Cycling Cycling every 5 seconds. Stop Cycling Stop cycling
Cycle Start Cycling
Previous
Next
Loading...
Aerial Robot Collision Avoidance

Aerial Robot Collision Avoidance

Reliable detection and reaction to obstacles on flying robots are constrained heavily by power and weight. We are assessing various sensor technologies and developing algorithms to increase the performance with limited resources.

Additional Information

Key Technologies:

  • Trajectory planning for obstacle avoidance
  • Evidence grids
  • Lidar
  • Ultra-wideband Radar

Air-Ground Collaboration

Air-Ground Collaboration

We are developing a decentralized framework that enables collaborative sensing to be performed by teams of unmanned air and ground vehicles. This work is being applied small air and ground robots conducting surveillance tasks such as search, pursuit and geo-location in rural and urban environments.

Additional Information

This work is supported by two Army ARDEC SBIR Phase 2 contracts in partnership with iRobot and AeroVironment.

Contacts

Personnel

  • Michael Dille

    Dille, Michael

  • Stephen Nuske

    Nuske, Stephen

    (412)268-5901

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Air-Ground Collaborative Surveillance

Air-Ground Collaborative Surveillance

This project developed a decentralized framework that enabled collaborative sensing to be performed by teams of unmanned air and ground vehicles. It was applied to small air and ground robots conducting surveillance tasks such as search, pursuit and geo-location in rural and urban environments.

Additional Information

This work was supported by two Army ARDEC SBIR Phase 2 contracts in partnership with iRobot and AeroVironment.

Contacts

Personnel

  • Michael Dille

    Dille, Michael

  • Stephen Nuske

    Nuske, Stephen

    (412)268-5901

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Assistive Technology

Assistive Technology

Despite the importance of literacy to employment, social well-being, and health, the literacy rate of visually impaired and deaf and hard-of-hearing populations are quite low. Furthermore, not many navigational technologies exist for these populations.

Assistive Technology, a program of TechBridgeWorld, aims to remedy these challenges by developing assistive technologies to enhance education and navigation for these populations around the world.

Such projects include our Braille Writing Tutor for improving braille writing literacy among the visually impaired, DeSIGN for improving sign language literacy among the deaf and hard-of-hearing, and NavPal for improving navigational independence among the visually impaired, deaf and deafblind. TechBridgeWorld has worked with or is currently working with partners from Bangladesh, China, India, Qatar, Tanzania, the United States, and Zambia.

Contacts

  • Bernardine Dias

    Dias, Bernardine

    (412)268-9365

Personnel

  • Sarah Belousov

    Belousov, Sarah

    412-915-4186

  • Beatrice Dias

    Dias, Beatrice

  • Gary Giger

    Giger, Gary

    412-268-9816

  • Ermine Teves

    Teves, Ermine

    (412)268-1289

Automated Orbital Mapping

Automated Orbital Mapping

The Automated Orbital Mapping project is developing machine vision techniques to extract features from hyperspectral imagery of Mars. Then machine learning is applied to interpret and classify the geology of the terrain. The goal is to improve the speed and rigor by which orbital imagery can be applied to geologic analysis of planetary surfaces.

Additional Information

This three year project is supported by the NASA Advanced Information Systems program of the Science Mission Directorate.

Contacts

Personnel

  • Alan Kraut

    Kraut, Alan

    909-632-6765

Automation for Specialty Crops

Automation for Specialty Crops

Comprehensive Automation for Specialty Crops (CASC) is a multi-institutional initiative led by Carnegie Mellon Robotics Institute to comprehensively address the needs of specialty agriculture focusing on apples and horticultural stock. CASC will develop methods to improve production efficiency, identify threats from pests and diseases, and, detect, monitor and respond to food safety hazards. We expect advances from the integration of robotics technology and plant science.

Contacts

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Personnel

  • Matthew Aasted

    Aasted, Matthew

    (412)268-7086

  • George Kantor

    Kantor, George

    (412)268-7084

  • Jacqueline Libby

    Libby, Jacqueline

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Autonomous Helicopter Landing

Autonomous Helicopter Landing

The Boeing Unmanned Little Bird equipped with a sensor payload and algorithms that enabled the first autonomous landing zone evaluation and landing by a full-scale helicopter.

Contacts

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Robotic Astrobiology

Robotic Astrobiology

The Life in the Atacama project is developing techniques to search for life in extreme environments on Earth and beyond. This field, called robotic astrobiology, seeks evidence of how life may develop in the universe. The search begins on Earth. We are probing the limits of life in the Atacama Desert of Chile, the driest desert on Earth. Organisms that survive in the Atacama are subjected to high levels of ultraviolet radiation and must survive on only tiny amounts of water. Our rover, called Zoe, uses science instruments to detect these organisms and a drill to access the shallow subsoil. Zoe operates autonomously like a robot exploring Mars, communicating with a science team only twice per day.

