Humanoid Robonaut "sees" with two AVT Prosilica GC2450C GigE Cameras
March 9, 2011 - Built in partnership with General Motors (GM) and the Oceaneering Space Systems of Houston, NASA’s Robonaut (R2) is the second generation of highly dexterous humanoid robot designed to work alongside humans and execute simple, repetitive or dangerous tasks on Earth or on board the International Space Station (ISS).
R2: The New Generation
Developed in 1997 the first generation of Robonaut (R1) was a human-like robotic assistant capable of performing simple maintenance tasks. Its successor, R2, is a fully modular, highly dexterous 300 pound robot that consists of a head and a torso with two arms and two hands. R2’s many technological improvements include an improved range of sensors that features two Prosilica GC2450 color cameras from Allied Vision Technologies and an Infra-Red Time-of-Flight (TOF) camera. Capable of speeds more than four times faster than R1, R2 features a total of 350 sensors (for tactile, force, position, range-finding and vision sensing) and 38 power PC processors enabling it to perform functions such as object recognition and manipulation.
R2 is also able to react to its surroundings and operate semi-autonomously.
Other technological improvements include optimized overlapping dual arm dexterous workspace, series elastic joint technology, extended finger and thumb travel, miniaturized 6-axis load cells, redundant force sensing, ultra-high speed joint controllers and extreme neck travel. Capable of 42 degrees of freedom (including 24 in its hands and fingers alone) R2’s dexterity allows it to use the same tools as astronauts removing the need for robot specific tools.
Real-Time Vision Recognition
R2’s vision equipment is housed inside his helmet. The system uses color, pixel intensity and texture based segmentation as well as advanced pattern recognition techniques to extract the necessary information. To simplify the procedure the system focuses on certain areas of the image using Region of Interests (ROI). ROI is a function that allows a certain portion of the available pixels to be read out from the camera resulting in a much faster frame rate and less data to be processed. In addition, the TOF sensor data allows the background to be removed in order to focus on the object of interest (tools, boxes, etc…) Built-in classification techniques within the software are used to perform 3D and pattern-recognition functions in real-time to allow R2 to compute feasible trajectories and decide where to place its hands to execute a set of pre-determined tasks, such as opening boxes autonomously.
The software used by the system is MVtec’s Halcon 9.0. MVtec is an AVT software partner.
R2 underwent a series of rigorous tests prior to its launch on space shuttle Discovery on 24th February 2011. During stage 1 R2 will initially be hard-mounted and stationed in the Destiny laboratory on board the ISS where it will be monitored while executing tasks and operations similar to those performed on Earth.
If successful R2 could move on to stage 2 of the mission and become mobile to perform station maintenance tasks such as vacuuming or cleaning filters. The ultimate goal is to send R2 outside the ISS to perform dangerous EVA (Extra-vehicular activity) tasks during stage 3. There are no plans to return R2 to Earth.
MORE CASE STUDIES
SKF automates factory with Egemin automated storage system
With the new system, SKF can organize the logistics of its bearings, lubricants and seal products more efficiently and economically. The completed...
Sensor Concepts chooses Acromag's XCOM-6400 for InfiniSCAN measurement systems
Although the original intent was to use the power management system to reduce processor throughput and keep the board operating under 20 watts per...
Rotork actuators support environmental improvement at Aberthaw Power Station
Through the use of automation that includes Rotork valve actuation, Aberthaw can efficiently generate around 1555 MW of electricity for the...
MAVERICK uses DCSNext solution to move DCS migration project to final phase
DCSNext capabilities allow INEOS Styrolution to avoid any additional downtime during migration and leverage the complete benefits of the latest...
Axiom automates B2C Europe with 100 destination packet mail sorter
The new sorter has automated B2C Europe's parcel and pack sortation, enabling the company to sort up to 8,000 packets an hour. This has given the...
Lighting Controllers – The Hidden Power Behind Automating Machine Vision
By Peter Bhagat, Gardasoft Vision
The ability of industrial vision systems to monitor, regulate, check, analyze, sort and classify with high...
VDMA: Germany sees record machine vision sales in 2015
In 2015, the German machine vision industry achieved record sales of 2 billion euros – a rise of 9 percent compared to the previous year. Sales...
T&M Associates announces Ivica Cacic as Senior Automation Specialist
Cacic’s skillset will provide clients with solutions to many automation challenges associated with process optimization, system integration and...
Best Industrial Networking Practices of Machine Vision Systems
In order to provide smooth production processes with critical machine vision applications, building a rugged Ethernet network is...
FANUC America announces expansion of CNC training program
FANUC currently offers a range of training courses covering CNC maintenance, operations and programming, servo and laser maintenance, Ladder/PMC...