Search arXiv⌕ Search

arXiv subjects

Arjun Gupta

Publications and source records attributed to Arjun Gupta.

At least 19 recordsLinked to original sources
arXiv2026

HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping

Visual loco-manipulation of arbitrary in-the-wild objects requires accurate end-effector (EE) control and a generalizable understanding of the scene from visual inputs (eg, RGB-D images). Existing imitation and sim2real methods jointly learn both these aspects via monolithic end-to-end learning and are thus hard to scale. In this work, we bring to bear the best tools for each of these problems -- large vision models for generalizable scene understanding and simulated training for accurate EE control -- leading to an overall modular loco-manipulation system that exhibits strong generalization. Our core technical innovation is HERO, an accurate residual-aware EE tracking policy made possible by combining classical robotics with machine learning. It uses a) inverse kinematics to convert residual end-effector targets into reference trajectories, b) a learned neural forward model for accurate forward kinematics, and c) goal adjustment and replanning. Together, these innovations reduce the end-effector tracking error to 2.44cm, outperforming the strongest prior method by 5.5x. Our overall system operates in diverse real-world environments, from offices to coffee shops, where the robot reliably grasps various everyday objects (eg, mugs, apples, toys) on surfaces ranging from 43cm to 92cm in height. Systematic modular and end-to-end tests demonstrate the effectiveness of our proposed design. We believe our advances open up new ways of training humanoids to interact with daily objects.

cs.RO↗
arXiv2025

Precise Mobile Manipulation of Small Everyday Objects

Many everyday mobile manipulation tasks require precise interaction with small objects, such as grasping a knob to open a cabinet or pressing a light switch. In this paper, we develop Servoing with Vision Models (SVM), a closed-loop framework that enables a mobile manipulator to tackle such precise tasks involving the manipulation of small objects. SVM uses state-of-the-art vision foundation models to generate 3D targets for visual servoing to enable diverse tasks in novel environments. Naively doing so fails because of occlusion by the end-effector. SVM mitigates this using vision models that out-paint the end-effector, thereby significantly enhancing target localization. We demonstrate that aided by out-painting methods, open-vocabulary object detectors can serve as a drop-in module for SVM to seek semantic targets (e.g. knobs) and point tracking methods can help SVM reliably pursue interaction sites indicated by user clicks. We conduct a large-scale evaluation spanning experiments in 10 novel environments across 6 buildings including 72 different object instances. SVM obtains a 71% zero-shot success rate on manipulating unseen objects in novel environments in the real world, outperforming an open-loop control method by an absolute 42% and an imitation learning baseline trained on 1000+ demonstrations also by an absolute success rate of 50%.

cs.RO↗
arXiv2024

Theoretical framework for enhancing or enabling cooling of a mechanical resonator via the anti-Stokes or Stokes interaction and zero-photon detection

We develop a theoretical framework to describe how zero-photon detection may be utilized to enhance laser cooling via the anti-Stokes interaction and, somewhat surprisingly, enable cooling via the Stokes interaction commonly associated with heating. Our description includes both pulsed and continuous measurements as well as optical detection efficiency and open-system dynamics. For both cases, we discuss how the cooling depends on the system parameters such as detection efficiency and optomechanical cooperativity, and we study the continuous-measurement-induced dynamics, contrasting to single-photon detection events. For the Stokes case, we explore the interplay between cooling and heating via optomechanical parametric amplification, and we find the efficiency required to cool a mechanical oscillator via zero-photon detection. This work serves as a companion article to the recent experiment [E. A. Cryer-Jenkins, K. D. Major, et al., arXiv:2408.01734 (2024)], which demonstrated enhanced laser cooling of a mechanical oscillator via zero-photon detection on the anti-Stokes signal. The framework developed here provides new approaches for cooling mechanical resonators that can be applied to a wide range of areas including nonclassical state preparation, quantum thermodynamics, and avoiding the often unwanted heating effects of parametric amplification.

quant-ph↗
arXiv2024

Enhanced Laser Cooling of a Mechanical Resonator via Zero-Photon Detection

Throughout quantum science and technology, measurement is used as a powerful resource for nonlinear operations and quantum state engineering. In particular, single-photon detection is commonly employed for quantum-information applications and tests of fundamental physics. By contrast, and perhaps counter-intuitively, measurement of the absence of photons also provides useful information, and offers significant potential for a wide range of new experimental directions. Here, we propose and experimentally demonstrate cooling of a mechanical resonator below its laser-cooled mechanical occupation via zero-photon detection on the anti-Stokes scattered optical field and verify this cooling through heterodyne measurements. Our measurements are well captured by a stochastic master equation and the techniques introduced here open new avenues for cooling, quantum thermodynamics, quantum state engineering, and quantum measurement and control.

