Organizational Unit:

Institute for Robotics and Intelligent Machines (IRIM)

Permanent Link

https://hdl.handle.net/1853/70657

Includes Organization(s)

Organizational Unit

Biorobotics and Human Modeling Lab

Organizational Unit

Humanoid Robotics Laboratory

Full item page

Publication Search Results

Now showing 1 - 10 of 10

A realistic benchmark for visual indoor place recognition

(Georgia Institute of Technology, 2009-08) Pronobis, A. ; Caputo, B. ; Jensfelt, Patric ; Christensen, Henrik I.

An important competence for a mobile robot system is the ability to localize and perform context interpretation. This is required to perform basic navigation and to facilitate local specific services. Recent advances in vision have made this modality a viable alternative to the traditional range sensors and visual place recognition algorithms emerged as a useful and widely applied tool for obtaining information about robot’s position. Several place recognition methods have been proposed using vision alone or combined with sonar and/or laser. This research calls for standard benchmark datasets for development, evaluation and comparison of solutions. To this end, this paper presents two carefully designed and annotated image databases augmented with an experimental procedure and extensive baseline evaluation. The databases were gathered in an uncontrolled indoor office environment using two mobile robots and a standard camera. The acquisition spanned across a time range of several months and different illumination and weather conditions. Thus, the databases are very well suited for evaluating the robustness of algorithms with respect to a broad range of variations, often occurring in real-world settings. We thoroughly assessed the databases with a purely appearance-based place recognition method based on Support Vector Machines and two types of rich visual features (global and local).
Learning about Objects with Human Teachers

(Georgia Institute of Technology, 2009) Thomaz, Andrea L. ; Cakmak, Maya

A general learning task for a robot in a new environment is to learn about objects and what actions/effects they afford. To approach this, we look at ways that a human partner can intuitively help the robot learn, Socially Guided Machine Learning. We present experiments conducted with our robot, Junior, and make six observations characterizing how people approached teaching about objects. We show that Junior successfully used transparency to mitigate errors. Finally, we present the impact of “social” versus “nonsocial” data sets when training SVM classifiers.
Curve Tracking Control for Autonomous Vehicles with Rigidly Mounted Range Sensors

(Georgia Institute of Technology, 2009) Kim, Jonghoek ; Zhang, Fumin ; Egerstedt, Magnus B.

In this paper, we present feedback control laws for an autonomous vehicle with rigidly mounted range sensors to track a desired curve. In particular, we consider a vehicle that has a group of rays around two center rays that are perpendicular to the velocity of the vehicle. Under such a sensor configuration, singularities are bound to occur in the curve tracking feedback control law when tracking concave curves. To overcome this singularity, we derive a hybrid strategy of switching between control laws when the vehicle gets close to singularities. Rigorous proof and extensive simulation results verify the validity of the proposed feedback control law.
Covariance Recovery from a Square Root Information Matrix for Data Association

(Georgia Institute of Technology, 2009) Kaess, Michael ; Dellaert, Frank

Data association is one of the core problems of simultaneous localization and mapping (SLAM), and it requires knowledge about the uncertainties of the estimation problem in the form of marginal covariances. However, it is often difficult to access these quantities without calculating the full and dense covariance matrix, which is prohibitively expensive. We present a dynamic programming algorithm for efficient recovery of the marginal covariances needed for data association. As input we use a square root information matrix as maintained by our incremental smoothing and mapping (iSAM) algorithm. The contributions beyond our previous work are an improved algorithm for recovering the marginal covariances and a more thorough treatment of data association now including the joint compatibility branch and bound (JCBB) algorithm. We further show how to make information theoretic decisions about measurements before actually taking the measurement, therefore allowing a reduction in estimation complexity by omitting uninformative measurements. We evaluate our work on simulated and real-world data.
Control of coordinated patterns for ocean sampling

(Georgia Institute of Technology, 2007) Zhang, Fumin ; Fratantoni, David M. ; Paley, Derek A. ; Lund, John M. ; Leonard, Naomi Ehrich

A class of underwater vehicles are modelled as Newtonian particles for navigation and control. We show a general method that controls cooperative Newtonian particles to generate patterns on closed smooth curves. These patterns are chosen for good sampling performance using mobile sensor networks. We measure the spacing between neighbouring particles by the relative curve phase along the curve. The distance between a particle and the desired curve is measured using an orbit function. The orbit value and the relative curve phase are then used as feedback to control motion of each particle. From an arbitrary initial configuration, the particles converge asymptotically to form an invariant pattern on the desired curves. We describe application of this method to control underwater gliders in a field experiment in Buzzards Bay, MA in March 2006.
Reactive Tuning of Target Estimate Accuracy in Multi-Sensor Data Fusion

