6th European PhD School in Robotic Systems. Models and Knowledge. Herman Bruyninckx University of Leuven Eindhoven University of Technology
|
|
- Camron Byrd
- 6 years ago
- Views:
Transcription
1 6th European PhD School in Robotic Systems Models and Knowledge Herman Bruyninckx University of Leuven Eindhoven University of Technology Leuven, August 4 8, 2014 Overview Knowledge representation & s structure & behaviour mechanism & policy decomposition/decoupling & composition/coupling examples Model Driven Engineering for knowledge representation: meta meta s meta s & Domains Specific Languages (DSLs) -to- transformations & reasoning Homeworks identifying structure & mechanism turning the insights into DSLs connect DSLs to your code European PhD School in Robotic Systems H. Bruyninckx Page 2 Overview Knowledge representation & s structure & behaviour mechanism & policy decomposition/decoupling & composition/coupling examples Model Driven Engineering for knowledge representation: meta meta s meta s & Domains Specific Languages (DSLs) -to- transformations & reasoning Homeworks identifying structure & mechanism turning the insights into DSLs connect DSLs to your code Knowledge engineering is still an immature science...! Basically no knowledge is already available in formal ways...! European PhD School in Robotic Systems H. Bruyninckx Page 2
2 Knowledge representation = Modelling Objective: to what one knows about the world State of the practice in knowledge representation: State of the practice in ling for engineering: European PhD School in Robotic Systems H. Bruyninckx Page 3 Knowledge representation = Modelling Objective: to what one knows about the world integration of large amounts of knowledge, from various expertise s structure is necessary... also the understanding by humans is better when they (are forced to...!) formalize it. (Check this out, this week!) use by robots requires formal representations... if they need to exchange or to reason about it... State of the practice in knowledge representation: State of the practice in ling for engineering: European PhD School in Robotic Systems H. Bruyninckx Page 3 Knowledge representation = Modelling Objective: to what one knows about the world integration of large amounts of knowledge, from various expertise s structure is necessary... also the understanding by humans is better when they (are forced to...!) formalize it. (Check this out, this week!) use by robots requires formal representations... if they need to exchange or to reason about it... State of the practice in knowledge representation: Glossary: list of definitions, for humans. Taxonomy: tree of properties, for humans and computers. Ontology: graph of relationships between concepts. State of the practice in ling for engineering: European PhD School in Robotic Systems H. Bruyninckx Page 3
3 Knowledge representation = Modelling Objective: to what one knows about the world integration of large amounts of knowledge, from various expertise s structure is necessary... also the understanding by humans is better when they (are forced to...!) formalize it. (Check this out, this week!) use by robots requires formal representations... if they need to exchange or to reason about it... State of the practice in knowledge representation: Glossary: list of definitions, for humans. Taxonomy: tree of properties, for humans and computers. Ontology: graph of relationships between concepts. State of the practice in ling for engineering: Simulink, LabView,... : algorithms, single-thread systems. 20Sim, Modelica,... : s + algorithms for physical systems. RobotStudio (ABB), KUKASim, RobotExpert (Siemens),... : s for robot kin&dyn and geometric trajectories. European PhD School in Robotic Systems H. Bruyninckx Page 3 Knowledge representation = Modelling (2) Types of knowledge: symbolic: manipulation needs a hand on an arm,... discrete: go left, then right, then stop,... continuous: the dynamic relations of deburring,... European PhD School in Robotic Systems H. Bruyninckx Page 4 Knowledge representation = Modelling (2) Types of knowledge: symbolic: manipulation needs a hand on an arm,... discrete: go left, then right, then stop,... continuous: the dynamic relations of deburring,... Knowledge at system level: must integrate symbolic, discrete and continuous knowledge! must be composable, also at runtime in robotics, open world assumption must be designed in! European PhD School in Robotic Systems H. Bruyninckx Page 4
4 Knowledge representation = Modelling (2) Types of knowledge: symbolic: manipulation needs a hand on an arm,... discrete: go left, then right, then stop,... continuous: the dynamic relations of deburring,... Knowledge at system level: must integrate symbolic, discrete and continuous knowledge! must be composable, also at runtime in robotics, open world assumption must be designed in! Discussion: how to ground formal knowledge? ( enumeration, verified implementations,... ) how to compose knowledge? ( follow the natural hierarchical structures,... ) European PhD School in Robotic Systems H. Bruyninckx Page 4 5X Meta to represent structure Composition "contains", "connects" Concern 4 Concern 3 Concern 2 Concern 1 Vertical RHS: natural hierarchy of decoupled concerns Horizontal: composition of decoupled concerns, via: mereology/ contains relationship: ling parts and their containment in wholes. and/or topology/ connects relationship: ling interconnection of parts and wholes. European PhD School in Robotic Systems H. Bruyninckx Page 5 5X Meta to represent structure (2) Note: sometimes, there is no natural hierarchy, and the composition reduces to a mere aggregation. For example: Robot World Model Task specification Common Knowledge Object Affordances What are the robots' motion capabilities? What can exist in the world, and where is it? What does the application want the robot to achieve? What should every robot system know? How can objects be sensed and manipulated? European PhD School in Robotic Systems H. Bruyninckx Page 6
