Search

Robots operating in the real world face significant but unavoidable issues in object localization that must be dealt with. A typical approach to address this is the addition of compliance mechanisms to hardware to absorb and compensate for some of these errors. However, for fine-grained manipulation tasks, the location and choice of appropriate compliance mechanisms are critical for success. For objects to be inserted in a target site on a flat surface, the object must first be successfully aligned with the opening of the slot, as well as correctly oriented along its central axis, before it can be inserted. We developed the Four-Axis Adaptive Finger Hand (FAAF hand) that is equipped with fingers that can passively adapt in four axes (x, y, z, yaw) enabling it to perform insertion tasks including lid fitting in the presence of significant localization errors. Furthermore, this adaptivity allows the use of simple control methods without requiring contact sensors or other devices. Our results confirm the ability of the FAAF hand on challenging insertion tasks of square and triangle-shaped pegs (or prisms) and placing of container lids in the presence of position errors in all directions and rotational error along the object's central axis, using a simple control scheme., Comment: 8 pages. Accepted at IEEE IROS 2024. An accompanying video is available at https://www.youtube.com/watch?v=s3yf2MQ5Pag

State estimation for nonlinear state space models is a challenging task. Existing assimilation methodologies predominantly assume Gaussian posteriors on physical space, where true posteriors become inevitably non-Gaussian. We propose Deep Bayesian Filtering (DBF) for data assimilation on nonlinear state space models (SSMs). DBF constructs new latent variables $h_t$ on a new latent (``fancy'') space and assimilates observations $o_t$. By (i) constraining the state transition on fancy space to be linear and (ii) learning a Gaussian inverse observation operator $q(h_t|o_t)$, posteriors always remain Gaussian for DBF. Quite distinctively, the structured design of posteriors provides an analytic formula for the recursive computation of posteriors without accumulating Monte-Carlo sampling errors over time steps. DBF seeks the Gaussian inverse observation operators $q(h_t|o_t)$ and other latent SSM parameters (e.g., dynamics matrix) by maximizing the evidence lower bound. Experiments show that DBF outperforms model-based approaches and latent assimilation methods in various tasks and conditions., Comment: Main text 9 pages

Image denoising is a representative image restoration task in computer vision. Recent progress of image denoising from only noisy images has attracted much attention. Deep image prior (DIP) demonstrated successful image denoising from only a noisy image by inductive bias of convolutional neural network architectures without any pre-training. The major challenge of DIP based image denoising is that DIP would completely recover the original noisy image unless applying early stopping. For early stopping without a ground-truth clean image, we propose to monitor JPEG file size of the recovered image during optimization as a proxy metric of noise levels in the recovered image. Our experiments show that the compressed image file size works as an effective metric for early stopping., Comment: IEEE International Conference on Image Processing (ICIP 2023)

A problem that plagues robotic grasping is the misalignment of the object and gripper due to difficulties in precise localization, actuation, etc. Under-actuated robotic hands with compliant mechanisms are used to adapt and compensate for these inaccuracies. However, these mechanisms come at the cost of controllability and coordination. For instance, adaptive functions that let the fingers of a two-fingered gripper adapt independently may affect the coordination necessary for grasping small objects. In this work, we develop a two-fingered robotic hand capable of grasping objects that are offset from the gripper's center, while still having the requisite coordination for grasping small objects via a novel gear-type synchronization mechanism with a magnet. This gear synchronization mechanism allows the adaptive finger's tips to be aligned enabling it to grasp objects as small as toothpicks and washers. The magnetic component allows this coordination to automatically turn off when needed, allowing for the grasping of objects that are offset/misaligned from the gripper. This equips the hand with the capability of grasping light, fragile objects (strawberries, creampuffs, etc) to heavy frying pan lids, all while maintaining their position and posture which is vital in numerous applications that require precise positioning or careful manipulation., Comment: 8 pages. Accepted at IEEE IROS 2023. An accompanying video is available at https://www.youtube.com/watch?v=RAO7Qb2ZGNs

