Related papers: Conformalized Interactive Imitation Learning: Hand…

Imitation learning has been applied to a range of robotic tasks, but can struggle when robots encounter edge cases that are not represented in the training data (i.e., distribution shift). Interactive fleet learning (IFL) mitigates…

Class-incremental learning (CIL) seeks to enable a model to sequentially learn new classes while retaining knowledge of previously learned ones. Balancing flexibility and stability remains a significant challenge, particularly when the task…

Most existing imitation learning approaches assume the demonstrations are drawn from experts who are optimal, but relaxing this assumption enables us to use a wider range of data. Standard imitation learning may learn a suboptimal policy…

Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor. However, there are many settings where the supervisor may evolve during policy learning, such as a human performing a novel task or an…

Quantifying a model's predictive uncertainty is essential for safety-critical applications such as autonomous driving. We consider quantifying such uncertainty for multi-object detection. In particular, we leverage conformal prediction to…

In this paper, we adopt conformal prediction, a distribution-free uncertainty quantification (UQ) framework, to obtain confidence prediction intervals with coverage guarantees for Deep Operator Network (DeepONet) regression. Initially, we…

Shared-autonomy imitation learning lets a human correct a robot in real time, mitigating covariate-shift errors. Yet existing approaches ignore two critical factors: (i) the operator's cognitive load and (ii) the risk created by delayed or…

Reliable uncertainty quantification (UQ) in machine learning (ML) regression tasks is becoming the focus of many studies in materials and chemical science. It is now well understood that average calibration is insufficient, and most studies…

Recent works have shown that most deep learning models are often poorly calibrated, i.e., they may produce overconfident predictions that are wrong. It is therefore desirable to have models that produce predictive uncertainty estimates that…

While deep learning offers tremendous promise for scientific and medical imaging, any failures and hallucinations (predictions that do not coincide with reality) are hard to pinpoint and can have serious downstream consequences. Uncertainty…

This paper focuses on the problem of detecting and reacting to changes in the distribution of a sensorimotor controller's observables. The key idea is the design of switching policies that can take conformal quantiles as input, which we…

Imitation Learning (IL) is a sample efficient paradigm for robot learning using expert demonstrations. However, policies learned through IL suffer from state distribution shift at test time, due to compounding errors in action prediction…

Practical Imitation Learning (IL) systems rely on large human demonstration datasets for successful policy learning. However, challenges lie in maintaining the quality of collected data and addressing the suboptimal nature of some…

Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks. Despite recent advances, these models are still prone to what are commonly known as hallucinations, causing them to emit…

This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images. Conventional deep metric learning methods focus on learning a discriminative embedding to describe the semantic features…

Limited data has become a major bottleneck in scaling up offline imitation learning (IL). In this paper, we propose enhancing IL performance under limited expert data by introducing a pre-training stage that learns dynamics representations,…

Uncertainty quantification is an important part of many performance critical applications. This paper provides a simple alternative to existing approaches such as ensemble learning and bayesian neural networks. By directly modeling the loss…

Robust waypoint prediction is crucial for mobile robots operating in open-world, safety-critical settings. While Imitation Learning (IL) methods have demonstrated great success in practice, they are susceptible to distribution shifts: the…

Several uncertainty estimation methods have been recently proposed for machine translation evaluation. While these methods can provide a useful indication of when not to trust model predictions, we show in this paper that the majority of…

Many applications of machine learning methods involve an iterative protocol in which data are collected, a model is trained, and then outputs of that model are used to choose what data to consider next. For example, one data-driven approach…