January 26, 2020

3099 words 15 mins read

Paper Group ANR 1412

A Research Platform for Multi-Robot Dialogue with Humans. Cognitive and motor compliance in intentional human-robot interaction. Hypothesis-based Belief Planning for Dexterous Grasping. Road Damage Detection Acquisition System based on Deep Neural Networks for Physical Asset Management. Dual Heuristic Dynamic Programing Control of Grid-Connected Sy …

A Research Platform for Multi-Robot Dialogue with Humans


Title	A Research Platform for Multi-Robot Dialogue with Humans
Authors	Matthew Marge, Stephen Nogar, Cory J. Hayes, Stephanie M. Lukin, Jesse Bloecker, Eric Holder, Clare Voss
Abstract	This paper presents a research platform that supports spoken dialogue interaction with multiple robots. The demonstration showcases our crafted MultiBot testing scenario in which users can verbally issue search, navigate, and follow instructions to two robotic teammates: a simulated ground robot and an aerial robot. This flexible language and robotic platform takes advantage of existing tools for speech recognition and dialogue management that are compatible with new domains, and implements an inter-agent communication protocol (tactical behavior specification), where verbal instructions are encoded for tasks assigned to the appropriate robot.
Tasks	Dialogue Management, Speech Recognition
Published	2019-10-12
URL	https://arxiv.org/abs/1910.05624v1
PDF	https://arxiv.org/pdf/1910.05624v1.pdf
PWC	https://paperswithcode.com/paper/a-research-platform-for-multi-robot-dialogue-1
Repo
Framework

Cognitive and motor compliance in intentional human-robot interaction


Title	Cognitive and motor compliance in intentional human-robot interaction
Authors	Hendry Ferreira Chame, Jun Tani
Abstract	Embodiment and subjective experience in human-robot interaction are important aspects to consider when studying both natural cognition and adaptive robotics to human environments. Although several researches have focused on nonverbal communication and collaboration, the study of autonomous physical interaction has obtained less attention. From the perspective of neurorobotics, we investigate the relation between intentionality, motor compliance, cognitive compliance, and behavior emergence. We propose a variational model inspired by the principles of predictive coding and active inference to study intentionality and cognitive compliance, and an intermittent control concept for motor deliberation and compliance based on torque feed-back. Our experiments with the humanoid Torobo portrait interesting perspectives for the bio-inspired study of developmental and social processes.
Tasks
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01753v3
PDF	https://arxiv.org/pdf/1911.01753v3.pdf
PWC	https://paperswithcode.com/paper/cognitive-and-motor-compliance-in-intentional
Repo
Framework

Hypothesis-based Belief Planning for Dexterous Grasping


Title	Hypothesis-based Belief Planning for Dexterous Grasping
Authors	Claudio Zito, Valerio Ortenzi, Maxime Adjigble, Marek Kopicki, Rustam Stolkin, Jeremy L. Wyatt
Abstract	Belief space planning is a viable alternative to formalise partially observable control problems and, in the recent years, its application to robot manipulation problems has grown. However, this planning approach was tried successfully only on simplified control problems. In this paper, we apply belief space planning to the problem of planning dexterous reach-to-grasp trajectories under object pose uncertainty. In our framework, the robot perceives the object to be grasped on-the-fly as a point cloud and compute a full 6D, non-Gaussian distribution over the object’s pose (our belief space). The system has no limitations on the geometry of the object, i.e., non-convex objects can be represented, nor assumes that the point cloud is a complete representation of the object. A plan in the belief space is then created to reach and grasp the object, such that the information value of expected contacts along the trajectory is maximised to compensate for the pose uncertainty. If an unexpected contact occurs when performing the action, such information is used to refine the pose distribution and triggers a re-planning. Experimental results show that our planner (IR3ne) improves grasp reliability and compensates for the pose uncertainty such that it doubles the proportion of grasps that succeed on a first attempt.
Tasks
Published	2019-03-13
URL	http://arxiv.org/abs/1903.05517v1
PDF	http://arxiv.org/pdf/1903.05517v1.pdf
PWC	https://paperswithcode.com/paper/hypothesis-based-belief-planning-for
Repo
Framework

Road Damage Detection Acquisition System based on Deep Neural Networks for Physical Asset Management


Title	Road Damage Detection Acquisition System based on Deep Neural Networks for Physical Asset Management
Authors	A. A. Angulo, J. A. Vega-Fernández, L. M. Aguilar-Lobo, S. Natraj, G Ochoa-Ruiz
Abstract	Research on damage detection of road surfaces has been an active area of re-search, but most studies have focused so far on the detection of the presence of damages. However, in real-world scenarios, road managers need to clearly understand the type of damage and its extent in order to take effective action in advance or to allocate the necessary resources. Moreover, currently there are few uniform and openly available road damage datasets, leading to a lack of a common benchmark for road damage detection. Such dataset could be used in a great variety of applications; herein, it is intended to serve as the acquisition component of a physical asset management tool which can aid governments agencies for planning purposes, or by infrastructure mainte-nance companies. In this paper, we make two contributions to address these issues. First, we present a large-scale road damage dataset, which includes a more balanced and representative set of damages. This dataset is composed of 18,034 road damage images captured with a smartphone, with 45,435 in-stances road surface damages. Second, we trained different types of object detection methods, both traditional (an LBP-cascaded classifier) and deep learning-based, specifically, MobileNet and RetinaNet, which are amenable for embedded and mobile and implementations with an acceptable perfor-mance for many applications. We compare the accuracy and inference time of all these models with others in the state of the art.
Tasks	Object Detection, Road Damage Detection
Published	2019-09-19
URL	https://arxiv.org/abs/1909.08991v1
PDF	https://arxiv.org/pdf/1909.08991v1.pdf
PWC	https://paperswithcode.com/paper/road-damage-detection-acquisition-system
Repo
Framework

Dual Heuristic Dynamic Programing Control of Grid-Connected Synchronverters


Title	Dual Heuristic Dynamic Programing Control of Grid-Connected Synchronverters
Authors	Sepehr Saadatmand, Mohammad Saleh Sanjarinia, Pourya Shamsi, Mehdi Ferdowsi
Abstract	In this paper a new approach to control a grid-connected synchronverter by using a dual heuristic dynamic programing (DHP) design is presented. The disadvantages of conventional synchronverter controller such as the challenges to cope with nonlinearity, uncertainties, and non-inductive grids are discussed.To deal with the aforementioned challenges a neural network based adaptive critic design is introduced to optimize the associated cost function. The characteristic of the neural networks facilitates the performance under uncertainties and unknown parameters (for example different power angles). The proposed DHP design includes three neural networks: system NN, action NN, and critic NN. The simulation results compare the performance of the proposed DHP with a traditional PI-based design and with a neural network predictive controller. It is shown a well trained DHP design performs in a trajectory, which is more optimal compared to the other two controllers.
Tasks
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05191v1
PDF	https://arxiv.org/pdf/1908.05191v1.pdf
PWC	https://paperswithcode.com/paper/dual-heuristic-dynamic-programing-control-of
Repo
Framework

On Learning Density Aware Embeddings


Title	On Learning Density Aware Embeddings
Authors	Soumyadeep Ghosh, Richa Singh, Mayank Vatsa
Abstract	Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The proposed method, termed as Density Aware Metric Learning, enforces the model to learn embeddings that are pulled towards the most dense region of the clusters for each class. It is achieved by iteratively shifting the estimate of the center towards the dense region of the cluster thereby leading to faster convergence and higher generalizability. In addition to this, the approach is robust to noisy samples in the training data, often present as outliers. Detailed experiments and analysis on two challenging cross-modal face recognition databases and two popular object recognition databases exhibit the efficacy of the proposed approach. It has superior convergence, requires lesser training time, and yields better accuracies than several popular deep metric learning methods.
Tasks	Face Recognition, Metric Learning, Object Recognition
Published	2019-04-08
URL	http://arxiv.org/abs/1904.03911v1
PDF	http://arxiv.org/pdf/1904.03911v1.pdf
PWC	https://paperswithcode.com/paper/on-learning-density-aware-embeddings
Repo
Framework

