January 31, 2020

3581 words 17 mins read

Paper Group ANR 142

Convergence analysis of Tikhonov regularization for non-linear statistical inverse learning problems. Prediction of Bottleneck Points for Manipulation Planning in Cluttered Environment using a 3D Convolutional Neural Network. Multiple Sclerosis Lesion Synthesis in MRI using an encoder-decoder U-NET. Task-Motion Planning for Navigation in Belief Spa …

Convergence analysis of Tikhonov regularization for non-linear statistical inverse learning problems


Title	Convergence analysis of Tikhonov regularization for non-linear statistical inverse learning problems
Authors	Abhishake Rastogi, Gilles Blanchard, Peter Mathé
Abstract	We study a non-linear statistical inverse learning problem, where we observe the noisy image of a quantity through a non-linear operator at some random design points. We consider the widely used Tikhonov regularization (or method of regularization, MOR) approach to reconstruct the estimator of the quantity for the non-linear ill-posed inverse problem. The estimator is defined as the minimizer of a Tikhonov functional, which is the sum of a data misfit term and a quadratic penalty term. We develop a theoretical analysis for the minimizer of the Tikhonov regularization scheme using the ansatz of reproducing kernel Hilbert spaces. We discuss optimal rates of convergence for the proposed scheme, uniformly over classes of admissible solutions, defined through appropriate source conditions.
Tasks
Published	2019-02-14
URL	http://arxiv.org/abs/1902.05404v2
PDF	http://arxiv.org/pdf/1902.05404v2.pdf
PWC	https://paperswithcode.com/paper/convergence-analysis-of-tikhonov
Repo
Framework

Prediction of Bottleneck Points for Manipulation Planning in Cluttered Environment using a 3D Convolutional Neural Network


Title	Prediction of Bottleneck Points for Manipulation Planning in Cluttered Environment using a 3D Convolutional Neural Network
Authors	Indraneel Patil, B. K. Rout, V. Kalaichelvi
Abstract	Latest research in industrial robotics is aimed at making human robot collaboration possible seamlessly. For this purpose, industrial robots are expected to work on the fly in unstructured and cluttered environments and hence the subject of perception driven motion planning plays a vital role. Sampling based motion planners are proven to be the most effective for such high dimensional planning problems with real time constraints. Unluckily random stochastic samplers suffer from the phenomenon of ‘narrow passages’ or bottleneck regions which need targeted sampling to improve their convergence rate. Also identifying these bottleneck regions in a diverse set of planning problems is a challenge. In this paper an attempt has been made to address these two problems by designing an intelligent ‘bottleneck guided’ heuristic for a Rapidly Exploring Random Tree Star (RRT) planner which is based on relevant context extracted from the planning scenario using a 3D Convolutional Neural Network and it is also proven that the proposed technique generalises to unseen problem instances. This paper benchmarks the technique (bottleneck guided RRT) against a 10% Goal biased RRT star planner, shows significant improvement in planning time and memory requirement and uses ABB 1410 industrial manipulator as a platform for implantation and validation of the results.
Tasks	Motion Planning
Published	2019-11-12
URL	https://arxiv.org/abs/1911.04676v1
PDF	https://arxiv.org/pdf/1911.04676v1.pdf
PWC	https://paperswithcode.com/paper/prediction-of-bottleneck-points-for
Repo
Framework

