Search

In this paper, we introduce the k-Dubins Traveling Salesman Problem with Neighborhoods (k-DTSPN), the problem of planning efficient paths among target regions for multiple robots with bounded curvature constraints (Dubins vehicles). This paper presents two approaches for the problem. Firstly, we present a heuristic that solves it in two steps, based on classical techniques found in the literature. Secondly, we employ a Memetic Algorithm to solve both combinatorial and continuous phases of the problem in a combined manner. We provide formal analysis about both proposed techniques, presenting upper bounds to the length of the longest tour. Numerous trials in simulated environments were executed, providing statistical examination of the final results. [ABSTRACT FROM PUBLISHER]

Human gesture recognition is a challenging task with many applications. The popularization of real time depth sensors even diversifies potential applications to end-user natural user interface (NUI). The quality of such NUI highly depends on the robustness and execution speed of the gesture recognition. This work introduces a method for real-time gesture recognition from a noisy skeleton stream, such as the ones extracted from Kinect depth sensors. Each pose is described using a tailored angular representation of the skeleton joints. Those descriptors serve to identify key poses through a multi-class classifier derived from Support Vector learning machines. The gesture is labeled on-the-fly from the key pose sequence through a decision forest, that naturally performs the gesture time warping and avoids the requirement for an initial or neutral pose. The proposed method runs in real time and shows robustness in several experiments. [ABSTRACT FROM PUBLISHER]

This work proposes a novel RGB-D feature descriptor called Binary Appearance and Shape Elements (BASE) that efficiently combines intensity and shape information to improve the discriminative power and enable an enhanced and faster matching process. The new descriptor is used to align a set of RGB point clouds to generate dense three dimensional models of indoor environments. We compare the performance of state-of-the-art feature descriptors with the proposed descriptor for scene alignment through the registration of multiple indoor textured depth maps. Experimental results show that the proposed descriptor outperforms the other approaches in computational cost, memory consumption and match quality. Additionally, experiments based on cloud alignment show that the BASE descriptor is suitable to be used in the registration of RBG-D data even when the environment is partially illuminated. [ABSTRACT FROM PUBLISHER]

Recent advances in robotics have led to the development of autonomous vehicles that navigate in outdoor environments. A fundamental premise for a mobile robot to perform a navigation task in an efficient and safe way is to calculate the path previously to its execution. Several path planning algorithms are only concerned with finding a route between the initial and the goal position, without taking into account the characteristics of the vehicle that would eventually perform it. Another important issue to be considered is the cost of performing the path, since a shorter path cannot be the best choice depending on the terrain where the robot navigates. This paper presents a path planning methodology for nonholonomic vehicles with curvature constraints that takes into account the different characteristics of the terrain in the environment. [ABSTRACT FROM PUBLISHER]

The present work proposes and evaluates a technique for improving the Turtlebot mobile robot localization system for navigation in unknown structured environments. In our proposal, the localization is refined by using a dense artificial landmark setup fixed in the environment ceiling. Although the use of artificial landmarks restricts the applicability of this methodology, the proposed methodology has the advantage of not depending on a previous mapping of the landmarks distribution in the environment, which makes its adoption a simple process. [ABSTRACT FROM PUBLISHER]

Localization is a fundamental problem that arises in many potential applications. The use of wireless technologies to perform localization has been a trend in recent years. Most existing approaches use the received signal strength indication (RSSI) to localize. In general, one of the several existing wireless standards such as ZigBee, Bluetooth or Wi-Fi, is chosen as the target standard. In this paper we present an experimental study on the use of multiple wireless technologies to perform mobile robot localization in indoor environments. We use real ZigBee and Wi-Fi compliant devices. In our study we analyse results obtained by fusing robot odometry data with distance estimations between the robot and wireless beacons. These distances are estimated based on the RSSI obtained from radio frequency (RF) signals received from those technologies compliant devices. The extended kalman filter (EKF) is used to fuse these information. We show that robots equipped with multiple wireless interfaces from different technologies can achieve better localization in regions where the coverage of one technology is reduced (e.g., we show that the robot can maintain a reasonable localization accuracy even in areas where Wi-Fi coverage is very poor, due to the presence of Zigbee sensor nodes). We also present a discussion of advantages and challenges of using multiple wireless technologies to perform localization in indoor environments. [ABSTRACT FROM PUBLISHER]