Contacts

Personnel

  • Greydon Foil

    Foil, Greydon

    412-268-8048

  • Michael Furlong

    Furlong, Michael

  • David Kohanbash

    Kohanbash, David

    (412)268-2856

  • Alex Long

    Long, Alex

  • Jim Teza

    Teza, Jim

    (412)268-1201

  • Srinivasan Vijayarangan

    Vijayarangan, Srinivasan

Beamed-power Lunar Rover

Beamed-power Lunar Rover

Power beaming, by laser or other wavelength, enables operation and recharging of rovers without fixed infrastructure. Rovers on the moon could operate on crater floors and areas of shadow.

Contacts

Personnel

  • Steven Huber

    Huber, Steven

  • Dominic Jonak

    Jonak, Dominic

Braille Writing Tutor

Braille Writing Tutor

TechBridgeWorld's Automated Braille Writing Tutor (BWT) project seeks to improve braille literacy among visually impaired youth around the world. In developing communities, braille is almost always written with a slate and stylus. For visually impaired children, learning to write braille in this manner can be a formidable process as they: (1) must learn mirror images of the letters, (2) may not have the individual guidance they need, (3) experience delayed feedback, and (4) must use limited or expensive paper supplies.

In response to the observed need for enhancing literacy for the visually impaired in developing communities, TechBridgeWorlddeveloped a low-cost device and software which use audio feedback to provide guided practice for beginners learning to write braille. The BWT consists of an electronic slate and wireless stylus, and is connected to a computer. As the user writes on the slate with the stylus, the tutor provides immediate audio feedback by repeating dots, written letters, numbers, or words, guiding writing and correcting mistakes. This feedback also serves as a diagnostic tool, giving instructors real-time understanding of students’ performance.

Since the project's beginning in 2006, the BWT now has several learning and educational game modes, is functional in English, Arabic, Bangla, Chinese, French and Swahili, and has been field tested in India, Tanzania and Bangladesh. Open source BWT hardware and software are available on SourceForge. The latest prototype, the Standalone Braille Tutor (SABT), has three hardware interface options for different levels of learning and contains onboard computing and power as a stand-alone tool to address the challenges of power failures and computer access in developing communities.

Contacts

  • Bernardine Dias

    Dias, Bernardine

    (412)268-9365

Personnel

  • Sarah Belousov

    Belousov, Sarah

    412-915-4186

  • Beatrice Dias

    Dias, Beatrice

  • Gary Giger

    Giger, Gary

    412-268-9816

  • Ermine Teves

    Teves, Ermine

    (412)268-1289

Cooperative Robotic Watercraft

Cooperative Robotic Watercraft

Small, autonomous watercraft are an ideal approach to a number of applications in flood mitigation and response, environmental sampling, and numerous other applications. Relative to other types of vehicles, watercraft are inexpensive, simple, robust and reliable. Specifically, we are developing low cost airboats: flat-bottomed boats that use an above-water fan to propel themselves forward safely and effectively through shallow or debris-filled water. The vision is to have large numbers of very inexpensive airboats provide situational awareness and deliver critical emergency supplies to victims, as well as low cost tools for environmental protection and monitoring.

Additional Information

This project is in collaboration with the Cooperative Robot Agent Systems Laboratory of CMU, namely Paul Scerri (pscerri [AT] cs.cmu.edu), Prasanna Velagapudi (pkv [AT] cs.cmu.edu) and Christopher Tomaszewski (christomaszewski [AT] cmu.edu).

Contacts

Personnel

  • Abhinav Valada

    Valada, Abhinav

    412-268-3856

Coordinated Assembly Teams

Coordinated Assembly Teams

Full autonomy achieves a task without human interaction. The other extreme is teleoperation under direct human control. Sliding autonomy is a spectrum of interaction among robots and humans that exploits the best of each to maximize reliability and capability. Our flexible architecture enables robot-human teams to perform tightly coupled tasks such as assembly of structures. We enable humans and robots to cooperate in a single framework. To improve the ability to handle unexpected events and failures, we employ sliding autonomy to remotely assist robots. The system models users to learn when and how best to ask for help. The system can perform task as fast as an autonomous system with the reliability of a dedicated teleoperator by leveraging the capabilities of the robots and humans.

