Skip to Content


Home > Intelligent Autonomous Vehicles > 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Conference Title: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Series Title: Intelligent Autonomous Vehicles, Volume# 6 | Part# 1
Publisher: International Federation of Automatic Control
Venue, City, Country: Conference Center Pierre Baudis, France
National Organizing Committee Chair: Devy, Michel
International Program Committee Chair: Devy, Michel; Asama, Hajime; Salichs, Miguel; Boverie, Serge
Conference Editor: Devy, Michel
ISBN: 978-3-902661-65-4
ISSN:  
Start Date: 2007-09-03
End Date: 2007-09-05
> >|

There are 95 articles

Paper Title Authors Updated  
Welcome and Introduction

» Quick View » View Full Details

2007-09-03
Authors: None
Abstract:
Keywords:
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.90001
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: ---
Technical Program

» Quick View » View Full Details

2007-09-03
Authors: None
Abstract:
Keywords:
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.90002
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: ---
On taxis for control and its qualitative solution on mobile robots

» Quick View » View Full Details

Rañó, Iñaki 2007-09-03
Authors: Rañó, Iñaki
Abstract: Animals show a great ability to move on real world. Taxis is a motion control technique used by simple animals. In this paper mathematical equations are derived from a taxis model for non-holonomous vehicles. A qualitative technique is applied to analyse the solutions of the nonlinear derived motion equations. To validate the model and qualitative analysis several simulations are performed.
Keywords: biologically inspired system,taxis model,nonholonomous vehicle,nonlinear qualitative analysis
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00003
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 1-6
A proposal for parameter tuning in fractional MRAC. application to the lateral control of an autonomous vehicle

» Quick View » View Full Details

Suárez, José Ignacio; Vinagre, Blas M. 2007-09-03
Authors: Suárez, José Ignacio; Vinagre, Blas M.
Abstract: A proposal for tuning the parameters in a fractional MRAC scheme is presented in this paper. The method is applied to the lateral control of an autonomous vehicle. We study the influence of the parameters on the system stability and in which manner these parameters change the system performance, both on time and frecuency domains. Integer and fractional order controllers are compared in several situations.
Keywords: autonomous vehicle,adaptive control,fractional controller,paramaters tuning
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00004
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 7-12
Motion planning and optimal control of an autonomous VTOL aircraft

» Quick View » View Full Details

Ailon, Amit 2007-09-03
Authors: Ailon, Amit
Abstract: This study presents a simple algorithm for motion-planning and state-to-state control of a Vertical Take-Off and Landing (VTOL) aircraft. The proposed motion-planning procedure is based on the solution of a linear algebraic equation. The resulting schemes are useful for flight control of an autonomous VTOL aircraft in case the objective is to transfer the system from a given state to a prescribed target. The proposed controller minimizes a selected quadratic index of performance. The solution to the (sub) optimal control problem is simple and reduces to the evaluation of a minimum point of a function of several variables.
Keywords: vertical take-off and landing aircraft,motion planning,controllability,state-to-state control,optimal control
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00005
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 13-18
Non-singular path-following control of wheeled robots with actuator velocity saturations

» Quick View » View Full Details

Lapierre, L.; Indiveri, G. 2007-09-03
Authors: Lapierre, L.; Indiveri, G.
Abstract: This paper proposes a kinematics path-following algorithm that drives a unicycle-type robot to a desired path, respecting velocity saturation constraint on the actuators. The solution, based on an extension of a globally convergent nonsingular path following solution, is formally shown. Simple conditions for the selection of the gains are provided.
Keywords:
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00006
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 19-24
RRT-D: A motion planning approach for autonomus vehicles based on wireless sensor network information

» Quick View » View Full Details

Gómez-Bravo, F.; López, D.; Cuesta, F.,... 2007-09-03
Authors: Gómez-Bravo, F.; López, D.; Cuesta, F.; Ollero, A.
Abstract: This paper focuses on motion planning of an autonomous vehicle considering the information provided by a wireless sensor network. The method takes into account the kinematics constraints providing a feasible path composed of basic movements and manoeuvres. A centralized or distributed strategy can be adopted to implement the method.
Keywords: mobile robots,nonholonomic systems,motion planning,sensor network,autonomous vehicles
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00007
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 25-30
A goal-directed reactive obstacle avoidance strategy with global proofs

