Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
37 Cards in this Set
- Front
- Back
|
Properties of industrial robots |
- Operate in a stable deterministic environment. - Normally fixed or restricted mobility. - Operate with no or limited interaction with the world. |
|
|
Properties of service robots |
- Operate in "The real world" - Move around. - Require a high degree of autonomy. - interact with the environment. |
|
|
Syntactical correctness (syntax) |
Defines all possible sequences of symbols that constitute sentences of The language. Ex a sentence in a book. |
|
|
Sematic correcness (semantic) |
Determines the facts in the world to which the sentence refer. - Each sentence makes a claim about the world. - An agent is said to belive a sentence about the world. |
|
|
Define optimal in a search algorithm |
The algorithm will find the least costly solution. |
|
|
Define complete in a search algorithm |
The algorithm will find the solution if the there is one. |
|
|
Define heuristic in a search algorithm |
Ranks alternatives in search algorithms at each branching step based on available information to decide which branch to follow. |
|
|
Subsumption architecture |
Control architecture that was proposed in opposition to traditional AI, or GOFAI. Instead of guiding behavior by symbolic mental representations of the world, subsumption architecture couples sensory information to action selection in an intimate and bottom-up fashion. |
|
|
Reflexes (a animal reflexive behavior) |
Rapid, automatic involuntary responses triggered by a stimulus. Stops when stimulus disappears. (Like an instinct). Ex: Turtle hides in it's shell, when scared. |
|
|
Fixed-action patterns (animal reflexive behavior) |
Time-extended responses to stimuli, which run to completion. Response not proportional to stimulus. Ex a fleeing deer. |
|
|
Taxes (animal reflexive behavior) |
Orient the animal toward or away from a stimulus. Ex a fly flies towards a light bulb. |
|
|
Behavior for low and high mutation in artificial evolution |
Low mutation results in slower learning (if no mutation no evolution) while high mutation goes towards a random next generation. |
|
|
Situatedness |
A major idea of situated AI is that a robot should be able to react to its environment within a human-like time-frame. i.e directly interact with the world as opposed to modelling it. |
|
|
Symbol grounding |
The symbol grounding problem is related to the problem of how words (symbols) get their meanings, and hence to the problem of what meaning itself really is. The problem of meaning is in turn related to the problem of consciousness, or how it is that mental states are meaningful. |
|
|
The frame problem |
The frame problem describes an issue with using first-order logic (FOL) to express facts about a robot in the world. Representing the state of a robot with traditional FOL requires the use of many axioms that simply imply that things in the environment do not change arbitrarily. |
|
|
Embodied |
Robots realized as physical systems capable of acting in the real world. An embodied agent is an agent that exists in a real physical environment. |
|
|
Self-sufficient |
Ability to sustain themselves over extended periods of time. Self-sufficiency can be seen as a more complex form of self-organization. |
|
|
Situated |
Situated agents sense and act upon the environment from their own perspective. A situated agent is an agent that interacts with the environment through its own sensors and actuators. – Has the ability to sense the environment – Has the ability to manipulate the environment |
|
|
Autonomous |
Function without supervision, intervention or instruction from another agent. |
|
|
Adaptivity |
An agent that is self-sufficient in a continually changing environment is adaptive.Four kinds of adaptation – Evolutionary – Physiological – Sensory adaptation – Learning |
|
|
Homeostasis |
– The ability to keep essential variables within certain limits – Keeping the body temperature stable in a changing environment – An adaptive agent is implementing homeostasis |
|
|
Whats the characteristics of the complete agent? |
- Self sufficient - Embodied - Situated - Autonomous |
|
|
Effector |
A device a robot has to make an impact on the environment. Ex wheels / tracks |
|
|
Actuator |
A mechanism that enables the effector (ex wheels on the robot) to execute an action. Ex Electric motors, hydraulics. |
|
|
Control unit |
Uses sensor data to compute control signals to the actuators that move the effectors. |
|
|
What dose the rationality of an agent depend on? |
- The performance measure. - The agent's prior knowledge of the environment. - The actions that the agent can perform. - The agent's percept sequence. |
|
|
Omniscience (omniscient agent) |
An omniscient agent maximizes the actual outcome of its actions. |
|
|
Whats the difference between an omniscient and a rational agent? |
Omniscient agent maximizes the actual outcome of its actions while a rational agent maximizes the expected outcome. |
|
|
Fully observable environment |
If the agent's sensors gives access to the complete state of the environment, it's called fully observable. (Environment is fully observable as long as all relevant aspects can be perceived) |
|
|
Partly observable environment |
If the agent can not perceive everything in the at once, making the environment partly observable. |
|
|
Deterministic environment |
An environment where the next state can be completely determined based on the previous state and the agent's action, is called deterministic. (If it's not deterministic its stochastic) |
|
|
Intelligent agent types |
Reactive. Model based. Goal based. Utility based. Learning agents. |
|
|
Reactive agent |
Reacts to a stimuli, have no memory or internal representation. |
|
|
Model based reflex agents |
- Models the world. - Acts reactively based on the model (internal representation). + : Can consider aspects of the world that it currently can't observe. - : Must maintain an internal representation. |
|
|
Goal based agents |
Maintains a representation of how to act in order to achieve a specific goal. |
|
|
Depth first search |
- Uses a stack as NodeList (LIFO) - Quickly finds one solution, but generally dose not find the best solution very fast. - Requires little memory. - Problematic in open search spaces. |
|
|
Breadth first search |
- Use a queue as NodeList (FIFO) - Reqires a lot of memory. - Since short paths are evaluated before longer ones, the first solution is often a good solution. |