Multiple Sclerosis Lesion Synthesis in MRI using an encoder-decoder U-NET


Title	Multiple Sclerosis Lesion Synthesis in MRI using an encoder-decoder U-NET
Authors	Mostafa Salem, Sergi Valverde, Mariano Cabezas, Deborah Pareto, Arnau Oliver, Joaquim Salvi, Àlex Rovira, Xavier Lladó
Abstract	In this paper, we propose generating synthetic multiple sclerosis (MS) lesions on MRI images with the final aim to improve the performance of supervised machine learning algorithms, therefore avoiding the problem of the lack of available ground truth. We propose a two-input two-output fully convolutional neural network model for MS lesion synthesis in MRI images. The lesion information is encoded as discrete binary intensity level masks passed to the model and stacked with the input images. The model is trained end-to-end without the need for manually annotating the lesions in the training set. We then perform the generation of synthetic lesions on healthy images via registration of patient images, which are subsequently used for data augmentation to increase the performance for supervised MS lesion detection algorithms. Our pipeline is evaluated on MS patient data from an in-house clinical dataset and the public ISBI2015 challenge dataset. The evaluation is based on measuring the similarities between the real and the synthetic images as well as in terms of lesion detection performance by segmenting both the original and synthetic images individually using a state-of-the-art segmentation framework. We also demonstrate the usage of synthetic MS lesions generated on healthy images as data augmentation. We analyze a scenario of limited training data (one-image training) to demonstrate the effect of the data augmentation on both datasets. Our results significantly show the effectiveness of the usage of synthetic MS lesion images. For the ISBI2015 challenge, our one-image model trained using only a single image plus the synthetic data augmentation strategy showed a performance similar to that of other CNN methods that were fully trained using the entire training set, yielding a comparable human expert rater performance
Tasks	Data Augmentation
Published	2019-01-17
URL	http://arxiv.org/abs/1901.05733v1
PDF	http://arxiv.org/pdf/1901.05733v1.pdf
PWC	https://paperswithcode.com/paper/multiple-sclerosis-lesion-synthesis-in-mri
Repo
Framework


Title	Task-Motion Planning for Navigation in Belief Space
Authors	Antony Thomas, Fulvio Mastrogiovanni, Marco Baglietto
Abstract	We present an integrated Task-Motion Planning (TMP) framework for navigation in large-scale environment. Autonomous robots operating in real world complex scenarios require planning in the discrete (task) space and the continuous (motion) space. In knowledge intensive domains, on the one hand, a robot has to reason at the highest-level, for example the regions to navigate to; on the other hand, the feasibility of the respective navigation tasks have to be checked at the execution level. This presents a need for motion-planning-aware task planners. We discuss a probabilistically complete approach that leverages this task-motion interaction for navigating in indoor domains, returning a plan that is optimal at the task-level. Furthermore, our framework is intended for motion planning under motion and sensing uncertainty, which is formally known as belief space planning. The underlying methodology is validated with a simulated office environment in Gazebo. In addition, we discuss the limitations and provide suggestions for improvements and future work.
Tasks	Motion Planning
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11683v1
PDF	https://arxiv.org/pdf/1910.11683v1.pdf
PWC	https://paperswithcode.com/paper/task-motion-planning-for-navigation-in-belief
Repo
Framework

MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction


Title	MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
Authors	Yuning Chai, Benjamin Sapp, Mayank Bansal, Dragomir Anguelov
Abstract	Predicting human behavior is a difficult and crucial task required for motion planning. It is challenging in large part due to the highly uncertain and multi-modal set of possible outcomes in real-world domains such as autonomous driving. Beyond single MAP trajectory prediction, obtaining an accurate probability distribution of the future is an area of active interest. We present MultiPath, which leverages a fixed set of future state-sequence anchors that correspond to modes of the trajectory distribution. At inference, our model predicts a discrete distribution over the anchors and, for each anchor, regresses offsets from anchor waypoints along with uncertainties, yielding a Gaussian mixture at each time step. Our model is efficient, requiring only one forward inference pass to obtain multi-modal future distributions, and the output is parametric, allowing compact communication and analytical probabilistic queries. We show on several datasets that our model achieves more accurate predictions, and compared to sampling baselines, does so with an order of magnitude fewer trajectories.
Tasks	Autonomous Driving, Motion Planning, Trajectory Prediction
Published	2019-10-12
URL	https://arxiv.org/abs/1910.05449v1
PDF	https://arxiv.org/pdf/1910.05449v1.pdf
PWC	https://paperswithcode.com/paper/multipath-multiple-probabilistic-anchor
Repo
Framework