Identifying the relationship between healthcare attributes, lifestyles, and personality is vital for understanding and improving physical and mental conditions. Machine learning approaches are promising for modeling their relationships and offering actionable suggestions. In this paper, we propose Virtual Human Generative Model (VHGM), a machine learning model for estimating attributes about healthcare, lifestyles, and personalities. VHGM is a deep generative model trained with masked modeling to learn the joint distribution of attributes conditioned on known ones. Using heterogeneous tabular datasets, VHGM learns more than 1,800 attributes efficiently. We numerically evaluate the performance of VHGM and its training techniques. As a proof-of-concept of VHGM, we present several applications demonstrating user scenarios, such as virtual measurements of healthcare attributes and hypothesis verifications of lifestyles., Comment: 14 pages, 4 figures

Variational autoencoders (VAEs) are one of the deep generative models that have experienced enormous success over the past decades. However, in practice, they suffer from a problem called posterior collapse, which occurs when the encoder coincides, or collapses, with the prior taking no information from the latent structure of the input data into consideration. In this work, we introduce an inverse Lipschitz neural network into the decoder and, based on this architecture, provide a new method that can control in a simple and clear manner the degree of posterior collapse for a wide range of VAE models equipped with a concrete theoretical guarantee. We also illustrate the effectiveness of our method through several numerical experiments., Comment: accepted to ICML 2023, some notations adjusted from the submitted version

It is challenging to grasp numerous objects with varying sizes and shapes with a single robot hand. To address this, we propose a new robot hand called the 'F3 hand' inspired by the complex movements of human index finger and thumb. The F3 hand attempts to realize complex human-like grasping movements by combining a parallel motion finger and a rotational motion finger with an adaptive function. In order to confirm the performance of our hand, we attached it to a mobile manipulator - the Toyota Human Support Robot (HSR) and conducted grasping experiments. In our results, we show that it is able to grasp all YCB objects (82 in total), including washers with outer diameters as small as 6.4mm. We also built a system for intuitive operation with a 3D mouse and grasp an additional 24 objects, including small toothpicks and paper clips and large pitchers and cracker boxes. The F3 hand is able to achieve a 98% success rate in grasping even under imprecise control and positional offsets. Furthermore, owing to the finger's adaptive function, we demonstrate characteristics of the F3 hand that facilitate the grasping of soft objects such as strawberries in a desirable posture., Comment: 8 pages. Accepted at IEEE RO-MAN 2022. An accompanying video is available at https://www.youtube.com/watch?v=l6GK5XTbty8

Teleoperation is often limited by the ability of an operator to react and predict the behavior of the robot as it interacts with the environment. For example, to grasp small objects on a table, the teleoperator needs to predict the position of the fingertips before the fingers are closed to avoid them hitting the table. For that reason, we developed the F1 hand, a single-motor gripper that facilitates teleoperation with the use of a fixed finger. The hand is capable of grasping objects as thin as a paper clip, and as heavy and large as a cordless drill. The applicability of the hand can be expanded by replacing the fixed finger with different shapes. This flexibility makes the hand highly versatile while being easy and cheap to develop. However, due to the atypical asymmetric structure and actuation of the hand usual grasping strategies no longer apply. Thus, we propose a controller that approximates actuation symmetry by using the motion of the whole arm. The F1 hand and its controller are compared side-by-side with the original Toyota Human Support Robot (HSR) gripper in teleoperation using 22 objects from the YCB dataset in addition to small objects. The grasping time and peak contact forces could be decreased by 20% and 70%, respectively while increasing success rates by 5%. Using an off-the-shelf grasp pose estimator for autonomous grasping, the system achieved similar success rates to the original HSR gripper, at the order of 80%., Comment: Accepted for publication at the IEEE Robotics and Automation Letters (RA-L)

We report on the charge-ordered structure of LiRh2O4 arising below the metal-insulator transition at 170 K. Structural studies using synchrotron X-rays have revealed that the charge-ordered states of Rh3+ and Rh4+ with dimerization are realized in the low-temperature phase below 170 K. Although the low-temperature ground state resembles that of CuIr2S4, a charge ordering pattern satisfying the Anderson condition is realized in LiRh2O4. Based on structural information such as the short-range order of dimers appearing above the transition temperature and the weakening of the correlation between rhodium one-dimensional chains appearing in the crystal structure, we argue that the Coulomb interaction plays an important role in determining the charge ordering patterns., Comment: 6 pages, 4figures Journal reference(accepted) https://journals.aps.org/prb/accepted/0b072Y1fT3817c8014452620ec61a998d0036f7ef