quant-ph↗
arXiv2024

Opening Articulated Structures in the Real World

What does it take to build mobile manipulation systems that can competently operate on previously unseen objects in previously unseen environments? This work answers this question using opening of articulated structures as a mobile manipulation testbed. Specifically, our focus is on the end-to-end performance on this task without any privileged information, i.e. the robot starts at a location with the novel target articulated object in view, and has to approach the object and successfully open it. We first develop a system for this task, and then conduct 100+ end-to-end system tests across 13 real world test sites. Our large-scale study reveals a number of surprising findings: a) modular systems outperform end-to-end learned systems for this task, even when the end-to-end learned systems are trained on 1000+ demonstrations, b) perception, and not precise end-effector control, is the primary bottleneck to task success, and c) state-of-the-art articulation parameter estimation models developed in isolation struggle when faced with robot-centric viewpoints. Overall, our findings highlight the limitations of developing components of the pipeline in isolation and underscore the need for system-level research, providing a pragmatic roadmap for building generalizable mobile manipulation systems. Videos, code, and models are available on the project website: https://arjung128.github.io/opening-articulated-structures/

cs.RO↗
arXiv2023

Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops

Objects undergo varying amounts of perspective distortion as they move across a camera's field of view. Models for predicting 3D from a single image often work with crops around the object of interest and ignore the location of the object in the camera's field of view. We note that ignoring this location information further exaggerates the inherent ambiguity in making 3D inferences from 2D images and can prevent models from even fitting to the training data. To mitigate this ambiguity, we propose Intrinsics-Aware Positional Encoding (KPE), which incorporates information about the location of crops in the image and camera intrinsics. Experiments on three popular 3D-from-a-single-image benchmarks: depth prediction on NYU, 3D object detection on KITTI & nuScenes, and predicting 3D shapes of articulated objects on ARCTIC, show the benefits of KPE.

cs.CV↗
arXiv2023

Predicting Motion Plans for Articulating Everyday Objects

Mobile manipulation tasks such as opening a door, pulling open a drawer, or lifting a toilet lid require constrained motion of the end-effector under environmental and task constraints. This, coupled with partial information in novel environments, makes it challenging to employ classical motion planning approaches at test time. Our key insight is to cast it as a learning problem to leverage past experience of solving similar planning problems to directly predict motion plans for mobile manipulation tasks in novel situations at test time. To enable this, we develop a simulator, ArtObjSim, that simulates articulated objects placed in real scenes. We then introduce SeqIK+$\theta_0$, a fast and flexible representation for motion plans. Finally, we learn models that use SeqIK+$\theta_0$ to quickly predict motion plans for articulating novel objects at test time. Experimental evaluation shows improved speed and accuracy at generating motion plans than pure search-based methods and pure learning methods.

cs.RO↗
arXiv2022

Source detection via multi-label classification

Radio source detection through conventional algorithms has been unreliable when trying to solve for large number of sources in the presence of low SINR and less number of snapshots. We address this by reformulating source detection as a multi-class classification problem solved using deep learning frameworks. Incoming waveforms are sampled using a centrosymmetric linear array with omni-directional elements and the normalized upper triangle of the autocorrelation matrix is extracted as the input feature to a modified convolutional neural network with uni-dimensional filters, trained to detect the sources in the presence of both uncorrelated and correlated signals. Two detection algorithms are introduced and referred to as CNNDetector and RadioNet, and subsequently benchmarked against the conventional source detection algorithms. By including preprocessing in forward backward spatial smoothing, RadioNet can also resolve the number of uncorrelated sources in the presence of correlated paths. Finally, the algorithms are stress tested under challenging operational conditions and extensive evaluations are presented showing the efficacy and contributions of the introduced predictive models.

