Search

Language-conditioned robot models (i.e., robotic foundation models) enable robots to perform a wide range of tasks based on natural language instructions. Despite strong performance on existing benchmarks, evaluating the safety and effectiveness of these models is challenging due to the complexity of testing all possible language variations. Current benchmarks have two key limitations: they rely on a limited set of human-generated instructions, missing many challenging cases, and they focus only on task performance without assessing safety, such as avoiding damage. To address these gaps, we introduce Embodied Red Teaming (ERT), a new evaluation method that generates diverse and challenging instructions to test these models. ERT uses automated red teaming techniques with Vision Language Models (VLMs) to create contextually grounded, difficult instructions. Experimental results show that state-of-the-art models frequently fail or behave unsafely on ERT tests, underscoring the shortcomings of current benchmarks in evaluating real-world performance and safety. Code and videos are available at: https://sites.google.com/view/embodiedredteam.

We provide a rigorous analysis of implicit regularization in an overparametrized tensor factorization problem beyond the lazy training regime. For matrix factorization problems, this phenomenon has been studied in a number of works. A particular challenge has been to design universal initialization strategies which provably lead to implicit regularization in gradient-descent methods. At the same time, it has been argued by Cohen et. al. 2016 that more general classes of neural networks can be captured by considering tensor factorizations. However, in the tensor case, implicit regularization has only been rigorously established for gradient flow or in the lazy training regime. In this paper, we prove the first tensor result of its kind for gradient descent rather than gradient flow. We focus on the tubal tensor product and the associated notion of low tubal rank, encouraged by the relevance of this model for image data. We establish that gradient descent in an overparametrized tensor factorization model with a small random initialization exhibits an implicit bias towards solutions of low tubal rank. Our theoretical findings are illustrated in an extensive set of numerical simulations show-casing the dynamics predicted by our theory as well as the crucial role of using a small random initialization., Comment: 58 pages, 4 figures

This study reports a comprehensive environmental scan of the generative AI (GenAI) infrastructure in the national network for clinical and translational science across 36 institutions supported by the Clinical and Translational Science Award (CTSA) Program led by the National Center for Advancing Translational Sciences (NCATS) of the National Institutes of Health (NIH) at the United States. With the rapid advancement of GenAI technologies, including large language models (LLMs), healthcare institutions face unprecedented opportunities and challenges. This research explores the current status of GenAI integration, focusing on stakeholder roles, governance structures, and ethical considerations by administering a survey among leaders of health institutions (i.e., representing academic medical centers and health systems) to assess the institutional readiness and approach towards GenAI adoption. Key findings indicate a diverse range of institutional strategies, with most organizations in the experimental phase of GenAI deployment. The study highlights significant variations in governance models, with a strong preference for centralized decision-making but notable gaps in workforce training and ethical oversight. Moreover, the results underscore the need for a more coordinated approach to GenAI governance, emphasizing collaboration among senior leaders, clinicians, information technology staff, and researchers. Our analysis also reveals concerns regarding GenAI bias, data security, and stakeholder trust, which must be addressed to ensure the ethical and effective implementation of GenAI technologies. This study offers valuable insights into the challenges and opportunities of GenAI integration in healthcare, providing a roadmap for institutions aiming to leverage GenAI for improved quality of care and operational efficiency.

This document presents the Center for Robot Assisted Search And Rescue - Uncrewed Aerial Systems - Disaster Response Overhead Inspection Dataset (CRASAR-U-DROIDs) for building damage assessment and spatial alignment collected from small uncrewed aerial systems (sUAS) geospatial imagery. This dataset is motivated by the increasing use of sUAS in disaster response and the lack of previous work in utilizing high-resolution geospatial sUAS imagery for machine learning and computer vision models, the lack of alignment with operational use cases, and with hopes of enabling further investigations between sUAS and satellite imagery. The CRASAR-U-DRIODs dataset consists of fifty-two (52) orthomosaics from ten (10) federally declared disasters (Hurricane Ian, Hurricane Ida, Hurricane Harvey, Hurricane Idalia, Hurricane Laura, Hurricane Michael, Musset Bayou Fire, Mayfield Tornado, Kilauea Eruption, and Champlain Towers Collapse) spanning 67.98 square kilometers (26.245 square miles), containing 21,716 building polygons and damage labels, and 7,880 adjustment annotations. The imagery was tiled and presented in conjunction with overlaid building polygons to a pool of 130 annotators who provided human judgments of damage according to the Joint Damage Scale. These annotations were then reviewed via a two-stage review process in which building polygon damage labels were first reviewed individually and then again by committee. Additionally, the building polygons have been aligned spatially to precisely overlap with the imagery to enable more performant machine learning models to be trained. It appears that CRASAR-U-DRIODs is the largest labeled dataset of sUAS orthomosaic imagery., Comment: 16 Pages, 7 Figures, 6 Tables

Metasurfaces have become one of the most prominent research topics in the field of optics owing to their unprecedented properties and novel applications on an ultrathin platform. By combining graphene with metasurfaces, electrical tunable functions can be achieved with fast tuning speed, large modulation depth and broad tuning range. However, the tuning efficiency of hybrid graphene metasurfaces within the short-wavelength infrared (SWIR) spectrum is typically low because of the small resonance wavelength shift in this wavelength range. In this work, through the integration of graphene and silicon metasurfaces that support quasi-bound states in the continuum (quasi-BIC), we experimentally demonstrate significant transmittance tuning even with less than 30 nm resonance wavelength shift thanks to the high quality-factor of quasi-BIC metasurfaces. The tunable transmittance spectrum was measured using Fourier Transform Infrared Spectroscopy (FTIR) with a modified reflective lens to improve the accuracy, and the electrical tuning was realized utilizing the cut-and-stick method of ion gel. At the wavelength of 3.0 um, the measured change of transmittance T_max-T_min and modulation depth (T_max-T_min)/T_max can reach 22.2% and 28.9%, respectively, under a small bias voltage ranging from -2 V to +2 V. To the best of our knowledge, this work is the first experimental demonstration of tunable graphene/quasi-BIC metasurfaces, which have potential applications in optical modulation, reconfigurable photonic devices, and optical communications., Comment: 14 pages, 5 figures

Large language models (LLMs) often struggle with temporal reasoning, crucial for tasks like historical event analysis and time-sensitive information retrieval. Despite advancements, state-of-the-art models falter in handling temporal information, especially when faced with irrelevant or noisy contexts. This paper addresses this gap by empirically examining the robustness of temporal question-answering (TQA) systems trained on various context types, including relevant, irrelevant, slightly altered, and no context. Our findings indicate that training with a mix of these contexts enhances model robustness and accuracy. Additionally, we show that the position of context relative to the question significantly impacts performance, with question-first positioning yielding better results. We introduce two new context-rich TQA datasets, ContextAQA and ContextTQE, and provide comprehensive evaluations and guidelines for training robust TQA models. Our work lays the foundation for developing reliable and context-aware temporal QA systems, with broader implications for enhancing LLM robustness against diverse and potentially adversarial information.

Various pose estimation and tracking problems in robotics can be decomposed into a correspondence estimation problem (often computed using a deep network) followed by a weighted least squares optimization problem to solve for the poses. Recent work has shown that coupling the two problems by iteratively refining one conditioned on the other's output yields SOTA results across domains. However, training these models has proved challenging, requiring a litany of tricks to stabilize and speed up training. In this work, we take the visual odometry problem as an example and identify three plausible causes: (1) flow loss interference, (2) linearization errors in the bundle adjustment (BA) layer, and (3) dependence of weight gradients on the BA residual. We show how these issues result in noisy and higher variance gradients, potentially leading to a slow down in training and instabilities. We then propose a simple, yet effective solution to reduce the gradient variance by using the weights predicted by the network in the inner optimization loop to weight the correspondence objective in the training problem. This helps the training objective `focus' on the more important points, thereby reducing the variance and mitigating the influence of outliers. We show that the resulting method leads to faster training and can be more flexibly trained in varying training setups without sacrificing performance. In particular we show $2$--$2.5\times$ training speedups over a baseline visual odometry model we modify., Comment: Accepted at CVPR 2024