Multi-Vehicle Interaction Scenarios Generation with Interpretable Traffic Primitives and Gaussian Process Regression


Title	Multi-Vehicle Interaction Scenarios Generation with Interpretable Traffic Primitives and Gaussian Process Regression
Authors	Weiyang Zhang, Wenshuo Wang, Ding Zhao
Abstract	Generating multi-vehicle interaction scenarios can benefit motion planning and decision making of autonomous vehicles when on-road data is insufficient. This paper presents an efficient approach to generate varied multi-vehicle interaction scenarios that can both adapt to different road geometries and inherit the key interaction patterns in real-world driving. Towards this end, the available multi-vehicle interaction scenarios are temporally segmented into several interpretable fundamental building blocks, called traffic primitives, via the Bayesian nonparametric learning. Then, the changepoints of traffic primitives are transformed into the desired road to generate collision-free interaction trajectories through a sampling-based path planning algorithm. The Gaussian process regression is finally introduced to control the variance and smoothness of the generated multi-vehicle interaction trajectories. Experiments with simulation results of three typical multi-vehicle trajectories at different road conditions are carried out. The experimental results demonstrate that our proposed method can generate a bunch of human-like multi-vehicle interaction trajectories that can fit different road conditions remaining the key interaction patterns of agents in the provided scenarios, which is import to the development of autonomous vehicles.
Tasks	Autonomous Vehicles, Decision Making, Motion Planning
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03633v1
PDF	https://arxiv.org/pdf/1910.03633v1.pdf
PWC	https://paperswithcode.com/paper/multi-vehicle-interaction-scenarios
Repo
Framework

Distributed Attack-Robust Submodular Maximization for Multi-Robot Planning


Title	Distributed Attack-Robust Submodular Maximization for Multi-Robot Planning
Authors	Lifeng Zhou, Vasileios Tzoumas, George J. Pappas, Pratap Tokekar
Abstract	We aim to guard swarm-robotics applications against denial-of-service (DoS) failures/attacks that result in withdrawals of robots. We focus on applications requiring the selection of actions for each robot, among a set of available ones, e.g., which trajectory to follow. Such applications are central in large-scale robotic/control applications, e.g., multi-robot motion planning for target tracking. But the current attack-robust algorithms are centralized, and scale quadratically with the problem size (e.g., number of robots). Thus, in this paper, we propose a general-purpose distributed algorithm towards robust optimization at scale, with local communications only. We name it distributed robust maximization (DRM). DRM proposes a divide-and-conquer approach that distributively partitions the problem among K cliques of robots. The cliques optimize in parallel, independently of each other. That way, DRM also offers significant computational speed-ups up to 1/K^2 the running time of its centralized counterparts. K depends on the robots’ communication range, which is given as input to DRM. DRM also achieves a close-to-optimal performance, equal to the guaranteed performance of its centralized counterparts. We demonstrate DRM’s performance in both Gazebo and MATLAB simulations, in scenarios of active target tracking with swarms of robots. We observe DRM achieves significant computational speed-ups (it is 3 to 4 orders faster) and, yet, nearly matches the tracking performance of its centralized counterparts.
Tasks	Motion Planning
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01208v2
PDF	https://arxiv.org/pdf/1910.01208v2.pdf
PWC	https://paperswithcode.com/paper/distributed-attack-robust-submodular
Repo
Framework

Distributed Online Convex Optimization with Time-Varying Coupled Inequality Constraints


