Learning from previously collected datasets of expert data offers the promise of acquiring robotic policies without unsafe and costly online explorations. However, a major challenge is a distributional shift between the states in the training dataset and the ones visited by the learned policy at the test time. While prior works mainly studied the distribution shift caused by the policy during the offline training, the problem of recovering from out-of-distribution states at the deployment time is not very well studied yet. We alleviate the distributional shift at the deployment time by introducing a recovery policy that brings the agent back to the training manifold whenever it steps out of the in-distribution states, e.g., due to an external perturbation. The recovery policy relies on an approximation of the training data density and a learned equivariant mapping that maps visual observations into a latent space in which translations correspond to the robot actions. We demonstrate the effectiveness of the proposed method through several manipulation experiments on a real robotic platform. Our results show that the recovery policy enables the agent to complete tasks while the behavioral cloning alone fails because of the distributional shift problem.
相關內容
We study a general setting of status updating systems in which a set of source nodes provide status updates about some physical process(es) to a set of monitors. The freshness of information available at each monitor is quantified in terms of the Age of Information (AoI), and the vector of AoI processes at the monitors (or equivalently the age vector) models the continuous state of the system. While the marginal distributional properties of each AoI process have been studied for a variety of settings using the stochastic hybrid system (SHS) approach, we lack a counterpart of this approach to systematically study their joint distributional properties. Developing such a framework is the main contribution of this paper. In particular, we model the discrete state of the system as a finite-state continuous-time Markov chain, and describe the coupled evolution of the continuous and discrete states of the system by a piecewise linear SHS with linear reset maps. Using the notion of tensors, we first derive first-order linear differential equations for the temporal evolution of both the joint moments and the joint moment generating function (MGF) for an arbitrary set of age processes. We then characterize the conditions under which the derived differential equations are asymptotically stable. The generality of our framework is demonstrated by recovering several existing results as special cases. Finally, we apply our framework to derive closed-form expressions of the stationary joint MGF in a multi-source updating system under non-preemptive and source-agnostic/source-aware preemptive in service queueing disciplines.
Applications of industrial robotic manipulators such as cobots can require efficient online motion planning in environments that have a combination of static and non-static obstacles. Existing general purpose planning methods often produce poor quality solutions when available computation time is restricted, or fail to produce a solution entirely. We propose a new motion planning framework designed to operate in a user-defined task space, as opposed to the robot's workspace, that intentionally trades off workspace generality for planning and execution time efficiency. Our framework automatically constructs trajectory libraries that are queried online, similar to previous methods that exploit offline computation. Importantly, our method also offers bounded suboptimality guarantees on trajectory length. The key idea is to establish approximate isometries known as $\epsilon$-Gromov-Hausdorff approximations such that points that are close by in task space are also close in configuration space. These bounding relations further imply that trajectories can be smoothly concatenated, which enables our framework to address batch-query scenarios where the objective is to find a minimum length sequence of trajectories that visit an unordered set of goals. We evaluate our framework in simulation with several kinematic configurations, including a manipulator mounted to a mobile base. Results demonstrate that our method achieves feasible real-time performance for practical applications and suggest interesting opportunities for extending its capabilities.
In this paper, we prove a local limit theorem and probability metrics bounds between the inverse Gaussian distribution (also called the Wald distribution) and the normal distribution with the same mean and variance. We also extend these results to the multivariate inverse Gaussian distribution introduced by Minami (2003).
Learning and reasoning about physical phenomena is still a challenge in robotics development, and computational sciences play a capital role in the search for accurate methods able to provide explanations for past events and rigorous forecasts of future situations. We propose a thermodynamics-informed active learning strategy for fluid perception and reasoning from observations. As a model problem, we take the sloshing phenomena of different fluids contained in a glass. Starting from full-field and high-resolution synthetic data for a particular fluid, we develop a method for the tracking (perception) and analysis (reasoning) of any previously unseen liquid whose free surface is observed with a commodity camera. This approach demonstrates the importance of physics and knowledge not only in data-driven (grey box) modeling but also in the correction for real physics adaptation in low data regimes and partial observations of the dynamics. The method presented is extensible to other domains such as the development of cognitive digital twins, able to learn from observation of phenomena for which they have not been trained explicitly.
In explainable machine learning, local post-hoc explanation algorithms and inherently interpretable models are often seen as competing approaches. In this work, offer a novel perspective on Shapley Values, a prominent post-hoc explanation technique, and show that it is strongly connected with Glassbox-GAMs, a popular class of interpretable models. We introduce $n$-Shapley Values, a natural extension of Shapley Values that explain individual predictions with interaction terms up to order $n$. As $n$ increases, the $n$-Shapley Values converge towards the Shapley-GAM, a uniquely determined decomposition of the original function. From the Shapley-GAM, we can compute Shapley Values of arbitrary order, which gives precise insights into the limitations of these explanations. We then show that Shapley Values recover generalized additive models of order $n$, assuming that we allow for interaction terms up to order $n$ in the explanations. This implies that the original Shapley Values recover Glassbox-GAMs. At the technical end, we show that there is a one-to-one correspondence between different ways to choose the value function and different functional decompositions of the original function. This provides a novel perspective on the question of how to choose the value function. We also present an empirical analysis of the degree of variable interaction that is present in various standard classifiers, and discuss the implications of our results for algorithmic explanations. A python package to compute $n$-Shapley Values and replicate the results in this paper is available at \url{//github.com/tml-tuebingen/nshap}.