Additional Information

Key Technologies:

  • Sliding Autonomy
  • Multi-Robot Architecture
  • User Modeling

Contacts

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Coordinated Robotics for Material Handling

Coordinated Robotics for Material Handling

Planetary robots which perform assembly tasks to prepare for human exploration must be able to operate in unmodeled environments and in unanticipated situations. We are working on a system of mobile robots that perform precise coordinated maneuvers for transporting assembly materials. We are also developing an interface that allows an operator to step in at various levels of autonomy, providing the system with both the efficiency of an autonomous system and the reliability of a human operator.

Contacts

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Personnel

  • Joseph Lisee

    Lisee, Joseph

 Distributed SensorWebs

Distributed SensorWebs

We are developing and implementing wireless technology for distributed sensing and actuation in horticultural enterprises. The heart of the sensor web is the "node", a low cost device capable of measuring moisture, photon flux, temperature, relative humidity, wind speed, and other parameters that affect plant growth and development while also providing control capabilities. The result is an inexpensive, easily installed system that monitors environmental data and implements remote (or even automatic) actuation of sprinklers, fans, heaters, and other devices.

Our system is in use at several horticultural enterprises throughout the country. Our sensor nodes are used by researchers trying to understand plant growth and development, and by growers interested in improving plant quality while decreasing the operating cost (water, pesticides, etc...).

Additional Information

We are actively deploying sensor networks in nurseries, greenhouses, greenroofs, and orchards. In all of these areas, we are working with growers and domain specialists to solve relevant problems. We also provide remote access to many of our sensor networks so growers and researchers can monitor the sites as well as allow the growers to control irrigation from remote locations. The first generation of sensor web technology was installed in September of 2003.

This work is funded by the United States Department of Agriculture (USDA) SCRI-MINDS project and is being led by the University of Maryland.

For more information please visit http://www.smart-farms.net/.

Contacts

Personnel

  • David Kohanbash

    Kohanbash, David

    (412)268-2856

  • Abhinav Valada

    Valada, Abhinav

    412-268-3856

Dynamic Human-Robot Teams

Dynamic Human-Robot Teams

Pickup teams of robots and humans can adapt to unknown, dynamic and adversarial environments, and efficiently execute complex tasks in a robust manner. Both human and robot team members may have only minimal knowledge of each other's behavior but are able to team effectively. Human members might plan while robots might sense and execute tasks. With this system developed in this project, dynamic and unknown obstacles, robot malfunctions, disruptions in communication, and changes in team resources were all handled gracefully and efficiently with team members adopting different roles best suited to efficiently executing the overall mission under the prevailing conditions. We focused specifically on the problem of dynamically forming teams of heterogeneous robots with a range of capabilities together with human team members. The human members of the team were responsible for the highest-level planning and the robots had comparatively limited capabilities: they could sense information about their environment, and they could be tasked to execute abstract tasks. Furthermore, the robots were capable of accepting spoken orders that specified high-level objectives, received important cue information about the terrain, and provided status reports as needed. These research objectives were demonstrated and evaluated in a treasure hunt scenario.

Contacts

  • Tony Stentz

    Stentz, Tony

    (412)268-8155

Personnel

  • Brenna Argall

    Argall, Brenna

    +41 021 693 591

  • Balajee Kannan

    Kannan, Balajee

    (412)268-9816

  • Marc Zinck

    Zinck, Marc

Dynamic Human-Robot Teams

Dynamic Human-Robot Teams

Many domains, such as disaster response, agriculture, construction, and mining, require the coordination of teams of robots and humans to accomplish a collection of spatially distributed tasks. Each agent (robotic or human) has specific capabilities that make that agent particularly suited to certain tasks. While some tasks are independent of each other, other tasks may be related by different constraints. These constraints are in some cases a result of the complementary capabilities of robots and humans which require them to cooperate to achieve certain goals. Many tasks may have a fixed pre-specified location at which they must be performed, but others may require movement from one location to another, and yet others may have a choice of locations where they may take place. In the face of this complexity, the problem of coordinating a team of robots and humans to achieve the desired goals is an important one. This vision of effective human-robot teams working together efficiently and seamlessly in uncertain and dynamic environments motivates our work.

Contacts

Personnel

  • Jimmy Bourne

    Bourne, Jimmy

  • Balajee Kannan

    Kannan, Balajee

    (412)268-9816

  • Nisarg Kothari

    Kothari, Nisarg

  • Victor Marmol

    Marmol, Victor

Education e-Village

Education e-Village

To address the need for relevant, accessible and useful resources to enhance technology education in developing regions, TechBridgeWorld initiated Education e-Village (E-Village). E-Village is an online community where educators from around the world can share ideas, experiences, expertise, educational resources, and strategies to promote and enhance technology education. The concept for E-Village began with an introductory robotics course co-taught at Ashesi University in Ghana.

