Artificial Intelligence (AI) models have demonstrated expert-level performance in melanoma detection, yet their clinical adoption is hindered by performance disparities across demographic subgroups such as gender, race, and age. Previous efforts to benchmark the performance of AI models have primarily focused on assessing model performance using group fairness metrics that rely on the Area Under the Receiver Operating Characteristic curve (AUROC), which does not provide insights into a model's ability to provide accurate estimates. In line with clinical assessments, this paper addresses this gap by incorporating calibration as a complementary benchmarking metric to AUROC-based fairness metrics. Calibration evaluates the alignment between predicted probabilities and observed event rates, offering deeper insights into subgroup biases. We assess the performance of the leading skin cancer detection algorithm of the ISIC 2020 Challenge on the ISIC 2020 Challenge dataset and the PROVE-AI dataset, and compare it with the second and third place models, focusing on subgroups defined by sex, race (Fitzpatrick Skin Tone), and age. Our findings reveal that while existing models enhance discriminative accuracy, they often over-diagnose risk and exhibit calibration issues when applied to new datasets. This study underscores the necessity for comprehensive model auditing strategies and extensive metadata collection to achieve equitable AI-driven healthcare solutions. All code is publicly available at https://github.com/bdominique/testing_strong_calibration.

Monitoring the internal temperature and humidity of shipping containers is essential to preventing quality degradation during cargo transportation. Sensorless monitoring -- machine learning models that predict the internal conditions of the containers using exogenous factors -- shows promise as an alternative to monitoring using sensors. However, it does not incorporate telemetry information and correct for systematic errors, causing the predictions to differ significantly from the live data and confusing the users. In this paper, we introduce the residual correction method, a general framework for correcting for systematic biases in sensorless models after observing live telemetry data. We call this class of models ``adaptive-sensorless'' monitoring. We train and evaluate adaptive-sensorless models on the 3.48 million data points -- the largest dataset of container sensor readings ever used in academic research -- and show that they produce consistent improvements over the baseline sensorless models. When evaluated on the holdout set of the simulated data, they achieve average mean absolute errors (MAEs) of 2.24 $\sim$ 2.31$^\circ$C (vs 2.43$^\circ$C by sensorless) for temperature and 5.72 $\sim$ 7.09% for relative humidity (vs 7.99% by sensorless) and average root mean-squared errors (RMSEs) of 3.19 $\sim$ 3.26$^\circ$C for temperature (vs 3.38$^\circ$C by sensorless) and 7.70 $\sim$ 9.12% for relative humidity (vs 10.0% by sensorless). Adaptive-sensorless models enable more accurate cargo monitoring, early risk detection, and less dependence on full connectivity in global shipping.

Diffusion models have been extensively leveraged for learning robot skills from demonstrations. These policies are conditioned on several observational modalities such as proprioception, vision and tactile. However, observational modalities have varying levels of influence for different tasks that diffusion polices fail to capture. In this work, we propose 'Factorized Diffusion Policies' abbreviated as FDP, a novel policy formulation that enables observational modalities to have differing influence on the action diffusion process by design. This results in learning policies where certain observations modalities can be prioritized over the others such as $\texttt{vision>tactile}$ or $\texttt{proprioception>vision}$. FDP achieves modality prioritization by factorizing the observational conditioning for diffusion process, resulting in more performant and robust policies. Our factored approach shows strong performance improvements in low-data regimes with $15\%$ absolute improvement in success rate on several simulated benchmarks when compared to a standard diffusion policy that jointly conditions on all input modalities. Moreover, our benchmark and real-world experiments show that factored policies are naturally more robust with $40\%$ higher absolute success rate across several visuomotor tasks under distribution shifts such as visual distractors or camera occlusions, where existing diffusion policies fail catastrophically. FDP thus offers a safer and more robust alternative to standard diffusion policies for real-world deployment. Videos are available at https://fdp-policy.github.io/fdp-policy/ .

Physical manipulation of garments is often crucial when performing fabric-related tasks, such as hanging garments. However, due to the deformable nature of fabrics, these operations remain a significant challenge for robots in household, healthcare, and industrial environments. In this paper, we propose GraphGarment, a novel approach that models garment dynamics based on robot control inputs and applies the learned dynamics model to facilitate garment manipulation tasks such as hanging. Specifically, we use graphs to represent the interactions between the robot end-effector and the garment. GraphGarment uses a graph neural network (GNN) to learn a dynamics model that can predict the next garment state given the current state and input action in simulation. To address the substantial sim-to-real gap, we propose a residual model that compensates for garment state prediction errors, thereby improving real-world performance. The garment dynamics model is then applied to a model-based action sampling strategy, where it is utilized to manipulate the garment to a reference pre-hanging configuration for garment-hanging tasks. We conducted four experiments using six types of garments to validate our approach in both simulation and real-world settings. In simulation experiments, GraphGarment achieves better garment state prediction performance, with a prediction error 0.46 cm lower than the best baseline. Our approach also demonstrates improved performance in the garment-hanging simulation experiment with enhancements of 12%, 24%, and 10%, respectively. Moreover, real-world robot experiments confirm the robustness of sim-to-real transfer, with an error increase of 0.17 cm compared to simulation results. Supplementary material is available at:https://sites.google.com/view/graphgarment.