eess.SP↗
arXiv2022

Learning Value Functions from Undirected State-only Experience

This paper tackles the problem of learning value functions from undirected state-only experience (state transitions without action labels i.e. (s,s',r) tuples). We first theoretically characterize the applicability of Q-learning in this setting. We show that tabular Q-learning in discrete Markov decision processes (MDPs) learns the same value function under any arbitrary refinement of the action space. This theoretical result motivates the design of Latent Action Q-learning or LAQ, an offline RL method that can learn effective value functions from state-only experience. Latent Action Q-learning (LAQ) learns value functions using Q-learning on discrete latent actions obtained through a latent-variable future prediction model. We show that LAQ can recover value functions that have high correlation with value functions learned using ground truth actions. Value functions learned using LAQ lead to sample efficient acquisition of goal-directed behavior, can be used with domain-specific low-level controllers, and facilitate transfer across embodiments. Our experiments in 5 environments ranging from 2D grid world to 3D visual navigation in realistic environments demonstrate the benefits of LAQ over simpler alternatives, imitation learning oracles, and competing methods.

cs.LG↗
arXiv2022

Spy in the GPU-box: Covert and Side Channel Attacks on Multi-GPU Systems

The deep learning revolution has been enabled in large part by GPUs, and more recently accelerators, which make it possible to carry out computationally demanding training and inference in acceptable times. As the size of machine learning networks and workloads continues to increase, multi-GPU machines have emerged as an important platform offered on High Performance Computing and cloud data centers. As these machines are shared between multiple users, it becomes increasingly important to protect applications against potential attacks. In this paper, we explore the vulnerability of Nvidia's DGX multi-GPU machines to covert and side channel attacks. These machines consist of a number of discrete GPUs that are interconnected through a combination of custom interconnect (NVLink) and PCIe connections. We reverse engineer the cache hierarchy and show that it is possible for an attacker on one GPU to cause contention on the L2 cache of another GPU. We use this observation to first develop a covert channel attack across two GPUs, achieving the best bandwidth of 3.95 MB/s. We also develop a prime and probe attack on a remote GPU allowing an attacker to recover the cache hit and miss behavior of another workload. This basic capability can be used in any number of side channel attacks: we demonstrate a proof of concept attack that fingerprints the application running on the remote GPU, with high accuracy. Our work establishes for the first time the vulnerability of these machines to microarchitectural attacks, and we hope that it guides future research to improve their security.

cs.CR↗
arXiv2021

Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks

Deep neural networks are powerful machines for visual pattern recognition, but reasoning tasks that are easy for humans may still be difficult for neural models. Humans possess the ability to extrapolate reasoning strategies learned on simple problems to solve harder examples, often by thinking for longer. For example, a person who has learned to solve small mazes can easily extend the very same search techniques to solve much larger mazes by spending more time. In computers, this behavior is often achieved through the use of algorithms, which scale to arbitrarily hard problem instances at the cost of more computation. In contrast, the sequential computing budget of feed-forward neural networks is limited by their depth, and networks trained on simple problems have no way of extending their reasoning to accommodate harder problems. In this work, we show that recurrent networks trained to solve simple problems with few recurrent steps can indeed solve much more complex problems simply by performing additional recurrences during inference. We demonstrate this algorithmic behavior of recurrent networks on prefix sum computation, mazes, and chess. In all three domains, networks trained on simple problem instances are able to extend their reasoning abilities at test time simply by "thinking for longer."

cs.LG↗
arXiv2021

DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations

Data poisoning and backdoor attacks manipulate training data to induce security breaches in a victim model. These attacks can be provably deflected using differentially private (DP) training methods, although this comes with a sharp decrease in model performance. The InstaHide method has recently been proposed as an alternative to DP training that leverages supposed privacy properties of the mixup augmentation, although without rigorous guarantees. In this work, we show that strong data augmentations, such as mixup and random additive noise, nullify poison attacks while enduring only a small accuracy trade-off. To explain these finding, we propose a training method, DP-InstaHide, which combines the mixup regularizer with additive noise. A rigorous analysis of DP-InstaHide shows that mixup does indeed have privacy advantages, and that training with k-way mixup provably yields at least k times stronger DP guarantees than a naive DP mechanism. Because mixup (as opposed to noise) is beneficial to model performance, DP-InstaHide provides a mechanism for achieving stronger empirical performance against poisoning attacks than other known DP methods.

cs.LG↗
arXiv2021

The Uncanny Similarity of Recurrence and Depth

It is widely believed that deep neural networks contain layer specialization, wherein neural networks extract hierarchical features representing edges and patterns in shallow layers and complete objects in deeper layers. Unlike common feed-forward models that have distinct filters at each layer, recurrent networks reuse the same parameters at various depths. In this work, we observe that recurrent models exhibit the same hierarchical behaviors and the same performance benefits with depth as feed-forward networks despite reusing the same filters at every recurrence. By training models of various feed-forward and recurrent architectures on several datasets for image classification as well as maze solving, we show that recurrent networks have the ability to closely emulate the behavior of non-recurrent deep models, often doing so with far fewer parameters.

