Abstract

In this paper, we present a framework for generating smooth and stable trajectories for wheeled mobile robots moving on uneven terrains. Instead of relying on static stability measures, the paper incorporates velocity and acceleration based constraints like no-slip and permanent wheel ground contact conditions in the planning framework. The paper solves this complicated problem in a computationally efficient manner with full 3D dynamics of the robot. The two major aspects of the proposed work are: Firstly, closed form functional relationships are derived which describes the 6 dof evolution of the robot’s state on an arbitrary 2.5D uneven terrain. This enables us to have a fast evaluation of robot’s dynamics along any candidate trajectory. Secondly, a novel concept of non-linear time scaling is introduced through which simple algebraic relations defining the bounds on velocities and accelerations are obtained. Moreover, non-linear time scaling also provides a new approach for manipulating velocities and accelerations along given geometric paths. It is thus exploited to obtain stable velocity and acceleration profiles. Extensive simulation results are presented to demonstrate the efficacy of the proposed methodology.

Abstract

Curb detection is a critical component of driver assistance and autonomous driving systems. In this paper, we present a discriminative approach to the problem of curb detection under diverse road conditions. We define curbs as the intersection of drivable and non-drivable area which are classified using dense Conditional random fields(CRF). In our method, we fuse output of a neural network used for pixel-wise semantic segmentation with depth and color information from stereo cameras. CRF fuses the output of a deep model and height information available in stereo data and provides improved segmentation. Further we introduce temporal smoothness using a weighted average of Segnet output and output from a probabilistic voxel grid as our unary potential. Finally, we show improvements over the current state of the art neural networks. Our proposed method shows accurate results over large range of variations in curb curvature and appearance, without the need of retraining the model for the specific dataset.

Abstract

Frontier detection is a critical component in autonomous exploration, wherein the robot decides the next best location to move in order to continue its mapping process. The existing frontier detection methods require dense reconstruction which is difficult to attain in a poorly textured indoor environment using a monocular camera. In this effort, we present an alternate method of detecting frontiers during the course of robot motion that circumvents the requirement of dense mapping. Based on the observation that frontiers typically occur around areas with sudden change in texture (zero-crossings), we propose a novel linear chain Conditional Random Field(CRF) formulation that is able to detect the presence or absence of frontier regions around such areas. We use cues like spread of 3D points and scene change around these areas as an observation to CRF. We demonstrate that this method gives us more relevant frontiers compared to other monocular camera based methods in the literature. Finally, we present results in an indoor environment, wherein frontiers are reliably detected around walls leading to new corridors, doors leading to new rooms or corridors and tables and other objects that open up to a new space in rooms.

Abstract

Recently, the interest in Micro Aerial Vehicles (MAVs) and their autonomous flights has increased tremendously and significant advances have been made. The monocular camera has turned out to be most popular sensing modality for MAVs as it is light-weight, does not consume more power, and encodes rich information about the environment around. In this paper, we present DeepFly, our framework for autonomous navigation of a quadcopter equipped with monocular camera. The navigable space detection and waypoint selection are fundamental components of autonomous navigation system. They have broader meaning than just detecting and avoiding immediate obstacles. Finding the navigable space emphasizes equally on avoiding obstacles and detecting ideal regions to move next to. The ideal region can be defined by two properties: 1) All the points in the region have approximately same high depth value and 2) The area covered by the points of the region in the disparity map is considerably large. The waypoints selected from these navigable spaces assure collision-free path which is safer than path obtained from other waypoint selection methods which do not consider neighboring information. In our approach, we obtain a dense disparity map by performing a translation maneuver. This disparity map is input to a deep neural network which predicts bounding boxes for multiple navigable regions. Our deep convolutional neural network with shortcut connections regresses variable number of outputs without any complex architectural add on. Our autonomous navigation approach has been successfully tested in both indoors and outdoors environment and in range of lighting conditions.

Abstract

Autonomous navigation of generic monocular quadcopter in the indoor environment requires sophisticated approaches for perception, planning and control. This paper presents a system which enables a miniature quadcopter with a frontal monocular camera to autonomously navigate and explore the unknown indoor environment. Initially, the system estimates dense depth map of the environment from a single video frame using our proposed novel supervised Hierarchical Structured Learning (hsl) technique, which yields both high accuracy levels and better generalization. The proposed hsl approach discretizes the overall depth range into multiple sets. It structures these sets hierarchically and recursively through partitioning the set of classes into two subsets with subsets representing apportioned depth range of the parent set, forming a binary tree. The binary classification method is applied to each internal node of binary tree separately using Support Vector Machine (svm). Whereas, the depth estimation of each pixel of the image starts from the root node in top-down approach, classifying repetitively till it reaches any of the leaf node representing its estimated depth. The generated depth map is provided as an input to Convolutional Neural Network (cnn), which generates flight planning commands. Finally, trajectory planning and control module employs a convex programming technique to generate collision-free minimum time trajectory which follows these flight planning commands and produces appropriate control inputs for the quadcopter. The results convey unequivocally the advantages of depth perception by hsl, while repeatable flights of successful nature in typical indoor corridors confirm the efficacy of the pipeline.