Partnerships with educators from universities around the world have greatly impacted research on this project. The E-Village prototype was designed based on educator feedback from universities in Bangladesh, China, Ghana, the Philippines, Thailand, the United Kingdom and the United States.

Contacts

  • Bernardine Dias

    Dias, Bernardine

    (412)268-9365

Personnel

  • Sarah Belousov

    Belousov, Sarah

    412-915-4186

  • Beatrice Dias

    Dias, Beatrice

  • Gary Giger

    Giger, Gary

    412-268-9816

  • Ermine Teves

    Teves, Ermine

    (412)268-1289

Girls of Steel

Girls of Steel

The FRC mentors the Girls of Steel, an all-girls robotics team that competes in the FIRST Robotics Competition. The team is composed of 40 girls from 20 different high schools in the Pittsburgh area.

Contacts

Hydroponic Automation

Hydroponic Automation

We are developing robotic approaches towards hydroponic growing. Hydroponic growing can increase overall crop yield. This is especially important for minimizing disease and controlling the quality of specialty crops. Our goal is to develop inexpensive robotic systems that a small-medium scale grower can afford to implement.

Additional Information

Personnel

iSTEP

iSTEP

iSTEP (innovative Student Technology ExPerience) is a TechBridgeWorld program that provides Carnegie Mellon students with real-world experience in applying their knowledge and skills for creative problem solving in unfamiliar settings. The multidisciplinary iSTEP team is comprised of a mix of undergraduate and graduate students and recent alumni from various departments at Carnegie Mellon. The students work in a globally-distributed team with some members working from campus with others living and working at the overseas partner location.

Together with TechBridgeWorld, the iSTEP team collaborates on technology research projects for underserved communities with local partners. The iSTEP internship locations include Tanzania in 2009, Bangladesh in 2010 and Uruguay in 2011 with projects in assistive technology, literacy tools and information exchange.

Contacts

  • Bernardine Dias

    Dias, Bernardine

    (412)268-9365

Personnel

  • Sarah Belousov

    Belousov, Sarah

    412-915-4186

  • Beatrice Dias

    Dias, Beatrice

  • Gary Giger

    Giger, Gary

    412-268-9816

  • Ermine Teves

    Teves, Ermine

    (412)268-1289

Irrigation Management

Irrigation Management

Sensor networks provide control and actuation for intelligent, precision irrigation in greenhouses and plant nurseries.

Contacts

 Long-Range Rover Navigation

Long-Range Rover Navigation

Upcoming planetary rovers will embark on ambitious campaigns of exploration. The Mobile Science Laboratory scenario called for a highly capable new class of rover to explore distinct science sites separated by a distance of several kilometers, collecting vast amounts of scientific data.

Important Mars science can be accomplished through detailed examination of constrained science sites but planetary surface investigation will move beyond detailed examination to regional exploration. Regional exploration is motivated by different science objectives, focusing on geologic units, their distributions and properties, and the discovery of interesting features within or at the contact of these units in order to understand the geologic record and development of the planet. Regional exploration is made possible by reliable long-range autonomous navigation.

This project addressed Rover Technology in the area of Long-Range Autonomous Navigation. We focused on maturing this technology to NASA Technology Readiness Level 6 (TRL-6), through experimentation in a relevant environment.

Using our solar-powered rovers Hyperion and Zoe we demonstrated preliminary results in long-range autonomous rover navigation with traverses of 300-600 meters in a single command cycle using 30 meter resolution digital terrain maps and onboard odometric information (meaning without GPS). We achieved one instance of single-command 1-kilometer autonomous rover traverse in the Atacama Desert, April 2003. This project aimed to enable planetary rovers to routinely exceed 1 kilometer in single-command autonomous traverse.

Contacts

  • Tony Stentz

    Stentz, Tony

    (412)268-8155

  • David Wettergreen

    Wettergreen, David

    (412)268-5421

  • Marc Zinck

    Zinck, Marc

Lunar Regolith Excavation and Transport

Lunar Regolith Excavation and Transport

This research is developing techniques for working lunar regolith (soil) in order to support resource extraction and site preparation. We are conducting a comprehensive study of excavation and transport mechanisms and scaling the results to the lunar environment. We are innovating new mechanisms and methods for lunar operations.

Additional Information

This work is supported by the NASA Exploration Systems Mission Directorate and is performed in collaboration with Astrobotic Technologies, Inc.