Most of the approaches addressing cooperative transport consider that robots have prior information about the object. In this work the robot estimates the object's characteristics required for the transportation process. A range sensor is used to map the object and the power applied by the robot/manipulator motor is used to estimate the effort required to transport it via pushing or grasping. With this information the robot can decide how the object will be manipulated and if it will request help from other robots to perform the transportation. We present experimental results to evaluate the framework efficacy and limitations. The framework enable cooperation among the robots to carry out the proposed task. [ABSTRACT FROM PUBLISHER]

This work introduces a novel descriptor called Binary Robust Appearance and Normals Descriptor (BRAND), that efficiently combines appearance and geometric shape information from RGB-D images, and is largely invariant to rotation and scale transform. The proposed approach encodes point information as a binary string providing a descriptor that is suitable for applications that demand speed performance and low memory consumption. Results of several experiments demonstrate that as far as precision and robustness are con- cerned, BRAND achieves improved results when compared to state of the art descriptors based on texture, geometry and combination of both information. We also demonstrate that our descriptor is robust and provides reliable results in a registration task even when a sparsely textured and poorly illuminated scene is used. [ABSTRACT FROM PUBLISHER]

The ability to detect changes in the environment is an essential trait for robots commissioned to work in several applications. In surveillance, for instance, a robot needs to detect meaningful changes in the environment which is achieved by comparing current sensory data with previously acquired information from the environment. The large amount of sensory data, which are often complex and very noisy, explains the inherent difficulty of this task. As an attempt to tackle this hard problem, we present an efficient method to automatically segment 3D data, corrupted with noise and outliers, into an implicit volume bounded by a surface. The method makes it possible to efficiently apply Boolean operations to 3D data in order to detect changes and to update existing maps. We show that our approach is powerful, albeit simple, with linear time complexity. The method has been validated through several trials using mobile robots operating in real environments and their performance was compared to another state-of-art algorithm. Experimental results demonstrate the performance of the proposed method, both in accuracy and computational cost. [ABSTRACT FROM PUBLISHER]

Successful state-of-the-art object recognition techniques from images have been based on powerful methods, such as sparse representation, in order to replace the also popular vector quantization (VQ) approach. Recently, sparse coding, which is characterized by representing a signal in a sparse space, has raised the bar on several object recognition benchmarks. However, one serious drawback of sparse space based methods is that similar local features can be quantized into different visual words. We present in this paper a new method, called Sparse Spatial Coding (SSC), which combines a sparse coding dictionary learning, a spatial constraint coding stage and an online classification method to improve object recognition. An efficient new off-line classification algorithm is also presented. We overcome the problem of techniques which make use of sparse representation alone by generating the final representation with SSC and max pooling, presented for an online learning classifier. Experimental results obtained on the Caltech 101, Caltech 256, Corel 5000 and Corel 10000 databases, show that, to the best of our knowledge, our approach supersedes in accuracy the best published results to date on the same databases. As an extension, we also show high performance results on the MIT-67 indoor scene recognition dataset. [ABSTRACT FROM PUBLISHER]

A Wireless Sensor Network consists of several sensor nodes deployed in an environment having as primary goal to collect data. However, due to limited sensor communication range, oftentimes it is necessary to use a mobile node that will visit other nodes to gather up their collected data. This work addresses the problem of planning efficient paths for data collection by a mobile node modeled as a nonholonomic vehicle with curvature constraints. We propose an efficient algorithm to identify areas of intersection among the nodes RF footprints which will guide the identification of a smaller set of waypoints through which the vehicle needs to traverse in order to collect available data. Then, a metric similar to the classical Traveling Salesman Problem is used to determine the best circuit that includes all these collecting points. In order to reduce the total path length for the mobile node, a meta-heuristic is used. The classical Dubins' path technique is employed to generate a feasible tour for the vehicle and a new heuristic is used to generate the required orientation at the collecting points. The methodology was validated in a simulated environment. Our methodology outperforms the classical Alternating Algorithm and the best performing state-of-the-art algorithm. [ABSTRACT FROM PUBLISHER]

Many problems in computer vision and robotics rely on automatically determining point correspondences from two images. Due to issues such as illumination variations, uncontrolled acquisition conditions and noise, this is a challenging problem. This work presents a method that combines visual and shape information to perform point correspondences which is invariant to rotation and scaling transformations in the image and geometry domains. Experimental results show that our approach is a robust and computationally efficient technique compared with classic descriptors in the literature. [ABSTRACT FROM PUBLISHER]