5 Example of grounding & composition Kinematics & dynamics of robots enumeration of platforms : verified implementations: European PhD School in Robotic Systems H. Bruyninckx Page 7 Example of grounding & composition Kinematics & dynamics of robots enumeration of platforms : mobile: bicycle, differentially driven, car,... serial arms: SCARA, industrial 6-DOF with structure, LWR-like 7-DOF, pan-tilt sensor head,... parallel arms: 3-DOF Delta, 6-DOF flex picker,... mobile manipulators: composition of two or more of the above humanoids: HRP-4 type, Asimo type,... The enumeration is structured knowledge in itself! verified implementations: European PhD School in Robotic Systems H. Bruyninckx Page 7 Example of grounding & composition Kinematics & dynamics of robots enumeration of platforms : mobile: bicycle, differentially driven, car,... serial arms: SCARA, industrial 6-DOF with structure, LWR-like 7-DOF, pan-tilt sensor head,... parallel arms: 3-DOF Delta, 6-DOF flex picker,... mobile manipulators: composition of two or more of the above humanoids: HRP-4 type, Asimo type,... The enumeration is structured knowledge in itself! verified implementations: we have correct implementations for the forward/inverse kinematics and dynamics of all these platforms. And for (some of the many ways) how these robots can apply these instantaneous behaviour to create trajectories. European PhD School in Robotic Systems H. Bruyninckx Page 7
6 Example of grounding & composition Kinematics & dynamics of robots (2) Robots systems have two complementary, natural structures: physical structure (hierarchical: contains ) motion capabilities (non-hierarchical: connects ) (Multi-) chain Composition LWR, 321, Justin, youbot, PR2,... Kinematic joint Mechanical joint Actuator motion constraints via revolute or prismatic joints,... transmission, limits, friction, inertia,... electric, hydraulic, pneumatic,... Power convertor electric-electric, electric-hydraulic,... (Multi)robot motion composition Manipulation dexterity Orientation dexterity Holonomic position mobility fingers,... wrist,... arm, shoulder, torso,... Non-holonomic position mobility wheels, legs,... (Discussion: other examples of structure...?) European PhD School in Robotic Systems H. Bruyninckx Page 8 Knowledge: graphs of connected concepts graphs: nodes & edges = binary relationships e.g.: tree, multi-tree, DAG,... hypergraphs: multi-node edges = n-ary relationships e.g.: factor graphs, info box,... X Y hidden observed A B C hierarchical hypergraphs: every containment level = a context but a context should not be a boundary of information hiding! e.g.: state machine, Bond Graph,... State 2.1 E_1 State1 State2 E_21 E_22 State 2.1 E_23 E_2 E_24 State 2.2 European PhD School in Robotic Systems H. Bruyninckx Page 9 Intermezzo: Context (Scope, namespace, frame, situation,... ) statement s semantics depends not only on statement itself, but especially on context in which it is used. for intelligent behaviour, context is everything! E.g., knowledge that Robot X can move at a speed of 1m/s can mean danger in one context, but opportunity in another context. The meaning is a property of the composition knowledge context, not of the knowledge relationship itself. all extra information needed to be able to decide (formally, by a computer algorithm) whether two different terms have the same meaning or not, or one single term has a different meaning or not in the two different contexts names/terminology: it is very difficult to avoid giving names that reflect one particular context ( looking up/outside, in the context ), instead of reflecting only the properties of the term ( looking down/inside ) implicit context is a major error in coding! European PhD School in Robotic Systems H. Bruyninckx Page 10
7 Knowledge: graphs of connected concepts (2) RDF/OWL triples: most popular approach in the semantic web links three concepts: relationship, subject, object. Example: a Wikipedia article about Tony Benn : European PhD School in Robotic Systems H. Bruyninckx Page 11 Knowledge: graphs of connected concepts (2) RDF/OWL triples: most popular approach in the semantic web links three concepts: relationship, subject, object. Example: a Wikipedia article about Tony Benn : advantage: lots of tools and documentation available. European PhD School in Robotic Systems H. Bruyninckx Page 11 Knowledge: graphs of connected concepts (2) RDF/OWL triples: most popular approach in the semantic web links three concepts: relationship, subject, object. Example: a Wikipedia article about Tony Benn : advantage: lots of tools and documentation available. disadvantages: exclusively symbolic level! ( description logic ) limitation to triples makes it difficult to represent tree and graph like representations in an easy syntax! Lisp represents trees. European PhD School in Robotic Systems H. Bruyninckx Page 11
