Q2. What are the mechanisms by which conflict resolution between actuator commands from different layers is achieved?
Inhibition and suppression are the mechanisms by which conflict resolution between actuator commands from different layers is achieved.
Q3. How many instructions did the two processors each expend?
Through a special purpose distributed serpentine memory, four of the onboard 8-bit processors were each able to expend about 30 instructions on each data pixel.
Q4. How do you build a system based on the physical grounding hypothesis?
To build a system based on the physical grounding hypothesis it is necessary to connect it to the world via a set of sensors and actuators.
Q5. What is the normal mode of operation of Squirt?
Its normal mode of operation is to act as a "bug", biding in dark corners and venturing out in the direction of noises, only after the noises are long gone, looking for a new place to hide near where the previous set of noises came from.
Q6. What is the mechanism used to spread the activity from the goal?
When a behavior (such as "go to some place") is activated (via a small panel of push buttons on the robot) a spreading of activation mechanism is used, which spreads from the goal via the neighbor links.
Q7. What is the current strategy for testing the limitations of the physical grounding hypothesis?
Their current strategy is to test the limitations of the physical grounding hypothesis by building robots which are more independent and can do more in the world.
Q8. How does it recapitulate the primate vestibular-occular system?
It recapitulates the primate vestibular-occular system by using vision as a slow calibration system for a gyroscope controlled movable platform which holds the camera.
Q9. What is the key thing to note with these robots?
A key thing to note with these robots is the ways in which seemingly goal-directed behavior emerges from the interactions of simpler non goal-directed behaviors.
Q10. How many Hertz could the subsumption architecture be compiled?
Tom and Jerry also demonstrated that the subsumption architecture could be compiled (by hand) down to the gate level, and that it could be run at clock speeds of only a few hundred Hertz.
Q11. What is the advantage of this approach?
The advantage of this approach is that there is no need to set up internal expectations for what is going to happen next; this means that the control system can both (1) be naturally opportunistic if fortuitous circumstances present themselves, and (2) it can easily respond to changed circumstances, such as some other object approaching it on a collision course.
Q12. What are the constraints on symbols that are necessary for the development of true intelligence?
These groundings provide the constraints on symbols necessary for them to be truly useful.[26] has argued rather eloquently that mobility, acute vision and the ability to carry out survival related tasks in a dynamic environment provide a necessary basis for the development of true intelligence.
Q13. How did the arm locate a soda can?
When the arm located a soda can with its local sensors, it simply drove the hand so that the two fingers lined up on either side of the can.
Q14. What is the hypothesis that is used to build a system that is intelligent?
This hypothesis states that to build a system that is intelligent it is necessary to have its representations grounded in the physical world.
Q15. What is the effect of a suppressing message?
When a message arrives on a suppressing side-tap, again no messages are allowed to flow, from the original source for some small time period, but now the suppressing message is gated through and it masquerades as having come from the original source.
Q16. What is the role of the physical grounding hypothesis in AI?
There is room for plenty of experimentation, and eventually, when the authors are mature enough, there is also room for much theoretical development of the approaches to Artificial Intelligence based on the physical grounding hypothesis.