» Quick View » View Full Details

Antich, Javier; Ortiz, Alberto 2007-09-03
Authors: Antich, Javier; Ortiz, Alberto
Abstract: Reactive mobile robot navigation based on potential field methods has shown to be a good solution for dealing with both unknown and dynamic scenarios, where timely responses are required. Unfortunately, the complexity of the tasks which can be successfully carried out is restricted by the inherent shortcomings of the approach such as trapping situations due to local minima, difficulties passing among closely spaced obstacles, oscillations in narrow corridors, etc... The first of the aforementioned limitations was fully overcome in (Antich and Ortiz, 2005) by applying the two new principles of Traversability and Tenacity in the context of artificial potential fields. As a result, navigation was achieved in quite difficult scenarios, even including maze-like environments. In this paper, continuing that previous work, it is intended to step forward by ensuring, whenever possible, that the target point is attained for any mission. To this end, a Bug derivative algorithm is incorporated into the approach.
Keywords: potential functions,reactive motion planning,Bug-like algorithms
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00008
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 31-36
Learning to coordinate in topological navigation tasks

» Quick View » View Full Details

Melo, Francisco S.; Ribeiro, Isabel 2007-09-03
Authors: Melo, Francisco S.; Ribeiro, Isabel
Abstract: In this paper we address multi-robot coordinated navigation from a topological perspective. The adopted topological representation of the environment leads naturally to a Markov game model to describe the interaction of the multiple robots in the environment. In this setting, we combine the Q-learning algorithm with a powerful coordination mechanism (biased adaptive play). We show that this combined algorithm, coordinated Q-learning, converges to an optimal, coordinated solution for the navigation problem. This implies that the team of robots is able to coordinate without using any communication protocol to enforce the coordination. We illustrate our method in some simple navigation tasks.
Keywords: topological navigation,Markov games,biased adaptive play,coordination
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00009
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 37-42
Cooperative route searching system considering dynamics of traffic flow

» Quick View » View Full Details

Tsutsumi, Keita; Yakoh, Takahiro 2007-09-03
Authors: Tsutsumi, Keita; Yakoh, Takahiro
Abstract: We proposed the new route searching system that can help us get the destination the earlier. This system predicts traffic condition for each road, and offers us the best route based on our travel plans. We confirm the validity and efficiency of this system by performing simulations. These simulations show the prediction works in many roads, and the travelling efficiency looks substantially better than that of two conventional systems. Moreover, as the number of vehicles using this system increases, the amount of traffic congestion decreases.
Keywords: navigation systems,traffic engineering,road traffic control,routing algorithms
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00010
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 43-48
Probabilistic filtering of sonar data

» Quick View » View Full Details

Burguera, Antoni; González, Yolanda; Oliver, Gabriel 2007-09-03
Authors: Burguera, Antoni; González, Yolanda; Oliver, Gabriel
Abstract: In this paper we propose an iterative probabilistic sonar filtering technique able to decide whether a sonar reading is good or not. This technique is applied to standard time-of-flight sonars, and may be used in real time applications. A non-iterative approach based on a voting schema is also discussed, reducing even more the computational cost. The technique does not depend on any specific mapping, localization or navigation technique. Thus, a large range of applications is possible. A quality metric to evaluate the goodness of sets of raw readings is also presented. Experimental results demonstrate the fast convergence of the algorithm, as well as its robustness and the quality of the filtered readings.
Keywords: map building,sonar,filtering
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00011
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 49-54
Interference modelization in multi-robot auction methods

» Quick View » View Full Details

Guerrero, José; Oliver, Gabriel 2007-09-03
Authors: Guerrero, José; Oliver, Gabriel
Abstract: Task allocation is one of the main problems in multi-robot systems, very specially when the robots form coalitions. To get a good task allocation, we have to take into account, among other factors, the interference effect or the interaction between robots. Interference is not easy to modelize because it depends on a lot of dynamic factors. This paper models the interference impact using auction methods and support vector regression. We will show how the performance of the auction utility function can be improved if the interference impact is included in it. This method has been tested using transport like tasks taking into account an specific interference called physical interference.
Keywords: multi-robot,task allocation,coalition,auction,transport,learning
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00012
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 55-60
A method for extracting lines and their uncertainty from acoustic underwater images for SLAM

» Quick View » View Full Details

Ribas, David; Ridao, Pere; Neira, José,... 2007-09-03
Authors: Ribas, David; Ridao, Pere; Neira, José; Tardós, Juan Domingo
Abstract: The extraction of reliable features is a key issue for autonomous underwater vehicle navigation. Imaging sonars can produce acoustic images of the surroundings of the vehicle. Despite of the noise, the phantom echoes and reflections, we believe that they are a good source for features since they can work in turbid water, where other sensors like vision fail. Moreover, they can cover wide areas, increasing the number of features visible within a scan. This work presents an algorithm to extract linear features from underwater structured environments including as major contributions a sonar sensor model, an adapted implementation of the Hough transform and a novel procedure to estimate feature uncertainty.
Keywords: robot navigation,sensors,feature extraction,Hough transform
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00013
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 61-66
Sensor fault diagnosis of autonomous underwater vehicle based on nonlinear principal component analysis

» Quick View » View Full Details

Zhu, Daqi; Gu, Wei 2007-09-03
Authors: Zhu, Daqi; Gu, Wei
Abstract: An approach of sensor fault diagnosis based on a NLPCA (Nonlinear Principal Component Analysis) model is described in this paper. Firstly, in order to perform NLPCA, a double RBF(Radial Basis Function) neural network is introduced; Secondly, NLPCA fault detection and isolation algorithm is presented; Finally, A simulation example of sensor fault diagnosis of autonomous underwater vehicle is given to show the performances of the proposed approach.
Keywords: fault diagnosis,autonomous underwater vehicle,nonlinear PCA,neural networks
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00014
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 67-71
Objective directed control using local minimisation for an autonomous underwater vehicle

» Quick View » View Full Details

Alminde, Lars; Bendtsen, Jan D.; Stoustrup, Jakob,... 2007-09-03
Authors: Alminde, Lars; Bendtsen, Jan D.; Stoustrup, Jakob; Pettersen, Kristin Y.
Abstract: This paper presents a new method for control of complex MIMO plants based on a quantised state description. The control algorithm solves a minimisation problem for a set of user defined convex control objective functions with the plant dynamics as a constraint. The solution makes use of local linear models that are effectively calculated by propagating the state on-line using a quantised state description. The method is demonstrated on a model of an autonomous underwater vehicle.
Keywords: non-linear MIMO control,optimisation,quantised state system
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00015
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 72-77
Fast prototyping of an autonomous underwater vehicle with the cubesystem

» Quick View » View Full Details

Albu, Diana; Birk, Andras; Dobrev, Petar,... 2007-09-03
Authors: Albu, Diana; Birk, Andras; Dobrev, Petar; Gammoh, Farah; Giurgiu, Andrei; Mihut, Sergiu-Cristian; Minzu, Bogdan; Pascanu, Razvan; Schwertfeger, Sören; Stan, Alexandru; Videv, Stefan
Abstract: This paper describes the Jacobs autonomous underwater vehicle (Jacobs-Atlas-AUV). The vehicle has been largely developed using the CubeSystem, a collection of hard- and software components for fast robot prototyping. The CubeSystem has previously been used for the development of various mobile robots, but never for an underwater system. As the development of the Jacobs-Atlas-AUV shows, a significant amount of component reuse across significantly different application domains is possible for autonomous robots.
Keywords: autonomous underwater robotics,fast prototyping
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00016
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 78-83
Cooperative path-following of multiple surface vessels with parametric model uncertainty and in the presence of ocean currents

» Quick View » View Full Details

Almeida, João; Silvestre, Carlos; Pascoal, António 2007-09-03
Authors: Almeida, João; Silvestre, Carlos; Pascoal, António
Abstract: This paper addresses the problem of cooperative path-following of multiple autonomous vehicles. Stated briefly, the problem consists in steering a group of vehicles along specified paths, while keeping a desired spatial formation arrangement. For a given class of autonomous surface vessels, it is shown how Lyapunov based techniques and graph theory can be brought together to design a decentralised control structure where the vehicle dynamics and the constraints imposed by the topology of the inter-vehicle communication network are explicitly taken into account. Path-following for each vehicle amounts to reducing an appropriately defined geometric error to zero, in the presence of ocean currents and parametric model uncertainty. Vehicle cooperation is achieved by adjusting the speed of each vehicle along its path according to information exchanged on the positions of a subset of the other vehicles, as determined by the communication topology adopted. Global stability and convergence of the closed-loop system are guaranteed.
Keywords: cooperative motion control,path-following,autonomous surface vehicles,graph theory,nonlinear control,adaptive control
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00017
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 84-89
A kinematic virtual potentials trajectory planner for AUV-S