8 Knowledge: graphs connected concepts (3) Wikipedia Info-boxes: structured tables (n-ary relationships!) with concepts and links as named (not led!) properties, in each article. Wikidata: n-ary relationship inverse of Info boxes, i.e., with centralized representation. Xlink: W3C standard to add single and n-ary relationships ( links ) to XML documents. More in particular, to make a link a first-class concept in itself, allowing to make statements about the relationship. More: KnowRob: (University of Bremen) combines multiple languages, for different purposes good! focus on (expression) trees a bit less good... misses hierarchical hypergraph natural structures the best one can get in robotics, for now... European PhD School in Robotic Systems H. Bruyninckx Page 12 Knowledge: graphs connected concepts (4) Topic Map ISO standard, n-ary relationship between concepts and contexts and occurrences (Source: Wikipedia) Not very popular. Open source topic maps database exists: Model-Driven Engineering paradigm: see later. European PhD School in Robotic Systems H. Bruyninckx Page 13 Reification Each relationship is a concept in itself too (knowledge_representation): statements can be made about statements! leads naturally to ( natural???) hierachies! Example: There is a 50% probability that the statement Robot X is in Room A is true. Importance: this ability/insight to treat each relationship/statement/knowledge as a primitive itself, about which statements can be made, is one of the keys to knowledge engineering in open worlds. European PhD School in Robotic Systems H. Bruyninckx Page 14
9 Open world assumptions Needs for open world assumption: one can not everything in advance. s must be updated at runtime = knowledge is added contexts come and go at runtime Types of open world assumption: 1. every rule that is not led is true. E.g.: semantic web s OWL language. 2. every rule that is not led as true is false. (= closed world assumption ) 3. a DSL that s knowledge can be given explicit tags to indicate where its world is open, that is, it needs other DSLs to complement itself. Examples: in robotics : Collada; in general: XCore. Counter examples in robotics: URDF, Gazebo s SDF. European PhD School in Robotic Systems H. Bruyninckx Page 15 Cartesian frame Primary example of knowledge graph Kinematic chains joint structure: mereology + topology mechanism: inward/outwards sweeps, to compute motion, articulated inertias, and forces joint axis branching joint link root behaviour: mass, friction, elasticity, controllers, estimators, geometry(?) (shape + location) policy: scheduling of behaviour to execute during sweeps, and tolerance of results European PhD School in Robotic Systems H. Bruyninckx Page 16 Cartesian frame Primary example of knowledge graph Kinematic chains joint structure: mereology + topology mechanism: inward/outwards sweeps, to compute motion, articulated inertias, and forces joint axis branching joint link behaviour: mass, friction, elasticity, controllers, estimators, geometry(?) (shape + location) policy: scheduling of behaviour root to execute during sweeps, and tolerance of results Similar examples:: probabilistic graphical s, control diagrams, Finite State Machines, multiple Level-of-Detail world s,... European PhD School in Robotic Systems H. Bruyninckx Page 16
10 Knowledge must be composable! Mainstream bad practice = API hierarchies Example: extremely non-composable library: inverse dynamics v1: Newton-Euler, by inward/outward sweeps over kinematic chain with ideal 1DOF joints: tau = ID NE (q, qdot, F) European PhD School in Robotic Systems H. Bruyninckx Page 17 Knowledge must be composable! Mainstream bad practice = API hierarchies Example: extremely non-composable library: inverse dynamics v1: Newton-Euler, by inward/outward sweeps over kinematic chain with ideal 1DOF joints: tau = ID NE (q, qdot, F) v2: what about posture control? tau = ID NE PC (q, qdot, F,tau p) European PhD School in Robotic Systems H. Bruyninckx Page 17 Knowledge must be composable! Mainstream bad practice = API hierarchies Example: extremely non-composable library: inverse dynamics v1: Newton-Euler, by inward/outward sweeps over kinematic chain with ideal 1DOF joints: tau = ID NE (q, qdot, F) v2: what about posture control? tau = ID NE PC (q, qdot, F,tau p) v3: and damped least-squares singularity robustness? tau = ID NE PC DLS (q, qdot, F,tau p,lambda) European PhD School in Robotic Systems H. Bruyninckx Page 17
11 Knowledge must be composable! Mainstream bad practice = API hierarchies Example: extremely non-composable library: inverse dynamics v1: Newton-Euler, by inward/outward sweeps over kinematic chain with ideal 1DOF joints: tau = ID NE (q, qdot, F) v2: what about posture control? tau = ID NE PC (q, qdot, F,tau p) v3: and damped least-squares singularity robustness? tau = ID NE PC DLS (q, qdot, F,tau p,lambda) v4: what about joint limit avoidance? tau = ID NE PC DLS JL (q, qdot, F,tau p,lambda,k) European PhD School in Robotic Systems H. Bruyninckx Page 17 Knowledge must be composable! Mainstream bad practice = API hierarchies Example: extremely non-composable library: inverse dynamics v1: Newton-Euler, by inward/outward sweeps over kinematic chain with ideal 1DOF joints: tau = ID NE (q, qdot, F) v2: what about posture control? tau = ID NE PC (q, qdot, F,tau p) v3: and damped least-squares singularity robustness? tau = ID NE PC DLS (q, qdot, F,tau p,lambda) v4: what about joint limit avoidance? tau = ID NE PC DLS JL (q, qdot, F,tau p,lambda,k) v5 v : what about N-DOF joints? mobile platforms? configuration of all parameters? trees? constraints? various trajectories?... European PhD School in Robotic Systems H. Bruyninckx Page 17 Inverse dynamics API bad practice It will get even worse... When sensing & control are added... : Cartesian point trajectory soft Cartesian point trajectory joint limits centre of gravity trajectory Cartesian link trajectory sliding contact with environment rigid connection to environment sensor space European PhD School in Robotic Systems H. Bruyninckx Page 18
12 Inverse dynamics API bad practice It will get even worse... When sensing & control are added... : Cartesian point trajectory soft Cartesian point trajectory joint limits centre of gravity trajectory Cartesian link trajectory sliding contact with environment rigid connection to environment sensor space Observations: main API problem: exposes behaviour coupled with structure, and policy coupled with mechanism! sensing & control are not libraries, but concurrent activities! European PhD School in Robotic Systems H. Bruyninckx Page 18 Model Driven Engineering (MDE) Knowledge representation via meta s M3 metameta conforms to M2 M1 meta (DSL) conforms to meta (DSL) DSL Designer DSL User DSL: Domain Specific Language realisation of M0 Real-world systems conforms-to : every relationship in the satisfies the constraints represented in the above. European PhD School in Robotic Systems H. Bruyninckx Page 19 Model-Driven Engineering (2) M3 = meta-meta (no -knowledge!) M2 = meta (Domain Specific Language) M1 = ( encoded in DSL) M0 = implementation (in specific programming language(s)) M3 M0: is an ontology! (And it extends traditional ontology design approaches with an extra meta meta for ontologies!) Conforms-to vs instance-of: (Discussion!) fundamental difference is composability: constraints compose, behaviour does not! European PhD School in Robotic Systems H. Bruyninckx Page 20
13 Model-Driven Engineering (2) M3 = meta-meta (no -knowledge!) M2 = meta (Domain Specific Language) M1 = ( encoded in DSL) M0 = implementation (in specific programming language(s)) M3 M0: is an ontology! (And it extends traditional ontology design approaches with an extra meta meta for ontologies!) Conforms-to vs instance-of: (Discussion!) fundamental difference is composability: constraints compose, behaviour does not! Meta levels: essential part of the Less is more objective! European PhD School in Robotic Systems H. Bruyninckx Page 20 Model-Driven Engineering (2) M3 = meta-meta (no -knowledge!) M2 = meta (Domain Specific Language) M1 = ( encoded in DSL) M0 = implementation (in specific programming language(s)) M3 M0: is an ontology! (And it extends traditional ontology design approaches with an extra meta meta for ontologies!) Conforms-to vs instance-of: (Discussion!) fundamental difference is composability: constraints compose, behaviour does not! Meta levels: essential part of the Less is more objective! Composition of knowledge: put semantic ( symbolic ) links between MDE s RDF, OWL, TopicMaps,...! Symbolic, Discrete & Physical/Continuous s: robotics needs this combination! ( difficult...!) European PhD School in Robotic Systems H. Bruyninckx Page 20 Model Driven Engineering: example of classes (Source: European PhD School in Robotic Systems H. Bruyninckx Page 21
14 Model Driven Engineering: other examples M3 M2 meta (DSL) metameta conforms to conforms to meta (DSL) XML Collada 1.5 URDF M1 youbot s realisation of M0 Real-world systems European PhD School in Robotic Systems H. Bruyninckx Page 22 Model Driven Engineering: other examples (2) M3 M2 meta (DSL) metameta conforms to conforms to meta (DSL) XML (metameta) XHTML, SVG languages (metas) M1 particular web page realisation of M0 this web page in your browser European PhD School in Robotic Systems H. Bruyninckx Page 23 Model Driven Engineering: classes vs s Class hierarchies are for: classification of behaviour inheritance: every subclass must behave as any of its superclasses multiple inheritance is extremely difficult Java allows inheritance of interfaces, i.e., of a, not a behaviour! Model hierarchies are for: knowledge representation knowledge is added by adding new relationships, anywhere a need not behave like its meta, but just satisfy all the latter s relationships, if applicable s are a lot more composable! European PhD School in Robotic Systems H. Bruyninckx Page 24
15 Should be: Intermezzo: Meta meta s small: full meaning must be graspable by human in five minutes. stand-alone: meaning should be clear from meta meta itself, and from the other imported meta meta s. fully formal: reasoning is possible, on wellformedness and meaningfulness. abstraction ( class vs instance ) is possible. categorization is possible. relationships are first-class concepts. European PhD School in Robotic Systems H. Bruyninckx Page 25 Should be: Intermezzo: Meta meta s small: full meaning must be graspable by human in five minutes. stand-alone: meaning should be clear from meta meta itself, and from the other imported meta meta s. fully formal: Examples: reasoning is possible, on wellformedness and meaningfulness. abstraction ( class vs instance ) is possible. categorization is possible. relationships are first-class concepts. hierarchical hypergraphs for lumped-parameter, port-based systems. physical units: QUDV, QUDT, UDUNITS, QUOMOS, Unified Code for Units of Measure,.... geometric frames: http: // software patterns: inversion of control, composite component,... European PhD School in Robotic Systems H. Bruyninckx Page 25 Intermezzo: Meta meta s (2) QUDT Quantities, Units, Dimensions and Data Types Semantic Sensor Network ontology: Semantic_Sensor_Net_Ontology describes sensors, the accuracy and capabilities of such sensors, observations, methods used for sensing, operating and survival ranges uses DOLCE-UltraLite3 (DUL) upper ontology. Dublin core: ontology of authorship & provenance of documents European PhD School in Robotic Systems H. Bruyninckx Page 26
16 Intermezzo: Meta meta s (3) Geospatial data: interconnected set of standards/ontologies: Geography Markup Language: where are things on earth. ISO standard: ISO 19136:2007. KML (Keyhole Markup Language): adds views to the geographic, and COLLADA as world language. CityGML: s how cities look like. IndoorGML: s how indoors of buildings look like. BIM (Building Information Models): s physical and functional characteristics of places. https: //en.wikipedia.org/wiki/building_information_modeling XDMF: s grids in 1D, 2D, 3D and above. European PhD School in Robotic Systems H. Bruyninckx Page 27 Intermezzo: Meta meta s (4) UML as ling language European PhD School in Robotic Systems H. Bruyninckx Page 28 Intermezzo: Meta meta s (5) UML as ling language (cont d) UML-specific problems: fine for class-instance relationships ( generalization of behaviour ). poor for link relationships ( associations ): a link is just a string, not a first-class ling primitive for humans, not robots! set of available relationships too limited: composition = is-a ; aggregation = has-a. no hyperedge relationships. Generic Observations: way too much language lock-in exists: people only use the features (for ling and processing of knowledge) that their familiar language and its tooling ecosystem provide. the XML (web services community) and RDF/OWL (X3C semantic web community) ecosystems are the two major competitors, with Lisp/Prolog (Artificial Intelligence community) a good ( better!) third. European PhD School in Robotic Systems H. Bruyninckx Page 29
17 Composition of meta s/knowledge M3 metameta conforms to metameta 2 M2 meta (DSL) conforms to meta (DSL) M1 realisation of M0 Real-world systems Discussion: compare to class multiple inheritance...! European PhD School in Robotic Systems H. Bruyninckx Page 30 Model Driven Engineering: transformations conforms to Source Language Meta Source Model conforms to Metaing Language Metameta conforms to Transformation Definition conforms to Transformation conforms to Target Language Meta conforms to Target Model Source Target M2-level transformations are key to integration, composition, harmonization, standardization! Discussion: advantages, disadvantages...! European PhD School in Robotic Systems H. Bruyninckx Page 31 Domain Specific Languages (DSL) DSL = artificial language in one particular. = one particular form of ontology. (At least, it should be... ) Necessary(?) parts in a DSL: Primitives: concepts, objects,... Relationships: between Primitives. Constraints on properties of Primitives and Relationships. Tolerances: on ( soft ) Constraints. European PhD School in Robotic Systems H. Bruyninckx Page 32
18 Domain Specific Languages (DSL) DSL = artificial language in one particular. = one particular form of ontology. (At least, it should be... ) Necessary(?) parts in a DSL: Primitives: concepts, objects,... Relationships: between Primitives. Constraints on properties of Primitives and Relationships. Tolerances: on ( soft ) Constraints. Discussion: which of the already mentioned examples is really a DSL? That is, do they have a M3-M0 formalisation? is it really useful to make DSLs that robots can understand & use...? European PhD School in Robotic Systems H. Bruyninckx Page 32 Examples: DSLs Contexts Constraints The talking horse flies through the ocean is well-formed (= syntactically correct, following the relationships) but its meaning depends on the context. the correctness of the syntactically correct statement The robot should not move faster than 1m/s to be safe depends on the context. European PhD School in Robotic Systems H. Bruyninckx Page 33 Examples: DSLs Contexts Constraints The talking horse flies through the ocean is well-formed (= syntactically correct, following the relationships) but its meaning depends on the context. the correctness of the syntactically correct statement The robot should not move faster than 1m/s to be safe depends on the context. Context provides the most important difficulties for formal language design: it brings constraints that come from above, and not from the sentence itself. computer tools can only work with context-free languages. complexity of context requires graph-shaped sets of DSLs context-dependent languages! European PhD School in Robotic Systems H. Bruyninckx Page 33
19 Hierarchical Hypergraphs for structural s NPC = Nodes, Ports, Connectors Structural primitives are: contains relationship: hierarchy. connects, via lumped-parameter ports. Example: connects(connector-i, port-p), connects(connector-i, port-s), connects(connector-j, port-n), connects(connector-j, port-q), i connects(connector-j, port-r), n B p connects(port-n, node-b), j connects(port-p, node-b), s q connects(port-q, node-c), r C X D connects(port-r, node-d), and A connects(port-s, node-x). contains(node-a, node-b), contains(node-a, node-c), and contains(node-a, node-d). European PhD School in Robotic Systems H. Bruyninckx Page 34 Meta /DSL example(s): robot kinematics, dynamics, motion & control kinematic joint mechanical joint + limits geometric frame kinematic chain + kinematics rigid body hybrid dynamics position, velocity, force motion specification motion control... l 6 l 4 = l 5 = 0 q 5 X 4 = X 5 = X 6 Discussion: why don t these DSLs exist already...? l 3 l 2 l 1 q 3 q 2 {ee} wrist centre q 6 point X 7 Y 7 X 1 X 3 X 2 q4 Y 4 = Y 5 = Y 6 Y 3 q 1 Y 2 Z 0 Y 1 X 0 Y 0 {bs} European PhD School in Robotic Systems H. Bruyninckx Page 35 Meta /DSL example(s): HH for robot motion stack actual motion Cartesian constraint motion constraints perception data bus Cartesian motion joint motion sensors actuator value Cartesian control joint constraint joint control actuator constraint actuator control joint & actuator constraints actuator constraints "current" setpoint action data bus actuators motion control stack software hardware Discussion: where does the motion stack stop, and the application start? European PhD School in Robotic Systems H. Bruyninckx Page 36
