scalable, neuromorphic quantum machine learning can now address complex, non-linear real-world problems.

quant-ph↗

An Input-Frugal Deep Learning Framework for Weather-Driven National Crop-Yield Forecasting: A Case Study of Brazilian Soybean

Reliable, timely crop-yield forecasts are essential for market stability and risk management, yet many approaches rely on costly or hard-to-scale inputs. We present a frugal, transferable, and architecture-agnostic deep learning framework that uses routine weather as the only time-varying input plus two lightweight static context inputs (crop year and an agro-environmental label) to capture long-run change and regional heterogeneity, while supporting multiple sequence encoders under identical data requirements. Using a 20-season Brazilian soybean case study (2001/02-2020/21) with leave-one-year-out cross-validation, we benchmark MLP, CNN, LSTM, CNN-LSTM, a Transformer encoder and the Mamba state-space model against linear ridge regression and a five-year moving-average "farmer" baseline. All deep learning variants outperform ridge, and all sequential encoders surpass the non-sequential MLP. The Transformer achieves the best national accuracy (RMSE 149 kg ha^-1; rRMSE 5.3%; R^2 = 0.784), reducing error by 47.6% relative to the farmer baseline. In-season forecasts improve monotonically from early- to late-season issuance, reaching approximately 50% lower error than the baseline at the latest forecast point. Ablations indicate that the agro-environmental label and spatial instance expansion (multiple grid-node weather sequences per municipality-year) contribute positively without increasing input complexity. SHAP diagnostics suggest crop year explains most of the long-run trajectory, whereas within-season weather and agro-environmental context primarily drive interannual deviations, with moisture/cloud and thermal-demand variables dominating. Overall, the framework is straightforward to deploy across other crops and geographic regions and is naturally compatible with operational weather forecasts for routine monitoring.

cs.LG↗

Development of Thomson parabola spectrometer for diagnostics of ions driven by ultrahigh intensity laser: Simulations and numerical analysis

A Thomson parabola ion spectrometer (TPIS) has been designed and developed for diagnostics of laseraccelerated ion beams in the MeV energy range. The TPIS has been validated by ion acceleration experiment at petawatt laser facility. Necessary simulations to evaluate the electric and magnetic field distributions have been performed with the help of a numerical simulation software to aid the selection of the spectrometer geometry while minimising fringe-field effects. Analytical dispersion expressions have been formulated from the simulations that take into account the spatial variation in the electromagnetic field profiles. The ion deflections obtained from these expressions demonstrate an improved agreement with experimentally measured proton trajectories compared to the case when constant fields are considered. The TPIS hence fabricated in-house has been subject to magnetic field measurements, which are in excellent agreement with the simulated field profile. The TPIS has the provision to change the field-free drift region, showcasing flexibility to be employed over a broad energy range and with different experimental setups. The spectrometer has been subsequently used for detecting laser-accelerated ion beams from thin aluminum foil targets. These experiments have demonstrated the capability of the spectrometer to resolve multiple ion species with sufficient separation between them. The developed TPIS provides a compact, flexible and accurate diagnostic for high-energy laser-plasma experiments.

physics.plasm-ph↗

Multiscale Physics-Informed Neural Network for Complex Fluid Flows with Long-Range Dependencies

Fluid flows are governed by the nonlinear Navier-Stokes equations, which can manifest multiscale dynamics even from predictable initial conditions. Predicting such phenomena remains a formidable challenge in scientific machine learning, particularly regarding convergence speed, data requirements, and solution accuracy. In complex fluid flows, these challenges are exacerbated by long-range spatial dependencies arising from distant boundary conditions, which typically necessitate extensive supervision data to achieve acceptable results. We propose the Domain-Decomposed and Shifted Physics-Informed Neural Network (DDS-PINN), a framework designed to resolve such multiscale interactions with minimal supervision. By utilizing localized networks with a unified global loss, DDS-PINN captures global dependencies while maintaining local precision. The robustness of the approach is demonstrated across a suite of benchmarks, including a multiscale linear differential equation, the nonlinear Burgers' equation, and data-free Navier-Stokes simulations of flat-plate boundary layers. Finally, DDS-PINN is applied to the computationally challenging backward-facing step (BFS) problem; for laminar regimes (Re = 100), the model yields results comparable to computational fluid dynamics (CFD) without the need for any data, accurately predicting boundary layer thickness, separation, and reattachment lengths. For turbulent BFS flow at Re = 10,000, the framework achieves convergence to O(10^-4) using only 500 random supervision points (< 0.3 % of the total domain), outperforming established methods like Residual-based Attention-PINN in accuracy. This approach demonstrates strong potential for the super-resolution of complex turbulent flows from sparse experimental measurements.