Contacts

Lunar Prospecting Rover

Lunar Prospecting Rover

The Lunar Rover Initiative is developing Scarab to evaluate and demonstrate a combined drilling and science rover platform for lunar exploration. Scarab needs to be able to withstand extreme temperatures, perpetual darkness, and intermittent communications to explore polar regions of the moon in order to survey sites and understand resources for future science and exploratory missions. Working for nearly a decade to develop feasible mission concepts and validate technologies in extreme environments here on Earth, we are experienced, skilled, and dedicated to the vision of lunar exploration.

Additional Information

This work supported by grants from NASA, NASA Johnson Space Center, and NASA Glenn Research Center.

Contacts

Personnel

  • Dominic Jonak

    Jonak, Dominic

  • David Kohanbash

    Kohanbash, David

    (412)268-2856

  • Scott Moreland

    Moreland, Scott

  • Chris Skonieczny

    Skonieczny, Chris

Google Lunar X Prize

Google Lunar X Prize

We are developing a rover to explore for ice at the pole of the moon. The robot will investigate methane, ammonia and water by drilling, heating, and onboard analysis. This “Icebreaker” mission will also claim Google’s Lunar X-Prize. Carnegie Mellon is collaborating with Astrobotic technology to land the first privately funded space robot beyond planet Earth.

Contacts

Personnel

  • Joshua Anhalt

    Anhalt, Joshua

  • Jason Calaiaro

    Calaiaro, Jason

  • Heather Jones

    Jones, Heather

  • John Thornton

    Thornton, John

    (412)268-6121

  • David Wettergreen

    Wettergreen, David

    (412)268-5421

  • Red Whittaker

    Whittaker, Red

    412-268-6559

NavPal

NavPal

Safe and independent navigation of urban environments is a key feature of accessible cities. People who have physical challenges need practical, customizable, low-cost and easily-deployable mobility aids to help them safely navigate urban environments. Technology tools provide opportunities to empower people with disabilities to overcome some day-to-day challenges.

Our work focuses on designing, implementing, testing and deploying a smart mobile phone-based personalized navigation aid (NavPal) to enhance the navigation capability and thereby the independence and safety of visually impaired and deafblind people. The goal of the project is to use the smart phone navigation application to assist visually impaired and deafblind people to safely evacuate specific buildings in emergency situations.

NavPal is a joint effort of TechBridgeWorld and the rCommerce lab, two research groups in the Robotics Institute at Carnegie Mellon University, in collaboration with Google Inc.

Contacts

  • Bernardine Dias

    Dias, Bernardine

    (412)268-9365

Personnel

  • Sarah Belousov

    Belousov, Sarah

    412-915-4186

  • Beatrice Dias

    Dias, Beatrice

  • Gary Giger

    Giger, Gary

    412-268-9816

  • Ermine Teves

    Teves, Ermine

    (412)268-1289

Nomadic Exploration

Nomadic Exploration

Like nomadic and migratory species traveling in search of sustenance and temperate climate, Nomadic Rovers will navigate entire moons and planets. Nomadic Rovers are cold-blooded, energy gathering, resource-aware agents that discover and exploit routes of eternal light. Points of eternal light may not exist in the universe, but infinite routes of eternal light await discovery. Regions of moderate climate may not exist, but continuous mild temperatures will exist along planetary routes. The discovery of such sun-lit temperate routes enables a fundamentally improved means of exploring a planetary body: long-term, continuous, and nomadic surface missions. Existence of circumnavigation routes was speculated on in the Phase I study. At that time map resolution was too low to enable route-finding and validation of route existence. New detailed surface maps for the Moon, Mars, Mercury, and some asteroids now exist, and the time is right for a great leap of viability for the visionary concept of Nomadic Exploration.

Contacts

Personnel

  • Christopher Cunningham

    Cunningham, Christopher

  • Steven Huber

    Huber, Steven

  • Heather Jones

    Jones, Heather

  • Nathan Otten

    Otten, Nathan

  • Chuck Whittaker

    Whittaker, Chuck

    (412)268-1119

  • Uland Wong

    Wong, Uland

    412-268-3978

Reefbot

Reefbot

ReefBot is a Pittsburgh-based team of individuals committed to developing and using underwater robotic technology for the purpose of ocean exploration, education, and coral reef conservation. ReefBot recognizes the importance of inspiring young children to explore and love the world they live in. Thanks to the development of novel robotic technology, young children can now become virtual explorers of the underwater world of the coral reefs.