20 Meta meta robot device capabilities Topological structure Perception Software Adaptation Sensing Modelling Learning Planning Mechanism Control Actuation ENVIRONMENT Hardware Discussion: capabilities must still be grounded! How...? European PhD School in Robotic Systems H. Bruyninckx Page 37 Meta meta Robot app Task specification Platform capabilities Models Common knowledge Robotics Application World Object affordances Algorithms and Data... perception... planning reasoning... kin& control dyn learning trajectory adaptation generation... Software Activities configuration calls Configurator constraint constraint flow flow functional Computation monitor Computation HW/SW platforms App framework SW framework Operating Syst. MoveIt,... ROS, Orocos, OpenRTM, OPRoS,... Linux, ecos, VxWorks, QNX, Windows,... Coordinator events HW framework PC architecture, data buses, FPGA, GPU,... Discussion: each robot vendor dreams of making its app platform into the app platform... European PhD School in Robotic Systems H. Bruyninckx Page 38 Intermezzo: Robot app literature coverage Task specifications Robot platforms Models Robotics Application Knowledge base World Algorithms... perception... planning reasoning... kin& control dyn learning trajectory adaptation generation... Software Activities data in functional Computation data out HW/SW platforms App framework SW framework Operating Syst. MoveIt,... ROS, Orocos, OpenRTM, OPRoS,... Linux, ecos, VxWorks, QNX, Windows,... HW framework PC architecture, data buses, FPGA, GPU,... Too many publications on details... Hardly any research results on integration! European PhD School in Robotic Systems H. Bruyninckx Page 39
21 Meta meta Perception networks HH-NPC + lots of behaviour/policy mission robot task env obj1 obj2 fea1 fea2 fea3 sen1 sen2 Discussion: information flows in all directions...! European PhD School in Robotic Systems H. Bruyninckx Page 40 Meta meta Cognitive sensori-motor control networks pre-cognitive preview robot feedback & feedforward memory/ focus Control obj1 task obj2 fea1 fea2 fea3 cause1 mission cause2 intention/ motivation understanding env Perception reaction interpretation Discussion: should this be the meta to guide robot software development...? European PhD School in Robotic Systems H. Bruyninckx Page 41 Task { { Platform Conclusions Learn to decompose first! But in the context of structural composition! most algorithms in robotics are already composites, or even worse, applications, since they contain (often implicitly) control, sensing and world ling aspects! For example: SLAM motion planning... definition of an algorithm : sequential computation without any side effects. Design is about removing as many features as possible from (the of) a sub-system, without compromising its composability! European PhD School in Robotic Systems H. Bruyninckx Page 42
22 Discussion + Homework How can we bring more structure to robotics? (For example, via Could it be done via by hierarchical structures like: action mobile manipulator action perception mobile manipulator perception pick-and-place move to pick location locate object to pick align for pick... pick... lift move to place... place... object affordance: relationship between some of the above... European PhD School in Robotic Systems H. Bruyninckx Page 43 References RDF: http: //en.wikipedia.org/wiki/resource_description_framework Topic Maps: Wikipedia InfoBox: Ontology engineering: WikiData: Semantic MediaWiki: RoboEarth: Using Semantic Technologies to Describe Robotic Embodiments, Alex Juarez, Christoph Bartneck, Loe Feijs. Proceedings of the 6th ACM/IEEE International Conference on Human-Robot Interaction, Lausanne pp /semanticTechnologyRobotEmbodiments/ European PhD School in Robotic Systems H. Bruyninckx Page 44 References (2) A robot ontology for urban search and rescue, Craig Schlenoff, and Elena Messina. KRAS 05 Proceedings of the 2005 ACM workshop on Research in knowledge representation for autonomous systems Integrating ontological knowledge into a robotic DSL, Gaëlle Lorta, Saadia Dhouib and Sébastien Gérard. Proceedings of the 2010 international conference on Models in software engineering, pp , Events/2010/RoSym/presentations/Integrating_Ontological_ Domain_Knowledge_into_a_Robotic_DSL.pdf Robot Ontology Formation: index.php/robot_ontology_formation Upper ontologies: general concepts that are the same across all knowledge s. European PhD School in Robotic Systems H. Bruyninckx Page 45
23 References (3) OBO RO: with a -specific list of relations: // //purl.obolibrary.org/obo/merged/ro OBO RO Wiki: OpenCyc: general knowledge base and commonsense reasoning engine. temporal relations, spatial relations, mereological relations UMLS: online_learning/sem_001.htm BFO applications: OBI: Investigations European PhD School in Robotic Systems H. Bruyninckx Page 46 References (4) Cognitive Paradigm Ontology Meronymy, holonymy, mereology Moritz Tenorth and Michael Beetz, KnowRob: A knowledge processing infrastructure for cognition-enabled robots. The International Journal of Robotics Research, 32(5): , John Hallam, and Herman Bruyninckx, An Ontology of Robotics Science. First European Robotics Symposium, pp. 1 14, Jean Bézivin, On the unification power of s. Software and Systems Modeling, 4(2): , European PhD School in Robotic Systems H. Bruyninckx Page 47
