From the Biorobotics Lab at Carnegie Mellon University, a snake robot (Snakebot) demonstrates how it can climb a tree and look around. Please keep in mind that this robot climbed a specific tree with a specific trunk width about 1 meter off of the ground. The researchers working to design, build and program these robots still have much work to do to get these bots to climb taller trees of various sizes and to navigate over branches and wires.

cmu carnegie mellon ri robotics institute snakebot snake climb tree

Benjamin Stephens is a Ph.D. student in the Robotics Institute at Carnegie Mellon University. He is originally from Oklahoma, but received his undergraduate degree in Mechanical Engineering at Northwestern University. His PhD research focuses on the control of humanoid robot balance and push recovery for force-controlled robots. He is interested in the use of real-time optimal control for robust control of very complex systems. Using his knowledge and experience, he hopes to make legged/humanoid robots more capable of operating in rough and uncertain environments. He also believes this work will lead to the creation of new intelligent assistive devices such as prosthetics and exoskeletons. To learn more about Ben's research and see other videos of the Sarcos Robot in action visit his personal webpage: www.cs.cmu.edu

sarcos robot robotics humanoid dance recover ben stephens cmu carnegie mellon ri institute pittsburgh

RI Seminar: Kayvon Fatahalian Evolving the OpenGL Graphics Pipeline in Pursuit of Real-Time, Film-Quality Rendering Kayvon Fatahalian Assistant Professor Computer Science Department, Carnegie Mellon University September 23, 2011 Abstract In the past fifteen years the capabilities of real-time graphics systems have increased rapidly as a result of domain-influenced co-design of algorithms, programming interfaces, and heterogeneous, parallel hardware (GPUs). Despite these improvements, rendering geometrically complex, film- quality scenes at interactive rates remains beyond the capabilities of current systems. Current GPU implementations not only require additional compute capability to handle high-resolution surfaces represented by pixel-sized "micropolygons", fundamental system operations such as geometry processing, surface visibility, and shading execute inefficiently under this workload. In this talk I will describe an evolution of the OpenGL graphics pipeline that significantly in- creases system efficiency when rendering micropolygons. The redesign modifies rendering al- gorithms, GPU hardware, and programming abstractions to increase parallelism and eliminate redundant work while preserving the graphics pipeline's simple parallel programming model and the throughput-optimized design of GPU processing cores. This talk focuses on the challenges of real-time graphics, but it is exciting to consider how future computational cameras and mobile computer vision tasks will <b>...</b>

Kayvon Fatahalian opengl Graphics ri seminar cmu carnegie mellon

Colony robots made by the Carnegie Mellon University Robotics Club.

robot colony recharge network robotics club carnegie mellon university CMU

This video demonstrates the CMU control software for the LittleDog robot, designed and manufactured by Boston Dynamics Inc. The capabilities demonstrated here were developed as part of the DARPA Learning Locomotion project, which focuses on planning and control for legged robots over rough terrain. Software by Matt Zucker, with additional contributions by Elliot Cuzzillo and Alex Grubb. See www.cs.cmu.edu for more info.

littledog robot CMU

This video captures the progress of the ASME Student Design Team for the Autonomous Waste Sorter. The objective of this year's challenge was to autonomously sort glass, plastic, aluminum, and tin-coated steel bottles. More details on the challenge can be found here: www.asme.org The team placed 1st regionally, qualifing it for international competition at the ASME International Mechanical Engineering Congress and Exposition (IMECE).

CMU Carnegie Mellon Robotics CMU Robotics Club recycling sorter ASME

After a 6 hour marathon of soldering and crimping the Colony Scout now has speed and direction control, enabling skid steering and controlled movements. The bot is currently running on an Arduino Mega, which uses the awesome ATMega 1280. In this video see the Scout skid steer on concrete and a slippery gravel base. For more details, see www.danshope.com/blog

robot swarm robotics technology computers pololu motors testing design validation solidworks engineering Carnegie Mellon Robotics

The second in the series; the upgraded CNC software supports really slow motion (I haven't modified the G-code translator to support dwells yet), so I can actually put in rests. The Kirby theme has rests in it, so what better to try it with? This is a good example, by the way, of using lots of expensive and complex technology to the end of doing something completely useless. In this equation is a 2.4GHz Core 2, which runs a program converting from MIDI to an array of notes in a C file; the latest and greatest compiler technology performing SSA optimization to the end of compiling this array of notes into a program that outputs a static set of G-Code; 3D visualizations predicting the location of a table on a GeForce FX powered by Intel's Finest (NetBurst), driving a parallel port stepper driver; stepper drivers dissipating an enormous amount of heat to drive a stepper motor; and finally, the stepper itself slinging around 20 pounds of steel -- all to produce this music. Technology is truly amazing; never before could we do so little with so much.