cs.LG↗
arXiv2021

Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs

Humans are able to form a complex mental model of the environment they move in. This mental model captures geometric and semantic aspects of the scene, describes the environment at multiple levels of abstractions (e.g., objects, rooms, buildings), includes static and dynamic entities and their relations (e.g., a person is in a room at a given time). In contrast, current robots' internal representations still provide a partial and fragmented understanding of the environment, either in the form of a sparse or dense set of geometric primitives (e.g., points, lines, planes, voxels) or as a collection of objects. This paper attempts to reduce the gap between robot and human perception by introducing a novel representation, a 3D Dynamic Scene Graph(DSG), that seamlessly captures metric and semantic aspects of a dynamic environment. A DSG is a layered graph where nodes represent spatial concepts at different levels of abstraction, and edges represent spatio-temporal relations among nodes. Our second contribution is Kimera, the first fully automatic method to build a DSG from visual-inertial data. Kimera includes state-of-the-art techniques for visual-inertial SLAM, metric-semantic 3D reconstruction, object localization, human pose and shape estimation, and scene parsing. Our third contribution is a comprehensive evaluation of Kimera in real-life datasets and photo-realistic simulations, including a newly released dataset, uHumans2, which simulates a collection of crowded indoor and outdoor scenes. Our evaluation shows that Kimera achieves state-of-the-art performance in visual-inertial SLAM, estimates an accurate 3D metric-semantic mesh model in real-time, and builds a DSG of a complex indoor environment with tens of objects and humans in minutes. Our final contribution shows how to use a DSG for real-time hierarchical semantic path-planning. The core modules in Kimera are open-source.

cs.RO↗
arXiv2020

Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff

Data poisoning and backdoor attacks manipulate victim models by maliciously modifying training data. In light of this growing threat, a recent survey of industry professionals revealed heightened fear in the private sector regarding data poisoning. Many previous defenses against poisoning either fail in the face of increasingly strong attacks, or they significantly degrade performance. However, we find that strong data augmentations, such as mixup and CutMix, can significantly diminish the threat of poisoning and backdoor attacks without trading off performance. We further verify the effectiveness of this simple defense against adaptive poisoning methods, and we compare to baselines including the popular differentially private SGD (DP-SGD) defense. In the context of backdoors, CutMix greatly mitigates the attack while simultaneously increasing validation accuracy by 9%.

cs.CR↗
arXiv2020

Random Network Distillation as a Diversity Metric for Both Image and Text Generation

Generative models are increasingly able to produce remarkably high quality images and text. The community has developed numerous evaluation metrics for comparing generative models. However, these metrics do not effectively quantify data diversity. We develop a new diversity metric that can readily be applied to data, both synthetic and natural, of any type. Our method employs random network distillation, a technique introduced in reinforcement learning. We validate and deploy this metric on both images and text. We further explore diversity in few-shot image generation, a setting which was previously difficult to evaluate.

cs.LG↗
arXiv2020

Heterogeneity in Food Expenditure amongst US families: Evidence from Longitudinal Quantile Regression

Empirical studies on food expenditure are largely based on cross-section data and for a few studies based on longitudinal (or panel) data the focus has been on the conditional mean. While the former, by construction, cannot model the dependencies between observations across time, the latter cannot look at the relationship between food expenditure and covariates (such as income, education, etc.) at lower (or upper) quantiles, which are of interest to policymakers. This paper analyzes expenditures on total food (TF), food at home (FAH), and food away from home (FAFH) using mean regression and quantile regression models for longitudinal data to examine the impact of economic recession and various demographic, socioeconomic, and geographic factors. The data is taken from the Panel Study of Income Dynamics (PSID) and comprises of 2174 families in the United States (US) observed between 2001-2015. Results indicate that age and education of the head, family income, female headed family, marital status, and economic recession are important determinants for all three types of food expenditure. Spouse education, family size, and some regional indicators are important for expenditures on TF and FAH, but not for FAFH. Quantile analysis reveals considerable heterogeneity in the covariate effects for all types of food expenditure, which cannot be captured by models focused on conditional mean. The study ends by showing that modeling conditional dependence between observations across time for the same family unit is crucial to reducing/avoiding heterogeneity bias and better model fitting.

econ.GN↗