physics.flu-dyn↗

Replaceable Bit-based Gripper for Picking Cluttered Food Items

The food packaging industry goes through changes in food items and their weights quite rapidly. These items range from easy-to-pick, single-piece food items to flexible, long and cluttered ones. We propose a replaceable bit-based gripper system to tackle the challenge of weight-based handling of cluttered food items. The gripper features specialized food attachments(bits) that enhance its grasping capabilities, and a belt replacement system allows switching between different food items during packaging operations. It offers a wide range of control options, enabling it to grasp and drop specific weights of granular, cluttered, and entangled foods. We specifically designed bits for two flexible food items that differ in shape: ikura(salmon roe) and spaghetti. They represent the challenging categories of sticky, granular food and long, sticky, cluttered food, respectively. The gripper successfully picked up both spaghetti and ikura and demonstrated weight-specific dropping of these items with an accuracy over 80% and 95% respectively. The gripper system also exhibited quick switching between different bits, leading to the handling of a large range of food items.

cs.RO↗

Evidence for in situ particle energization during the May-2024 event based on ASPEX instrument on board Aditya-L1

The interaction between interplanetary Coronal Mass Ejection (ICME) structures can alter the geo-effectiveness of the ICME events in myriad ways. Many aspects of these interaction processes are not well-understood till date. Using the energy spectra measured in two mutually orthogonal top hat analyzers (THA 1 and 2), which are part of the Solar Wind Ion Spectrometer (SWIS) subsystem of the Aditya Solar Wind Particle EXperiment (ASPEX) on board India's Aditya L1 mission, we gain insights into intricate features of ICME ICME interactions during May 2024 solar event. We report here an unprecedented two-orthogonal-plane perspective of ICME ICME interactions for the first time from the L1 point. The investigation reveals a special interaction region formed by the propagation of the forward shock driven by complex ejecta in the preceding ICME. The interaction causes the formation of a downstream region spanning over 13 hours, which propagates in the interplanetary medium. The observations reveal that this region serves as a site for proton and alpha particle energization, and the particles within this region get distributed from one plane to the other. The presence of forward shock and particle energization is confirmed by the energetic particle flux measurements by the SupraThermal and Energetic Particle Spectrometer (STEPS) of ASPEX. These observations provide an unprecedented perspective on how solar wind ions become energized and distributed in an ICME-ICME interaction region.

astro-ph.SR↗

Multi-directional investigations on quiet time suprathermal ions measured by ASPEX-STEPS on-board Aditya L1

The origin, acceleration and anisotropy of suprathermal ions in the interplanetary medium during quiet periods have remained poorly understood issues in solar wind physics. To address these aspects, we derive the spectral indices for the quiet time suprathermal ions based on the measurements by the four directionally separated sensors that are part of the Supra-Thermal and Energetic Particle Spectrometer (STEPS) of Aditya Solar Wind Particle EXperiment (ASPEX) on-board Aditya L1 spacecraft. Three out of four STEPS sensors Parker Spiral (PS), Inter-Mediate (IM), Earth Pointing (EP) are in one plane (nearly aligned with the ecliptic plane) while the fourth sensor North Pointing (NP) is in a mutually orthogonal plane. The energy ranges covered by the PS, IM, EP and NP sensors are 0.36-1.32 MeV, 0.14-1.22 MeV, 0.39-1.33 MeV and 0.12-1.23 MeV respectively. The quiet intervals are identified during January November, 2024 and the derived spectral indices (differential directional flux versus energy) are found to be in the range of 2.0 for all directions in the time scale of a few days revealing isotropic nature of their distribution. Further analysis of elemental abundance ratios (3He/4He, Fe/O, and C/O) during the same quiet intervals obtained from the Ultra-Low Energy Isotope Spectrometer (ULEIS) on board the Advanced Composition Explorer (ACE) spacecraft suggests possible contributions from the leftover ions from the previous impulsive (Solar flares) and gradual events (CMEs) in the quiet time suprathermal ion pool.