Title	Distributed Online Convex Optimization with Time-Varying Coupled Inequality Constraints
Authors	Xinlei Yi, Xiuxian Li, Lihua Xie, Karl H. Johansson
Abstract	This paper considers distributed online optimization with time-varying coupled inequality constraints. The global objective function is composed of local convex cost and regularization functions and the coupled constraint function is the sum of local convex functions. A distributed online primal-dual dynamic mirror descent algorithm is proposed to solve this problem, where the local cost, regularization, and constraint functions are held privately and revealed only after each time slot. Without assuming Slater’s condition, we first derive regret and constraint violation bounds for the algorithm and show how they depend on the stepsize sequences, the accumulated dynamic variation of the comparator sequence, the number of agents, and the network connectivity. As a result, under some natural decreasing stepsize sequences, we prove that the algorithm achieves sublinear dynamic regret and constraint violation if the accumulated dynamic variation of the optimal sequence also grows sublinearly. We also prove that the algorithm achieves sublinear static regret and constraint violation under mild conditions. Assuming Slater’s condition, we show that the algorithm achieves smaller bounds on the constraint violation. In addition, smaller bounds on the static regret are achieved when the objective function is strongly convex. Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results.
Tasks
Published	2019-03-06
URL	https://arxiv.org/abs/1903.04277v2
PDF	https://arxiv.org/pdf/1903.04277v2.pdf
PWC	https://paperswithcode.com/paper/distributed-online-convex-optimization-with
Repo
Framework

Adversarial Feature Training for Generalizable Robotic Visuomotor Control


Title	Adversarial Feature Training for Generalizable Robotic Visuomotor Control
Authors	Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt
Abstract	Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it’s application to visuomotor robotic policy training has been limited because of the challenge of large-scale data collection when working with physical hardware. A suitable visuomotor policy should perform well not just for the task-setup it has been trained for, but also for all varieties of the task, including novel objects at different viewpoints surrounded by task-irrelevant objects. However, it is impractical for a robotic setup to sufficiently collect interactive samples in a RL framework to generalize well to novel aspects of a task. In this work, we demonstrate that by using adversarial training for domain transfer, it is possible to train visuomotor policies based on RL frameworks, and then transfer the acquired policy to other novel task domains. We propose to leverage the deep RL capabilities to learn complex visuomotor skills for uncomplicated task setups, and then exploit transfer learning to generalize to new task domains provided only still images of the task in the target domain. We evaluate our method on two real robotic tasks, picking and pouring, and compare it to a number of prior works, demonstrating its superiority.
Tasks	Transfer Learning
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07745v1
PDF	https://arxiv.org/pdf/1909.07745v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-feature-training-for
Repo
Framework

A XGBoost risk model via feature selection and Bayesian hyper-parameter optimization


Title	A XGBoost risk model via feature selection and Bayesian hyper-parameter optimization
Authors	Yan Wang, Xuelei Sherry Ni
Abstract	This paper aims to explore models based on the extreme gradient boosting (XGBoost) approach for business risk classification. Feature selection (FS) algorithms and hyper-parameter optimizations are simultaneously considered during model training. The five most commonly used FS methods including weight by Gini, weight by Chi-square, hierarchical variable clustering, weight by correlation, and weight by information are applied to alleviate the effect of redundant features. Two hyper-parameter optimization approaches, random search (RS) and Bayesian tree-structured Parzen Estimator (TPE), are applied in XGBoost. The effect of different FS and hyper-parameter optimization methods on the model performance are investigated by the Wilcoxon Signed Rank Test. The performance of XGBoost is compared to the traditionally utilized logistic regression (LR) model in terms of classification accuracy, area under the curve (AUC), recall, and F1 score obtained from the 10-fold cross validation. Results show that hierarchical clustering is the optimal FS method for LR while weight by Chi-square achieves the best performance in XG-Boost. Both TPE and RS optimization in XGBoost outperform LR significantly. TPE optimization shows a superiority over RS since it results in a significantly higher accuracy and a marginally higher AUC, recall and F1 score. Furthermore, XGBoost with TPE tuning shows a lower variability than the RS method. Finally, the ranking of feature importance based on XGBoost enhances the model interpretation. Therefore, XGBoost with Bayesian TPE hyper-parameter optimization serves as an operative while powerful approach for business risk modeling.
Tasks	Feature Importance, Feature Selection
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08433v1
PDF	http://arxiv.org/pdf/1901.08433v1.pdf
PWC	https://paperswithcode.com/paper/a-xgboost-risk-model-via-feature-selection
Repo
Framework

