ICub is a 1 metre tall open source robotics humanoid robot testbed for research into human cognition and artificial intelligence. It was designed by the RobotCub Consortium of several European universities and built by Italian Institute of Technology, is now supported by other projects such as ITALK; the robot is open-source, with the hardware design and documentation all released under the GPL license. The name is cub standing for Cognitive Universal Body. Initial funding for the project was €8.5 million from Unit E5 – Cognitive Systems and Robotics – of the European Commission's Seventh Framework Programme, this ran for 65 months from 1 September 2004 until 31 January 2010. The motivation behind the humanoid design is the embodied cognition hypothesis, that human-like manipulation plays a vital role in the development of human cognition. A baby learns many cognitive skills by interacting with its environment and other humans using its limbs and senses, its internal model of the world is determined by the form of the human body.
The robot was designed to test this hypothesis by allowing cognitive learning scenarios to be acted out by an accurate reproduction of the perceptual system and articulation of a small child so that it could interact with the world in the same way that such a child does. The dimensions of the iCub are similar to that of a 3.5-year-old child. The robot is controlled by an on-board PC104 controller which communicates with actuators and sensors using CANBus, it utilises tendon driven joints for the hand and shoulder, with the fingers flexed by teflon-coated cable tendons running inside teflon-coated tubes, pulling against spring returns. Joint angles are measured using custom-designed Hall-effect sensors and the robot can be equipped with torque sensors; the finger tips can be equipped with tactile touch sensors, a distributed capacitive sensor skin is being developed. The software library is written in C++ and uses YARP for external communication via Gigabit Ethernet with off-board software implementing higher level functionality, the development of, taken over by the RobotCub Consortium.
The robot was not designed for autonomous operation, is not equipped with onboard batteries or processors required for this —instead an umbilical cable provides power and a network connection. In its final version, the robot has 53 actuated degrees of freedom organized as follows: 7 in each arm 9 in each hand 6 in the head 3 in the torso/waist 6 in each legThe head has stereo cameras in a swivel mounting where eyes would be located on a human and microphones on the side, it has lines of red LEDs representing mouth and eyebrows mounted behind the face panel for making facial expressions. Since the first robots were constructed the design has undergone several revisions and improvements, for example smaller and more dexterous hands, lighter, more robust legs with greater joint angles and which permit walking rather than just crawling; the iCub has been demonstrated with capabilities to perform the following tasks, among others: crawling, using visual guidance with optic marker on the floor solving complex 3D mazes archery, shooting arrows with a bow and learning to hit the center of the target facial expressions, allowing the iCub to express emotions force control, exploiting proximal force/torque sensors grasping small objects, such as balls, plastic bottles, etc. collision avoidance within non-static environments, as well as, self-collision avoidance These robots were built by Istituto Italiano di Tecnologia in Genoa and are used by a small but lively community of scientists that use the iCub to study embodied cognition in artificial systems.
There are about thirty iCubs in various laboratories in the European Union but one in the United States. The first researcher in North America to be granted an iCub was Stephen E. Levinson, for studies of computational models of the brain and mind and language acquisition; the robots are constructed by IIT and cost about €250,000 or $266,186.38 each depending upon the version. Most of the financial support comes from the European Commission's Unit E5 or the Istituto Italiano di Tecnologia via the created iCub Facility department; the development and construction of iCub at IIT is part of an independent documentary film called Plug & Pray, released in 2010. Android Artificial intelligence Cyborg Ibn Sina Robot Robotics Nosengo, Nicola. "Robotics: The bot that plays ball". Nature. 460: 1076–8. Doi:10.1038/4601076a. PMID 19713909. Retrieved 2010-07-30. - Nature article about the iCub. YouTube Channel - a YouTube channel about the iCub. iCub presentations - from the Humanoid robotics symposium 2010. IROS'10 - Videos and workshop on iCub research.
Toward Intelligent Humanoids - Video showing current abilities of the iCub RobotCub Consortium the iCub project
IRobot Corporation is an American advanced technology company founded in 1990 by three members of MIT's Artificial Intelligence Lab who designed robots for space exploration and military defense. Incorporated in Delaware, the company designs and builds consumer robots for inside and outside of the home, including a range of autonomous home vacuum cleaners, floor moppers, other autonomous cleaning devices. IRobot was founded in 1990 by Rodney Brooks, Colin Angle and Helen Greiner after working in MIT's Artificial Intelligence Lab. In 1998, the company received a DARPA research contract. In September 2002, iRobot unveiled its home robots flagship, the Roomba, which sold a million units by 2004. IRobot began being traded on the NASDAQ in November 2005, under ticker symbol IRBT. On September 17, 2012, iRobot announced that it had acquired Evolution Robotics, manufacturer of automated floor mopper Mint.iRobot has sold more than 8 million home robots, has deployed more than 5,000 defense & security robots, as of 2012.
In addition to deployment as bomb-disposal units with the US military in Iraq and Afghanistan, PackBots have been used to gather data in dangerous conditions at the Fukushima Daiichi nuclear disaster site, an IRobot Seaglider detected underwater pools of oil after the Deepwater Horizon oil spill.iRobot has been criticized for attempting unregulated use of 6240-6740 MHz band, asking for an FCC exemption to do so. This band is for use for the lawn mowing robot without needing to use an electronic fence as a boundary marker, instead by using radio beacons; the band falls into a band reserved for radio astronomy use, thus interfering with radio telescope observations of methanol's 6.66852 GHz emissions. In February 2016, iRobot announced that it would sell its military robotics business to Arlington Capital Partners, in order to focus more on the consumer market. Roomba is an automated vacuum cleaning robot first released in 2002. Roomba is powered by a rechargeable battery, many models are available with a docking station to which the Roomba should return to recharge at the end of its cleaning cycle.
They work in conjunction with accessories that use both IR and RF. The company intentionally allows customers to hack the robot because they want people to experiment and improve the product; the API for the serial has been published and the serial port made accessible to make modifications easy to perform. In 2015 iRobot released a updated Roomba called the Roomba 980 with a camera that maps out a room of its objects; the camera uses VSlam technology to map out a room and the objects in the room to clean an entire floor of a home. The Roomba 980 includes Carpet boost where the suction is turned up when the Roomba sensor detects itself on carpets or rugs; this was one of the first Roombas to include Wi-FI connectivity with app control. Braava is iRobot's Floor Mopping Robot, designed to work on all hard-surface floors. Braava uses disposable or microfiber cleaning cloths for damp and/or dry cleaning; the design was known as the Mint until 2013. It was developed by Evolution Robotics, acquired by iRobot in 2012.
Create is a hobby robot, released in 2007. Create offers users the possibility of changing or adapting the robot's functions through experimentation with the basic elements of robotics as well as by adding sensors, wireless connections, computers, or other hardware. Mirra is a swimming-pool cleaning robot released in 2013; the Mirra cleans walls of large and small debris. It is the successor of the Verro. In recent developments, iRobot received FCC approval to move forward with their plans to commercialize and build a robotic lawn mower capable of using wireless technology, similar to their Roomba robot In early 2019 iRobot announced the Terra; the Terra uses Vslam and smart imprint mapping similar to the Roomba i7 to navigate and mow the lawn in a up and down pattern. The Terra has smart beacons stakes to form a boundary where the lawn mower robot should avoid going into such as a garden; the Terra includes WI-Fi capabilities with a docking station. The Terra will be available as a beta program in 2019 in the United States.
Scooba was iRobot's floor-washing robot. The product became commercially available in limited quantities in late 2005 before a full product release in 2006. Early models required either a special non-bleach cleaning solution or white vinegar to wash hard floors. Newer units could use plain water. Several versions were marketed. IRobot phased out the Scooba line of products in favor of the Braava line of floor moppers in 2016. Dirt Dog was designed for workshop use and was released in 2006; this product picks up small objects such as nuts, bolts and debris from a workshop or similar floor. The unit was able to be used on shop carpets and industrial floor surfaces; the Dirt Dog was discontinued in late 2010. My Real Baby was a robotic toy marketed by iRobot from 2000 and produced in partnership with the toy manufacturer Hasbro, it is no longer in production. This product, meant to look like a human infant, employed animatronic facial expressions and was developed from an expressive and responsive robot developed by iRobot corporation called "IT."
