MOBILE & SERVICE ROBOTICS RO OBOTIC CA 01. Supervision and control

Size: px

Start display at page:

Download "MOBILE & SERVICE ROBOTICS RO OBOTIC CA 01. Supervision and control"

Lindsay Payne
5 years ago
Views:

1 CY 02CFIC CFIDV MOBILE & SERVICE ROBOTICS Supervision and control Basilio Bona DAUIN Politecnico di Torino Basilio Bona DAUIN Politecnico di Torino 001/1

2 Supervision and Control 02CFIC CY a priori knowledge Task/mission commands Position Global map Localization Path planning Map Building reasoning CFIDV Per rception Data treatment data Sensors Data treatment commands Actuators Motio on contro ol Environment Basilio Bona DAUIN Politecnico di Torino 001/2

3 Supervision and Control 02CFIC CY Localization Map Building Position Global map Path planning Reasoning CFIDV Local map World model Path Perception Environment Motion control Basilio Bona DAUIN Politecnico di Torino 001/3

4 Control Strategies CFIDV 02CFIC CY Structure t of the control loop World changes dynamically A compact model of the world does not exist There are many sources of uncertainty, both in the world and in the robot Two possible approaches Classic AI deliberative model Complete modeling (model-based method) Function based Horizontal decomposition Top-down approach Modern AI reactive model No world model: behavior-based Vertical decomposition Bottom-up approach Basilio Bona DAUIN Politecnico di Torino 001/4

5 Control Strategies 02CFIC CY DELIBERATIVE Model-based Purely symbolic Speed of response REACTIVE Behavior-based Reflexive CFIDV Predictive capabilities Depends on accurate world models Depends on the world representation Representation-free Slow response Real-time response High level intelligence (cognition) Low level intelligence (stimulus-response) Variable latency Fast and easy computation Basilio Bona DAUIN Politecnico di Torino 001/5

6 Control Characteristics 02CFIC CY Sense Plan Act Subsumption/Reactive model This architecture may prevent a fast and timely response CFIDV Vertical approac ch sense use model plan act Task 1 Task 2 Task 3 Task 4 Task 5 Basilio Bona DAUIN Politecnico di Torino 001/6

7 Model-Based Approach CFIDV 02CFIC CY Complete modeling of the world Each block is a computed function Vertical decomposition and nested-embodiment of functions An example sensors Perception Localization - Map building Cognitive planning Motion control actuators Basilio Bona DAUIN Politecnico di Torino 001/7

8 Model-Based Approach A second example: nested embodiment 02CFIC CY CFIDV High level mission Service Task Elemental move Motion primitives Servo Basilio Bona DAUIN Politecnico di Torino 001/8

9 Model-Based Approach A third example: nested embodiment Planner GOAL RECOGNITION 02CFIC CY Navigator GLOBAL PATH PLANNING SUB-GOAL FORMULATION LOCAL PATH PLANNING CFIDV Pilot Path monitor TARGET GENERATOR DYNAMIC PATH PLANNING TARGET LOCATION PATH CORRECTION/OBSTACLE AVOIDANCE Controller Low level control COMMANDS SENSORS ACTUATORS Basilio Bona DAUIN Politecnico di Torino 001/9

10 Behavior-Based Approach 02CFIC CY Reactive systems Reflexive behavior Perception-action Subsumption CFIDV Action 2 Perception 2 ROBOT WORLD Perception 1 Action 1 Basilio Bona DAUIN Politecnico di Torino 001/10

11 Behavior-Based Approach Rodney Brooks is the father of this approach: CFIDV 02CFIC CY Some of his key sentences Complex behavior need not necessarily be the product of a complex control system Intelligence is in the eye of the observer The world is its best model Simplicity is a virtue Robots should be cheap Robustness in the presence of noisy or failing sensors is a design goal Planning is just a way of avoiding figuring out what to do next All onboard computation is important Systems should be built incrementally No representation. No calibration. No complex computers. No high band communication Basilio Bona DAUIN Politecnico di Torino 001/11

12 Behavior-Based Approach 02CFIC CY CFIDV CA 01 OBOTIC RO No model is necessary Horizontal decomposition Coordination + Priority it = Fusion Biomimesis = observe and copy animal behavior Subsumption Embodiment Basilio Bona DAUIN Politecnico di Torino 001/12