Satisficing Mentalizing: Bayesian Models of Theory of Mind Reasoning in Scenarios with Different Uncertainties


Title	Satisficing Mentalizing: Bayesian Models of Theory of Mind Reasoning in Scenarios with Different Uncertainties
Authors	Jan Pöppel, Stefan Kopp
Abstract	The ability to interpret the mental state of another agent based on its behavior, also called Theory of Mind (ToM), is crucial for humans in any kind of social interaction. Artificial systems, such as intelligent assistants, would also greatly benefit from such mentalizing capabilities. However, humans and systems alike are bound by limitations in their available computational resources. This raises the need for satisficing mentalizing, reconciling accuracy and efficiency in mental state inference that is good enough for a given situation. In this paper, we present different Bayesian models of ToM reasoning and evaluate them based on actual human behavior data that were generated under different kinds of uncertainties. We propose a Switching approach that combines specialized models, embodying simplifying presumptions, in order to achieve a more statisficing mentalizing compared to a Full Bayesian ToM model.
Tasks
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10419v1
PDF	https://arxiv.org/pdf/1909.10419v1.pdf
PWC	https://paperswithcode.com/paper/190910419
Repo
Framework

Scratch that! An Evolution-based Adversarial Attack against Neural Networks


Title	Scratch that! An Evolution-based Adversarial Attack against Neural Networks
Authors	Malhar Jere, Briland Hitaj, Gabriela Ciocarlie, Farinaz Koushanfar
Abstract	Recent research has shown that Deep Neural Networks (DNNs) for image classification are vulnerable to adversarial attacks. However, most works on adversarial samples utilize sub-perceptual noise that, while invisible or slightly visible to humans, often covers the entire image. Additionally, most of these attacks often require knowledge of the neural network architecture and its parameters, and the ability to calculate the gradients of the parameters with respect to the inputs. In this work, we show that it is possible to attack neural networks in a highly restricted threat setting, where attackers have no knowledge of the neural network (i.e., in a black-box setting) and can only modify highly localized adversarial noise in the form of randomly chosen straight lines or scratches. Our Adversarial Scratches attack method covers only 1-2% of the image pixels and are generated using the Covariance Matrix Adaptation Evolutionary Strategy, a purely black-box method that does not require knowledge of the neural network architecture and its gradients. Against ImageNet models, Adversarial Scratches requires 3 times fewer queries than GenAttack (without any optimizations) and 73 times fewer queries than ZOO, both prior state-of-the-art black-box attacks. We successfully deceive state-of-the-art Inception-v3, ResNet-50 and VGG-19 models trained on ImageNet with deceiving rates of 75.8%, 62.7%, and 45% respectively, with fewer queries than several state-of-the-art black-box attacks, while modifying less than 2% of the image pixels. Additionally, we provide a new threat scenario for neural networks, demonstrate a new attack surface that can be used to perform adversarial attacks, and discuss its potential implications.
Tasks	Adversarial Attack, Image Classification
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02316v1
PDF	https://arxiv.org/pdf/1912.02316v1.pdf
PWC	https://paperswithcode.com/paper/scratch-that-an-evolution-based-adversarial
Repo
Framework

Region-Wise Attack: On Efficient Generation of Robust Physical Adversarial Examples