Ontologies & Meta meta models at KU Leuven
Ontologies & Meta meta models at KU Leuven Herman Bruyninckx University of Leuven Eindhoven University of Technology European Robotics Forum, Ljubljana March 23, 2016 1 Meta models for geometry in robotics
More information10/25/2018. Robotics and automation. Dr. Ibrahim Al-Naimi. Chapter two. Introduction To Robot Manipulators
Robotics and automation Dr. Ibrahim Al-Naimi Chapter two Introduction To Robot Manipulators 1 Robotic Industrial Manipulators A robot manipulator is an electronically controlled mechanism, consisting of
More informationJohn Hsu Nate Koenig ROSCon 2012
John Hsu Nate Koenig ROSCon 2012 Outline What is Gazebo, and why should you use it Overview and architecture Environment modeling Robot modeling Interfaces Getting Help Simulation for Robots Towards accurate
More informationWritten exams of Robotics 2
Written exams of Robotics 2 http://www.diag.uniroma1.it/~deluca/rob2_en.html All materials are in English, unless indicated (oldies are in Year Date (mm.dd) Number of exercises Topics 2018 07.11 4 Inertia
More informationEmbedded Motion Control Suggestions for the design of robotic tasks and of their software architectures
Embedded Motion Control Suggestions for the design of robotic tasks and of their software architectures Eindhoven University of Technology KU Leuven http://people.mech.kuleuven.be/~bruyninc/ Introduction:
More informationMCE/EEC 647/747: Robot Dynamics and Control. Lecture 1: Introduction
MCE/EEC 647/747: Robot Dynamics and Control Lecture 1: Introduction Reading: SHV Chapter 1 Robotics and Automation Handbook, Chapter 1 Assigned readings from several articles. Cleveland State University
More informationBasilio Bona ROBOTICA 03CFIOR 1
Kinematic chains 1 Readings & prerequisites Chapter 2 (prerequisites) Reference systems Vectors Matrices Rotations, translations, roto-translations Homogeneous representation of vectors and matrices Chapter
More informationROBOTICS 01PEEQW. Basilio Bona DAUIN Politecnico di Torino
ROBOTICS 01PEEQW Basilio Bona DAUIN Politecnico di Torino Kinematic chains Readings & prerequisites From the MSMS course one shall already be familiar with Reference systems and transformations Vectors
More informationInverse Kinematics. Given a desired position (p) & orientation (R) of the end-effector
Inverse Kinematics Given a desired position (p) & orientation (R) of the end-effector q ( q, q, q ) 1 2 n Find the joint variables which can bring the robot the desired configuration z y x 1 The Inverse
More informationChapter 1: Introduction
Chapter 1: Introduction This dissertation will describe the mathematical modeling and development of an innovative, three degree-of-freedom robotic manipulator. The new device, which has been named the
More informationTable of Contents. Chapter 1. Modeling and Identification of Serial Robots... 1 Wisama KHALIL and Etienne DOMBRE
Chapter 1. Modeling and Identification of Serial Robots.... 1 Wisama KHALIL and Etienne DOMBRE 1.1. Introduction... 1 1.2. Geometric modeling... 2 1.2.1. Geometric description... 2 1.2.2. Direct geometric
More informationDynamic Analysis of Manipulator Arm for 6-legged Robot
American Journal of Mechanical Engineering, 2013, Vol. 1, No. 7, 365-369 Available online at http://pubs.sciepub.com/ajme/1/7/42 Science and Education Publishing DOI:10.12691/ajme-1-7-42 Dynamic Analysis
More informationDeveloping Algorithms for Robotics and Autonomous Systems
Developing Algorithms for Robotics and Autonomous Systems Jorik Caljouw 2015 The MathWorks, Inc. 1 Key Takeaway of this Talk Success in developing an autonomous robotics system requires: 1. Multi-domain
More informationAutomatic Control Industrial robotics
Automatic Control Industrial robotics Prof. Luca Bascetta (luca.bascetta@polimi.it) Politecnico di Milano Dipartimento di Elettronica, Informazione e Bioingegneria Prof. Luca Bascetta Industrial robots
More informationConstruction of SCARA robot simulation platform based on ROS
Construction of SCARA robot simulation platform based on ROS Yingpeng Yang a, Zhaobo Zhuang b and Ruiqi Xu c School of Shandong University of Science and Technology, Shandong 266590, China; ayangyingp1992@163.com,
More informationEE-565-Lab2. Dr. Ahmad Kamal Nasir
EE-565-Lab2 Introduction to Simulation Environment Dr. Ahmad Kamal Nasir 29.01.2016 Dr. -Ing. Ahmad Kamal Nasir 1 Today s Objectives Introduction to Gazebo Building a robot model in Gazebo Populating robot
More informationWhat Is SimMechanics?
SimMechanics 1 simulink What Is Simulink? Simulink is a tool for simulating dynamic systems with a graphical interface specially developed for this purpose. Physical Modeling runs within the Simulink environment
More informationStructural Configurations of Manipulators
Structural Configurations of Manipulators 1 In this homework, I have given information about the basic structural configurations of the manipulators with the concerned illustrations. 1) The Manipulator
More informationSimcenter Motion 3D. Mechatronics - Improve Design Dynamics Performance: Combine 3D Multi-Body Simulation with 1D Actuation & Controls Simulation
Simcenter Motion 3D Mechatronics - Improve Design Dynamics Performance: Combine 3D Multi-Body Simulation with 1D Actuation & Controls Simulation Iurie TERNA Email: iurie.terna@siemens.com Tuesday 16:00-17:00
More informationWhat is an industrial robot?