physics.space-ph↗

Exploring the nature of the emergent gauge field in composite-fermion metals: A large-scale microscopic study

Field theories of the composite-fermion (CF) metal model it as a Fermi sea of composite fermions coupled to an emergent gauge field. Within a random phase approximation, these theories predict that the Landau damping of the gauge field resulting from its coupling to the low-energy, long-wavelength CF particle-hole excitations modifies the electrons' density-density correlation function related to the static structure factor $S(q)$ at wave vector $q$. This produces a non-analytic correction $\propto q^{3}\ln q$ to $S(q)$ (with the magnetic length $\ell_{B}=1$). Thanks to the recently developed quaternion formulation for Jain-Kamilla projection of CF wave functions, the evaluation of $S(q)$ from the accurate microscopic theory of composite fermions has now become possible for systems containing as many as $N=900$ CFs, which enables a reliable determination of the small-$q$ behavior of $S(q)$. We study CF metals corresponding to electrons at Landau level filling factors $ν=1/2$ and $1/4$, and for completeness, also of bosons at $ν=1$ and $1/3$. In the $q\rightarrow0$ limit, our microscopic calculation reveals a $q^{3}$ term in $S(q)$ of the CF metals rather than $q^{3} \ln q$. This behavior is well-predicted by a model of a non-interacting Fermi sea of dipolar CFs, which also obtains its coefficient accurately.

cond-mat.str-el↗

Controlled spin-to-charge conversion in noncollinear antiferromagnet-based Py/Mn$_{3}$Pt heterostructure

Noncollinear antiferromagnets (NCAFs) have recently emerged as promising candidates for future spintronic technologies, offering ultrafast switching, negligible stray fields allowing dense packing, and robustness against external magnetic perturbations. When interfaced with ferromagnets (FMs), they can strongly influence interfacial exchange and spin-torque mechanisms that enable manipulating magnetic order and realizing functionalities beyond conventional heavy metals (HMs) based FM/HM heterostructures. Here, we perform a broadband ferromagnetic resonance (FMR) study to systematically investigate the magnetization dynamics and spin-to-charge conversion in permalloy (Py) and Mn$_3$Pt bilayers. High-quality Py films provide a well-defined FMR spectra with a low Gilbert damping parameter ( $α_{\mathrm{eff}} \approx 9.8 \times 10^{-3}$). We observe a pronounced enhancement of damping with intrinsic value $α_{\mathrm{int}} \approx 3.1 \times 10^{-2}$ in the Py/Mn$_3$Pt bilayer, indicating efficient spin pumping into the NCAF layer. Frequency dependent linewidth analysis shows a predominantly Gilbert type damping in the bilayers and the corresponding effective spin-mixing conductance ( $g^{\uparrow\downarrow}_{\mathrm{eff}} \approx 4.8 \times 10^{18}$m$^{-2}$) is comparable to that of other high-performance antiferromagnetic heterostructures. These results are significant for establishing NCAFs as a candidate material for spin generation and highlights the potential of Py/Mn$_3$Pt bilayers for efficient and ultrafast spintronic applications.

cond-mat.mtrl-sci↗

Energetic ($<$ 2 MeV) ion fluxes measured by ASPEX-STEPS on board Aditya-L1 during its earth-bound phase