Connect R was made in 2010 it did not pass pilot test, was never introduced to public. Verro was a swimming-pool cleaning robot released in April 2007. Looj was a gutter-cleaning robot released in September 2007, based on an autonomous version created for a science fair project created by Lucas Garrow in 2004. Looj is not an autonomous robot, but rather a remote-contr
In computer science, artificial intelligence, sometimes called machine intelligence, is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and animals. Computer science defines AI research as the study of "intelligent agents": any device that perceives its environment and takes actions that maximize its chance of achieving its goals. Colloquially, the term "artificial intelligence" is used to describe machines that mimic "cognitive" functions that humans associate with other human minds, such as "learning" and "problem solving"; as machines become capable, tasks considered to require "intelligence" are removed from the definition of AI, a phenomenon known as the AI effect. A quip in Tesler's Theorem says "AI is whatever hasn't been done yet." For instance, optical character recognition is excluded from things considered to be AI, having become a routine technology. Modern machine capabilities classified as AI include understanding human speech, competing at the highest level in strategic game systems, autonomously operating cars, intelligent routing in content delivery networks and military simulations.
Artificial intelligence can be classified into three different types of systems: analytical, human-inspired, humanized artificial intelligence. Analytical AI has only characteristics consistent with cognitive intelligence. Human-inspired AI has elements from emotional intelligence. Humanized AI shows characteristics of all types of competencies, is able to be self-conscious and is self-aware in interactions with others. Artificial intelligence was founded as an academic discipline in 1956, in the years since has experienced several waves of optimism, followed by disappointment and the loss of funding, followed by new approaches and renewed funding. For most of its history, AI research has been divided into subfields that fail to communicate with each other; these sub-fields are based on technical considerations, such as particular goals, the use of particular tools, or deep philosophical differences. Subfields have been based on social factors; the traditional problems of AI research include reasoning, knowledge representation, learning, natural language processing and the ability to move and manipulate objects.
General intelligence is among the field's long-term goals. Approaches include statistical methods, computational intelligence, traditional symbolic AI. Many tools are used in AI, including versions of search and mathematical optimization, artificial neural networks, methods based on statistics and economics; the AI field draws upon computer science, information engineering, psychology, linguistics and many other fields. The field was founded on the claim that human intelligence "can be so described that a machine can be made to simulate it"; this raises philosophical arguments about the nature of the mind and the ethics of creating artificial beings endowed with human-like intelligence which are issues that have been explored by myth and philosophy since antiquity. Some people consider AI to be a danger to humanity if it progresses unabated. Others believe that AI, unlike previous technological revolutions, will create a risk of mass unemployment. In the twenty-first century, AI techniques have experienced a resurgence following concurrent advances in computer power, large amounts of data, theoretical understanding.
Thought-capable artificial beings appeared as storytelling devices in antiquity, have been common in fiction, as in Mary Shelley's Frankenstein or Karel Čapek's R. U. R.. These characters and their fates raised many of the same issues now discussed in the ethics of artificial intelligence; the study of mechanical or "formal" reasoning began with philosophers and mathematicians in antiquity. The study of mathematical logic led directly to Alan Turing's theory of computation, which suggested that a machine, by shuffling symbols as simple as "0" and "1", could simulate any conceivable act of mathematical deduction; this insight, that digital computers can simulate any process of formal reasoning, is known as the Church–Turing thesis. Along with concurrent discoveries in neurobiology, information theory and cybernetics, this led researchers to consider the possibility of building an electronic brain. Turing proposed that "if a human could not distinguish between responses from a machine and a human, the machine could be considered "intelligent".
The first work, now recognized as AI was McCullouch and Pitts' 1943 formal design for Turing-complete "artificial neurons". The field of AI research was born at a workshop at Dartmouth College in 1956. Attendees Allen Newell, Herbert Simon, John McCarthy, Marvin Minsky and Arthur Samuel became the founders and leaders of AI research, they and their students produced programs that the press described as "astonishing": computers were learning checkers strategies (and by 1959 were playing better than the average human
KAIST is a national research university located in Daedeok Innopolis, South Korea. KAIST was established by the Korean government in 1971 as the nation's first research-oriented science and engineering institution. KAIST has been internationally accredited in business education, hosting the Secretariat of AAPBS. KAIST has 10,200 full-time students and 1,140 faculty researchers and had a total budget of US$765 million in 2013, of which US$459 million was from research contracts. From 1980 to 2008, the institute was known as the Korea Advanced Institute of Science and Technology. In 2008, the name was shortened to "KAIST". In 2007, KAIST partnered with international institutions and adopted dual degree programs for its students, its partner institutions include the Technical University of Denmark, Carnegie Mellon University, the Georgia Institute of Technology, the Technical University of Berlin, the Technical University of Munich. The institute was founded in 1971 as the Korea Advanced Institute of Science by a loan of US$6 million from the United States Agency for International Development and supported by President Park Chung-Hee.
The institute's academic scheme was designed by Frederick E. Terman, vice president of Stanford University, Chung Geum-mo, a professor at the Polytechnic Institution of Brooklyn; the institute's two main functions were to train advanced scientists and engineers and develop a structure of graduate education in the country. Research studies began by 1973 and undergraduates studied for bachelor's degrees by 1984. In 1981 the government merged the Korean Advanced Institute of Science and the Korean Institute of Science and Technology to form the Korea Advanced Institute of Science and Technology, or KAIST. Due to differing research philosophies, KIST and KAIST split in 1989. In the same year KAIST and the Korea Institute of Technology combined and moved from Seoul to the Daedeok Science Town in Daejeon; the first act of President Suh upon his inauguration in July 2006 was to lay out the KAIST Development Plan. The ‘KAIST Development Five-Year Plan’ was finalized on February 5, 2007 by KAIST Steering Committee.
The goals of KAIST set by Suh were to become one of the best science and technology universities in the world, to become one of the top-10 universities by 2011. In January 2008, the university dropped its full name, Korea Advanced Institute of Science and Technology, changed its official name to only KAIST. Admission to KAIST is based on overall grades, grades on math and science courses, recommendation letters from teachers, study plan, personal statements, other data that show the excellence of potential students, does not rely on a standardized test conducted by the university. In 2014, the acceptance rate for local students was 14.9%, for international students at 13.2%. Full scholarships are given to all students including international students in the bachelor and doctorate courses. Doctoral students are given military-exemption benefits from South Korea's compulsory military service. Up to 80% of courses taught in KAIST are conducted in English. Undergraduate students can join the school through an “open major system” that allows students to take classes for three terms and choose a discipline that suits their aptitude, undergraduates are allowed to change their major anytime.
KAIST has produced many doctorates through the integrated master’s and doctoral program and early-completion system. Students must publish papers in internationally renowned academic journals for graduation. KAIST produced a total of 48,398 alumni from 1975 to 2014, with 13,743 bachelor's, 24,776 master's, 9,879 doctorate degree holders; as of October 2015, 11,354 students were enrolled in KAIST with 4,469 bachelor’s, 3,091 master’s, 3,794 doctoral students. More than 70 percent of KAIST undergraduates come from specialized science high schools. On average, about 600 international students from more than 70 different countries come to study at KAIST, making KAIST one of the most ethnically diverse universities in the country. KAIST is organized into 2 schools and 33 departments/divisions. KAIST has three affiliated institutes including the Korea Institute of Advanced Study, National NanoFab Center, Korea Science Academy. KAIST has one campus in Seoul; the university is located in the Daedeok Science Town in the city of Daejeon, 150 kilometers south of the capital Seoul.
Daedeok is home to some 50 public and private research institutes, universities such as CNU and high-tech venture capital companies. Most lectures, research activities, housing services are located in the Daejeon main campus, it has a total of 29 dormitories. Twenty-three dormitories for male students and four dormitories for female students are located on the outskirts of the campus, two apartments for married students are located outside the campus; the Seoul campus is the home of the Business Faculty of the university. The graduate schools of finance and information & media management are located there; the total area of the Seoul campus is 413,346 m2. The Munji campus, the former campus of Information and Communications University until its merger with KAIST, is located ca. 4 km away from the main campus. It has a total of two dormitories, one for undergraduate students and the other for graduate students; the Institute for Basic Science Center for Axion and Precision Physics Research is located here doing particle and nuclear physics related to dark matter and the Rare Isotope Science Project has the Superconducting Radio Frequency test facility.
ASIMO is a humanoid robot created by Honda in 2000. It is displayed in the Miraikan museum in Tokyo, Japan. Honda began developing humanoid robots in the 1980s, including several prototypes that preceded ASIMO, it was the company's goal to create a walking robot. E0 was the first bipedal model produced as part of the Honda E series, an early experimental line of self-regulating, humanoid walking robot with wireless movements created between 1986 and 1993; this was followed by the Honda P series of robots produced from 1993 through 1997. The research made on the E- and P-series led to the creation of ASIMO. Development began at Honda's Wako Fundamental Technical Research Center in Japan in 1999 and ASIMO was unveiled in October 2000. ASIMO weighs 54 kg. Research conducted by Honda found that the ideal height for a mobility assistant robot was between 120 cm and the height of an average adult, conducive to operating door knobs and light switches. ASIMO is powered by a rechargeable 51.8 V lithium-ion battery with an operating time of one hour.