Line-based Camera Pose Estimation in Point Cloud of Structured Environments


Title	Line-based Camera Pose Estimation in Point Cloud of Structured Environments
Authors	Huai Yu, Weikun Zhen, Wen Yang, Sebastian Scherer
Abstract	Accurate registration of 2D imagery with point clouds is a key technology for image-LiDAR point cloud fusion, camera to laser scanner calibration and camera localization. Despite continuous improvements, automatic registration of 2D and 3D data without using additional textured information still faces great challenges. In this paper, we propose a new 2D-3D registration method to estimate 2D-3D line feature correspondences and the camera pose in untextured point clouds of structured environments. Specifically, we first use geometric constraints between vanishing points and 3D parallel lines to compute all feasible camera rotations. Then, we utilize a hypothesis testing strategy to estimate the 2D-3D line correspondences and the translation vector. By checking the consistency with computed correspondences, the best rotation matrix can be found. Finally, the camera pose is further refined using non-linear optimization with all the 2D-3D line correspondences. The experimental results demonstrate the effectiveness of the proposed method on the synthetic and real dataset (outdoors and indoors) with repeated structures and rapid depth changes.
Tasks	Calibration, Camera Localization, Pose Estimation
Published	2019-11-23
URL	https://arxiv.org/abs/1912.05013v2
PDF	https://arxiv.org/pdf/1912.05013v2.pdf
PWC	https://paperswithcode.com/paper/line-based-camera-pose-estimation-in-point
Repo
Framework

Neural Conversational QA: Learning to Reason v.s. Exploiting Patterns


Title	Neural Conversational QA: Learning to Reason v.s. Exploiting Patterns
Authors	Abhishek Sharma, Danish Contractor, Harshit Kumar, Sachindra Joshi
Abstract	In this paper we work on the recently introduced ShARC task - a challenging form of conversational QA that requires reasoning over rules expressed in natural language. Attuned to the risk of superficial patterns in data being exploited by neural models to do well on benchmark tasks (Niven and Kao 2019), we conduct a series of probing experiments and demonstrate how current state-of-the-art models rely heavily on such patterns. To prevent models from learning based on the superficial clues, we modify the dataset by automatically generating new instances reducing the occurrences of those patterns. We also present a simple yet effective model that learns embedding representations to incorporate dialog history along with the previous answers to follow-up questions. We find that our model outperforms existing methods on all metrics, and the results show that the proposed model is more robust in dealing with spurious patterns and learns to reason meaningfully.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03759v1
PDF	https://arxiv.org/pdf/1909.03759v1.pdf
PWC	https://paperswithcode.com/paper/neural-conversational-qa-learning-to-reason
Repo
Framework

A Survey of Machine Learning Applied to Computer Architecture Design


Title	A Survey of Machine Learning Applied to Computer Architecture Design
Authors	Drew D. Penney, Lizhong Chen
Abstract	Machine learning has enabled significant benefits in diverse fields, but, with a few exceptions, has had limited impact on computer architecture. Recent work, however, has explored broader applicability for design, optimization, and simulation. Notably, machine learning based strategies often surpass prior state-of-the-art analytical, heuristic, and human-expert approaches. This paper reviews machine learning applied system-wide to simulation and run-time optimization, and in many individual components, including memory systems, branch predictors, networks-on-chip, and GPUs. The paper further analyzes current practice to highlight useful design strategies and identify areas for future work, based on optimized implementation strategies, opportune extensions to existing work, and ambitious long term possibilities. Taken together, these strategies and techniques present a promising future for increasingly automated architectural design.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12373v1
PDF	https://arxiv.org/pdf/1909.12373v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-machine-learning-applied-to
Repo
Framework

EnforceNet: Monocular Camera Localization in Large Scale Indoor Sparse LiDAR Point Cloud