During its earth-bound phase of the Aditya-L1 spacecraft of India, the Supra-Thermal and Energetic Particle Spectrometer (STEPS) of the Aditya Solar wind Particle EXperiment (ASPEX) was operated whenever the orbit was above 52000 km during 11 - 19 September 2023. This phase of operation provided measurements of energetic ions (with energies 0.1--2 MeV) in the magnetosphere, magnetosheath, and interplanetary medium. Three interplanetary coronal mass ejections (ICME) hit the magnetosphere during this period. This provided opportunity to examine the relative roles of ICME-generated solar energetic particles (SEPs) and substorm generated energetic ions on the magnetosphere. We approach this objective by detailed spectral analyses of energetic ion fluxes measured by two units of ASPEX-STEPS. We identify three distinctly different conditions of the north-south component of the interplanetary magnetic field (IMF $B_z$ = 0, $>$ 0, and $<$ 0) and use the derived spectral indices to understand this relative role. By combining these with the simultaneous energetic ion flux variations from the Advanced Composition Explorer (ACE) around the Sun-Earth first Lagrangian (L1) point and the Geostationary Operational Environmental Satellite (GOES) in the Earth's magnetosphere, we show that the polarity of IMF $B_z$ influences the energetic ion spectra in the magnetosphere by modulating the interplay of the ICME-generated SEP with the energetic particles generated inside the magnetosphere by substorms. Interestingly, ASPEX-STEPS observations also indicate towards directional anisotropy based on spectral indices. This suggests spatially inhomogeneous mixing of energetic ions coming from different source processes.

physics.space-ph↗

One Year of ASPEX-STEPS Operation: Characteristic Features, Observations and Science Potential

The SupraThermal and Energetic Particle Spectrometer (STEPS), a subsystem of the Aditya Solar wind Particle EXperiment (ASPEX) onboard India's Aditya-L1 satellite, is designed to study different aspects of energetic particles in the interplanetary medium from the Sun-Earth L1 point using six detector units oriented in different directions. This article presents details of the one-year operation (08 January 2024 - 28 February 2025) of the AL1-ASPEX-STEPS after the insertion of the satellite into the final halo orbit around the L1 point with emphasis on performance, science observations, and scientific potentials. Four out of six AL1-ASPEX-STEPS units exhibit a stable detector response throughout the observation period, confirming operational robustness. This work also includes the temporal variation of particle fluxes, spectra of ions during selected quiet times and transient events, and cross-comparisons with existing instruments at the L1 point. A strong correlation (with coefficient of determination, R2 ~ 0.9) is observed in the cross-comparison study, establishing the reliability of the AL1- ASPEX-STEPS observations. AL1-ASPEX-STEPS also captures different forms of energetic ion spectra similar to those observed by previous missions. These results underscore the instrument's potential to contribute significantly to the study of energetic particle acceleration, transport, and long-term space weather monitoring from the Sun-Earth L1 vantage point.

physics.space-ph↗

One year of ASPEX-SWIS operation -- Characteristic features, observations and science potential

The Aditya-L1 mission, India's first dedicated solar observatory positioned at the first Lagrange point (L1) of the Sun-Earth system, carries the Solar Wind Ion Spectrometer (SWIS) as part of the ASPEX payload suite. Even before settling into its Halo orbit, SWIS has been providing nearly continuous in-situ measurements of solar wind ion spectra. Moments of the velocity distribution functions (VDFs) have been calculated to derive key solar wind parameters such as density, bulk speed, and temperature. In this study, we assess the performance of SWIS (hereafter referred to as AL1-ASPEX-SWIS) by comparing its measurements with contemporaneous data from the Wind and DSCOVR missions. In this study, we assess the performance of SWIS (hereafter referred to as AL1-ASPEX-SWIS) by comparing its measurements with contemporaneous data from the Wind and DSCOVR missions. A detailed case study of the interplanetary coronal mass ejection (ICME) event on August 7, 2024, is presented, where sharp changes in bulk speed, thermal speed, and number density were found to be well-aligned with independent observations-confirming the instrument's ability to capture dynamic solar wind features. Spectral analysis of kinetic fluctuations revealed a well-defined inertial range with a spectral slope consistent with magnetohydrodynamic (MHD) turbulence. Furthermore, a 17-month statistical comparison (from January 2024 to May 2025) shows a strong correlation in bulk velocity (R2 = 0.94 with Wind), with expected variations in thermal speed and density arising from differences between instruments. These findings demonstrate the scientific value of AL1-ASPEX-SWIS for monitoring both transient solar events and long-term solar wind conditions.