Deep learning models for semantic segmentation rely on expensive, large-scale, manually annotated datasets. Labelling is a tedious process that can take hours per image. Automatically annotating video sequences by propagating sparsely labeled frames through time is a more scalable alternative. In this work, we propose a novel label propagation method, termed Warp-Refine Propagation, that combines semantic cues with geometric cues to efficiently auto-label videos. Our method learns to refine geometrically-warped labels and infuse them with learned semantic priors in a semi-supervised setting by leveraging cycle consistency across time. We quantitatively show that our method improves label-propagation by a noteworthy margin of 13.1 mIoU on the ApolloScape dataset. Furthermore, by training with the auto-labelled frames, we achieve competitive results on three semantic-segmentation benchmarks, improving the state-of-the-art by a large margin of 1.8 and 3.61 mIoU on NYU-V2 and KITTI, while matching the current best results on Cityscapes., Comment: 16 pages, 12 figures, including supplementary material. To be published in ICCV 2021

Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks. The most significant advantage of using synthetic images is that the ground-truth labels are automatically available, enabling unlimited expansion of the data size without human cost. However, synthetic data may have a huge domain gap, in which case increasing the data size does not improve the performance. How can we know that? In this study, we derive a simple scaling law that predicts the performance from the amount of pre-training data. By estimating the parameters of the law, we can judge whether we should increase the data or change the setting of image synthesis. Further, we analyze the theory of transfer learning by considering learning dynamics and confirm that the derived generalization bound is consistent with our empirical findings. We empirically validated our scaling law on various experimental settings of benchmark tasks, model sizes, and complexities of synthetic images.

Food packing industry workers typically pick a target amount of food by hand from a food tray and place them in containers. Since menus are diverse and change frequently, robots must adapt and learn to handle new foods in a short time-span. Learning to grasp a specific amount of granular food requires a large training dataset, which is challenging to collect reasonably quickly. In this study, we propose ways to reduce the necessary amount of training data by augmenting a deep neural network with models that estimate its uncertainty through self-supervised learning. To further reduce human effort, we devise a data collection system that automatically generates labels. We build on the idea that we can grasp sufficiently well if there is at least one low-uncertainty (high-confidence) grasp point among the various grasp point candidates. We evaluate the methods we propose in this work on a variety of granular foods -- coffee beans, rice, oatmeal and peanuts -- each of which has a different size, shape and material properties such as volumetric mass density or friction. For these foods, we show significantly improved grasp accuracy of user-specified target masses using smaller datasets by incorporating uncertainty., Comment: 7 pages. Accepted to ICRA2021. An accompanying video is available at the following link: https://youtu.be/5pLkg7SpmiE

Meta-Learning is a family of methods that use a set of interrelated tasks to learn a model that can quickly learn a new query task from a possibly small contextual dataset. In this study, we use a probabilistic framework to formalize what it means for two tasks to be related and reframe the meta-learning problem into the problem of Bayesian risk minimization (BRM). In our formulation, the BRM optimal solution is given by the predictive distribution computed from the posterior distribution of the task-specific latent variable conditioned on the contextual dataset, and this justifies the philosophy of Neural Process. However, the posterior distribution in Neural Process violates the way the posterior distribution changes with the contextual dataset. To address this problem, we present a novel Gaussian approximation for the posterior distribution that generalizes the posterior of the linear Gaussian model. Unlike that of the Neural Process, our approximation of the posterior distributions converges to the maximum likelihood estimate with the same rate as the true posterior distribution. We also demonstrate the competitiveness of our approach on benchmark datasets.

In this paper we target the problem of transferring policies across multiple environments with different dynamics parameters and motor noise variations, by introducing a framework that decouples the processes of policy learning and system identification. Efficiently transferring learned policies to an unknown environment with changes in dynamics configurations in the presence of motor noise is very important for operating robots in the real world, and our work is a novel attempt in that direction. We introduce MANGA: Method Agnostic Neural-policy Generalization and Adaptation, that trains dynamics conditioned policies and efficiently learns to estimate the dynamics parameters of the environment given off-policy state-transition rollouts in the environment. Our scheme is agnostic to the type of training method used - both reinforcement learning (RL) and imitation learning (IL) strategies can be used. We demonstrate the effectiveness of our approach by experimenting with four different MuJoCo agents and comparing against previously proposed transfer baselines., Comment: Under Review. Video available at https://drive.google.com/file/d/12GsDq3iQDXEutE-xpzXxqrEfD6dYhKjs/view?usp=sharing Other details will be made available in the author's webpage www.homangabharadhwaj.com

Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while satisfying a set of prescribed safety constraints. In this study, we propose a novel simulator-based method to approximately solve a CMDP problem without making any compromise on the safety constraints. We achieve this by decomposing the CMDP into a pair of MDPs; reconnaissance MDP and planning MDP. The purpose of reconnaissance MDP is to evaluate the set of actions that are safe, and the purpose of planning MDP is to maximize the return while using the actions authorized by reconnaissance MDP. RMDP can define a set of safe policies for any given set of safety constraint, and this set of safe policies can be used to solve another CMDP problem with different reward. Our method is not only computationally less demanding than the previous simulator-based approaches to CMDP, but also capable of finding a competitive reward-seeking policy in a high dimensional environment, including those involving multiple moving obstacles.

Tensor decomposition methods are widely used for model compression and fast inference in convolutional neural networks (CNNs). Although many decompositions are conceivable, only CP decomposition and a few others have been applied in practice, and no extensive comparisons have been made between available methods. Previous studies have not determined how many decompositions are available, nor which of them is optimal. In this study, we first characterize a decomposition class specific to CNNs by adopting a flexible graphical notation. The class includes such well-known CNN modules as depthwise separable convolution layers and bottleneck layers, but also previously unknown modules with nonlinear activations. We also experimentally compare the tradeoff between prediction accuracy and time/space complexity for modules found by enumerating all possible decompositions, or by using a neural architecture search. We find some nonlinear decompositions outperform existing ones., Comment: NeurIPS 2019

What is the role of unlabeled data in an inference problem, when the presumed underlying distribution is adversarially perturbed? To provide a concrete answer to this question, this paper unifies two major learning frameworks: Semi-Supervised Learning (SSL) and Distributionally Robust Learning (DRL). We develop a generalization theory for our framework based on a number of novel complexity measures, such as an adversarial extension of Rademacher complexity and its semi-supervised analogue. Moreover, our analysis is able to quantify the role of unlabeled data in the generalization under a more general condition compared to the existing theoretical works in SSL. Based on our framework, we also present a hybrid of DRL and EM algorithms that has a guaranteed convergence rate. When implemented with deep neural networks, our method shows a comparable performance to those of the state-of-the-art on a number of real-world benchmark datasets., Comment: 41 pages, 9 figures

Graph Neural Network (GNN) is a popular architecture for the analysis of chemical molecules, and it has numerous applications in material and medicinal science. Current lines of GNNs developed for molecular analysis, however, do not fit well on the training set, and their performance does not scale well with the complexity of the network. In this paper, we propose an auxiliary module to be attached to a GNN that can boost the representation power of the model without hindering with the original GNN architecture. Our auxiliary module can be attached to a wide variety of GNNs, including those that are used commonly in biochemical applications. With our auxiliary architecture, the performances of many GNNs used in practice improve more consistently, achieving the state-of-the-art performance on popular molecular graph datasets., Comment: Augmented experiments, title slightly modified

Exploration has been one of the greatest challenges in reinforcement learning (RL), which is a large obstacle in the application of RL to robotics. Even with state-of-the-art RL algorithms, building a well-learned agent often requires too many trials, mainly due to the difficulty of matching its actions with rewards in the distant future. A remedy for this is to train an agent with real-time feedback from a human observer who immediately gives rewards for some actions. This study tackles a series of challenges for introducing such a human-in-the-loop RL scheme. The first contribution of this work is our experiments with a precisely modeled human observer: binary, delay, stochasticity, unsustainability, and natural reaction. We also propose an RL method called DQN-TAMER, which efficiently uses both human feedback and distant rewards. We find that DQN-TAMER agents outperform their baselines in Maze and Taxi simulated environments. Furthermore, we demonstrate a real-world human-in-the-loop RL application where a camera automatically recognizes a user's facial expressions as feedback to the agent while the agent explores a maze.