cnc mill experimental music kirby roboclub

Now outfitted with quadrature encoders and digital Sharp GP2Y0D810Z0F sensors, the Scout is ready to explore new terrain. Today Scout handled outdoor terrain, a first for the Colony robots. A front facing and ground facing pair of sensors enable a rudimentary obstacle and cliff navigation routine that prevents falls and collisions. The grass was an interesting challenge, but not dense enough to trip the proximity sensor. All four wheel encoders are now used for straight line and curvilinear driving. Check out www.danshope.com/blog for more details.

robot swarm robotics technology computers pololu motors testing design validation solidworks engineering Carnegie Mellon

We CNC and manually milled parts for the Scout platform and assembled the motors, encoders, wheels, and bumper today. In the videos you can see the rocker mechanism that lets the front axle swivel and cross some pretty tough terrain. Colony Scout is an exciting new platform for swarm robotics developed in the Carnegie Mellon Robotics Club. Prototype testing is ongoing so keep tuned for more updates!

robot swarm robotics technology computers pololu motors testing design validation solidworks engineering Carnegie Mellon Robotics

The amazing race of the century!

CMU Piggyback RI Robotics Institute

DigitalSpace: Highlander Lunar Rover design, simulation for CMU Robotics Institute (2006)

space lunar exploration robotics 3D simulation

Robust motion planning for walking robots and robotic birds Russ Tedrake Associate Professor, MIT October 28, 2011 Abstract Building robots that can walk or fly with the dexterity of an animal is hard. Our best models of these robots are complicated because they are nonlinear and underactuated, and because the robots are fundamentally subjected to large sources of uncertainty relative to their control authority - for instance, large disturbances like a gust of wind and/or model uncertainty because they are locomoting on unknown terrain. While the field of robotics has seen some success from "intuitive" controllers based on simple models, I believe that a more algorithmic approach is required to scale much beyond the complexity and performance of today's robots. In this talk, I will demonstrate that combinations of randomized motion planning and trajectory optimization can produce open-loop trajectories for models of the required complexity (nonlinear, hybrid, underactuated). But when one goes to implement these on the real systems, they inevitably fail, in part because trajectory motion planning by itself doesn't provide any language for talking about robustness. Therefore, I'll describe tools from robustness analysis (both linear and nonlinear), feedback planning, and planning in belief space that can help close this gap, and produce solutions that work on real systems. These ingredients can be added on top of most existing motion planners, and can make a substantial <b>...</b>

russ tedrake robot motion planning ri seminar cmu robotics institute mit robotic birds

Video 1 of 4 Illah Nourbakhsh of Carnegie Mellon's Robotics Institute teaches you how to set up and use your Gigapan robotic system. Watch all four videos to see the process from start to finish, then explore more at: www.gigapan.org

gigapan giga pan camera robot tripod system cmu carnegie mellon robotics Illah Nourbakhsh

Siddhartha Srinivasa of The Robotics Institute's Personal Robotics Lab at CMU demonstrates how Herb is the closest thing we have to the Jetsons Rosey the Robot in 2012. www.ri.cmu.edu

robot robobutler butler rosie rosey herb cmu robotics jetsons microwave science professor Siddhartha Srinivasa Robotics Institute

www.tartanracing.org Carnegie Mellon's Tartan Racing team qualified for the race to be held on Saturday, November 3, 2007. Here is an excellent video showing "Boss" in full autonomous mode. Yes, that means the car is driving itself... No remote control. No magic tricks. Boss can see, makes judgements and drive. The camera views were downloaded from the vehicle after the successful run.

cmu robotics carnegie mellon tartan racing red whittaker chris urmson

There is more to getting a robot to see the world than connecting a video camera to it. Without software that can analyze the images coming from that video, a robot would not be able to make much sense of the information. The way our eyes and brain work together is quite amazing and the inspiration for the field of Computer Vision. CV Algorithms are needed to break apart the images into meaningful pieces and begin the process of understanding context. Much work remains to be done in the area, but progress shown in the video is certainly exciting and promising. Video Narration: Getting a computer to understand what it is "seeing" is a very challenging problem. To do this in real-time, even more so. In this prototype, a camera is attached to Alvaro's glasses. The black and white video is not being shown to him, but rather, that video is what the software is "seeing". The video is being analyzed by a task-specific vision algorithm and finds milk in his hand and boxes of rice on the shelves. In the future, having a robot help in the kitchen will require it to understand what it is seeing, before it attempts to pick anything up. Or the robot might be a smart agent looking over someone with a cognitive disability and will understand what someone is attempting to do and then help coach them through the task.