Abstract

Interactive visualization and analysis of the class boundaries is important because it tells us how and why the classes differ. However, the problem of modeling the boundary of classes of arbitrary size, shape and density is challenging. The boundary of a class should not be limited to the points/shape which encloses the points within the class but it should be, the points/shape which encloses the region of influence of a class. The "region of influence" refers to the space around the class where any point lying within the region is likely to be classified to the class based on a nearest neighbor classifier. We have developed interactive boundary visualization toolkit for classified datasets which provides insights about the classifier model used on the dataset. Our algorithm first generates a candidate boundary set for each class based on reverse k-nearest neighbors approach and extends this boundary iteratively through the region of influence of the class. Further, we present these boundary points enclosing the region of influence as a linear approximated shape using triangulation techniques. We show experimental results on 2D and 3D datasets.

Abstract

Periodic-frequent patterns (or itemsets) are an important class of regularities that exist in a transactional database. Finding these patterns involves discovering all frequent patterns that satisfy the user specified maximum periodicity constraint. This constraint controls the maximum inter-arrival time of a pattern in a database. The time complexity to measure periodicity of a pattern is O(n), where n represents the number of timestamps at which the corresponding pattern has appeared in a database. As unusually represents a high value in voluminous databases, determining the periodicity of every candidate pattern in the itemset lattice makes the periodic-frequent pattern mining a computationally expensive process. This paper introduces a novel approach to address this problem. Our approach determines the periodic interestingness of a pattern by adopting greedy search. The basic idea of our approach is to discover all periodic-frequent patterns by eliminating a periodic patterns based on suboptimal solutions. The best and worst case time complexities of our approach to determine the periodic interestingness of a frequent pattern are O(1) and O(n), respectively. We introduce two pruning techniques and propose a pattern-growth algorithm to find these patterns efficiently. Experimental results show that our algorithm is runtime efficient and highly scalable as well.

Abstract

n the banner advertising scenario, an advertiser aims to reach the maximum number of potential visitors and a publisher tries to meet the requests of increased number of advertisers to maximize the revenue. In the literature, a model was introduced to extract the knowledge of coverage patterns from transactional database. In this paper, we propose an ad slots allocation approach by extending the notion of coverage patterns to select distinct sets of ad slots to meet the requests of multiple advertisers. The preliminary experimental results on a real world dataset show that the proposed approach meets the requests of increased number of advertisers when compared with the baseline approach of allocation.

Abstract

Community-driven Question Answering (Q&A) platforms are gaining popularity now-a-days and the number of posts on such platforms are increasing tremendously. Thus, the challenge to keep these platforms noise-free is attracting the interest of research community. Stack Overflow is one such popular computer programming related Q&A platform. The established users on Stack Overflow have learnt the accept-able format and scope of questions in due course. Even if their questions get closed, they are aware of the required ed-its, therefore the chances of their questions being reopened increases. On the other hand, non-established users have not adapted to the Stack Overflow system and find difficulty in editing their closed questions. In this work, we aim to identify features which help differentiate editing approaches of established and non-established users, and motivate the need of recommendation model. Such a recommendation model can assist every user to edit their closed questions leveraging the edit-style of the established users of the platform.

Abstract

Recommender system (RS) helps customers to select appropriate products from millions of products and has become a key component in e-commerce systems. Collaborative filtering (CF) based approaches are widely employed to build RSs. In CF, recommendation to the target user is computed after forming the corresponding neighbour-hood of users. Neighborhood of a target user is extracted based on the similarity between the product rating vector of the target user and the product rating vectors of individual users. In CF, the methodology employed for neighborhood formation influences the performance. In this paper, we have made an effort to improve the performance of CF by proposing a different approach to compute recommendations by considering two kinds of neighborhood. One is the neighborhood by considering the product ratings of the user as a single vector and the other is based on the neighborhood of the corresponding virtual users. For the target user,the virtual users are formed by dividing the ratings based on the category of products. We have proposed a combined approach to compute better recommendations by considering both kinds of neighborhoods.The experiments results on real world Movie Lens dataset show that the proposed approach improves the performance over CF.