» Quick View » View Full Details

Barisic, Matko; Vukic, Zoran; Miskovic, Nikola 2007-09-03
Authors: Barisic, Matko; Vukic, Zoran; Miskovic, Nikola
Abstract: This paper deals with trajectory planning for an autonomous, noncommunicating submerged vehicle (AUV). Most maneuvering, esp. that related to obstacle avoidance, in a typical mission scenario for an AUV consists of motion at single submerged depth. Therefore a trajectory planning scheme operating in 2D has sufficient merit and applicability. A scheme for trajectory planning with cross-layer features, such as implicit inclusion of obstacle-avoidance and forming up with other moving agents, is developed in a simulated environment, at a kinematic level. The trajectory planner is based on virtual potentials, an approach that guarantees good extendibility, scalability and performance in a hard-real-time hardware-in-the-loop system.
Keywords: autonomous mobile robots,trajectory planning,gradients,robot kinematics,robot navigation
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00018
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 90-95
ANSER: Airport night surveillance expert robot

» Quick View » View Full Details

Capezio, Francesco; Mastrogiovanni, Fulvio; Sgorbissa, Antonio,... 2007-09-03
Authors: Capezio, Francesco; Mastrogiovanni, Fulvio; Sgorbissa, Antonio; Zaccaria, Renato
Abstract: The paper describes the ANSER project, focusing on mobile robots for autonomous surveillance in civilian airports and similar wide outdoor areas. The robot is able to navigate autonomously both outdoor and indoor, with a localization subsystem composed only of a single Non-Differential GPS and a laser scanner (inertial sensors are absents). The paper shows that an augmented state vector approach and an Extended Kalman Filter can be successfully employed to estimate the colored components in GPS noise, thus getting closer to the conditions for the EKF to be applicable. The overall system capabilities are described with respect to a typical surveillance scenario, where ANSER is requested to recognize unexpected events through a laser rangefinder for outdoor security, and to consequently alert a human supervisor.
Keywords: mobile robotics,localization,state estimation
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00019
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 96-101
Deterministic path planning and navigation for an autonomous fork lift truck

» Quick View » View Full Details

Hentschel, Matthias; Lecking, Daniel; Wagner, Bernardo 2007-09-03
Authors: Hentschel, Matthias; Lecking, Daniel; Wagner, Bernardo
Abstract: This paper introduces a novel trajectory planner for flexible material handling with an autonomous fork lift truck. Based on a set of predefined waypoints, a continuous-curvature path is computed by a concatenation of line and polar spline segments. Regarding the nonholonomic constraints of the vehicle, the trajectory as well as an associated speed profile is generated. As flexible path planning is required for this kind of application, trajectory generation is not only limited to the base points of a single route. From a list of multiple predefined routes the proper set of waypoints is chosen for guiding the vehicle to a desired destination. Furthermore, a graph-based routing algorithm enables the combination of different routes for trajectory generation. Following the description of the trajectory planner for single and multiple paths, experimental results with speeds up to 1.7 m/s demonstrate the effectiveness of this approach.
Keywords: trajectory planning,autonomous mobile robots,automated guided vehicles
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00020
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 102-107
RIOL—Robotic inspection over power lines

» Quick View » View Full Details

Tavares, Luís; Sequeira, João Silva 2007-09-03
Authors: Tavares, Luís; Sequeira, João Silva
Abstract: This paper describes ongoing work on a prototype robot capable of moving on electric power lines executing monitoring tasks. The inspection of the power lines infrastructure, forest fire surveillance and wildlife study are the some of the potential applications. The robot is composed by a central body with three serial arms. Two of these are used to provide motion, using a statically stable variation of the brachiation movement, whereas the third arm is used to insure stability and assisting in the overtaking of obstacles in the lines. In addition, this third arm helps maintaining the torques required by the other two arms within reasonable values. Two vertical rotation joints allow the robot to perform curves and control its center of mass. The paper presents basic simulation results and details of the prototype under construction.
Keywords: robot kinematics,robot dynamics,power lines
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00021
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 108-113
Application of neural networks based ANARX structure to backing up control of a truck-trailer