This work presents the first quantitative study of alignment errors between small uncrewed aerial systems (sUAS) geospatial imagery and a priori building polygons and finds that alignment errors are non-uniform and irregular. The work also introduces a publicly available dataset of imagery, building polygons, and human-generated and curated adjustments that can be used to evaluate existing strategies for aligning building polygons with sUAS imagery. There are no efforts that have aligned pre-existing spatial data with sUAS imagery, and thus, there is no clear state of practice. However, this effort and analysis show that the translational alignment errors present in this type of data, averaging 82px and an intersection over the union of 0.65, which would induce further errors and biases in downstream machine learning systems unless addressed. This study identifies and analyzes the translational alignment errors of 21,619 building polygons in fifty-one orthomosaic images, covering 16787.2 Acres (26.23 square miles), constructed from sUAS raw imagery from nine wide-area disasters (Hurricane Ian, Hurricane Harvey, Hurricane Michael, Hurricane Ida, Hurricane Idalia, Hurricane Laura, the Mayfield Tornado, the Musset Bayou Fire, and the Kilauea Eruption). The analysis finds no uniformity among the angle and distance metrics of the building polygon alignments as they present an average degree variance of 0.4 and an average pixel distance variance of 0.45. This work alerts the sUAS community to the problem of spatial alignment and that a simple linear transform, often used to align satellite imagery, will not be sufficient to align spatial data in sUAS orthomosaic imagery., Comment: 6 pages, 5 figures, 1 table

As factories continue to evolve into collaborative spaces with multiple robots working together with human supervisors in the loop, ensuring safety for all actors involved becomes critical. Currently, laser-based light curtain sensors are widely used in factories for safety monitoring. While these conventional safety sensors meet high accuracy standards, they are difficult to reconfigure and can only monitor a fixed user-defined region of space. Furthermore, they are typically expensive. Instead, we leverage a controllable depth sensor, programmable light curtains (PLC), to develop an inexpensive and flexible real-time safety monitoring system for collaborative robot workspaces. Our system projects virtual dynamic safety envelopes that tightly envelop the moving robot at all times and detect any objects that intrude the envelope. Furthermore, we develop an instrumentation algorithm that optimally places (multiple) PLCs in a workspace to maximize the visibility coverage of robots. Our work enables fence-less human-robot collaboration, while scaling to monitor multiple robots with few sensors. We analyze our system in a real manufacturing testbed with four robot arms and demonstrate its capabilities as a fast, accurate, and inexpensive safety monitoring solution., Comment: Under review for IROS '24. Webpage http://cmu-mfi.github.io/plc-safety

We propose two provably accurate methods for low CP-rank tensor completion - one using adaptive sampling and one using nonadaptive sampling. Both of our algorithms combine matrix completion techniques for a small number of slices along with Jennrich's algorithm to learn the factors corresponding to the first two modes, and then solve systems of linear equations to learn the factors corresponding to the remaining modes. For order-$3$ tensors, our algorithms follow a "sandwich" sampling strategy that more densely samples a few outer slices (the bread), and then more sparsely samples additional inner slices (the bbq-braised tofu) for the final completion. For an order-$d$, CP-rank $r$ tensor of size $n \times \cdots \times n$ that satisfies mild assumptions, our adaptive sampling algorithm recovers the CP-decomposition with high probability while using at most $O(nr\log r + dnr)$ samples and $O(n^2r^2+dnr^2)$ operations. Our nonadaptive sampling algorithm recovers the CP-decomposition with high probability while using at most $O(dnr^2\log n + nr\log^2 n)$ samples and runs in polynomial time. Numerical experiments demonstrate that both of our methods work well on noisy synthetic data as well as on real world data., Comment: 25 pages, 8 figures

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning techniques such as behavior cloning is to find a policy that achieves a higher average return than the trajectories constituting the dataset. However, we empirically find that when a dataset is dominated by suboptimal trajectories, state-of-the-art offline RL algorithms do not substantially improve over the average return of trajectories in the dataset. We argue this is due to an assumption made by current offline RL algorithms of staying close to the trajectories in the dataset. If the dataset primarily consists of sub-optimal trajectories, this assumption forces the policy to mimic the suboptimal actions. We overcome this issue by proposing a sampling strategy that enables the policy to only be constrained to ``good data" rather than all actions in the dataset (i.e., uniform sampling). We present a realization of the sampling strategy and an algorithm that can be used as a plug-and-play module in standard offline RL algorithms. Our evaluation demonstrates significant performance gains in 72 imbalanced datasets, D4RL dataset, and across three different offline RL algorithms. Code is available at https://github.com/Improbable-AI/dw-offline-rl., Comment: Accepted NeurIPS 2023

