• Feed RSS

Busqueda Internet

Intelligent Robots

Lynxmotion Visual Sequencer is a servo control program specially developed for use with SCC32 circuit capable of controlling up to 32 servos. The program is compatible with Windows 95, 98, 2000, XP and Vista and connects to the circuit from any serial port. You can also connect via USB with the help of an optional converter cable. The program lets you control all the servos of a robot easily and controls that lets you add the servos in the desired position of the screen to match visually with the actual position of the servos in the robot. The program can generate all sorts of complex movements and you can set the speed and delay of each servo. It has a large number of additional features that make it easy to control any robot.
AL5B robot arm is part of the new series of robotic arms metal replace the old plastic. These arms are all very similar in functionality and appearance, with the main difference in the size and capacity. The arm is made up of aluminum parts that are attached directly to the servos to form a very solid structure running movements with grace and ease and good repeatability. The arm has 5 axes, but can be expanded to sixth axis with the expansion kit adds S300137 rotation of the wrist. Features Max.: 400 mm. Max. with an outstretched arm: 140 gr. Food 6 V. This kit includes all components required to set and implement the robot with a serial connection to a PC. Includes the mechanical part, the 5 servos, electronics SCC32 and mounted, the power supply of 6V, the RIOS program control and all cables and connectors needed for installation and commissioning.
La electrónica
SCC32 is a servo control circuit of up to 32 channels that features high resolution, precision and smooth movements with which operates by incorporating motion control functions based on time, speed, or a combination of both. The circuit has a working range of 180 degrees with an output ranging from 0.50 ms to 2.50 ms. The resolution is 1 uS to ensure the accuracy of movements on all servos. Has a group mode that allows all servos to begin and end group motion at a time regardless of whether they have traveled around longer than others.

There is also a mode compatible with the circuit MiniSSC II. (See the instruction manual.) The servo outputs can also be used as digital output ports TTL level. It also has 4 digital inputs that can be interlocked to detect impulses of short duration or may even be used as analog inputs. The connection to the control processor is made using DB9 RS232 level or through connector TTL level posts. The speed can be switched between 2400, 9600, 38400 and 115200 baud. The power may be unique to the electronics and servos or servos independent and electronics. Food from 5.5 to 9 V. Recommended 6V whether to use the unique power.

La mecánica

It includes all the machined parts and fasteners, screws, etc. needed to build the robot. Also included are 5 servos Hitec high quality and different size for each of the joints. All arm parts are made of laser cut aluminum to provide strength and lightness. The rotating base and platform are made of polycarbonate circuit. The specially designed robot design allows it to be easily constructed without special knowledge. Even children (with adult supervision) can assemble the robot arm, helping them to understand its operation.

El software
Along with the kit includes a complete copy of the S370120 RIOS . The program includes advanced features for performing all types of movements with the robot arm including compensation of gravity and weight. Lets use a Playstation joystick to control type robot arm. You can also use a GP2D12 type sensor to capture 3D images experimentally. The program allows to control any robot arm up to 8 channels, as they include adjustments and control channels 7 and 8 in addition to six commonly used by the robot arm.

As the control board SCC-32 can be placed in compatibility mode SCC-II Mini, this means that all programs and utilities written for this controller, it can run smoothly on the SCC-32. You can also use the free software plate SC Visual servo control for Windows that allows you to control the movements of a very simple and graphic and store them in a text file that can save and restore disk or export to use them in our own programs. Other utility programs and routines can be found later in the Examples section and Projects.

Intelligent robots have three levels of consciousness

embodied Cognitive Science and Artificial Intelligence can conceive new advanced systems capable of self-government

Interdisciplinary knowledge embodied cognitive science and artificial intelligence can conceive new advanced systems capable of self-government. The maximum level of these systems is represented by the so-called three-tier architecture that includes three different processes related to Freud's theory on the integration of the id, the superego and the ego. Reactant levels, deliberative and reflective are the future features of intelligent robots. By Sergio Moriello.

Agents can be defined in several ways and there is to date no universally accepted definition. In its simplest form, an agent is a complex adaptive system that can sense and act on their environment (which may be real or simulated)
[Moriello, 2005, p. 137].

For Stuart Russell and Peter Norvig, an "agent" is all that can be viewed as perceiving its environment through sensors and acting upon that environment through effectors [Russell and Norvig, 1996, p. 33]. That is, its main feature is that it is "located" (situatedness) is embedded within a local environment with which it interacts and which directly influences-behavior-on
[Florian, 2003] [Muñoz Moreno, 2000] [Innocenti Badano, 2000].

An "autonomous agent" is one that interacts, by itself, with its surrounding environment. For that, you should be able to perceive, reason and act. In other words, should have appropriate sensors to collect information from both of their intorno and its environment (perceived) needs to be able to turn that information into knowledge and use it to achieve its objectives (reason), and should have appropriate effectors likely to change the environment (acting)
[Moriello, 2005, p. 221/2].

Agentes Inteligentes

An "autonomous intelligent agent" is one that can detect and record whether an action done in a given situation was favorable [Fritz, García Martínez and Marsiglio, 1990, p. 3] [García Martínez, 1997, p. 3]. In this way, you can gain experience and adjust their behavior as you learn.

The animals perceive their environment (and its intorno) through its sensory systems, process that information (assimilating, classifying and interpreting) through the neural circuits of cerebral cortex, and acting-out, thanks to your device and musculoskeletal "inward-through homeostatic mechanisms. But the overall process is not unidirectional and linear, but circular and cyclical: perception interprets reality through action, body movement
[Moriello, 2005, p. 233].