Additional Information

This work supported by grants from Pittsburgh Zoo & Aquarium, Carnegie Mellon University, Spark, a program of The Sprout Fund

Contacts

Personnel

  • Mark Desnoyer

    Desnoyer, Mark

  • Michael Furlong

    Furlong, Michael

  • Scott Moreland

    Moreland, Scott

  • John Thornton

    Thornton, John

    (412)268-6121

Riverine Mapping

Riverine Mapping

This project is developing technology to map riverine environments from a low-flying rotorcraft. Challenges include dealing with varying appearance of the river and surrounding canopy, intermittent GPS and a highly constrained payload. We are developing self-supervised algorithms that can segment images from onboard cameras to determine the course of the river ahead, and we are developing devices and methods capable of mapping the shoreline.

Contacts

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Personnel

  • Andrew Chambers

    Chambers, Andrew

  • Sezal Jain

    Jain, Sezal

  • Sebastian Scherer

    Scherer, Sebastian

    (412)589-9581

  • Luke Yoder

    Yoder, Luke

Robot Teams in Dynamic Environments

Robot Teams in Dynamic Environments

This group harnesses economic principles to design capable and reliable multirobot systems. We create and transfer algorithms to vehicles that range in size and ability from small research robots to autonomous outdoor platforms. We apply market-based multirobot coordination techniques to difficult domains such as mapping, exploration, reconnaissance, and monitoring.

Contacts

  • Tony Stentz

    Stentz, Tony

    (412)268-8155

Robotic Desert Racing

Robotic Desert Racing

The Grand Challenge was a 300km autonomous robotic desert race. We are out to win with two HUMMERS, fast autonomous navigation technology, and a great team.
The race is a winner-take-all, autonomy-only rumble across 300 kilometers of desert trails, mountains and wide-open flats. 118 teams are vying for 20 starting positions, and on race day only one will win. The Red Team is playing to win, with world-class terrain modeling, robotic vehicles, and blazing-fast navigation.

Additional Information

Key Technologies:

  • Ultra-resolution topography
  • Fused lidar, radar and bifocal stereo
  • Active suspension and gimbal-stabilized sensors
  • Fast trajectory planning with dynamics
  • Two autonomous HUMMERS:
    Sandstorm & H1ghlander

Contacts

Robotic Traverse

Robotic Traverse

Long-distance tractor convoys traverse Antarctica to deliver fuel and supplies. Traveling thousands of miles and carrying millions of pounds of cargo, they require months to reach the South Pole and other field sites in the Antarctic interior. By incorporating terrain modeling, obstacle detection, path planning and automatic guidance, this project seeks to make traverses safer, faster, and more efficient.

Contacts

Personnel

  • Dominic Jonak

    Jonak, Dominic

Science on the Fly

Science on the Fly

The Science on the Fly project developed approaches to enable planetary rovers to reason abou the science investigation that they are undertaking, but interpreting science observations in real-time and making decisions the improve the quality and quantity of their scientific data return.

Sense and Avoid for Unmanned Aerial Vehicles

Sense and Avoid for Unmanned Aerial Vehicles

Unmanned Aerial Vehicles (UAVs) today cannot sense and avoid autonomously. However, these aircraft represent a significant mid-air collision hazard to other aircraft operating in the same airspace. In addition, these types of UAS are frequently operated in close proximity to the ground and cultural features (buildings, towers, etc.). Unless they become better than human pilots they will not be allowed to freely operate in commercial air spaces. UAVs do not have the required payload and power to use radar and other active sensors in order to detect other aircraft in a wide field of regard. Cameras with their wide field of regard, low power and weight provide a feasible alternative to active sensors for detecting intruding aircraft within a certain radius. In the U.S. there are approximately 0.5 midair collisions per 1 million flight hours. There have already been several near misses with UAVs and both the military and commercial aviation have called for a system that can automatically avoid mid-air collisions. As stipulated by FAA a human equivalent sense and avoid system must be able to reliably detect and avoid intruding aircraft within a 3 mile radius with a field of regard of 270 x 30 degrees.

Contacts

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Personnel

Shipboard Navigation for Micro Air Vehicles

Shipboard Navigation for Micro Air Vehicles

The goal of this project is to develop an autonomous Micro Air Vehicle to conduct routine shipboard inspections for fire control and damage assessment. The challenges include construction of a small and light vehicle which can navigate through narrow passageways on the ship and accurate localization of the vehicle to enable such navigation.

Contacts

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Personnel

Exploration of Planetary Skylights and Caves

Exploration of Planetary Skylights and Caves

Skylights are recently-discovered “holes” on the surface of the Moon and Mars that may lead to planetary caves. These openings represent an unparalleled opportunity to access subterranean spaces. Robots are well-suited to utilize skylights for accessing, exploring, surveying, and operating in cave destinations as low-risk, high-return precursors to human missions.