In this paper, a learning based Model Predictive Control (MPC) using a low dimensional residual model is proposed for autonomous driving. One of the critical challenge in autonomous driving is the complexity of vehicle dynamics, which impedes the formulation of accurate vehicle model. Inaccurate vehicle model can significantly impact the performance of MPC controller. To address this issue, this paper decomposes the nominal vehicle model into invariable and variable elements. The accuracy of invariable component is ensured by calibration, while the deviations in the variable elements are learned by a low-dimensional residual model. The features of residual model are selected as the physical variables most correlated with nominal model errors. Physical constraints among these features are formulated to explicitly define the valid region within the feature space. The formulated model and constraints are incorporated into the MPC framework and validated through both simulation and real vehicle experiments. The results indicate that the proposed method significantly enhances the model accuracy and controller performance.

Reinforcement learning (RL) agents need to explore their environment to learn optimal behaviors and achieve maximum rewards. However, exploration can be risky when training RL directly on real systems, while simulation-based training introduces the tricky issue of the sim-to-real gap. Recent approaches have leveraged safety filters, such as control barrier functions (CBFs), to penalize unsafe actions during RL training. However, the strong safety guarantees of CBFs rely on a precise dynamic model. In practice, uncertainties always exist, including internal disturbances from the errors of dynamics and external disturbances such as wind. In this work, we propose a new safe RL framework based on disturbance rejection-guarded learning, which allows for an almost model-free RL with an assumed but not necessarily precise nominal dynamic model. We demonstrate our results on the Safety-gym benchmark for Point and Car robots on all tasks where we can outperform state-of-the-art approaches that use only residual model learning or a disturbance observer (DOB). We further validate the efficacy of our framework using a physical F1/10 racing car. Videos: https://sites.google.com/view/res-dob-cbf-rl

When the physics is wrong, physics-informed machine learning becomes physics-misinformed machine learning. A powerful black-box model should not be able to conceal misconceived physics. We propose two criteria that can be used to assert integrity that a hybrid (physics plus black-box) model: 0) the black-box model should be unable to replicate the physical model, and 1) any best-fit hybrid model has the same physical parameter as a best-fit standalone physics model. We demonstrate them for a sample nonlinear mechanical system approximated by its small-signal linearization.

Accuracy and computational efficiency are the most important metrics to Visual Inertial Navigation System (VINS). The existing VINS algorithms with either high accuracy or low computational complexity, are difficult to provide the high precision localization in resource-constrained devices. To this end, we propose a novel filter-based VINS framework named SchurVINS, which could guarantee both high accuracy by building a complete residual model and low computational complexity with Schur complement. Technically, we first formulate the full residual model where Gradient, Hessian and observation covariance are explicitly modeled. Then Schur complement is employed to decompose the full model into ego-motion residual model and landmark residual model. Finally, Extended Kalman Filter (EKF) update is implemented in these two models with high efficiency. Experiments on EuRoC and TUM-VI datasets show that our method notably outperforms state-of-the-art (SOTA) methods in both accuracy and computational complexity. We will open source our experimental code to benefit the community.

In a well-calibrated risk prediction model, the average predicted probability is close to the true event rate for any given subgroup. Such models are reliable across heterogeneous populations and satisfy strong notions of algorithmic fairness. However, the task of auditing a model for strong calibration is well-known to be difficult -- particularly for machine learning (ML) algorithms -- due to the sheer number of potential subgroups. As such, common practice is to only assess calibration with respect to a few predefined subgroups. Recent developments in goodness-of-fit testing offer potential solutions but are not designed for settings with weak signal or where the poorly calibrated subgroup is small, as they either overly subdivide the data or fail to divide the data at all. We introduce a new testing procedure based on the following insight: if we can reorder observations by their expected residuals, there should be a change in the association between the predicted and observed residuals along this sequence if a poorly calibrated subgroup exists. This lets us reframe the problem of calibration testing into one of changepoint detection, for which powerful methods already exist. We begin with introducing a sample-splitting procedure where a portion of the data is used to train a suite of candidate models for predicting the residual, and the remaining data are used to perform a score-based cumulative sum (CUSUM) test. To further improve power, we then extend this adaptive CUSUM test to incorporate cross-validation, while maintaining Type I error control under minimal assumptions. Compared to existing methods, the proposed procedure consistently achieved higher power in simulation studies and more than doubled the power when auditing a mortality risk prediction model.

Regime switching is ubiquitous in many complex dynamical systems with multiscale features, chaotic behavior, and extreme events. In this paper, a causation entropy boosting (CEBoosting) strategy is developed to facilitate the detection of regime switching and the discovery of the dynamics associated with the new regime via online model identification. The causation entropy, which can be efficiently calculated, provides a logic value of each candidate function in a pre-determined library. The reversal of one or a few such causation entropy indicators associated with the model calibrated for the current regime implies the detection of regime switching. Despite the short length of each batch formed by the sequential data, the accumulated value of causation entropy corresponding to a sequence of data batches leads to a robust indicator. With the detected rectification of the model structure, the subsequent parameter estimation becomes a quadratic optimization problem, which is solved using closed analytic formulae. Using the Lorenz 96 model, it is shown that the causation entropy indicator can be efficiently calculated, and the method applies to moderately large dimensional systems. The CEBoosting algorithm is also adaptive to the situation with partial observations. It is shown via a stochastic parameterized model that the CEBoosting strategy can be combined with data assimilation to identify regime switching triggered by the unobserved latent processes. In addition, the CEBoosting method is applied to a nonlinear paradigm model for topographic mean flow interaction, demonstrating the online detection of regime switching in the presence of strong intermittency and extreme events.