What is an industrial robot? A robot is CFIDV 02CFIC CY A kinematic chain A multi-body dynamical system A system with motors and drives A system with digital and analogic sensors An electronic system A
More informationROBOTICS 01PEEQW. Basilio Bona DAUIN Politecnico di Torino
ROBOTICS 01PEEQW Basilio Bona DAUIN Politecnico di Torino Control Part 4 Other control strategies These slides are devoted to two advanced control approaches, namely Operational space control Interaction
More informationABOUT ME. Gianluca Bardaro, PhD student in Robotics Contacts: Research field: goo.gl/dbwhhc.
ABOUT ME Gianluca Bardaro, PhD student in Robotics Contacts: gianluca.bardaro@polimi.it 02 2399 3565 Research field: Formal approach to robot development Robot and robot architecture models Robot simulation
More informationRobotics. SAAST Robotics Robot Arms
SAAST Robotics 008 Robot Arms Vijay Kumar Professor of Mechanical Engineering and Applied Mechanics and Professor of Computer and Information Science University of Pennsylvania Topics Types of robot arms
More information10/11/07 1. Motion Control (wheeled robots) Representing Robot Position ( ) ( ) [ ] T
3 3 Motion Control (wheeled robots) Introduction: Mobile Robot Kinematics Requirements for Motion Control Kinematic / dynamic model of the robot Model of the interaction between the wheel and the ground
More informationCecilia Laschi The BioRobotics Institute Scuola Superiore Sant Anna, Pisa
University of Pisa Master of Science in Computer Science Course of Robotics (ROB) A.Y. 2016/17 cecilia.laschi@santannapisa.it http://didawiki.cli.di.unipi.it/doku.php/magistraleinformatica/rob/start Robot
More informationRobotics 2 Information
Robotics 2 Information Prof. Alessandro De Luca Robotics 2! 2017/18! Second semester! Monday, February 26 Wednesday, May 30, 2018! Courses of study (code)! Master in Artificial Intelligence and Robotics
More informationMODELING AND DYNAMIC ANALYSIS OF 6-DOF PARALLEL MANIPULATOR
MODELING AND DYNAMIC ANALYSIS OF 6-DOF PARALLEL MANIPULATOR N Narayan Rao 1, T Ashok 2, Anup Kumar Tammana 3 1 Assistant Professor, Department of Mechanical Engineering, VFSTRU, Guntur, India. nandurerao@gmail.com
More informationABOUT ME. Gianluca Bardaro, PhD student in Robotics Contacts: Research field:
ABOUT ME Gianluca Bardaro, PhD student in Robotics Contacts: gianluca.bardaro@polimi.it 02 2399 3565 Research field: Formal approach to robot development Robot and robot architecture models Robot simulation
More informationRobot mechanics and kinematics
University of Pisa Master of Science in Computer Science Course of Robotics (ROB) A.Y. 2016/17 cecilia.laschi@santannapisa.it http://didawiki.cli.di.unipi.it/doku.php/magistraleinformatica/rob/start Robot
More informationAdvanced Robotic Manipulation
Advanced Robotic Manipulation Handout CS327A (Spring 2017) Problem Set #4 Due Thurs, May 26 th Guidelines: This homework has both problem-solving and programming components. So please start early. In problems
More information1. Introduction 1 2. Mathematical Representation of Robots
1. Introduction 1 1.1 Introduction 1 1.2 Brief History 1 1.3 Types of Robots 7 1.4 Technology of Robots 9 1.5 Basic Principles in Robotics 12 1.6 Notation 15 1.7 Symbolic Computation and Numerical Analysis
More informationRobot mechanics and kinematics
University of Pisa Master of Science in Computer Science Course of Robotics (ROB) A.Y. 2017/18 cecilia.laschi@santannapisa.it http://didawiki.cli.di.unipi.it/doku.php/magistraleinformatica/rob/start Robot
More informationIndustrial Robots : Manipulators, Kinematics, Dynamics
Industrial Robots : Manipulators, Kinematics, Dynamics z z y x z y x z y y x x In Industrial terms Robot Manipulators The study of robot manipulators involves dealing with the positions and orientations
More information2. Motion Analysis - Sim-Mechanics
2 Motion Analysis - Sim-Mechanics Figure 1 - The RR manipulator frames The following table tabulates the summary of different types of analysis that is performed for the RR manipulator introduced in the
More informationTable of Contents Introduction Historical Review of Robotic Orienting Devices Kinematic Position Analysis Instantaneous Kinematic Analysis
Table of Contents 1 Introduction 1 1.1 Background in Robotics 1 1.2 Robot Mechanics 1 1.2.1 Manipulator Kinematics and Dynamics 2 1.3 Robot Architecture 4 1.4 Robotic Wrists 4 1.5 Origins of the Carpal
More informationIntroduction To Robotics (Kinematics, Dynamics, and Design)
Introduction To Robotics (Kinematics, Dynamics, and Design) SESSION # 5: Concepts & Defenitions Ali Meghdari, