1 basic concepts

Introduction to Robots  and Multi-Robot Systems Agents in Physical and Virtual Environments: 

Introduction to Robots and Multi-Robot Systems Agents in Physical and Virtual Environments Lecture 1: Basic Concepts Gal A. Kaminka galk@cs.biu.ac.il

Slide2: 

Some examples of robots

What is a robot?: 

Give me a few examples. Is a rock a robot? What is a robot?

What is a robot?: 

What is a robot? A toy spring car can move and act. a robot can sense. Actuators (Effectors)

What is a robot?: 

What is a robot? A sorting algorithm senses and acts. a robot is persistent. Actuators (Effectors) Sensors

What is a robot?: 

What about a remote alarm? a robot is situated in an environment. What is a robot? Actuators (Effectors) Sensors

What is a robot?: 

We’re missing something here. a robot is responsive. What is a robot? Actuators (Effectors) Sensors Environment

What is a robot?: 

We’re missing something here. a robot is responsive. What is a robot? Actuators (Effectors) Sensors Environment

Here’s what we have so far: 

Robots: Are persistent with respect to their environment Sense and act Sense/act within the same environment (situated) Respond to senses using action Here’s what we have so far Environment Robot

Here’s what we have so far: 

Here’s what we have so far Robots: Are persistent with respect to their environment Sense and act Sense/act within the same environment (situated) Respond to senses using action These characteristic are true for agents, not just robots Environment Robot

Why investigate robots?: 

Why investigate robots? Because we want to understand how to build them. So that they do things for us. So that we can do other things instead. In other words, We are studying robotics because we are lazy.

The Agent/Environment/Task Framework: 

The Agent/Environment/Task Framework We want the robot to do tasks for us (or for itself) Therefore, it must take a task into account Environment Robot Task

Slide13: 

In this course we focus on physical environments Agents are embodied Part of the environment is their own body Sensing and acting with uncertainty Slippery grips, sensing is inaccurate Environment is dynamic, changes even without robot …. We will talk more about environments later, but first….

A Taxonomy of Environments: 

A Taxonomy of Environments There are a number of characteristic dimensions: Dynamic vs. static Accessible vs. inaccessible transparent vs. translucent Deterministic vs. non-deterministic Discrete vs. continuous …..

Dynamic vs. Static: 

Dynamic vs. Static Dynamic: Environment changes even if agent takes no action Static: Environment does not change until agent takes action Key question: Is the agent only cause of change in the environment? Physical environment is dynamic Wind, other agents, continuous mechanical forces

Accessible vs. Inaccessible: 

Accessible vs. Inaccessible Accessible (transparent): Agent can sense everything and anything. Nothing is hidden. Inaccessible (translucent): Agent can only sense part of the environment. Some features of the environment are hidden. Key question: What can the agent sense about the environment? Physical environments typically inaccessible: Cannot see behind you, nor over long distances, nor inside people.

Determinism: 

Determinism Deterministic: An action results in a completely predictable change Non-deterministic: An action can result in one of a range of possible changes Uncertainty in the result Key question: If agent takes action, is it sure of the outcome? Physical environment is non-deterministic: Slippery grasp, coin-flips, gambling

Discrete or continuous?: 

Discrete or continuous? Discrete: Actions or senses are clearly separated, limited number Continuous: Infinite possible values within a range Note: Different from discrete/continuous senses and actions Physical environments are continuous

A Taxonomy of Environments: 

A Taxonomy of Environments There are a number of characteristic dimensions: Dynamic vs. static Accessible vs. non-accessible transparent vs. translucent Deterministic vs. non-deterministic Discrete vs. continuous Open question: Quantifying the above

The Agent/Environment/Task Framework: 

The Agent/Environment/Task Framework Given environment and task, how do we build a robot that carries out the task? Environment Robot Task

Agents and Environments: 

Agents and Environments Many different environments can exist Different techniques are used with different environments We focus on techniques used in physical environments

Agent Control: 

Agent Control In principle, our view is of an agent with three components: Effectors/actuators Sensors Think This view is sometimes referred to as sense-think-act cycle But this can be misleading: not necessarily so sequential Sense Think Act Robot Environment

Three components, three challenges*: 

Three components, three challenges* The action selection problem: Given task/goals, how to select the next action(s) The sensor planning problem: Given task/goals, how to use sensors The pose planning problem: Given needed target body position, how to get there Sense Think Act Robot Environment

Three components, three challenges*: 

Three components, three challenges* The sensor planning problem: Which sensors to use? When? How to integrate their information (sensor fusion)? How to overcome uncertainty in their readings? May depend on what think is thinking, and may need to influence what action to take Sense Think Act Robot Environment

Three components, three challenges*: 

Three components, three challenges* The pose planning problem: Which (combination of) actuators to use to achieve pose? What trajectory should they take? How to compensate for actuation uncertainty? May depend on what think is thinking, and may need to depend what sense reads, and needs Sense Think Act Robot Environment

Three components, three challenges*: 

Three components, three challenges* The action-selection problem (our focus): How to select action in real-time? How to select action that is good for task/goal? How to integrate competing needs of different subtasks? Depends on the capabilities of sense and act Sense Think Act Robot Environment

Three challenges: 

Three challenges These three challenges are highly coupled Not easy to separate them out. Many systems/techniques provide integrated solutions Multiple levels at which can be addressed: hardware, control, software, … Example: better vision by blurring camera Example: using probabilistic inference to handle uncertainty Example: sensor placement affects foraging behavior Robotics is a highly inter-disciplinary field.

Empirical research : 

Empirical research As you can see, these are complex concepts Many of problems/solutions affect each other in very subtle ways Physical environments very uncertain, unpredictable Difficult to predict system behavior from analysis Cannot just browse at the algorithms and hardware involved Use empirical research methods in investigations

Empirical research: 

Empirical research Experiment design issues: Study system with and without proposed techniques Compare performance of many systems Compare performance across different environments or tasks Faces generality problems in drawing conclusions Tied to the actual challenges of the real world:

Simulations: 

Simulations Significance issues: Run many experiments, draw statistical conclusions Simulation is very useful here Many roboticists frown at simulations (I was called “a theoretician”) Simulation and virtual environment are not same thing

Science and Scientists: 

Science and Scientists Scruffies and Neaties The revolution of 86: Plans are not enough!

The Sense-Think-Act Cycle:What's in Think (for scruffies) in late 80's?: 

The Sense-Think-Act Cycle: What's in Think (for scruffies) in late 80's? No need to Think: If sensors read X, then do Y Reactive Camp (Brooks 1986, Schoppers 1987) Limited thinking: Behavior-based control Behaviors may have state, memory, procedures Arkin, Firby (1986), Maes, ... Deep thinking: integrated planning, monitoring e.g., IPEM (1988) Hybrid architectures (e.g., Gat 1992)

The Sense-Think-Act Cycle:What's in Think (for neaties) in late 80's?: 

The Sense-Think-Act Cycle: What's in Think (for neaties) in late 80's? "The Old View" Plans as sequences of actions for execution Plans as mental attitudes (Pollack 1992) Plans as recipes: Some get executed, some just known BDI: Belief-Desire-Intention (approximately): Belief: What the agent knows Desire: What the agents ideally wants to see happening Intention: What the agents actually acts towards Commitments

An Historical Perspective on Teamwork:From a Single Agent to Multiple Agents: 

An Historical Perspective on Teamwork: From a Single Agent to Multiple Agents Time Scruffiness Neatness '86 '90 '96 Subjective

Slide35: 

שאלות?

Readings: 

Readings Related readings: Empirical methods in artificial intelligence (book by Paul Cohen) AI Magazine articles by same Toby Tyrell: the action selection problem Readings for next week: On the web page

Homework: 

Homework Give 3 examples of environments that are different from the real world along at least one dimension Characterize the “information environment” existing on the web, where agents may discover, exchange, and manipulate information. Can non-determinism occur when an environment is static? Give an example Extra credit: Propose a way of measuring environments quantitatively along the 4 dimensions discussed in class. Discuss: Is a human a robot? Is a cockroach? Is a cell? Is a thermostat? Is a web-server?

Slide38: 

The End