Continuum robots have the potential to enable new applications in medicine, inspection, and countless other areas due to their unique shape, compliance, and size. Excellent progess has been made in the mechanical design and dynamic modelling of continuum robots, to the point that there are some canonical designs, although new concepts continue to be explored. In this paper, we turn to the problem of state estimation for continuum robots that can been modelled with the common Cosserat rod model. Sensing for continuum robots might comprise external camera observations, embedded tracking coils or strain gauges. We repurpose a Gaussian process (GP) regression approach to state estimation, initially developed for continuous-time trajectory estimation in $SE(3)$. In our case, the continuous variable is not time but arclength and we show how to estimate the continuous shape (and strain) of the robot (along with associated uncertainties) given discrete, noisy measurements of both pose and strain along the length. We demonstrate our approach quantitatively through simulations as well as through experiments. Our evaluations show that accurate and continuous estimates of a continuum robot's shape can be achieved, resulting in average end-effector errors between the estimated and ground truth shape as low as 3.5mm and 0.016$^\circ$ in simulation or 3.3mm and 0.035$^\circ$ for unloaded configurations and 6.2mm and 0.041$^\circ$ for loaded ones during experiments, when using discrete pose measurements.
Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidden confounders in the causal graph. We break down the space of confounded imitation learning problems and identify three settings with different data requirements in which the correct imitation policy can be identified. We then introduce an algorithm for deconfounded imitation learning, which trains an inference model jointly with a latent-conditional policy. At test time, the agent alternates between updating its belief over the latent and acting under the belief. We show in theory and practice that this algorithm converges to the correct interventional policy, solves the confounding issue, and can under certain assumptions achieve an asymptotically optimal imitation performance.
Modern-day civil, mechanical, and aeronautical structures are transitioning towards a continuous, online, and automated maintenance paradigm in order to ensure increased safety and reliability. The field of structural health monitoring (SHM) is playing a key role in this respect and active sensing acousto-ultrasound guided-wave based SHM techniques have shown great promise due to their potential sensitivity to small changes in the structure. However, the methods' robustness and diagnosis capability become limited in the presence of environmental and operational variability such as changing temperature. In order to circumvent this difficulty, in this paper, a novel stochastic time series-based framework was adopted to model guided wave propagation under varying temperatures. Different stochastic time-varying time series models, such as Recursive Maximum Likelihood Time-varying Auto-Regressive (RML-TAR) and Recursive Maximum Likelihood Time-varying Auto-Regressive with Exogenous Excitation (RML-TARX) models are put forward to model and capture the underlying dynamics of guided wave propagation under varying temperatures. The steps and facets of the identification procedure are presented and clearly explained. Then the identified models are used to perform one-step-ahead prediction as well as "simulation" of the guided wave signals. In order to gain insight from a physics perspective, high-fidelity finite element (FE) models were also established to model the effect of temperature variation on guided wave propagation. Finally, surrogate models are formulated through the use of stochastic time-dependent RML-TARX models and compared with the FE models under varying temperatures.
Recent progress towards learning from limited supervision has encouraged efforts towards designing models that can recognize novel classes at test time (generalized zero-shot learning or GZSL). GZSL approaches assume knowledge of all classes, with or without labeled data, beforehand. However, practical scenarios demand models that are adaptable and can handle dynamic addition of new seen and unseen classes on the fly (that is continual generalized zero-shot learning or CGZSL). One solution is to sequentially retrain and reuse conventional GZSL methods, however, such an approach suffers from catastrophic forgetting leading to suboptimal generalization performance. A few recent efforts towards tackling CGZSL have been limited by difference in settings, practicality, data splits and protocols followed-inhibiting fair comparison and a clear direction forward. Motivated from these observations, in this work, we firstly consolidate the different CGZSL setting variants and propose a new Online-CGZSL setting which is more practical and flexible. Secondly, we introduce a unified feature-generative framework for CGZSL that leverages bi-directional incremental alignment to dynamically adapt to addition of new classes, with or without labeled data, that arrive over time in any of these CGZSL settings. Our comprehensive experiments and analysis on five benchmark datasets and comparison with baselines show that our approach consistently outperforms existing methods, especially on the more practical Online setting.
Mobile cloud offloading is indispensable for inference tasks based on large-scale deep models. However, transmitting privacy-rich inference data to the cloud incurs concerns. This paper presents the design of a system called PriMask, in which the mobile device uses a secret small-scale neural network called MaskNet to mask the data before transmission. PriMask significantly weakens the cloud's capability to recover the data or extract certain private attributes. The MaskNet is em cascadable in that the mobile can opt in to or out of its use seamlessly without any modifications to the cloud's inference service. Moreover, the mobiles use different MaskNets, such that the collusion between the cloud and some mobiles does not weaken the protection for other mobiles. We devise a {\em split adversarial learning} method to train a neural network that generates a new MaskNet quickly (within two seconds) at run time. We apply PriMask to three mobile sensing applications with diverse modalities and complexities, i.e., human activity recognition, urban environment crowdsensing, and driver behavior recognition. Results show PriMask's effectiveness in all three applications.