astro-ph.SR↗

RiskLabs: Predicting Financial Risk Using Large Language Model based on Multimodal and Multi-Sources Data

The integration of Artificial Intelligence (AI) techniques, particularly large language models (LLMs), in finance has garnered increasing academic attention. Despite progress, existing studies predominantly focus on tasks like financial text summarization, question-answering, and stock movement prediction (binary classification), the application of LLMs to financial risk prediction remains underexplored. Addressing this gap, in this paper, we introduce RiskLabs, a novel framework that leverages LLMs to analyze and predict financial risks. RiskLabs uniquely integrates multimodal financial data, including textual and vocal information from Earnings Conference Calls (ECCs), market-related time series data, and contextual news data to improve financial risk prediction. Empirical results demonstrate RiskLabs' effectiveness in forecasting both market volatility and variance. Through comparative experiments, we examine the contributions of different data sources to financial risk assessment and highlight the crucial role of LLMs in this process. We also discuss the challenges associated with using LLMs for financial risk prediction and explore the potential of combining them with multimodal data for this purpose.

q-fin.RM↗

SLACK: Attacking LiDAR-based SLAM with Adversarial Point Injections

The widespread adoption of learning-based methods for the LiDAR makes autonomous vehicles vulnerable to adversarial attacks through adversarial \textit{point injections (PiJ)}. It poses serious security challenges for navigation and map generation. Despite its critical nature, no major work exists that studies learning-based attacks on LiDAR-based SLAM. Our work proposes SLACK, an end-to-end deep generative adversarial model to attack LiDAR scans with several point injections without deteriorating LiDAR quality. To facilitate SLACK, we design a novel yet simple autoencoder that augments contrastive learning with segmentation-based attention for precise reconstructions. SLACK demonstrates superior performance on the task of \textit{point injections (PiJ)} compared to the best baselines on KITTI and CARLA-64 dataset while maintaining accurate scan quality. We qualitatively and quantitatively demonstrate PiJ attacks using a fraction of LiDAR points. It severely degrades navigation and map quality without deteriorating the LiDAR scan quality.

cs.CV↗

Revisiting Point Cloud Completion: Are We Ready For The Real-World?

Point clouds acquired in constrained, challenging, uncontrolled, and multi-sensor real-world settings are noisy, incomplete, and non-uniformly sparse. This presents acute challenges for the vital task of point cloud completion. Using tools from Algebraic Topology and Persistent Homology (PH), we demonstrate that current benchmark object point clouds lack rich topological features that are integral part of point clouds captured in realistic environments. To facilitate research in this direction, we contribute the first real-world industrial dataset for point cloud completion, RealPC - a diverse, rich and varied set of point clouds. It consists of ~ 40,000 pairs across 21 categories of industrial structures in railway establishments. Benchmark results on several strong baselines reveal that existing methods fail in real-world scenarios. We discover a striking observation - unlike current datasets, RealPC consists of multiple 0- and 1-dimensional PH-based topological features. We prove that integrating these topological priors into existing works helps improve completion. We present how 0-dimensional PH priors extract the global topology of a complete shape in the form of a 3D skeleton and assist a model in generating topologically consistent complete shapes. Since computing Homology is expensive, we present a simple, yet effective Homology Sampler guided network, BOSHNet that bypasses the Homology computation by sampling proxy backbones akin to 0-dim PH. These backbones provide similar benefits of 0-dim PH right from the start of the training, unlike similar methods where accurate backbones are obtained only during later phases of the training.

cs.CV↗