Title	Region-Wise Attack: On Efficient Generation of Robust Physical Adversarial Examples
Authors	Bo Luo, Qiang Xu
Abstract	Deep neural networks (DNNs) are shown to be susceptible to adversarial example attacks. Most existing works achieve this malicious objective by crafting subtle pixel-wise perturbations, and they are difficult to launch in the physical world due to inevitable transformations (e.g., different photographic distances and angles). Recently, there are a few research works on generating physical adversarial examples, but they generally require the details of the model a priori, which is often impractical. In this work, we propose a novel physical adversarial attack for arbitrary black-box DNN models, namely Region-Wise Attack. To be specific, we present how to efficiently search for region-wise perturbations to the inputs and determine their shapes, locations and colors via both top-down and bottom-up techniques. In addition, we introduce two fine-tuning techniques to further improve the robustness of our attack. Experimental results demonstrate the efficacy and robustness of the proposed Region-Wise Attack in real world.
Tasks	Adversarial Attack
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02598v1
PDF	https://arxiv.org/pdf/1912.02598v1.pdf
PWC	https://paperswithcode.com/paper/region-wise-attack-on-efficient-generation-of
Repo
Framework

Reflective-AR Display: An Interaction Methodology for Virtual-Real Alignment in Medical Robotics


Title	Reflective-AR Display: An Interaction Methodology for Virtual-Real Alignment in Medical Robotics
Authors	Javad Fotouhi, Tianyu Song, Arian Mehrfard, Giacomo Taylor, Qiaochu Wang, Fengfang Xian, Alejandro Martin-Gomez, Bernhard Fuerst, Mehran Armand, Mathias Unberath, Nassir Navab
Abstract	Robot-assisted minimally invasive surgery has shown to improve patient outcomes, as well as reduce complications and recovery time for several clinical applications. While increasingly configurable robotic arms can maximize reach and avoid collisions in cluttered environments, positioning them appropriately during surgery is complicated because safety regulations prevent automatic driving. We propose a head-mounted display (HMD) based augmented reality (AR) system designed to guide optimal surgical arm set up. The staff equipped with HMD aligns the robot with its planned virtual counterpart. In this user-centric setting, the main challenge is the perspective ambiguities hindering such collaborative robotic solution. To overcome this challenge, we introduce a novel registration concept for intuitive alignment of AR content to its physical counterpart by providing a multi-view AR experience via reflective-AR displays that simultaneously show the augmentations from multiple viewpoints. Using this system, users can visualize different perspectives while actively adjusting the pose to determine the registration transformation that most closely superimposes the virtual onto the real. The experimental results demonstrate improvement in the interactive alignment of a virtual and real robot when using a reflective-AR display. We also present measurements from configuring a robotic manipulator in a simulated trocar placement surgery using the AR guidance methodology.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.10138v2
PDF	https://arxiv.org/pdf/1907.10138v2.pdf
PWC	https://paperswithcode.com/paper/reflective-ar-display-an-interaction
Repo
Framework

Learning When Not to Answer: A Ternary Reward Structure for Reinforcement Learning based Question Answering


Title	Learning When Not to Answer: A Ternary Reward Structure for Reinforcement Learning based Question Answering
Authors	Fréderic Godin, Anjishnu Kumar, Arpit Mittal
Abstract	In this paper, we investigate the challenges of using reinforcement learning agents for question-answering over knowledge graphs for real-world applications. We examine the performance metrics used by state-of-the-art systems and determine that they are inadequate for such settings. More specifically, they do not evaluate the systems correctly for situations when there is no answer available and thus agents optimized for these metrics are poor at modeling confidence. We introduce a simple new performance metric for evaluating question-answering agents that is more representative of practical usage conditions, and optimize for this metric by extending the binary reward structure used in prior work to a ternary reward structure which also rewards an agent for not answering a question rather than giving an incorrect answer. We show that this can drastically improve the precision of answered questions while only not answering a limited number of previously correctly answered questions. Employing a supervised learning strategy using depth-first-search paths to bootstrap the reinforcement learning algorithm further improves performance.
Tasks	Knowledge Graphs, Question Answering
Published	2019-02-26
URL	http://arxiv.org/abs/1902.10236v2
PDF	http://arxiv.org/pdf/1902.10236v2.pdf
PWC	https://paperswithcode.com/paper/using-ternary-rewards-to-reason-over
Repo
Framework