The visual simultaneous localization and mapping(vSLAM) is widely used in GPS-denied and open field environments for ground and surface robots. However, due to the frequent perception failures derived from lacking visual texture or the {swing} of robot view direction on rough terrains, the accuracy and robustness of vSLAM are still to be enhanced. The study develops a novel view planning approach of actively perceiving areas with maximal information to address the mentioned problem; a gimbal camera is used as the main sensor. Firstly, a map representation based on feature distribution-weighted Fisher information is proposed to completely and effectively represent environmental information richness. With the map representation, a continuous environmental information model is further established to convert the discrete information space into a continuous one for numerical optimization in real-time. Subsequently, the receding horizon optimization is utilized to obtain the optimal informative viewpoints with simultaneously considering the robotic perception, exploration and motion cost based on the continuous environmental model. Finally, several simulations and outdoor experiments are performed to verify the improvement of localization robustness and accuracy by the proposed approach.
Data are rapidly growing in size and importance for society, a trend motivated by their enabling power. The accumulation of new data, sustained by progress in technology, leads to a boundless expansion of stored data, in some cases with an exponential increase in the accrual rate itself. Massive data are hard to process, transmit, store, and exploit, and it is particularly hard to keep abreast of the data store as a whole. This paper distinguishes three phases in the life of data: acquisition, curation, and exploitation. Each involves a distinct process, that may be separated from the others in time, with a different set of priorities. The function of the second phase, curation, is to maximize the future value of the data given limited storage. I argue that this requires that (a) the data take the form of summary statistics and (b) these statistics follow an endless process of rescaling. The summary may be more compact than the original data, but its data structure is more complex and it requires an on-going computational process that is much more sophisticated than mere storage. Rescaling results in dimensionality reduction that may be beneficial for learning, but that must be carefully controlled to preserve relevance. Rescaling may be tuned based on feedback from usage, with the proviso that our memory of the past serves the future, the needs of which are not fully known.
Power transformers are an important component of a nuclear power plant (NPP). Currently, the NPP operates a lot of power transformers with extended service life, which exceeds the designated 25 years. Due to the extension of the service life, the task of monitoring the technical condition of power transformers becomes urgent. An important method for monitoring power transformers is Chromatographic Analysis of Dissolved Gas. It is based on the principle of controlling the concentration of gases dissolved in transformer oil. The appearance of almost any type of defect in equipment is accompanied by the formation of gases that dissolve in oil, and specific types of defects generate their gases in different quantities. At present, at NPPs, the monitoring systems for transformer equipment use predefined control limits for the concentration of dissolved gases in the oil. This study describes the stages of developing an algorithm to detect defects and faults in transformers automatically using machine learning and data analysis methods. Among machine learning models, we trained Logistic Regression, Decision Trees, Random Forest, Gradient Boosting, Neural Networks. The best of them were then combined into an ensemble (StackingClassifier) showing F1-score of 0.974 on a test sample. To develop mathematical models, we used data on the state of transformers, containing time series with values of gas concentrations (H2, CO, C2H4, C2H2). The datasets were labeled and contained four operating modes: normal mode, partial discharge, low energy discharge, low-temperature overheating.
Gait phase detection with convolution neural network provides accurate classification but demands high computational cost, which inhibits real time low power on-sensor processing. This paper presents a segmentation based gait phase detection with a width and depth downscaled U-Net like model that only needs 0.5KB model size and 67K operations per second with 95.9% accuracy to be easily fitted into resource limited on sensor microcontroller.
This paper proposes LPC-AD, a fast and accurate multivariate time series (MTS) anomaly detection method. LPC-AD is motivated by the ever-increasing needs for fast and accurate MTS anomaly detection methods to support fast troubleshooting in cloud computing, micro-service systems, etc. LPC-AD is fast in the sense that its reduces the training time by as high as 38.2% compared to the state-of-the-art (SOTA) deep learning methods that focus on training speed. LPC-AD is accurate in the sense that it improves the detection accuracy by as high as 18.9% compared to SOTA sophisticated deep learning methods that focus on enhancing detection accuracy. Methodologically, LPC-AD contributes a generic architecture LPC-Reconstruct for one to attain different trade-offs between training speed and detection accuracy. More specifically, LPC-Reconstruct is built on ideas from autoencoder for reducing redundancy in time series, latent predictive coding for capturing temporal dependence in MTS, and randomized perturbation for avoiding overfitting of anomalous dependence in the training data. We present simple instantiations of LPC-Reconstruct to attain fast training speed, where we propose a simple randomized perturbation method. The superior performance of LPC-AD over SOTA methods is validated by extensive experiments on four large real-world datasets. Experiment results also show the necessity and benefit of each component of the LPC-Reconstruct architecture and that LPC-AD is robust to hyper parameters.