Title	EnforceNet: Monocular Camera Localization in Large Scale Indoor Sparse LiDAR Point Cloud
Authors	Yu Chen, Guan Wang
Abstract	Pose estimation is a fundamental building block for robotic applications such as autonomous vehicles, UAV, and large scale augmented reality. It is also a prohibitive factor for those applications to be in mass production, since the state-of-the-art, centimeter-level pose estimation often requires long mapping procedures and expensive localization sensors, e.g. LiDAR and high precision GPS/IMU, etc. To overcome the cost barrier, we propose a neural network based solution to localize a consumer degree RGB camera within a prior sparse LiDAR map with comparable centimeter-level precision. We achieved it by introducing a novel network module, which we call resistor module, to enforce the network generalize better, predicts more accurately, and converge faster. Such results are benchmarked by several datasets we collected in the large scale indoor parking garage scenes. We plan to open both the data and the code for the community to join the effort to advance this field.
Tasks	Autonomous Vehicles, Camera Localization, Pose Estimation
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07160v1
PDF	https://arxiv.org/pdf/1907.07160v1.pdf
PWC	https://paperswithcode.com/paper/enforcenet-monocular-camera-localization-in
Repo
Framework

CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Images


Title	CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Images
Authors	Yanning Zhou, Simon Graham, Navid Alemi Koohbanani, Muhammad Shaban, Pheng-Ann Heng, Nasir Rajpoot
Abstract	Colorectal cancer (CRC) grading is typically carried out by assessing the degree of gland formation within histology images. To do this, it is important to consider the overall tissue micro-environment by assessing the cell-level information along with the morphology of the gland. However, current automated methods for CRC grading typically utilise small image patches and therefore fail to incorporate the entire tissue micro-architecture for grading purposes. To overcome the challenges of CRC grading, we present a novel cell-graph convolutional neural network (CGC-Net) that converts each large histology image into a graph, where each node is represented by a nucleus within the original image and cellular interactions are denoted as edges between these nodes according to node similarity. The CGC-Net utilises nuclear appearance features in addition to the spatial location of nodes to further boost the performance of the algorithm. To enable nodes to fuse multi-scale information, we introduce Adaptive GraphSage, which is a graph convolution technique that combines multi-level features in a data-driven way. Furthermore, to deal with redundancy in the graph, we propose a sampling technique that removes nodes in areas of dense nuclear activity. We show that modeling the image as a graph enables us to effectively consider a much larger image (around 16$\times$ larger) than traditional patch-based approaches and model the complex structure of the tissue micro-environment. We construct cell graphs with an average of over 3,000 nodes on a large CRC histology image dataset and report state-of-the-art results as compared to recent patch-based as well as contextual patch-based techniques, demonstrating the effectiveness of our method.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01068v1
PDF	https://arxiv.org/pdf/1909.01068v1.pdf
PWC	https://paperswithcode.com/paper/cgc-net-cell-graph-convolutional-network-for
Repo
Framework

Structural Design Using Laplacian Shells


Title	Structural Design Using Laplacian Shells
Authors	Erva Ulu, James McCann, Levent Burak Kara
Abstract	We introduce a method to design lightweight shell objects that are structurally robust under the external forces they may experience during use. Given an input 3D model and a general description of the external forces, our algorithm generates a structurally-sound minimum weight shell object. Our approach works by altering the local shell thickness repeatedly based on the stresses that develop inside the object. A key issue in shell design is that large thickness values might result in self-intersections on the inner boundary creating a significant computational challenge during optimization. To address this, we propose a shape parametrization based on the solution to the Laplace’s equation that guarantees smooth and intersection-free shell boundaries. Combined with our gradient-free optimization algorithm, our method provides a practical solution to the structural design of hollow objects with a single inner cavity. We demonstrate our method on a variety of problems with arbitrary 3D models under complex force configurations and validate its performance with physical experiments.
Tasks
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10669v1
PDF	https://arxiv.org/pdf/1906.10669v1.pdf
PWC	https://paperswithcode.com/paper/structural-design-using-laplacian-shells
Repo
Framework