13 Subsumption CFIDV 02CFIC CY The subsumption architecture was originally proposed by Brooks [1986]. The subsumption (or 'Brooksian') architecture is based on the synergy between sensation and actuation in lower animals such as insects. Brooks argues that instead of building complex agents in simple worlds, we should follow the evolutionary path and start building simple agents in the real, complex and unpredictable world. From this argument, a number of key features of subsumption result: Basilio Bona DAUIN Politecnico di Torino 001/13

14 Subsumption 1. No explicit knowledge representation is used. Brooks often refers to this as The world is its own best model CFIDV 02CFIC CY 2. Behavior is distributed d rather than centralized. 3. Response to stimuli is reflexive the perception-action p sequence is not modulated by cognitive deliberation 4. The agents are organized in a bottom-up fashion. Thus, complex behaviors are fashioned from the combination of simpler, underlying ones 5. Individual agents are inexpensive, allowing a domain to be populated by many simple agents rather than a few complex ones. These simple agents individually consume little resources (such as power) and are expendable, making the investment t in each agent minimal i Basilio Bona DAUIN Politecnico di Torino 001/14

15 Subsumption CFIDV 02CFIC CY Several extensions (Mataric, 1992) have been proposed to pure reactive subsumption systems. These extensions are known as behavior-based architectures. Capabilities of behavior-based systems include landmark detection and map building, learning to walk, collective behaviors with homogeneous agents, group learning with homogeneous agents, and heterogeneous agents. Basilio Bona DAUIN Politecnico di Torino 001/15

16 Embodiment CFIDV 02CFIC CY To embody (verb) = manifest or personify in concrete form; incarnate; incorporate, unite into one body Embodiment is the way in which human (or any other animal) psychology arises from the brain & body physiology It is specifically concerned with the way the adaptive function of categorization works, and how things acquire names It is distinguished from developmental psychology and physical anthropology by its focus on cognitive science, ontogeny, ontogenetics, chaos theory and cognitive notions of entropy far more abstract and more reliant on mathematics Basilio Bona DAUIN Politecnico di Torino 001/16

17 Embodiment CFIDV 02CFIC CY Embodiment theory was brought into AI by Rodney Brooks in the 1980s Brooks and others showed that t robots could be more effective if they thought (planned or processed) and perceived as little as possible The robot's intelligence is geared towards only handling the minimal amount of information necessary to make its behavior be appropriate and/or as desired by its creator Brooks (and others) have claimed that all autonomous agents need to be both embodied and situated. t They claim that t this is the only way to achieve strong AI Basilio Bona DAUIN Politecnico di Torino 001/17

18 Embodiment 02CFIC CY CFIDV (Rolf Pfeifer AILab Zurich) there are essentially two directions in artificial intelligence: one concerned with developing useful algorithms or robots; and another direction that focuses on understanding intelligence, biological or otherwise. In order to make progress on the latter, an embodied perspective is mandatory. In this research branch, artificial intelligence is embodied. Basilio Bona DAUIN Politecnico di Torino 001/18

19 Some terms CFIDV 02CFIC CY Ontogeny is that t branch of life science which h deals with the study of origin and development of an organism from fertilized ovum to its mature form. In more general terms, ontogeny is defined as the history of structural change in a unity, which can be a cell, an organism, or a society of organisms, without the loss of the organization that allows that unity to exist Embodied Embedded Cognition, a position in cognitive science stating that intelligent behavior emerges out of the interplay between brain, body and world Embodied Cognition (or the embodied mind thesis), a position in cognitive science and the philosophy of mind emphasizing the role that the body plays in shaping the mind AA 2007/08 Basilio Bona DAUIN Politecnico di Torino 001/19

20 Situated robot CFIDV 02CFIC CY A situated robot is one which does not deal with abstract representations of the world (which may be simulated or real), but rather reacts directly to its environment as seen through its sensors. An alternative to having a situated robot would be one which builds up a representation of its world and then makes plans based on the representation. Because of the limitations of our present technology, these two approaches often seem contradictory. In the present, each approach is better for different applications. If we want to make an artificial person at some point in the future, we will need to incorporate both approaches. Basilio Bona DAUIN Politecnico di Torino 001/20