We propose an adaptive and provably accurate tensor completion approach based on combining matrix completion techniques (see, e.g., arXiv:0805.4471, arXiv:1407.3619, arXiv:1306.2979) for a small number of slices with a modified noise robust version of Jennrich's algorithm. In the simplest case, this leads to a sampling strategy that more densely samples two outer slices (the bread), and then more sparsely samples additional inner slices (the bbq-braised tofu) for the final completion. Under mild assumptions on the factor matrices, the proposed algorithm completes an $n \times n \times n$ tensor with CP-rank $r$ with high probability while using at most $\mathcal{O}(nr\log^2 r)$ adaptively chosen samples. Empirical experiments further verify that the proposed approach works well in practice, including as a low-rank approximation method in the presence of additive noise., Comment: 6 pages, 5 figures. Sampling Theory and Applications Conference 2023

The deployment of extensive sensor arrays in nuclear reactors is infeasible due to challenging operating conditions and inherent spatial limitations. Strategically placing sensors within defined spatial constraints is essential for the reconstruction of reactor flow fields and the creation of nuclear digital twins. We develop a data-driven technique that incorporates constraints into an optimization framework for sensor placement, with the primary objective of minimizing reconstruction errors under noisy sensor measurements. The proposed greedy algorithm optimizes sensor locations over high-dimensional grids, adhering to user-specified constraints. We demonstrate the efficacy of optimized sensors by exhaustively computing all feasible configurations for a low-dimensional dynamical system. To validate our methodology, we apply the algorithm to the Out-of-Pile Testing and Instrumentation Transient Water Irradiation System (OPTI-TWIST) prototype capsule. This capsule is electrically heated to emulate the neutronics effect of the nuclear fuel. The TWIST prototype that will eventually be inserted in the Transient Reactor Test facility (TREAT) at the Idaho National Laboratory (INL), serves as a practical demonstration. The resulting sensor-based temperature reconstruction within OPTI-TWIST demonstrates minimized error, provides probabilistic bounds for noise-induced uncertainty, and establishes a foundation for communication between the digital twin and the experimental facility.

Dynabeads are superparamagnetic particles used for immunomagnetic purification of cells and biomolecules. Post-capture, however, target identification relies on tedious culturing, fluorescence staining and/or target amplification. Raman spectroscopy presents a rapid detection alternative, but current implementations target cells themselves with weak Raman signals. We present antibody-coated Dynabeads as strong Raman reporter labels whose effect can be considered a Raman parallel of immunofluorescent probes. Recent developments in techniques for separating target-bound Dynabeads from unbound Dynabeads makes such an implementation feasible. We deploy Dynabeads anti-Salmonella to bind and identify Salmonella enterica, a major foodborne pathogen. Dynabeads present signature peaks at 1000 and 1600 1/cm from aliphatic and aromatic C-C stretching of polystyrene, and 1350 1/cm and 1600 1/cm from amide, alpha-helix and beta-sheet of antibody coatings of the Fe2O3 core, confirmed with electron dispersive X-ray (EDX) imaging. Their Raman signature can be measured in dry and liquid samples even at single shot ~30 x 30-micrometer area imaging using 0.5 s, 7 mW laser acquisition with single and clustered beads providing a 44- and 68-fold larger Raman intensity compared to signature from cells. Higher polystyrene and antibody content in clusters yields to the larger signal intensity and conjugation to bacteria strengthens clustering as a bacterium can bind to more than one bead as observed via transmission electron microscopy (TEM). Our findings shed light on the intrinsic Raman reporter nature of Dynabeads, demonstrating their dual function for target isolation and detection without additional sample preparation, staining, or unique plasmonic substrate engineering, advancing their applications in heterogeneous samples like food, water, and blood., Comment: 35 pages, 19 figures, submitted to the Journal of Raman Spectroscopy

Indoor localization systems often fuse inertial odometry with map information via hand-defined methods to reduce odometry drift, but such methods are sensitive to noise and struggle to generalize across odometry sources. To address the robustness problem in map utilization, we propose a data-driven prior on possible user locations in a map by combining learned spatial map embeddings and temporal odometry embeddings. Our prior learns to encode which map regions are feasible locations for a user more accurately than previous hand-defined methods. This prior leads to a 49% improvement in inertial-only localization accuracy when used in a particle filter. This result is significant, as it shows that our relative positioning method can match the performance of absolute positioning using bluetooth beacons. To show the generalizability of our method, we also show similar improvements using wheel encoder odometry., Comment: Project page at https://klabcmu.github.io/learned-map-prior/