Authors: Luke Ng; Chris Clark; Jan Huissoon; Gabriele D'Eleuterio

Abstract: Research in the collaborative driving domain strives to create control systems that coordinate the motion of multiple vehicles in order to navigate traffic both efficiently and safely. In this paper a novel individual vehicle controller based on reinforcement learning is introduced. This controller is capable of both lateral and longitudinal control while driving in a multi-vehicle platoon. The design and development of this controller is discussed in detail and simulation results showing learning progress and performance are presented.

Keywords: autonomous vehicles,co-ordination,decentralized control,machine learning,control

Identifier: 10.3182/20061002-2-BR-4906.00015

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Andre Scolari Conceicao; A. Paulo Moreira; Paulo J. Costa; Luis Paulo Reis

Abstract: This paper presents a new architecture for coordinating multiple autonomous robots in the execution of cooperative tasks. The architecture is based on the definition of a strategy that uses different tactics, setplays and roles. Roles enable to configure individual behaviour by performing specific tasks using a given set of actions. The proposed architecture allows flexible and efficient multi-robot operation in dynamic environments. The paper also presents an application of the proposed architecture to a complex domain such as middle-size robotic soccer. Our architecture is also generally enough to be applied in different robotic soccer leagues and similar multi-robot problems.

Keywords: architectures for cooperation,multi agent systems,artificial intelligence,coordination,teamwork

Identifier: 10.3182/20061002-2-BR-4906.00009

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: None

Abstract:

Keywords:

Identifier: 10.3182/20061002-2-BR-4906.00021

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Italo Romani de Oliveira; Renato Jorge Galvao Teixeira; Paulo Sergio Cugnasca

Abstract: The aircraft density in the airspace is growing, and this may increase the risk of accidents. In this sense, it is very important for air traffic controllers to work under safe traffic conditions, which include a good airspace division. The goal of this paper is to study the use of a well known airspace complexity measure, applied to evaluate air traffic controller workload in different organizations of the airspace around São Paulo. The results obtained by simulating two different scenarios show the relations between sector geometry, complexity and controller workload conditions.

Keywords: air traffic control,human factors,safety,tasks,complex systems,simulation

Identifier: 10.3182/20061002-2-BR-4906.00012

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Mike Peasgood; John McPhee; Christopher Clark

Abstract: This paper addresses the challenging problem of finding collision-free trajectories for many robots moving to individual goals within a common environment. Most popular algorithms for multi-robot planning manage the complexity of the problem by planning trajectories for robots sequentially; such decoupled methods may fail to find a solution even if one exists. In contrast, this paper describes a multi-phase approach to the planning problem that guarantees a solution by creating and maintaining obstacle-free paths through the environment as required for each robot to reach its goal. Using a topological graph and spanning tree representation of a tunnel or corridor environment, the multi-phase planner is capable of planning trajectories for up to r = L-1 robots, where the spanning tree includes L leaves. Monte Carlo simulations in a large environment with varying number of robots demonstrate that the algorithm can solve planning problems requiring complex coordination of many robots that cannot be solved with a decoupled approach, and is scalable with complexity linear in the number of robots.

Keywords: mobile robots,efficient algorithms,path planning,trajectory planning

Identifier: 10.3182/20061002-2-BR-4906.00006

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Gedson Faria; Edson Prestes; Roseli A. F. Romero

Abstract: In this work, an intelligent control architecture for controlling multirobots, denominated ACIn, that integrates planning and RBS, has been proposed. With this objective, some techniques have been investigated for the planning of trajectories, such as Potential Fields and Potential Fields based on the solution of the Boundary Value Problem (BVP). Such techniques, generally used for a single robot, have been adapted to work on multi-robots into ACIn architecture. Then, a modification of the Potential Fields based on BVP, called Locally Oriented Potential Field (LOPF), is used together ACIn to overcome the drawback existing in BVP based techniques, when they are applied for controlling multi robots. To get collaborative interactions among the robots in a team, a rule based system has been also proposed to as part of the ACIn architecture. The objective of RBS is to characterize the functionality of each robot for realizing an specific task. Experiments performed in the robot soccer simulated environment show that ACIn works on satisfactory.