cmu ri robotics institute intel quality of life qolt pittsburgh carnegie mellon computer vision

Carnegie Mellon's Tartan Racing team is on location in Victorville, California for the 2007 Darpa Urban Grand Challenge. Stay tuned to: tartanracing.org ...for daily updates, video clips, press releases and photos.

tartanracing tartan carnegie mellon cmu robotics urban challenge darpa

CMU Robotics Club sponsored UC Late Night thetartan.org

CMU Carnegie Mellon University Robotics Club UC Late Night

Mike Gleicher Professor, University of Wisconsin From Art and Perception to Visualization and Video Processing November 18, 2011 Abstract My research revolves around the question ``How can we use our understanding of human perception and artistic traditions to improve our tools for communicating and understanding data.'' The former (Art and Perception) often point us in similar directions, and provide ideas for a wide range applications. In this talk, I will survey some of our recent work where we apply insights from art and perception to some practical problems in visualization and graphics. I will describe our work to develop tools to help understand the shape and motion of proteins, and to help compare large collections of genomes and other sequence data. I will describe our work in creating tools to enhance consumer video, particularly to perform video stabilization in ways that avoid hard computer vision problems. Speaker Biography Michael Gleicher is a Professor in the Department of Computer Sciences at the University of Wisconsin, Madison. Prof. Gleicher is founder and leader of the Department's Computer Graphics group. His research interests include visualization, image and video processing tools, and character animation techniques for films and games. Prior to joining the university, Prof. Gleicher was a researcher at The Autodesk Vision Technology Center and in Apple Computer's Advanced Technology Group. He earned his Ph. D. in Computer Science from Carnegie <b>...</b>

Gleicher Wisconsin uw ri seminar cmu robotics institute carnegie mellon university robotics institute human perception artistic traditions

Even when robotics technologies were relatively primitive, their potential role in boosting the productivity and competitiveness of the United States was foreseen in the evolving global marketplace. The Robotics Institute at Carnegie Mellon University was established in 1979 to conduct basic and applied research in robotics technologies relevant to industrial and societal tasks. Seeking to combine the practical and the theoretical, the Robotics Institute has diversified its efforts and approaches to robotics science while retaining its original goal of realizing the potential of the robotics field.

Carnegie Mellon CMU Robotics RI

Red Robot Dancing in the CMU Robotics Club to La Vie Boheme.

Red Robot Dancing CMU Robotics Club La Vie Boheme

Video 2 of 4 Illah Nourbakhsh of Carnegie Mellon's Robotics Institute teaches you how to set up and use your Gigapan robotic system. Watch all four videos to see the process from start to finish, then explore more at: www.gigapan.org

gigapan giga pan robot camera illah cmu robotics carnegie mellon

Video 3 of 4 Illah Nourbakhsh of Carnegie Mellon's Robotics Institute teaches you how to set up and use your Gigapan robotic system. Watch all four videos to see the process from start to finish, then explore more at: www.gigapan.org

gigapan giga pan camera robot tripod system cmu carnegie mellon robotics Illah Nourbakhsh

Video 4 of 4 Illah Nourbakhsh of Carnegie Mellon's Robotics Institute teaches you how to set up and use your Gigapan robotic system. Watch all four videos to see the process from start to finish, then explore more at: www.gigapan.org

gigapan giga pan camera robot tripod system cmu carnegie mellon robotics Illah Nourbakhsh

gigapan.org http After a two-year collaboration with colleagues at NASA's Ames Research Center, Carnegie Mellon University scientists unveil their Gigapan camera system this week. It's a robotic device that attaches to any digital camera. The device enables the public to shoot interactive, multi-billion pixel panoramas that can be explored in great depth on the Internet.

cmu gigapan robotics carnegie mellon Illah Nourbakhsh Randy Sargent

The Intro to Robotics class at The Robotics Institute at Carnegie Mellon University is an intense and wonderful one. Over the course of one semester students study many aspects of robotics including: Vision, Artificial Intelligence, Motion Planning, Sensors and Sensor Planning, Mobile Robot Platforms, Forward Kinematics, Inverse Kinematics, and Non-Holonomic constraints To kick off the class, groups each create a Rube Goldberg energy transfer system. Then, they try to connect all of them together... A difficult, if not impossible task, but the students have fun exploring the process. generalrobotics.org

intro robotics choset howie cmu carnegie Carnegie Mellon University rube goldberg