Switching from a nickel metal hydride in 2004 increased the amount of time ASIMO can operate before recharging. ASIMO has a three-dimensional computer processor, created by Honda and consists of a three stacked die, a processor, a signal converter and memory; the computer that controls ASIMO's movement is housed in the robot's waist area and can be controlled by a PC, wireless controller, or voice commands. ASIMO has the ability to recognize moving objects, gestures, its surrounding environment and faces, which enables it to interact with humans; the robot can detect the movements of multiple objects by using visual information captured by two camera "eyes" in its head and determine distance and direction. This feature allows ASIMO to face a person when approached; the robot interprets voice commands and human gestures, enabling it to recognize when a handshake is offered or when a person waves or points, respond accordingly. ASIMO's ability to distinguish between voices and other sounds allows it to identify its companions.
ASIMO is able to respond to its name and recognizes sounds associated with a falling object or collision. This allows the robot to look towards a sound. ASIMO responds to questions by nodding or providing a verbal answer in different languages and can recognize 10 different faces and address them by name. There are sensors; the two cameras inside the head are used as a visual sensor to detect obstacles. The lower portion of the torso has ground sensor which comprises one laser sensor and one infrared sensor; the laser sensor is used to detect ground surface. The infrared sensor with automatic shutter adjustment based on brightness is used to detect pairs of floor markings to confirm the navigable paths of the planned map; the pre-loaded map and the detection of floor markings help the robot to identify its present location and continuously adjust its position. There are rear ultrasonic sensors to sense the obstacles; the front sensor is located at the lower portion of the torso together with the ground sensor.
The rear sensor is located at the bottom of the backpack. Honda's work with ASIMO led to further research on walking assist devices that resulted in innovations such as the Stride Management Assist and the Bodyweight Support Assist. In honor of ASIMO's 10th anniversary in November 2010, Honda developed an application for the iPhone and Android smartphones called "Run with ASIMO." Users learn about the development of ASIMO by walking the robot through the steps of a race and sharing their lap times on Twitter and Facebook. Since ASIMO was introduced in 2000, the robot has traveled around the world and performed in front of international audiences. ASIMO made its first public appearance in the U. S. in 2002 when it rang the bell to open trade sessions for the New York Stock Exchange. From January 2003 to March 2005, the robot toured the U. S. and Canada, demonstrating its abilities for more than 130,000 people. From 2003 to 2004, ASIMO was part of the North American educational tour, where it visited top science and technology museums and academic institutions throughout North America.
The goal of the tour was to encourage students to study science through a live show that highlighted ASIMO's abilities. Additionally, the robot visited top engineering and computer science colleges and universities across the USA as part of the ASIMO Technology Circuit Tour in an effort to encourage students to consider scientific careers. In 2004, ASIMO was inducted into the Carnegie Mellon Robot Hall of Fame. In March 2005, the robot walked the red carpet at the world premiere of the computer-animated film, Robots. In June 2005, ASIMO became a feature in a show called "Say'Hello' to Honda's ASIMO" at Disneyland's Innoventions attraction, a part of the Tomorrowland area of the park; this was the only permanent installation of ASIMO in North America until Innoventions was closed in April 2015. The robot first visited the United Kingdom in January 2004 for public demonstrations at the Science Museum in London. ASIMO continued on a world tour, making stops in countries such as Spain, the United Arab Emirates, South Africa and Australia.