Keywords: robot soccer,potential fields,boundary value problem

Identifier: 10.3182/20061002-2-BR-4906.00016

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Augusto Loureiro da Costa; Guilherme Bittencourt

Abstract: Mobile Robots and Autonomous Agents are very similar concepts that present several common aspects. In particular, Multi-Robot Systems that are intended to perform cooperative tasks can be seen as Multi-Agent Systems. This paper presents the implementation of a distributed control for mobile multi-robot system that perform cooperative tasks, under soft real-time restriction and using the best effort approach, based on a Multi-Agent approach.

Keywords: cooperative robots,muti-robots systems,multi-agent systems,mobile robots

Identifier: 10.3182/20061002-2-BR-4906.00014

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Jurandy Antonio do Nascimento; Jose Raimundo de Oliveira

Abstract: Following the technologies evolution of all kind of vehicles and parts of vehicles, it came together the increasing need for communication and interaction between these parts. Thus, it could be testified in few years the evolution of protocols, standards, methodologies and embedded systems created in order to maximize the security and the efficiency of all kinds of vehicles. Now there is a more complex task to solve that is to maximize the security and efficiency on vehicle systems and due to it there are some challenges to transpose like information exchange between vehicles and the right use of this information with local and global interactions.

Keywords: navigation systems,network topologies,road traffic,telemetry,traffic control,vehicles,cooperative perception

Identifier: 10.3182/20061002-2-BR-4906.00003

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Fabiano Rogerio Correa; Jun Okamoto; Marcos Ribeiro Pereira Barretto

Abstract: In these networked days cooperative perception means that multiple robots with multiple sensors can share their data creating a common knowledge base so that they can plan and interact with the environment in a more appropriate and efficient way. We propose in this work an architecture for cooperative perception for mobile robots based on distributed objects in a network. The implementation follow the CORBA specification, created to facilitate development of distributed applications in heterogeneous network. Objects could be the sensors and actuators of a robot or processes that treat common sensor data. An implementation of an image acquisition and distribution service is presented and others are proposed to compose the architecture.

Keywords: robot vision,multicomputer systems,robot navigation,distributed models,real-time computer systems

Identifier: 10.3182/20061002-2-BR-4906.00017

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Luis Paulo Reis; Nuno Lau; Francisco Reinaldo; Nuno Cordeiro; Joao Certo

Abstract: FC Portugal Rescue team is the result of a cooperation project between the Universities of Aveiro and Porto in Portugal. Following previous collaborations of these two Portuguese Universities in RoboCup simulation league and associated competitions, this project intends to fully adapt the coordination methodologies developed by FC Portugal simulated soccer team to the search and rescue scenario. After FC Portugal's first successful participation in RoboCup rescue simulation league (Osaka, 2005), the team aimed at introducing new high-level strategic analysis tools in the Rescue league and developed FCPx tool. This tool enables an easy comparison of different teams' strategies, and the use of learning methodologies for high-level strategic decisions in rescue. The tool also enabled us to evaluate our coordination methodologies, analysing the results achieved in several rescue parameters, and conclude that they are very promising for the search and rescue domain. FC Portugal Rescue team results are very promising achieving first place in RoboCup European Championship 2006 (Dutch Open) held in Eindhoven.

Keywords: multi-robot systems,artificial intelligence,agents,simulation,cooperation,distributed simulation

Identifier: 10.3182/20061002-2-BR-4906.00011

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Martin Hess; Martin Saska; Klaus Schilling

Abstract: This paper presents a new leader following approach for a formation of carlike robots. The path planning problem is solved for the leader with optimized spline functions, which are generated by an evolutionary technique called particle swarm optimization. Because of the expansion of the formation, a collision free path is not guaranteed for the following vehicles. In our approach the followers reactively avoid collisions with path-blocking obstacles and also with other robots within the formation. The developed algorithms have been tested intensively in various simulations.

Keywords: multi robot,formation driving,leader following,carlike robots,obstacle avoidance,path planning,particle swarm optimization

Identifier: 10.3182/20061002-2-BR-4906.00007

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: None

Abstract:

Keywords:

Identifier: 10.3182/20061002-2-BR-4906.00001

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Joao Figueiredo; Nuno Lau; Artur Pereira

Abstract: In this paper we present a framework developed for the CAMBADA Middle-sized league robotic team, which allows human developers to better understand the robots actions during a game. Robotic soccer teams are in their nature dynamic multi-process and multi-agent systems, and knowing what is happening in all processes running on the agents at the same time is a hard task. To accomplish this task we developed a framework to create log files, one per process, and to interlace them later. The logs represent robot's knowledge. The framework allows the synchronization and visualization of logs and videos. Videos give the actual real behaviors. This will allow us to understand the robot's reasoning. A GUI utility to navigate and search inside log files was also developed.

Keywords: monitoring,debug,multi-agent,multi-systems,robotics,MSL,middle-sized league

Identifier: 10.3182/20061002-2-BR-4906.00020

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Pedro Almeida; Gil M. Goncalves; Joao Borges Sousa

Abstract: The Apollo system for unmanned air vehicle (UAV) control is described. This is done in the context of the AsasF project from Porto University. Apollo is the UAV controller component of the AsasF control hierarchy. Apollo provides a uniform vehicle interface which is targeted at multi-vehicle operations in a mixed initiative environment allowing the intervention of experienced human operators. Apollo decouples the details of UAV control from the organization of external controllers in the AsasF control hierarchy. Apollo has a layered structure modelled in the framework of dynamic networks of hybrid automata. There is a mission supervisor, a vehicle supervisor and manoeuvre controllers, one per type of manoeuvre.

Keywords: aircraft control,aircraft operations,automata theory,middleware,networked vehicle system,tracking systems

Identifier: 10.3182/20061002-2-BR-4906.00013

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Valguima Odakura; Anna Helena Reali Costa

Abstract: This paper describes a new technique to cooperative multirobot localization based on multidetection. In conventional multirobot localization, the poses beliefs of two robots are updated whenever one robot detects another one and measures their relative distance. When a group of robots localize themselves in the same environment, it may happen that one robot detects more than one robot at once or that one robot sees other robot that sees another one - both cases depict a multidetection situation. We propose a communication structure to incorporate the multidetection information in the pose belief. The key idea is that robots more certain about their poses have more useful information to share with other robots, so they should communicate first, propagating their knowledge to the rest of the group. The technique has been implemented and tested in simulated environments. Experiments show significant improvements in localization accuracy when compared with the conventional multirobot localization.

Keywords: cooperative mobile robots, multirobot localization, multidetection

Identifier: 10.3182/20061002-2-BR-4906.00005

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Markus Glocker; Christian Reinl; Oskar von Stryk

Abstract: Based on a nonlinear hybrid dynamical systems model a new planning method for optimal coordination and control of multiple unmanned vehicles is investigated. The time dependent hybrid state of the overall system consists of discrete (roles, actions) and continuous (e.g. position, orientation, velocity) state variables of the vehicles involved. The evolution in time of the system's hybrid state is described by a hybrid state automaton. The presented approach enables a tight and formal coupling of discrete and continuous state dynamics, i.e. of dynamic role and action assignment and sequencing as well as of the physical motion dynamics of a single vehicle modeled by nonlinear differential equations. The planning problem of determining optimal hybrid state trajectories that minimize a cost function as time or energy for optimal multi-vehicle cooperation subject to constraints including the vehicle's motion dynamics is transformed to a mixed-binary dynamic optimization problem being solved numerically. The numerical method consists of an inner iteration where multiphase optimal control problems are solved using a direct collocation method and an outer iteration based on a branch-and-bound search of the discrete solution space. The approach presented in this paper is applied to the scenarios of optimal simultaneous waypoint or target sequencing and dynamic trajectory planning for a team of unmanned aerial vehicles in a plane and to optimal role assignment and physics-based trajectories in robot soccer.

Keywords: multi-vehicle task allocation and trajectory planning,nonlinear hybrid dynamical systems,mixed-integer optimal control,multiple motorized salesmen problem

Identifier: 10.3182/20061002-2-BR-4906.00008

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Marcelo Borges Nogueira; Adelardo A. D. Medeiros; Pablo J. Alsina

Abstract: This paper describes an ongoing project to move a simple humanoid robot, without an advanced embedded electronics. We used another wheeled mobile robot which already has a locating system and is equipped with a camera. We will locate the humanoid in the environment based on images, and then take the necessary actions to move it. In the future, we will also move the robot with the camera, so it will take good images of the humanoid.

Keywords: multi-robot cooperation,relative positioning,humanoid,pose estimation

Identifier: 10.3182/20061002-2-BR-4906.00002

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Martin Friedmann; Jutta Kiener; Sebastian Petters; Dirk Thomas; Oskar von Stryk

Abstract: The software framework RoboFrame has been designed to meet the special requirements for teams of lightweight autonomous heterogeneous robot systems. Due to platform abstraction and modern object oriented design, it allows the reuse of components of common robot control software. It can also efficiently be implemented on new platforms and enables different control architectures for different tasks. For the exemplary application in autonomous robot soccer teams configurable and portable algorithms for vision, world modeling, behavior and motion control have been developed on top of the framework. For debugging, controlling and monitoring, an extendable graphical user interface and a generic simulator package have been implemented around the framework. Based on these instruments, different applications for homogeneous and heterogeneous robot teams can be realized in short time.

Keywords: reusable robotic software,lightweight mobile autonomous robots,cooperation of heterogeneous robots,tools for debugging and monitoring,robot simulation

Identifier: 10.3182/20061002-2-BR-4906.00010

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Mario A. Correa; Joao B. Camargo; Ricardo A. V. Gimenes; Jorge R. Almeida

Abstract: Developed countries have made significant efforts to integrate UAV operations in controlled aerial space due to a rising interest of using Unmanned Aerial Vehicles (UAV) for civilian purposes. This study focuses the use of multi-agent architecture to distribute the workload of detecting and solving conflicts between the aircraft and the UAV with no intervention from ground-based facilities. Midair collision risk was the main unsafe situation evaluated using an aircraft collision model based on air traffic density data.

Keywords: agents,air traffic control,aircraft control,autonomous vehicles,computer controlled systems,detection algorithms,reliability,risk,safety analysis

Identifier: 10.3182/20061002-2-BR-4906.00018

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Christiano Couto Gava; Raquel Frizera Vassallo; Ricardo Carelli; Teodiano Freire Bastos Filho

Abstract: In this work a mobile robot cooperation strategy based on computational vision is presented. Such strategy is applied to a mobile robot team formed by simple and cheap robots and a leader robot with more computational power. The leader has an omnidirectional visual system and uses color segmentation to obtain the pose of the followers. This visual information is used by a nonlinear stable controller that manages team formation. Simulations and tests were run and current results are encouraging.

Keywords: robot cooperation,nonlinear control,omnidirectional vision

Identifier: 10.3182/20061002-2-BR-4906.00004

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006

Authors: Eduardo R. B. Marques; Gil M. Goncalves; Joao B. Sousa

Abstract: Seaware is a publish-subscribe middleware used in multi-vehicle networked systems composed of autonomous and semi-autonomous vehicles and systems. Seaware provides a high level interface to network communications and may be deployed with a combination of heterogeneous components within a dynamic network. Seaware supports the RTPS (Real Time Publish Subscribe) protocol, underwater acoustic modems and other forms of network transport. This paper gives an overview of Seaware's implementation and its application to multi-vehicle networked sysems.

Keywords: antonomous vehicles,communication networks,distributed control

Identifier: 10.3182/20061002-2-BR-4906.00019

Conference: 1st IFAC Workshop on Multivehicle Systems, 2006

Location: Centro de Convenções da Bahia, Brazil

Start Date: Mon Oct 02 2006 - End Date: Tue Oct 03 2006