Unprecedented insight into the geological origin and evolution of the planets can be gleaned from the interiors of planetary caves, such as lava tubes, on the Moon and Mars. Their subterranean nature offers shelter from radiation and their expansiveness is also well suited for early human habitation. They may be the prime locations to search for the evidence of prior life on Mars and other worlds.

This program develops mechanism, perception, autonomy, modeling and operations to enable robotic exploration of planetary skylights and caves. These focus areas will build roadmap with the objective of a robotic lunar skylight mission. The program will popularize robots for skylights and caves by engendering collaboration between planetary scientists and roboticists, leading public technology demonstrations at terrestrial analog sites, and by engaging in broad dissemination of scholarly data.

Personnel

  • Christopher Cunningham

    Cunningham, Christopher

  • Heather Jones

    Jones, Heather

  • Nathan Otten

    Otten, Nathan

  • Chuck Whittaker

    Whittaker, Chuck

    (412)268-1119

  • Red Whittaker

    Whittaker, Red

    412-268-6559

  • Uland Wong

    Wong, Uland

    412-268-3978

Subterranean Robotics

Subterranean Robotics

Robots are exploring underground spaces such as mines, caves, and sewers to map voids and repair infrastructure like pipes and tanks. The goal of subterranean robotics is to use robots to explore an underground world that is inaccessible and too dangerous for human entry . We are working on systems that drive, swim, and transform to operate in narrow passages. Groundhog is a first generation mobile system for autonomous mine mapping. Cave Crawler is a newer robot that is faster and smaller. Ferret is a robotic imaging device that can be lowered down narrow passages, such as boreholes. Helix and Minefish are two robots under development for the mobile exploration of hard-to-access spaces.

Additional Information

Key Technologies:

  • Reliable autonomous exploration
  • 3D sensing and mapping
  • Operation in dry and flooded environments
  • Novel mechanisms for subterranean spaces

Contacts

  • Aaron Morris

    Morris, Aaron

    412-682-6498

TechBridgeWorld

TechBridgeWorld

TechBridgeWorld is a research group at Carnegie Mellon University that innovates and implements technology solutions to meet sustainable development needs around the world. Through strong collaborations with partners in developing communities, we explore and enhance the role of technology globally, focusing on two main principles: sharing expertise to create innovative and locally suitable solutions, and empowerment of indigenous populations to create sustainable solutions. Through these efforts TechBridgeWorld creates technology accessible and relevant to all.

TechBridgeWorld was founded in 2004 by Robotics Assistant Research Professor M. Bernardine Dias, TechBridgeWorld is pioneering research in the field of Information and Communication Technology for Development (ICTD).

Additional Information

TechBridgeWorld has several projects and programs. Our work includes:

  • Assistive Technology - Developing educational and navigational tools for visually impaired and deaf communities.
  • TechCaFE - Creating technology tools for customizable and fun education.
  • iSTEP - An internship opportunity for Carnegie Mellon students to conduct technology research projects in underserved communities.
  • Education e-Village - An online community for technology education in underserved communities.

Contacts

  • Bernardine Dias

    Dias, Bernardine

    (412)268-9365

Personnel

  • Sarah Belousov

    Belousov, Sarah

    412-915-4186

  • Beatrice Dias

    Dias, Beatrice

  • Gary Giger

    Giger, Gary

    412-268-9816

  • Ermine Teves

    Teves, Ermine

    (412)268-1289

TechCaFE

TechCaFE

TechCaFE (Technology for Customizable and Fun Education) is a TechBridgeWorld program that provides educators with simple and customizable tools to make learning fun for students. TechCaFE currently offers tools for teaching and practicing English literacy. This includes CaFE Teach, a web-accessible content authoring tool that teachers use to create and modify English grammar exercises. Students learn content added by teachers through CaFE Teach via CaFE Web, a web-based practice tool, or CaFE Phone, a mobile phone game. Future work involves developing CaFE Play for customizing educational games.

TechBridgeWorld has worked with or is currently working with primary school and university students, deaf and hard-of-hearing students and migrant workers, in Bangladesh, Qatar, Tanzania and the United States.

Contacts

  • Bernardine Dias

    Dias, Bernardine

    (412)268-9365

Personnel

  • Sarah Belousov

    Belousov, Sarah

    412-915-4186

  • Beatrice Dias

    Dias, Beatrice

  • Gary Giger

    Giger, Gary

    412-268-9816

  • Ermine Teves

    Teves, Ermine

    (412)268-1289

Underwater Cave Exploration

Underwater Cave Exploration

The Deep Phreatic Thermal Explorer initiative created the navigation and autonomy needed to enable an underwater robot to map the depths of the Zacaton Cenote in central Mexico. This scientific investigation sought to understand the unique organisms that survive in this, the deepest sink hole in the world.

Contacts

Personnel

  • Dominic Jonak

    Jonak, Dominic

Unmanned Security Robots

Unmanned Security Robots

This project developed autonomous ATVs to secure borders and facility perimeters. The goal of these scouts was to automatically patrol a desired path, detect and avoid obstacles, and provide operators with live video and audio feeds. They aimed assist their human counterparts by providing eyes and ears in dangerous locations. Streaming audio and video enabled an operator to evaluate threats and suspicious activities from the safety of a command-and-control center. Vehicles could automatically detect and avoid obstacles as they navigated assigned patrol areas, relieving operators from constant vehicle monitoring. Many scouts could operate concurrently, enabling a security officer to cover an area much larger than could be handled alone.

Additional Information

Key Technologies:

  • High speed navigation
  • Path following
  • Obstacle detection
  • Collision avoidance
  • Wireless graphical user interface

Contacts

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

  • Tony Stentz

    Stentz, Tony

    (412)268-8155

Personnel

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

Urban Challenge

Urban Challenge

Boss is an autonomous 2007 Chevrolet Tahoe that uses on-board sensors (GPS, lasers, radars, and cameras) to track other vehicles, detect static obstacles and localize itself relative to a road model. A three layer planning system combines mission, behavioral and motion planning to drive in urban environments. The mission planning layer considers which street to take to achieve a mission goal. The behavioral layer determines when to change lanes, precedence at intersections and performs error recovery maneuvers. The motion planning layer selects actions to avoid obstacles while making progress towards local goals. The system was developed from the ground up to address the requirements of the DARPA Urban Challenge using a cyclic system development process with a heavy emphasis on regular, regressive system testing. During the national qualification event and the urban challenge final event Boss demonstrated some of its capabilities, qualifying first and winning the 85km DARPA 85 Urban Challenge.

Contacts

  • Michele Gittleman

    Gittleman, Michele

    412-268-4691

  • Chris Urmson

    Urmson, Chris

  • Red Whittaker

    Whittaker, Red

    412-268-6559

Personnel

  • Joshua Anhalt

    Anhalt, Joshua

  • Michele Gittleman

    Gittleman, Michele

    412-268-4691

  • Thomas Howard

    Howard, Thomas

    585-544-0794

  • Maxim Likhachev

    Likhachev, Maxim

    412-268-5581

  • Nick Miller

    Miller, Nick

  • Dave Seneker

    Seneker, Dave

  • Sanjiv Singh

    Singh, Sanjiv

    (412)268-6577

  • Jarrod Snider

    Snider, Jarrod

    412-596-2601

  • Spencer Spiker

    Spiker, Spencer

    412-215-3713

  • Tony Stentz

    Stentz, Tony

    (412)268-8155

  • Chris Urmson

    Urmson, Chris

  • Red Whittaker

    Whittaker, Red

    412-268-6559

Rover Wheel Analysis

Rover Wheel Analysis

The rover wheel analysis project analyzes different wheel and grouser designs using methods developed at CMU. We have a wheel test rig that is capable of measuring 6 axis forces on a wheel, while using a camera to quantify soil particles as they move.

Additional Information

We have several simulants that can be put in the test rig for simulating wheel interactions on different planetary locations.

Contacts

Personnel

  • Hiroaki Inotsume

    Inotsume, Hiroaki

  • Scott Moreland

    Moreland, Scott

Visual Yield Mapping

Visual Yield Mapping

Growers of high-value agriculture require information about the current state of the crop to efficiently manage production. We are designing methods to collect crop information automatically with accuracy, efficiency, precision.

Additional Information

There are three main themes to our work:

  • Generative Visual Estimation
  • A visual estimation framework applicable across different commodities (strawberry, grape, apple, mushroom, peaches etc.) measuring desired crop characteristics from images with minimal human burden

  • Active Sampling
  • Adaptive statistical sampling by human-robot teams to develop optimal strategies with respect to:

    • Number of samples
    • Location of samples
    • Cost of sampling
    • Accuracy of crop estimates

  • Active Perception
  • Physical actuation to improve the measurements collected by the robots, by estimating occluded area on plant and move sensor head or actuator to reveal hidden crop.

      Contacts

      • Sanjiv Singh

        Singh, Sanjiv

        (412)268-6577

      Personnel

      • Zania Pothen

        Pothen, Zania

      • Kyle Wilshusen

        Wilshusen, Kyle

      • Chunlong Zhang

        Zhang, Chunlong