Finally, it should be noted that, although not necessarily, an autonomous intelligent agent "is embodied" (embodiment) has a physical body able to experience their environment directly. Their actions have immediate feedback on their own perceptions
[Florian, 2003] [Muñoz Moreno, 2000] [Innocenti Badano, 2000].

Regulations and Controls

You can define the concept of "governance" (translation of the English word "governance") as the way a complex system is self-government (self-guided and self-directed) to a previously defined goal.

The main objective intrinsic (ie, the "attractor" principal) of any system is its own survival, however, there are several sub-objectives. Thus, according to the American psychologist Abraham Maslow, in humans there is a hierarchy of objectives that seek to satisfy: physiological, security, belonging, esteem and personal fulfillment.

An autonomous agent has different regulatory mechanisms that allow you to maintain dynamic equilibrium. These mechanisms consist, in turn, by different feedback loops (both negative and positive).

The more complex the agent, have a wider range of modes of regulation and different levels of regulation. All the different regulatory mechanisms is a hierarchy and each level acts as "referee" on the regulatory mechanisms of the lower levels.

Intelligent Autonomous Agents

The "natural autonomous agents" (ie, animals) have a sufficient number of automatic mechanisms of internal regulation that will ensure their survival, at least for a relatively long period prolonged
[François, 2005].

The "natural autonomous intelligent agents" (ie, human beings, as individuals or as groups) acquired, with the neo-cortex of the brain-the ability to speak on some automation of the regulations to modify. It is what is commonly known as "controls" [François, 2005].

The "autonomous artificial intelligent agents" (ie, intelligent robots) are, in essence, complex systems that have a precise mechanical structure polyarticulated governed by a sophisticated electronic control system.

The key is the government of each of its components, so as to measure, monitor and modify, with continuity and speed-all the variables involved (movement extremities, motor speed, body position, fluid pressure, acceleration of the mass) as a function of the goal and the environment in which it is immersed [Moriello, 2005, p. 172 / 3].

Intelligent Robots

Regardless of its kind, and Broadly, the robots are made of different subsystems [Moriello, 2005, p. 172 / 3]:

• The "structure or chassis" is responsible for shaping the robot and sustain their components. May consist of many materials (plastics, metals, etc..) And have the most varied forms, but usually consists of rigid parts connected by joints. You can be like: "endoskeleton" (where the structure is internal and other external components) and "exoskeleton" (where the structure is outside and covers the other elements).

· The "sensors" are systems which allow the robot to perceive certain phenomena or events in their local environment. Is the robotic equivalent of human sensory systems. Can be "internal" or "proprioceptive" (provides information about the internal state of the robot itself) and "external" or "exteroceptive" (provides information about the environment surrounding the robot).

· The "effector" are systems which allow the robot to interact with their local environment. Is the robotic equivalent of the human motor system. May be: "locomotion" (is the ability to move from one place to another) and "manipulation" (is the ability to handle objects).

· The "drivers" or "control circuitry" allow the proper administration of the entire system, continuously coupling the skills of perception and action: receive sensor data and send commands to effectors. Is the robotic equivalent of the human brain.

• The "energy source" is the system responsible for feeding all parts of the robot. Might be "battery" or "batteries" (if the robot has to move independently), "drive" (if the robot is fixed, or moves a short distance) and "solar cells" (if the robot is very low or if it moves through interplanetary space).

Architecture "three layers"

Obviously, the complexity of the environment has a close relationship with the complexity of the control system that governs the behavior of the machine. Indeed, if the robot has to react quickly and intelligently in a dynamic and challenging environment, the problem becomes very difficult to control. If the robot, however, need not respond quickly, reducing the complexity required to develop the [Mataric, 2002].

The "three-tier architecture" can be considered three different kinds of processes [Davis, 1998] [Sloman, 1996], similar to the neurological hypothesis MacLean triune brain or Freud's psychological hypothesis of the interaction between the "It" (or collection of instinctual drives), the "Super-I" (which includes the objectives and social prohibitions high level) and "Yo" (which resolves or eliminate the conflicts between them) [Minsky, 2000].

is likely that these processes operate in parallel and through many types of interaction. Are basically three (Moriello, 2005, p. 194 / 5):

· "Reagent" is the lowest level and is equivalent to the oldest and most primitive parts of the human brain (the paleoencephal or reptilian brain). The information is acquired through external and internal sensors and translates into commands for the effectors. Process is very fast, or immediate, allowing a direct response to sensory events.

· "Deliberation" is the intermediate level and is equivalent to a little more modern parts of the human brain (midbrain, or mammalian brain). You could say that is the true heart of the system because it provides the capabilities of reasoning, planning and troubleshooting. Are those processes that play an important role in what is known as "thought", plus other processes related to the management of low-level actions.

· "Reflective" is the highest level and is equivalent to the most recent human brain (the neocortex or brain neomamífero). Allows the monitoring, evaluation, and some control of internal processes and the provision of typically human capabilities (such as introspection, learning and explicit decisions to redirect the attention.) It's basically learning mechanisms, one way or another, permeates the entire architecture.
Sergio Alejandro Moriello is Electronic Engineer (1989), Postgraduate Diploma in Science Journalism (1996), Master in Business Administration (1997), Specialist in Information Systems Engineering (2005), Studying Masters in Information Systems from the UTN-FRBA (finished the thesis). He has authored books and Intelligence Intelligence Synthetic natural and synthetic.

No comments: