ASIMO: the humanoid robot
Officially, the name is an acronym for "Advanced Step in Innovative MObility". As of 2002, there were 20 ASIMO units in existence. Each one costs $1 million to manufacture, and some units are available to be hired out for $150,000 per month.
With 2000's ASIMO model Honda added many features, labelled "Intelligence Technology", that enable ASIMO to interact better with humans. These features fall under 5 categories:
- Recognition of moving objects
Using the visual information captured by the camera mounted in its head, ASIMO can detect the movements of multiple objects, assessing distance and direction. Common applications this feature would serve include: the ability to follow the movements of people with its camera, to follow a person, or greet a person when he or she approaches. - Recognition of postures and gestures
ASIMO can also interpret the positioning and movement of a hand, recognizing postures and gestures. Because of this ASIMO can react and be directed not only to voice commands, but also to the natural movements of human beings. This enables it to, for example, recognize when a handshake is offered or when a person waves and respond accordingly. It can also recognize movement directions such as pointing. - Environment recognition
ASIMO can recognize the objects and terrain of its environment and act in a way that is safe for both itself and nearby humans. For example, recognizing potential hazards such as stairs, and by stopping and starting to avoid hitting humans or other moving objects. - Distinguishing sounds
ASIMO's ability to identify the source of sounds has been improved, and it can distinguish between voices and other sounds. It can respond to its name, face people when being spoken to, and recognize sudden, unusual sounds such as that of a falling object or a collision, and face in that direction. - Facial recognition
ASIMO has the ability to recognize faces, even when ASIMO or the human being is moving. It can individually recognize approximately 10 different faces. Once they are registered it can address them by name.
BigDog: the robotic mule
BigDog is a meter long, 0.7 meters tall, and weighs 75 kilograms. It is currently capable of traversing difficult terrain at 5.3 kilometers per hour, carry a 54 kilogram load, and climb a 35 degree incline.
HRP-2 Promet: the robotic butler
It even responds to requests like "Please come here" with "What can I do for you?". Capture 3D images with its four built-in 2.8mm wide angular cameras located behind the visor.
Albert Hubo: an "Einstein" Robot
The head has 35 joints, so it can impersonate various facial expressions using independent movements of eyes and lips. It has 2 CCD cameras to do vision recognition. Also, the body of Albert HUBO can perform all the HUBO's performances, so it is possible to express more natural feature and movements. In the body, there are lithium polymer batteries wich can get about 2 and half hours of the operating time.
By using remote network, it is possible to access the Albert HUBO from an external computer. Albert HUBO was announced first at 2005 APEC Summit in Pusan, Korea. It was praised from many World leaders, such as the USA president, the Japanese Prime Minister and so on.
QRIO: the dancing robot
QRIO is capable of voice and face recognition, making it able to remember people as well as their likes and dislikes. QRIO can run at 23cm/second, and is credited in Guinness World Records (2005 edition) as being the first (and fastest) bipedal robot capable of running. The 4th generation QRIO's internal battery lasts about 1 hour.
Two fourth-generation Qrio prototype robots were featured dancing in Hell Yes, a music video by recording artist Beck. These prototypes lacked a third camera in the center of the forehead and the improved hands and wrists which were added to later prototypes. It took programmers three weeks to program their choreography.
RHex: the Robotic Pooch
RHex is controlled remotely from an operator control unit at distances up to 600 meters. A video uplink provides front and rear views from RHex's onboard cameras. RHex also uplinks navigational data from onboard compass and GPS and from payload sensors. A downlink allows the operator to control mobility and to operate mission payloads.
RiSE: the climbing robot
Each of RiSE's six legs is powered by two electric motors. An onboard computer controls leg motion, manages communications, and services a variety of sensors. The sensors include an inertial measurement unit, jointposition sensors for each leg, leg strain sensors and foot contact sensors.
Future versions of RiSE will use dry adhesion to climb sheer vertical surfaces such as glass and metal. RiSE is being developed in conjunction with researchers at University of Pennsylvania, Carnegie Mellon, Berkeley, Stanford, and Lewis and Clark University. RiSE is funded by the DARPA Defense Sciences Office.
Stanley: the autonomous vehicle
The sensors used by Stanley include five LIDAR laser-ranging units, a pair of RADAR units, a stereo camera, and a single-lens camera. Position sensing was provided by a GPS receiver, a GPS compass, an inertial guidance system, and wheel odometry information provided by the Touareg's internal CAN bus. Computing was provided by six low-power Intel Pentium M based computers running various incarnations of the Linux operating system.
Stanley was characterized by a machine learning based approach to obstacle detection. Data from the LIDARs was fused with images from the vision system to perform more distant look-ahead. If a path of drivable terrain could not be detected for at least 40 meters in front of the vehicle, speed was decreased and the LIDARs used to locate a safe passage.
Also, Stanley drove by recording how a human drove the car through the desert, then assigning an accuracy value to each bit of data generated by its slew of sensors. After this modification was made, it began to speed at 45 mph down roads which were crisscrossed by shadows of trees. Before it started assigning accuracy values to its data, it would have shied away from the road - it would have been perceived as being crisscrossed with ditches, not shadows.
WR-07: a real Transformer
The lego robotic bartender
Lego blocks can be used to build just about anything, including this robotic bartender which was spotted at CeBIT 2006.
No comments:
Post a Comment