Recent advances in graph convolutional networks have significantly improved the performance of chemical predictions, raising a new research question: "how do we explain the predictions of graph convolutional networks?" A possible approach to answer this question is to visualize evidence substructures responsible for the predictions. For chemical property prediction tasks, the sample size of the training data is often small and/or a label imbalance problem occurs, where a few samples belong to a single class and the majority of samples belong to the other classes. This can lead to uncertainty related to the learned parameters of the machine learning model. To address this uncertainty, we propose BayesGrad, utilizing the Bayesian predictive distribution, to define the importance of each node in an input graph, which is computed efficiently using the dropout technique. We demonstrate that BayesGrad successfully visualizes the substructures responsible for the label prediction in the artificial experiment, even when the sample size is small. Furthermore, we use a real dataset to evaluate the effectiveness of the visualization. The basic idea of BayesGrad is not limited to graph-structured data and can be applied to other data types.

This study presents a new lossy image compression method that utilizes the multi-scale features of natural images. Our model consists of two networks: multi-scale lossy autoencoder and parallel multi-scale lossless coder. The multi-scale lossy autoencoder extracts the multi-scale image features to quantized variables and the parallel multi-scale lossless coder enables rapid and accurate lossless coding of the quantized variables via encoding/decoding the variables in parallel. Our proposed model achieves comparable performance to the state-of-the-art model on Kodak and RAISE-1k dataset images, and it encodes a PNG image of size $768 \times 512$ in 70 ms with a single GPU and a single CPU process and decodes it into a high-fidelity image in approximately 200 ms., Comment: 15 pages, 15 figures

Many continuous control tasks have bounded action spaces. When policy gradient methods are applied to such tasks, out-of-bound actions need to be clipped before execution, while policies are usually optimized as if the actions are not clipped. We propose a policy gradient estimator that exploits the knowledge of actions being clipped to reduce the variance in estimation. We prove that our estimator, named clipped action policy gradient (CAPG), is unbiased and achieves lower variance than the conventional estimator that ignores action bounds. Experimental results demonstrate that CAPG generally outperforms the conventional estimator, indicating that it is a better policy gradient estimator for continuous control tasks. The source code is available at https://github.com/pfnet-research/capg., Comment: Accepted at ICML 2018

With the rapid increase of compound databases available in medicinal and material science, there is a growing need for learning representations of molecules in a semi-supervised manner. In this paper, we propose an unsupervised hierarchical feature extraction algorithm for molecules (or more generally, graph-structured objects with fixed number of types of nodes and edges), which is applicable to both unsupervised and semi-supervised tasks. Our method extends recently proposed Paragraph Vector algorithm and incorporates neural message passing to obtain hierarchical representations of subgraphs. We applied our method to an unsupervised task and demonstrated that it outperforms existing proposed methods in several benchmark datasets. We also experimentally showed that semi-supervised tasks enhanced predictive performance compared with supervised ones with labeled molecules only., Comment: 8 pages, 2 figures. Appeared as a poster presentation in workshop on Machine Learning for Molecules and Materials in NIPS 2017

We propose a new neural sequence model training method in which the objective function is defined by $\alpha$-divergence. We demonstrate that the objective function generalizes the maximum-likelihood (ML)-based and reinforcement learning (RL)-based objective functions as special cases (i.e., ML corresponds to $\alpha \to 0$ and RL to $\alpha \to1$). We also show that the gradient of the objective function can be considered a mixture of ML- and RL-based objective gradients. The experimental results of a machine translation task show that minimizing the objective function with $\alpha > 0$ outperforms $\alpha \to 0$, which corresponds to ML-based methods., Comment: 2017 ICML Workshop on Learning to Generate Natural Language (LGNL 2017)

We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local perturbation. Unlike adversarial training, our method defines the adversarial direction without label information and is hence applicable to semi-supervised learning. Because the directions in which we smooth the model are only "virtually" adversarial, we call our method virtual adversarial training (VAT). The computational cost of VAT is relatively low. For neural networks, the approximated gradient of virtual adversarial loss can be computed with no more than two pairs of forward- and back-propagations. In our experiments, we applied VAT to supervised and semi-supervised learning tasks on multiple benchmark datasets. With a simple enhancement of the algorithm based on the entropy minimization principle, our VAT achieves state-of-the-art performance for semi-supervised learning tasks on SVHN and CIFAR-10., Comment: To be appeared in IEEE Transactions on Pattern Analysis and Machine Intelligence