(Georgia Institute of Technology, 2007-01) Xiong, Ning ; Christensen, Henrik I. ; Svensson, Per

Dealing with conflicting and target-specific requirements is an important issue in multi-sensor and multi-target tracking. This paper aims to allocate sensing resources among various targets in reaction to individual information requests. The approach proposed is to introduce agents for every relevant target responsible for its tracking. Such agents are expected to bargain with each other for a division of resources. A bilateral negotiation model is established for resource allocation in two-target tracking. The applications of agent negotiation to target covariance tuning are illustrated together with simulation results presented. Moreover, we suggest a way of organizing simultaneous one-to-one negotiations, making our negotiation model still applicable in scenarios of tracking more than two targets.
Measurement Errors in Visual Servoing

(Georgia Institute of Technology, 2006-10) Kryki, V. ; Kragic, Danica ; Christensen, Henrik I.

This paper addresses the issue of measurement errors in visual servoing. The error characteristics of the vision based state estimation and the associated uncertainty of the control are investigated. The major contribution is the analysis of the propagation of image error through pose estimation and visual servoing control law. Using the analysis, two classical visual servoing methods are evaluated: position-based and 2 1/2 D visual servoing. The evaluation offers a tool to build and analyze hybrid control systems such as switching or partitioning control.
Approximate Reasoning for Safety and Survivability of Planetary Rovers

(Georgia Institute of Technology, 2003-02) Tunstel, Edward ; Howard, Ayanna M.

Operational safety and health monitoring are critical matters for autonomous planetary rovers operating on remote and challenging terrain. This paper describes rover safety issues and presents an approximate reasoning approach to maintaining vehicle safety in a navigational context. The proposed rover safety module is composed of two distinct behaviors: safe attitude (pitch and roll) management and safe traction management. Fuzzy logic implementations of these behaviors on outdoor terrain is presented. Sensing of vehicle safety coupled with visual neural network-based perception of terrain quality are used to infer safe speeds during rover traversal. In addition, approximate reasoning for self-regulation of internal operating conditions is briefly discussed. The core theoretical foundations of the applied soft computing techniques is presented and supported by descriptions of field tests and laboratory experimental results. For autonomous rovers, the approach provides intrinsic safety cognizance and a capacity for reactive mitigation of navigation risks.
Inertial Vibration Damping Control of a Flexible Base Manipulator

(Georgia Institute of Technology, 2002-11) George, Lynnane E. ; Book, Wayne J.

A rigid (micro) robot mounted serially to the tip of a long, flexible (macro) manipulator is often used to increase reach capability, but flexibility in the macromanipulator can interfere with positioning accuracy. A rigid manipulator attached to a flexible but un actuated base was used to study a scheme to achieve positioning of the micromanipulator combined with enhanced vibration damping of the base. Ineltial interaction forces and torques acting between the robot and its base were modeled and studied to determine how to use them to damp the vibration. One issue is that there are locations in the workspace where the rigid robot loses its ability to create interactions in one or more degrees of freedom. These "ineltial singularities" are functions of the rigid robot's joint variables. A performance index was developed to predict the ability of the rigid robot to damp vibrations and will help ensure the robot is operating in joint space configurations favorable for inertial damping. It is shown that when the performance index is used along with the appropriate choice of feedback gains, the inertia effects, or those directly due to accelerating the robot's links, have the greatest influence on the interactions. By commanding the robot link's accelerations propOitional to the base velocity, vibration energy will be removed from the system. This signal is then added to the rigid robot's position control signal. Simulations of a three-degree of freedom anthropomorphic rigid robot mounted on a flexible base were developed and show the effectiveness of the control scheme. In addition, results from two degree of freedom vibration damping are included.
Rule-based reasoning and neural network perception for safe off-road robot mobility

(Georgia Institute of Technology, 2002-09) Tunstel, Edward ; Howard, Ayanna M. ; Seraji, Homayoun

Operational safety and health monitoring are critical matters for autonomous field mobile robots such as planetary rovers operating on challenging terrain. This paper describes relevant rover safety and health issues and presents an approach to maintaining vehicle safety in a mobility and navigation context. The proposed rover safety module is composed of two distinct components: safe attitude (pitch and roll) management and safe traction management. Fuzzy logic approaches to reasoning about safe attitude and traction management are presented, wherein inertial sensing of safety status and vision-based neural network perception of terrain quality are used to infer safe speeds of traversal. Results of initial field tests and laboratory experiments are also described. The approach provides an intrinsic safety cognizance and a capacity for reactive mitigation of robot mobility and navigation risks.