We present a novel deep learning framework named the Iteratively Optimized Patch Label Inference Network (IOPLIN) for automatically detecting various pavement distresses that are not solely limited to specific ones, such as cracks and potholes. IOPLIN can be iteratively trained with only the image label via the Expectation-Maximization Inspired Patch Label Distillation (EMIPLD) strategy, and accomplish this task well by inferring the labels of patches from the pavement images. IOPLIN enjoys many desirable properties over the state-of-the-art single branch CNN models such as GoogLeNet and EfficientNet. It is able to handle images in different resolutions, and sufficiently utilize image information particularly for the high-resolution ones, since IOPLIN extracts the visual features from unrevised image patches instead of the resized entire image. Moreover, it can roughly localize the pavement distress without using any prior localization information in the training phase. In order to better evaluate the effectiveness of our method in practice, we construct a large-scale Bituminous Pavement Disease Detection dataset named CQU-BPDD consisting of 60,059 high-resolution pavement images, which are acquired from different areas at different times. Extensive results on this dataset demonstrate the superiority of IOPLIN over the state-of-the-art image classification approaches in automatic pavement distress detection. The source codes of IOPLIN are released on \url{//github.com/DearCaat/ioplin}, and the CQU-BPDD dataset is able to be accessed on \url{//dearcaat.github.io/CQU-BPDD/}.
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias prompts from a few samples but also captures the distribution of diverse prompts to handle the varying visual representations. In this way, we provide high-quality task-related content for facilitating recognition. This prompt distribution learning is realized by an efficient approach that learns the output embeddings of prompts instead of the input embeddings. Thus, we can employ a Gaussian distribution to model them effectively and derive a surrogate loss for efficient training. Extensive experiments on 12 datasets demonstrate that our method consistently and significantly outperforms existing methods. For example, with 1 sample per category, it relatively improves the average result by 9.1% compared to human-crafted prompts.
Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine learning systems. For instance, in autonomous driving, we would like the driving system to issue an alert and hand over the control to humans when it detects unusual scenes or objects that it has never seen before and cannot make a safe decision. This problem first emerged in 2017 and since then has received increasing attention from the research community, leading to a plethora of methods developed, ranging from classification-based to density-based to distance-based ones. Meanwhile, several other problems are closely related to OOD detection in terms of motivation and methodology. These include anomaly detection (AD), novelty detection (ND), open set recognition (OSR), and outlier detection (OD). Despite having different definitions and problem settings, these problems often confuse readers and practitioners, and as a result, some existing studies misuse terms. In this survey, we first present a generic framework called generalized OOD detection, which encompasses the five aforementioned problems, i.e., AD, ND, OSR, OOD detection, and OD. Under our framework, these five problems can be seen as special cases or sub-tasks, and are easier to distinguish. Then, we conduct a thorough review of each of the five areas by summarizing their recent technical developments. We conclude this survey with open challenges and potential research directions.
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question answering or machine translation). However, it builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. Moreover, it is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime. The first goal of this thesis is to characterize the different forms this shift can take in the context of natural language processing, and propose benchmarks and evaluation metrics to measure its effect on current deep learning architectures. We then proceed to take steps to mitigate the effect of distributional shift on NLP models. To this end, we develop methods based on parametric reformulations of the distributionally robust optimization framework. Empirically, we demonstrate that these approaches yield more robust models as demonstrated on a selection of realistic problems. In the third and final part of this thesis, we explore ways of efficiently adapting existing models to new domains or tasks. Our contribution to this topic takes inspiration from information geometry to derive a new gradient update rule which alleviate catastrophic forgetting issues during adaptation.
Classic machine learning methods are built on the $i.i.d.$ assumption that training and testing data are independent and identically distributed. However, in real scenarios, the $i.i.d.$ assumption can hardly be satisfied, rendering the sharp drop of classic machine learning algorithms' performances under distributional shifts, which indicates the significance of investigating the Out-of-Distribution generalization problem. Out-of-Distribution (OOD) generalization problem addresses the challenging setting where the testing distribution is unknown and different from the training. This paper serves as the first effort to systematically and comprehensively discuss the OOD generalization problem, from the definition, methodology, evaluation to the implications and future directions. Firstly, we provide the formal definition of the OOD generalization problem. Secondly, existing methods are categorized into three parts based on their positions in the whole learning pipeline, namely unsupervised representation learning, supervised model learning and optimization, and typical methods for each category are discussed in detail. We then demonstrate the theoretical connections of different categories, and introduce the commonly used datasets and evaluation metrics. Finally, we summarize the whole literature and raise some future directions for OOD generalization problem. The summary of OOD generalization methods reviewed in this survey can be found at //out-of-distribution-generalization.com.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191