In October 2008, ASIMO greeted Prince Charles during a visit to the Miraikan Museum in Tokyo, where it performed a seven-minute step and dance routine. In a demonstration at Honda's Tokyo headquarters in 2007, the company demonstrated new intelligence technologies that enabled multiple ASIMO robots to work together; the demonstration showed the robot's ability to identify and avoid oncoming people, work with anoth
Military robots are autonomous robots or remote-controlled mobile robots designed for military applications, from transport to search & rescue and attack. Some such systems are in use, many are under development. Broadly defined, military robots date back to World War II and the Cold War in the form of the German Goliath tracked mines and the Soviet teletanks; the MQB-1 Predator drone was when "CIA officers began to see the first practical returns on their decade-old fantasy of using aerial robots to collect intelligence". The use of robots in warfare, although traditionally a topic for science fiction, is being researched as a possible future means of fighting wars. Several military robots have been developed by various armies; some believe. The U. S. military is investing in research and development towards testing and deploying automated systems. The most prominent system in use is the unmanned aerial vehicle which can be armed with air-to-ground missiles and remotely operated from a command center in reconnaissance roles.
DARPA has hosted competitions in 2004 & 2005 to involve private companies and universities to develop unmanned ground vehicles to navigate through rough terrain in the Mojave Desert for a final prize of 2 million. Artillery has seen promising research with an experimental weapons system named "Dragon Fire II" which automates loading and ballistics calculations required for accurate predicted fire, providing a 12-second response time to fire support requests. However, military weapons are prevented from being autonomous. There have been some developments towards developing autonomous fighter bombers; the use of autonomous fighters and bombers to destroy enemy targets is promising because of the lack of training required for robotic pilots, autonomous planes are capable of performing maneuvers which could not otherwise be done with human pilots, plane designs do not require a life support system, a loss of a plane does not mean a loss of a pilot. However, the largest drawback to robotics is their inability to accommodate for non-standard conditions.
Advances in artificial intelligence in the near future may help to rectify this. US Mechatronics has produced a working automated sentry gun and is developing it further for commercial and military use. MIDARS, a four-wheeled robot outfitted with several cameras, a firearm, that automatically performs random or preprogrammed patrols around a military base or other government installation, it alerts a human overseer when it detects movement in unauthorized areas, or other programmed conditions. The operator can instruct the robot to ignore the event, or take over remote control to deal with an intruder, or to get better camera views of an emergency; the robot would regularly scan radio frequency identification tags placed on stored inventory as it passed and report any missing items. Tactical Autonomous Combatant units, described in Project Alpha study Unmanned Effects: Taking the Human out of the Loop. Autonomous Rotorcraft Sniper System is an experimental robotic weapons system being developed by the U.
S. Army since 2005, it consists of a remotely operated sniper rifle attached to an unmanned autonomous helicopter. It is intended for several other missions requiring snipers. Flight tests are scheduled to begin in summer 2009; the "Mobile Autonomous Robot Software" research program was started in December 2003 by the Pentagon who purchased 15 Segways in an attempt to develop more advanced military robots. The program was part of a $26 million Pentagon program. Autonomous robotics would save and preserve soldiers' lives by removing serving soldiers, who might otherwise be killed, from the battlefield. Lt. Gen. Richard Lynch of the United States Army Installation Management Command and assistant Army chief of staff for installation stated at a conference: As I think about what’s happening on the battlefield today... I contend, and you all know. Major Kenneth Rose of the US Army's Training and Doctrine Command outlined some of the advantages of robotic technology in warfare: Machines don't get tired.
They don't close their eyes. They don't hide under trees when it rains and they don't talk to their friends... A human's attention to detail on guard duty drops in the first 30 minutes... Machines know no fear. Increasing attention is paid to how to make the robots more autonomous, with a view of allowing them to operate on their own for extended periods of time behind enemy lines. For such functions, systems like the Energetically Autonomous Tactical Robot are being tried, intended to gain its own energy by foraging for plant matter; the majority of military robots are not equipped with weapons. Current robots that are equipped with weapons are tele-operated so they are not capable of taking lives autonomously. Advantages regarding the lack of emotion and passion in robotic combat is taken into consideration as a beneficial factor in reducing instances of unethical behavior in wartime. Autonomous machines are created not to be "truly'ethical' robots", yet ones that comply with the laws of war and rules of engagement.
Hence the fatigue, str
Boston Dynamics is an American engineering and robotics design company founded in 1992 as a spin-off from the Massachusetts Institute of Technology. Headquartered in Waltham, Boston Dynamics is a wholly owned subsidiary of the Japanese conglomerate SoftBank Group. Boston Dynamics is best known for the development of BigDog, a quadruped robot designed for the U. S. military with funding from Defense Advanced Research Projects Agency, DI-Guy, software for realistic human simulation. Early in the company's history, it worked with the American Systems Corporation under a contract from the Naval Air Warfare Center Training Systems Division to replace naval training videos for aircraft launch operations with interactive 3D computer simulations featuring DI-Guy characters; the company is a pioneer in the field of robotics and it is one of the most advanced in its domain. Marc Raibert is the company's project manager, he spun the company off from the Massachusetts Institute of Technology in 1992. On 13 December 2013, the company was acquired by Google X for an unknown price, where it was managed by Andy Rubin until his departure from Google in 2014.