21 Situated robot CFIDV 02CFIC CY The situated approach can only deal with a small domain of problems. When a robot gets into a situation where it needs to reason or plan ahead in order to reach a goal, simply reacting to its environment is insufficient. i A situated robot can be thought of as sensors and goals feeding into a fixed network of difference engines which have actuators as their outputs. For example, we might have a light sensors and a goal of reaching lights fed into a difference engine. The robot would then activate its actuators in an attempt to reach its goal. Basilio Bona DAUIN Politecnico di Torino 001/21

22 Situated robot CFIDV 02CFIC CY This network might be slightly more complex with a controller o suppressing and activating at difference e engines es in response to an FSM state or a sensor input (for example, causing the robot to flee when danger is detected). However, this architecture does not give us the flexibility we need to solve more complicated problems, such as figuring out that we need to move further from some goals in order to reach an overall goal. A situated t robot might have special cases built into it (e.g. for dealing with getting stuck in a corner or down a dead-end hallway), but it would be very difficult to deal with the general case this way. Basilio Bona DAUIN Politecnico di Torino 001/22

23 Situated robot CFIDV 02CFIC CY The situated approach is good for dealing with problems where planning ahead is unnecessary or takes too much time. However, the representation approach is needed for solving more complicated problems where it is necessary to reason about the state of the world. For dealing with complicated tasks in the real world, it will probably be necessary to fuse the two approaches. Reasoning can be used to build up higher level plans and solve high level problems while lower level agencies may use a more situated approach for carrying out plans and dealing with problems which need immediate attention. Basilio Bona DAUIN Politecnico di Torino 001/23

24 Robotics and AI CFIDV 02CFIC CY The structure t and relations that t originates i from the interaction od simple controllers and complex environment is called emergent behavior Seven areas of AI applied to robotics Knowledge representation Understanding natural languages Learning Planning and problem solving Inference Search Vision R.R. Murphy, Introduction to AI Robotics, MIT Press, Basilio Bona DAUIN Politecnico di Torino 001/24

25 Knowledge representation CFIDV 02CFIC CY Define and build the physical and virtual structures t used by the robot to represent the world the tasks itself Example: a robot is looking after a human being under the wreckage of a fallen building: how it is represented? Structural model: Head (oval) + trunk (cylindrical) + arms (cylindrical) Bilateral symmetry Physical model (thermical image?) What happens if the body is only partially visible? Basilio Bona DAUIN Politecnico di Torino 001/25

26 Understanding Natural Languages Natural language is one of the most simple and human ways to interact CFIDV 02CFIC CY But Understand the words does not mean to understand the sentence Grammatical structure vs Semantical structure Example We gave the monkeys two bananas because they were hungry We gave the monkeys two bananas because they were over-ripe They have the same grammatical structure bu a very differente semantical structure To understand the sense we must know both the monkeys and the bananas Necessity to develop ontologies Basilio Bona DAUIN Politecnico di Torino 001/26

27 Understanding Natural Languages For example, the string Time flies like an arrow may be interpreted t in a variety of ways: CFIDV 02CFIC CY time moves quickly just like an arrow does; measure the speed of flying insects like you would measure that of an arrow - i.e., (You should) time (verb) flies like you would an arrow; measure the speed of flying insects like an arrow would - i.e. Time flies in the same way that an arrow would (time them).; measure the speed of flying insects that are like arrows - i.e. Time those flies that are like arrows; a type of flying insect, "time-flies time-flies, " enjoy arrows (compare Fruit flies like a banana.) The word time alone can be interpreted as three different parts of speech, (noun in the first example, verb in 2, 3, 4, and adjective in 5). English is particularly challenging g in this regard because it has little inflectional morphology to distinguish between parts of speech. AA 2007/08 Basilio Bona DAUIN Politecnico di Torino 001/27

28 Learning CFIDV 02CFIC CY Is the capacity to memorize actions and behaviors and to repeat them to adapt to the implicit or explicit objectives In a broad sense, learning is the ability to adapt during life We know that most living organisms with a nervous system display some type of adaptation during life. The ability to adapt quickly is crucial for autonomous robots that operate in dynamic and partially unpredictable environments, but the learning systems developed so far have so many constraints that are hardly applicable to robots that interact with an environment without human intervention. Learning requires A structure able to store and retrieve data One or more explicit objectives An adaptation mechanism (reward + punishment) An explicit or implicit teacher Basilio Bona DAUIN Politecnico di Torino 001/28

CA 01CFIDV OBOTIC RO Planning and problem

problems arising when plans fail Go there Go

29 CA 01CFIDV OBOTIC RO Planning and problem solving 02CFIC CY Intelligence is associated to the ability to plan actions toward the the given task fulfillment, and to solve problems arising when plans fail Go there Go there Basilio Bona DAUIN Politecnico di Torino 001/29

30 CY CA 01CFIDV 02CFIC OBOTIC RO Planning and problem solving Basilio Bona DAUIN Politecnico di Torino 001/30

31 ROBOTICA 01CFIDV 02CFICY SLAM Basilio Bona DAUIN Politecnico di Torino 001/31

32 Inference CY 02CFIC CFIDV Inference is a procedure that allows to generate an answer also when the data or information are incomplete Inference is based on statistical models (bayesian networks) or semantical models Basilio Bona DAUIN Politecnico di Torino 001/32

33 Search 02CFIC CY CFIDV Not necessarily a search of objects in space, but the ability to examine a knowledge representation database (search space) to find the required answer Consider a computer playing chess: the best move is found looking for a solution in the search space of all possible moves, starting from the present chessboard state Basilio Bona DAUIN Politecnico di Torino 001/33

34 Vision CY 02CFIC CFIDV Vision is the most important sense in human beings Psychological studies have demonstrated that the ability to solve problems is due to our brain capacity to visualize the effects of each action Basilio Bona DAUIN Politecnico di Torino 001/34

35 Ontology CFIDV 02CFIC CY In philosophy, ontology listed as a part of the major branch of philosophy known as metaphysics, ontology deals with questions concerning what entities exist or can be said to exist, and how such entities can be grouped, related within a hierarchy, h and subdivided d d according to similarities and differences It derives from Greek οντος, òntos (present participle of ειναι, einai, to be) and λογος, "lògos". In computer sciences, an ontology is a formal representation of a set of concepts within a domain and the relationships between those concepts. It is used to reason about the properties of that domain, and may be used to define the domain. An ontology provides a shared vocabulary, which can be used to model a domain that is, the type of objects and/or concepts that exist, and their properties and relations. [ Basilio Bona DAUIN Politecnico di Torino 001/35

36 Books CY 02CFIC CFIDV R.C. Arkin Behavior-Based Robotics MIT Press, 1998 RR R.R. Murphy Introduction to AI Robotics MIT Press, 2000 Basilio Bona DAUIN Politecnico di Torino 001/36

37 Books CY 02CFIC CFIDV G. Dudek, M. Jenkin Computational Principles of Mobile Robotics Cambridge U.P., 2000 R. Siegwart, I.R. Nourbakhsh Autonomous Mobile Robots MIT Press, 2004 Basilio Bona DAUIN Politecnico di Torino 001/37

38 Books CY 02CFIC CFIDV Autori Vari Principles of Robot Motion MIT Press, 2005 How the Body Shapes the Way We Think A New View of Intelligence Rolf Pfeifer and Josh C. Bongard Foreword by Rodney Brooks Basilio Bona DAUIN Politecnico di Torino 001/38

39 Books CY 02CFIC CFIDV S. Thrun, W. Burgard, D. Fox Probabilistic Robotics MIT Press, 2005 Rolf Pfeifer, Josh C. Bongard How the Body Shapes the Way We Think A New View of Intelligence Foreword by Rodney Brooks MIT Press, 2006 Basilio Bona DAUIN Politecnico di Torino 001/39

Unmanned autonomous vehicles in air land and sea

based on Gianni A. Di Caro lecture on ROBOT CONTROL RCHITECTURES SINGLE AND MULTI-ROBOT SYSTEMS: A CASE STUDY IN SWARM ROBOTICS Unmanned autonomous vehicles in air land and sea Robots and Unmanned Vehicles