Calibration of Encoder Decoder Models for Neural Machine Translation


Title	Calibration of Encoder Decoder Models for Neural Machine Translation
Authors	Aviral Kumar, Sunita Sarawagi
Abstract	We study the calibration of several state of the art neural machine translation(NMT) systems built on attention-based encoder-decoder models. For structured outputs like in NMT, calibration is important not just for reliable confidence with predictions, but also for proper functioning of beam-search inference. We show that most modern NMT models are surprisingly miscalibrated even when conditioned on the true previous tokens. Our investigation leads to two main reasons – severe miscalibration of EOS (end of sequence marker) and suppression of attention uncertainty. We design recalibration methods based on these signals and demonstrate improved accuracy, better sequence-level calibration, and more intuitive results from beam-search.
Tasks	Calibration, Machine Translation
Published	2019-03-03
URL	http://arxiv.org/abs/1903.00802v1
PDF	http://arxiv.org/pdf/1903.00802v1.pdf
PWC	https://paperswithcode.com/paper/calibration-of-encoder-decoder-models-for
Repo
Framework

A Scalable Test Suite for Continuous Dynamic Multiobjective Optimisation


Title	A Scalable Test Suite for Continuous Dynamic Multiobjective Optimisation
Authors	Shouyong Jiang, Marcus Kaiser, Shengxiang Yang, Stefanos Kollias, Natalio Krasnogor
Abstract	Dynamic multiobjective optimisation has gained increasing attention in recent years. Test problems are of great importance in order to facilitate the development of advanced algorithms that can handle dynamic environments well. However, many of existing dynamic multiobjective test problems have not been rigorously constructed and analysed, which may induce some unexpected bias when they are used for algorithmic analysis. In this paper, some of these biases are identified after a review of widely used test problems. These include poor scalability of objectives and, more importantly, problematic overemphasis of static properties rather than dynamics making it difficult to draw accurate conclusion about the strengths and weaknesses of the algorithms studied. A diverse set of dynamics and features is then highlighted that a good test suite should have. We further develop a scalable continuous test suite, which includes a number of dynamics or features that have been rarely considered in literature but frequently occur in real life. It is demonstrated with empirical studies that the proposed test suite is more challenging to the dynamic multiobjective optimisation algorithms found in the literature. The test suite can also test algorithms in ways that existing test suites can not.
Tasks
Published	2019-03-06
URL	http://arxiv.org/abs/1903.02510v1
PDF	http://arxiv.org/pdf/1903.02510v1.pdf
PWC	https://paperswithcode.com/paper/a-scalable-test-suite-for-continuous-dynamic
Repo
Framework

A New Framework for Distance and Kernel-based Metrics in High Dimensions


Title	A New Framework for Distance and Kernel-based Metrics in High Dimensions
Authors	Shubhadeep Chakraborty, Xianyang Zhang
Abstract	The paper presents new metrics to quantify and test for (i) the equality of distributions and (ii) the independence between two high-dimensional random vectors. We show that the energy distance based on the usual Euclidean distance cannot completely characterize the homogeneity of two high-dimensional distributions in the sense that it only detects the equality of means and the traces of covariance matrices in the high-dimensional setup. We propose a new class of metrics which inherits the desirable properties of the energy distance and maximum mean discrepancy/(generalized) distance covariance and the Hilbert-Schmidt Independence Criterion in the low-dimensional setting and is capable of detecting the homogeneity of/completely characterizing independence between the low-dimensional marginal distributions in the high dimensional setup. We further propose t-tests based on the new metrics to perform high-dimensional two-sample testing/independence testing and study their asymptotic behavior under both high dimension low sample size (HDLSS) and high dimension medium sample size (HDMSS) setups. The computational complexity of the t-tests only grows linearly with the dimension and thus is scalable to very high dimensional data. We demonstrate the superior power behavior of the proposed tests for homogeneity of distributions and independence via both simulated and real datasets.
Tasks
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13469v1
PDF	https://arxiv.org/pdf/1909.13469v1.pdf
PWC	https://paperswithcode.com/paper/a-new-framework-for-distance-and-kernel-based
Repo
Framework