Before the acquisition, Boston Dynamics transferred their DI-Guy software product line to VT MÄK, a simulation software vendor based in Cambridge, Massachusetts. On 8 June 2017, Alphabet Inc. announced the sale of the company to Japan's SoftBank Group for an undisclosed sum. BigDog was a quadrupedal robot created in 2005 by Boston Dynamics, in conjunction with Foster-Miller, the Jet Propulsion Laboratory, the Harvard University Concord Field Station, it was funded by the DARPA in the hopes that it would be able to serve as a robotic pack mule to accompany soldiers in terrain too rough for vehicles, but the project was shelved after BigDog was deemed too loud to be used in combat. Instead of wheels, BigDog used four legs for movement, allowing it to move across surfaces that would defeat wheels. Called "the world's most ambitious legged robot", it was designed to carry 340 pounds alongside a soldier at 4 miles per hour, traversing rough terrain at inclines up to 35 degrees; the Cheetah is a four-footed robot that gallops at 28 miles per hour, which as of August 2012 is a land speed record for legged robots.
A similar but independently developed robot known as Cheetah is made by MIT's Biomimetic Robotics Lab, which, by 2014, could jump over obstacles while running. By 2018 the robot was able to climb stairs. LittleDog is a small quadruped robot developed for DARPA by Boston Dynamics for research. Unlike BigDog, run by Boston Dynamics, LittleDog is intended as a testbed for other institutions. Boston Dynamics maintains the robots for DARPA as a standard platform. LittleDog has four legs, each powered by three electric motors; the legs have a large range of motion. The robot is strong enough for dynamic locomotion gaits; the onboard PC-level computer does actuator control and communications. LittleDog's sensors measure motor currents, body orientation and foot/ground contact. Control programs access the robot through the Boston Dynamics Robot API. Onboard lithium polymer batteries allow for 30 minutes of continuous operation without recharging. Wireless communications and data logging support remote operation and data analysis.
LittleDog development is funded by the DARPA Information Processing Technology Office. PETMAN is a bipedal device constructed for testing chemical protection suits, it is the first anthropomorphic robot. Legged Squad Support System known as AlphaDog, is a militarized version of BigDog, it is ruggedized for military use, with the ability to operate in hot, cold and dirty environments. The Agile Anthropomorphic Robot "Atlas" is a 6-foot bipedal humanoid robot, based on Boston Dynamics' earlier PETMAN humanoid robot, designed for a variety of search and rescue tasks. In February 2016 Boston Dynamics published a YouTube video entitled "Atlas, The Next Generation" showing a new humanoid robot about 5' 9" tall. In the video, the robot is shown performing a number of tasks that would have been difficult or impossible for the previous generation of humanoid robots. A video posted to the Boston Dynamics channel of Youtube dated 11 October 2018, titled "Parkour Atlas", shows the robot running up 2' high steps onto a platform.
On June 23, 2016, Boston Dynamics revealed the four-legged canine-inspired SpotMini which only weighs 25 kg and is lighter than their other products. In February 2018, a promotional video of the SpotMini using its forward claw to open a door for another robot reached #1 on YouTube, with over 2 million views. A video the same month showed the SpotMini persisting in attempting to open the door in the face of human interference. Viewers perceived the robot as "creepy" and "reminiscent of all kinds of sci-fi robots that wouldn't give up in their missions to seek and destroy". On May 11, 2018 CEO of Boston Dynamics Marc Raibert on TechCrunch Robotics Session 2018 announced that SpotMini robot is in pre-production and preparing for commercial availability in 2019. On its website, Boston Dynamics highlights that SpotMini is the “quietest robot have built.” The company says it has plans with contract manufacturers to build the first 100 SpotMinis this year for commercial purposes, with them starting to scale production with the goal of selling SpotMini in 2019.
Handle is a research robot that travels at 9 mph and jumps 4 feet vertically. It uses electric power to operate both el