logging in or signing up robo poster v2 Elodie Download Post to : URL : Related Presentations : Share Add to Flag Embed Email Send to Blogs and Networks Add to Channel Uploaded from authorPOINTLite Insert YouTube videos in PowerPont slides with aS Desktop Copy embed code: (To copy code, click on the text box) Embed: URL: Thumbnail: WordPress Embed Customize Embed The presentation is successfully added In Your Favorites. Views: 48 Category: Entertainment License: All Rights Reserved Like it (0) Dislike it (0) Added: January 02, 2008 This Presentation is Public Favorites: 0 Presentation Description No description available. Comments Posting comment... By: vinodnusum (13 month(s) ago) bChz Saving..... Post Reply Close Saving..... Edit Comment Close Premium member Presentation Transcript Slide1: Distributed and Parallel Portable Robot System Using Commodity Components High Performance Distributed Computing Group Department of Computer Science University of Tromsø Otto J. Anshus, John Markus Bjørndalen, Ole Martin Bjørndalen, Daniel Stødle, Ken Arne Jensen High Performance Distributed Computing Group (HPDC): High Performance Distributed Computing Group (HPDC) Systems research on distributed and parallel systems We design, implement, measure, and evaluate software and hardware More than 20 papers and two Ph.D. dissertations over the last five years; all in the area of design and implementation of infrastructure mechanisms for grid and cluster computing Do You Want To Know More? http://www.cs.uit.no/forskning/DOS/hpdc/The Robot System 2000-2002: The Robot System 2000-2002 Mandatory project at a course on Distributed and Parallel Systems at UiTø Robo 2000 – “Rendezvous” (or “Dating” according to a local newspaper) Stand-alone robots w/simple on-robot sensors (pressure, rotation, light) The robots compete on doing the highest number of “CSP rendezvous” with each other Robo 2001 – “Dogs herd a single Sheep” Stand-alone robots w/simple sensors Enhancements Each robot supported by a laptop for more off-robot compute cycles A camera-based positioning system looking down on the robot arena provides each robot with position information on all robots The robots compete on herding a resisting “Sheep” robot Robo 2002 – “Sheeps tries to avoid a single Dog – a.k.a. Dr. X” Stand-alone robots w/simple sensors Enhancements A compute cluster and a file server provides the robots with data storage and compute cycles to compute where in the world the Dog Dr. X is located Robots compete by being good at avoiding the troublemaker Dr. X Robots need to know where the mobile Dr. X is But the position of Dr. X is encrypted Robots must use the compute cluster to break the cloak hiding Dr. X Overview of the Robot System: Overview of the Robot System Robots with small on-board computers cooperate or compete inside an arena according to a set of rules. brickOS, C, multi-threading Separate support computer, one per robot, enhances the robots low processing, memory, and I/O performance. Linux, GNU C compiler and tools. A compute cluster and a file server provide even higher performance. The robots are under constant surveillance by a positioning computer with a video camera. The camera positioning system enhances the robots very limited on-board sensors, and provides the robots with positioning information. To report the progress and the state of the system, a scoreboard computer monitors many activities, and report them on a scoreboard through a projector. A control and management computer starts, stops, and manipulates the system according to user input. An infrastructure computer makes the system independent of other infrastructures and networks by providing network services (DNS, DHCP, gateway to other networks)How Come “a Toy” is Useful at an Advanced University Course?: How Come “a Toy” is Useful at an Advanced University Course? The system is small, but complex Realistic, while still understandable and programmable: High intensity learning The system is very visual Failures and errors easy to notice Failures and errors create surprisingly funny situations instead of stomach pain The system is distributed Division of labor between robots, laptops, servers, cluster Fails like a distributed system Strong Dependencies: When the camera positioning system fails all robots go almost blind Weaker dependencies: When the laptop supporting a robot fails, the robot must do on its own with lower performance and tricks to survive The system comprises computers and networks with widely different CPU, memory, I/O, and failure characteristics Robots → laptops → servers → cluster 16MHz → 2 GHz → 3GHz → n*GHz CPUs 32KB → GB → a few GB → n*GB RAM Infrared (Kb) → radio Wi-Fi (10Mb) → Cable 100Mb → Interconnect Gigabit The system is parallel Concurrent and Parallel algorithms and architectures exercised in practice No cluster results in less accurate and/or slower decisions by robots The system is based on commodity components Cheap, and rapid progressBenefits of the Robot System: Benefits of the Robot System Attention grabber “Forskningsdagene” at the University of Tromsø Recruiting students to university studies Mathematics It is easy to raise the audience’s interest in other sciences including mathematics. The robots navigate using mathematics, and they utilize the cluster to do more complicated computations like parallel matrix multiplication and differential equations. The robot system demonstrate an actual use of mathematics answering the typical question from pupils: “why do I have to study mathematics?” Demonstrating supercomputing (“Supercomputing day”) The system demonstrates in a visual and direct way that clusters are needed to enable lower performance computers to function better It attracts students to work and develop the system. This both supports the CS Department, and provides students with deep knowledge about cluster programming The system is visual and fun both to work on, and to look at. This benefits both developers and the audience Scoreboard 2001 and 2002: Scoreboard 2001 and 2002Play Game: Play Game04:00am Before the Competition: 04:00am Before the CompetitionRobots in Action: Robots in ActionSelect Technical Details: Select Technical DetailsTechnical Details: Technical DetailsAcknowledgements: Acknowledgements The students at the concurrency and parallel cluster programming course the last three years for making it all worth the effort The technical and administrative staff at the Department of Computer Science, Univ. of Tromsø for 1001±1 things Ken Arne Jensen, Kai-Even Nilssen, Jon Ivar Kristiansen, Torfinn Holand Jan Fuglesteg, Svein Tore Jensen Mikroverkstedet AS v/Per Jørgen Ødegaard for fast deliveries into our pipeline of Lego robots Svenn A. Hansen, NOTUR Outreach & Dissemination project for pushing us to do a portable version Hewlett-Packard for making a portable robot system possible with modern and cool computers You do not have the permission to view this presentation. In order to view it, please contact the author of the presentation.
robo poster v2 Elodie Download Post to : URL : Related Presentations : Share Add to Flag Embed Email Send to Blogs and Networks Add to Channel Uploaded from authorPOINTLite Insert YouTube videos in PowerPont slides with aS Desktop Copy embed code: (To copy code, click on the text box) Embed: URL: Thumbnail: WordPress Embed Customize Embed The presentation is successfully added In Your Favorites. Views: 48 Category: Entertainment License: All Rights Reserved Like it (0) Dislike it (0) Added: January 02, 2008 This Presentation is Public Favorites: 0 Presentation Description No description available. Comments Posting comment... By: vinodnusum (13 month(s) ago) bChz Saving..... Post Reply Close Saving..... Edit Comment Close Premium member Presentation Transcript Slide1: Distributed and Parallel Portable Robot System Using Commodity Components High Performance Distributed Computing Group Department of Computer Science University of Tromsø Otto J. Anshus, John Markus Bjørndalen, Ole Martin Bjørndalen, Daniel Stødle, Ken Arne Jensen High Performance Distributed Computing Group (HPDC): High Performance Distributed Computing Group (HPDC) Systems research on distributed and parallel systems We design, implement, measure, and evaluate software and hardware More than 20 papers and two Ph.D. dissertations over the last five years; all in the area of design and implementation of infrastructure mechanisms for grid and cluster computing Do You Want To Know More? http://www.cs.uit.no/forskning/DOS/hpdc/The Robot System 2000-2002: The Robot System 2000-2002 Mandatory project at a course on Distributed and Parallel Systems at UiTø Robo 2000 – “Rendezvous” (or “Dating” according to a local newspaper) Stand-alone robots w/simple on-robot sensors (pressure, rotation, light) The robots compete on doing the highest number of “CSP rendezvous” with each other Robo 2001 – “Dogs herd a single Sheep” Stand-alone robots w/simple sensors Enhancements Each robot supported by a laptop for more off-robot compute cycles A camera-based positioning system looking down on the robot arena provides each robot with position information on all robots The robots compete on herding a resisting “Sheep” robot Robo 2002 – “Sheeps tries to avoid a single Dog – a.k.a. Dr. X” Stand-alone robots w/simple sensors Enhancements A compute cluster and a file server provides the robots with data storage and compute cycles to compute where in the world the Dog Dr. X is located Robots compete by being good at avoiding the troublemaker Dr. X Robots need to know where the mobile Dr. X is But the position of Dr. X is encrypted Robots must use the compute cluster to break the cloak hiding Dr. X Overview of the Robot System: Overview of the Robot System Robots with small on-board computers cooperate or compete inside an arena according to a set of rules. brickOS, C, multi-threading Separate support computer, one per robot, enhances the robots low processing, memory, and I/O performance. Linux, GNU C compiler and tools. A compute cluster and a file server provide even higher performance. The robots are under constant surveillance by a positioning computer with a video camera. The camera positioning system enhances the robots very limited on-board sensors, and provides the robots with positioning information. To report the progress and the state of the system, a scoreboard computer monitors many activities, and report them on a scoreboard through a projector. A control and management computer starts, stops, and manipulates the system according to user input. An infrastructure computer makes the system independent of other infrastructures and networks by providing network services (DNS, DHCP, gateway to other networks)How Come “a Toy” is Useful at an Advanced University Course?: How Come “a Toy” is Useful at an Advanced University Course? The system is small, but complex Realistic, while still understandable and programmable: High intensity learning The system is very visual Failures and errors easy to notice Failures and errors create surprisingly funny situations instead of stomach pain The system is distributed Division of labor between robots, laptops, servers, cluster Fails like a distributed system Strong Dependencies: When the camera positioning system fails all robots go almost blind Weaker dependencies: When the laptop supporting a robot fails, the robot must do on its own with lower performance and tricks to survive The system comprises computers and networks with widely different CPU, memory, I/O, and failure characteristics Robots → laptops → servers → cluster 16MHz → 2 GHz → 3GHz → n*GHz CPUs 32KB → GB → a few GB → n*GB RAM Infrared (Kb) → radio Wi-Fi (10Mb) → Cable 100Mb → Interconnect Gigabit The system is parallel Concurrent and Parallel algorithms and architectures exercised in practice No cluster results in less accurate and/or slower decisions by robots The system is based on commodity components Cheap, and rapid progressBenefits of the Robot System: Benefits of the Robot System Attention grabber “Forskningsdagene” at the University of Tromsø Recruiting students to university studies Mathematics It is easy to raise the audience’s interest in other sciences including mathematics. The robots navigate using mathematics, and they utilize the cluster to do more complicated computations like parallel matrix multiplication and differential equations. The robot system demonstrate an actual use of mathematics answering the typical question from pupils: “why do I have to study mathematics?” Demonstrating supercomputing (“Supercomputing day”) The system demonstrates in a visual and direct way that clusters are needed to enable lower performance computers to function better It attracts students to work and develop the system. This both supports the CS Department, and provides students with deep knowledge about cluster programming The system is visual and fun both to work on, and to look at. This benefits both developers and the audience Scoreboard 2001 and 2002: Scoreboard 2001 and 2002Play Game: Play Game04:00am Before the Competition: 04:00am Before the CompetitionRobots in Action: Robots in ActionSelect Technical Details: Select Technical DetailsTechnical Details: Technical DetailsAcknowledgements: Acknowledgements The students at the concurrency and parallel cluster programming course the last three years for making it all worth the effort The technical and administrative staff at the Department of Computer Science, Univ. of Tromsø for 1001±1 things Ken Arne Jensen, Kai-Even Nilssen, Jon Ivar Kristiansen, Torfinn Holand Jan Fuglesteg, Svein Tore Jensen Mikroverkstedet AS v/Per Jørgen Ødegaard for fast deliveries into our pipeline of Lego robots Svenn A. Hansen, NOTUR Outreach & Dissemination project for pushing us to do a portable version Hewlett-Packard for making a portable robot system possible with modern and cool computers