» Quick View » View Full Details

Belikov, Juri; Petlenkov, Eduard; Nõmm, Sven 2007-09-03
Authors: Belikov, Juri; Petlenkov, Eduard; Nõmm, Sven
Abstract: Combination of NN-based modelling and dynamic feedback linearization is proposed in present paper as a solution for the problem of backing up control of a truck-trailer. Backing up truck-trailer is modelled by NN based Additive Nonlinear Autoregressive Exogenous model which is linearized by dynamic output feedback.
Keywords: truck-trailer,neural networks- based modelling,dynamic output feedback linearization
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00022
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 114-118
Fast vision-based localization for outdoor robots using a combination of global image features

» Quick View » View Full Details

Weiss, Christian; Masselli, Andreas; Zell, Andreas 2007-09-03
Authors: Weiss, Christian; Masselli, Andreas; Zell, Andreas
Abstract: In this paper, we present a geometrical localization method based on a combination of global image features. Our method represents each image by two feature vectors. The first feature vector is a Weighted Gradient Orientation Histogram (WGOH). The second feature vector is a Weighted Grid Integral Invariant (WGII) feature vector based on Integral Invariants. For localization, we use a particle filter which updates the weights of the particles based on image similarities calculated from the two feature vectors. We evaluate our approach on outdoor images of two different areas and under varying illumination and compare it to a SIFT-based approach. The comparison shows that the SIFT approach is slightly more exact than our method, but our method is more than four times faster than the SIFT approach and allows a localization frequency of more than 2 Hz.
Keywords: outdoor localization,integral invariants,WGOH,SIFT
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00023
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 119-124
Efficient global localization by searching a bit-encoded graph

» Quick View » View Full Details

Segundo, P. San; Rodríguez-Losada, D.; Galán, R.,... 2007-09-03
Authors: Segundo, P. San; Rodríguez-Losada, D.; Galán, R.; Matía, F.; Jiménez, A.
Abstract: Global localization is the problem of finding a totally unknown robot pose given a known map and a set of observations relative to the robot. This is the combinatorial correspondence problem between map landmarks and observations, and its complete solution is an NP-hard problem that makes it computationally intractable when the size of the map increases. We propose the use of bit encoded graphs that take advantage of bit parallelism when solving instances of the deeply studied in graph theory Maximum Clique Problem (MCP). We have implemented and compared our solution with standard branch and bound heuristic search over the space of possible associations. Although the computational complexity of our algorithm is still exponential because it is complete, our results prove an impressive reduction of two orders of magnitude in required processing time thanks to the efficient underlying model, making it possible to deal with previously computationally intractable scenarios. Moreover, it is the first time (up to our knowledge) that this kind of technique is used in the robotics domain and it could possibly be applied to other problems such as path planning.
Keywords: bitboards,global localization,maximum clique,search,algorithm
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00024
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 125-130
An integrated framework for simultaneous robot and sensor network localization

» Quick View » View Full Details

Gasparri, Andrea; Panzieri, Stefano; Pascucci, Federica,... 2007-09-03
Authors: Gasparri, Andrea; Panzieri, Stefano; Pascucci, Federica; Ulivi, Giovanni
Abstract: Localization has been recognized as one of the most significant problems in mobile robotics. A robot must have a knowledge of its position in an environment in order to correctly perform almost any task. Moreover, having accurate information about the nodes positions turns out to be substantial in a sensor network context. In fact, several middle-ware services often rely on location knowledge to properly operate. In this paper, an overall scenario in which a robot is moving within a collaborative sensor network is considered. The aim is to provide an unified framework in which the robot can localize itself gathering information coming from the network, while nodes simultaneously try to find out their location. Simulation are provided in order to validate the effectiveness of the proposed framework.
Keywords: mobile robotics,sensor networks,evolutionary algorithms,EKF
Digital Object Identifier (DOI): 10.3182/20070903-3-FR-2921.00025
Conference: 6th IFAC Symposium on Intelligent Autonomous Vehicles (2007)
Location: Conference Center Pierre Baudis, France
Start Date: Mon Sep 03 2007 - End Date: Wed Sep 05 2007
Page Numbers: 131-136
> >|