Randy Sargent and Tom Lauwers of Carnegie Mellon University with a quick overview on the the Gigapan system. For an in-depth tutorial, watch 4 videos from Illah beginning here: www.youtube.com Then learn more at gigapan.org

gigapan cmu carnegie mellon robotics

A look back at the Robotics Institute's Manipulation Lab set to the groovy tune "Do What You Do" by Eldridge Gravy & The Court Supreme. This video was created in a special collaboration with the band and the MLab. Thanks for the Gravy! The video features work from MLab Alumni Mike...

Eldridge Gravy Court Supreme manipulation robotics robot robots do what you do cmu Carnegie Mellon ri robotics institute Pittsburgh Seattle science technology robotfilmfestival film festival robofestival math electronics computer gadget

Intro to Robotics Class May 2012 Howie Choset's class isn't all fun and games. Sure, these robots are fighting to push the other one out of the ring and, yes, there is screaming and swearing, but a lot more goes into building a battle bot than meets the eye. A sample of the topics covered from the class syllabus: Vision Projection Convolution Edge Detection Image Interpretation and ENS Mobility - (mobile robot platforms) Inertial Navigation Systems Graph Search Controls (and encoders) Motion Planning Potential Functions Roadmaps Cell Decompositions Sensing and Sensors Human Robot Interaction Forward and Inverse Kinematics Transformation Matrices Inverse Kinematics Geometric methods Algebraic methods Non-holonomic constraints

cmu carnegie mellon robotics ri scs battlebot robot fun bots choset

www.cs.cmu.edu Carnegie Mellon School of Computer Science The Mobot competition is designed to allow the participants to explore some of the main technical aspects involved in building an autonomous robotic agent.

cmu mobot mobot2007 robotics carnegie mellon

www.robot250.org The first sampling of 3 of the Robot 250 BigBot Robotic Installations you can visit around the Pittsburgh area this July 2008. Featuring: The Green Roof Roller Coaster at the Children's Museum, You're Number One perched on top of the Andy Warhol Museum and Prototype for an Infinite Array of Semi-Autonomous Percussive Devices at the Mattress Factory. All can be found on the North Side.

robot250 pittsburgh250 robot bigbots carnegie mellon pittsburgh art robotic installation cmu robotics institute cfa fine arts

For those of you out there who wanted me to share my unedited video, here it is in all of its shaky glory. I was shifting my view during the run to capture a variety of views, different depths of field and give me a tighter, more interesting edit. You'll see also that some orange cones in the background added a visual distraction that I ran over and removed. Thanks for helping to spread the word about the cool robotics research being done at CMU's Robotics Institute!

robotics snake robot snakebot cmu carnegie mellon unedited tree climb choset biorobotics

www.ri.cmu.edu This new robot is named Scarab and is part of the the Lunar Ice Discovery Initiative. The LIDI intends to conduct a robotic ground investigation of the southern polar region of the Moon.

robot robotics institute cmu carnegie mellon lunar whittaker pittsburgh

Tom Lauwers of Bird Brain Technologies unboxes the Hummingbird kit. April 2012

birdbrain hummingbird unboxing diy

Three users explain what it was like to use Classroom Salon to facilitate rich discussions of texts they wrote for class. What is Classroom Salon? It is a new way to facilitate a community of readers around text. Salon is a digital environment that translates individual work like annotations and comments into dynamic communities. It helps teachers, authors and group leaders to gauge perspectives and camps of opinion through aggregation and rich visualizations. classroomsalon.org

cmu scs carnegie mellon classroomsalon salon computer science english writing dynamic commments

The Search-based Planning Laboratory demonstrates how the PR2 dual-arm mobile robot could be bartender - or at least how it would make a plan and then move through a crowded space to pick up a coke and a snack for a visitor. April 20, 2012 Live during National Robotics Week at Carnegie Mellon University's Robotics Institute Thanks to everyone in the Search-based Planning Laboratory for giving this demo! www.ri.cmu.edu

pr2 robot coke coca-cola robo robotics robotender bartender cmu carnegie mellon pittsburgh nrw robotics institute

www.snackbot.org

ri cmu carnegie mellon robotics hcii human interaction snackbot robot

From Sorcery to Science: how Hollywood Physics impacts the Sciences Eitan Grinspun Associate Professor, Columbia November 11, 2011 Abstract Cinema uses computers to animate physics. Special effects such as explosions and lifelike depictions of imaginary characters are made possible by mathematical and computational models that capture qualitative, characteristic behavior of a mechanical system. This is scientific computing with a twist. I will describe the process by which we derive and compute models of physics, and show actual examples of resulting technologies in film, consumer products, physics, and medicine. Our research group develops scientific computing tools by focusing on the underlying geometry of the mechanical system. I will describe a process in which we build a discrete picture from the ground up, mimicking the axioms, structures, and symmetries of the smooth setting. I will survey the problems we address using this methodology, such as computing the motion of flexible surfaces, cloth, hair, honey, and solids experiencing mechanical contact. Industry and academia has adopted these methods to improve products such as Adobe Photoshop, films such as Disney's Tangled, train surgeons, and understand nonlinear soft-matter phenomena. Speaker Biography Eitan Grinspun is Associate Professor of Computer Science at Columbia University in the City of New York. He was Professeur d'Université Invité at l'Université Pierre et Marie Curie in 2009, a Research Scientist at <b>...</b>

Eitan Grinspun columbia Carnegie Mellon University ri seminar cmu robotics institute

Three educators discuss how Classroom Salon has changed the way they teach by increasing the visibility of students and their work. This video features perspectives from teachers who have used Classroom Salon in Middle School and Graduate level college courses.

classroom salon cmu carnegie mellon social media discussion educators college

Herb is a robot from the Intel Personal Robotics Lab and a research platform for Carnegie Mellon's Quality of Life Technology Research Center. During Intel Pittsburgh's 2010 open house, Herb greeted guests by demonstrating his abilities to pick up different bottles and cans, travel while avoiding obstacles, offer the object to someone and then put it back or in a recycle bin. During the video you can see how the arm is able to be manipulated by someone and then it resumes doing the task it was doing. Herb's computer vision - his view of the world in data point clouds - was on display too being projected for all to see. To learn more visit these links: personalrobotics.intel-research.net www.cmu.edu

home butler robot robotics institute qolt quality life cmu ri pittsburgh rosie intel carnegie mellon

www.frc.ri.cmu.edu Zoë is designed to be a highly capable robotic astrobiologist. Equipped with specialized sensors, Zoë will roam the Atacama desert in search of life.

robotics institute carnegie mellon cmu ri atacama pittsburgh

tartanracing.org The Urban Challenge is a 60-mile skill competition of driverless vehicles through streets and intersections. Urban Challenge vehicles must drive effectively and safely, react and interact with other traffic, and reason about intention. This competition will be held November 3, 2007.

carnegie mellon cmu tartan racing darpa urban challenge boss gm caterpillar continental robotics robot

Takeo Kanade discusses environmental robotic systems. A symposium in honor of his 60th birthday was held at Carnegie Mellon on March 9th. Learn more on the Robotics Institute website: www.ri.cmu.edu

robotics robot robotics institute carnegie mellon takeo kanade tk60.org

Magnetic Levitation Gives Computer Users Sense of Touch NSF Makes Carnegie Mellon Invention Available to More Researchers PITTSBURGH -- Computers, long used as tools to design and manipulate three-dimensional objects, may soon provide people with a way to sense the texture of those objects or feel how they fit together, thanks to a haptic, or touch-based, interface developed at Carnegie Mellon University. Unlike most other haptic interfaces that rely on motors and mechanical linkages to provide some sense of touch or force feedback, the device developed by Ralph Hollis, research professor in Carnegie Mellon's Robotics Institute, uses magnetic levitation and a single moving part to give users a highly realistic experience. Users can perceive textures, feel hard contacts and notice even slight changes in position while using an interface that responds rapidly to movements.

carnegie mellon robotics institute maglev haptic cmu hollis ri

From ICCP11 Hosted by Carnegie Mellon University, Robotics Institute April 9, 2011 Lihong V. Wang, Photoacoustic Tomography: Ultrasonically Breaking through the Optical Diffusion Limit

2011 iccp iccp11 Photoacoustic Tomography

From ICCP11 Hosted by Carnegie Mellon University, Robotics Institute April 9, 2011 Session 1: Optics Validity of Wigner Distribution Function for Ray-based Imaging Tom Cuypers, Roarke Horstmeyer, Se Baek Oh, Philippe Bekaert, Ramesh Raskar

iccp2011 iccp iccp11 cmu carnegie mellon Wigner optics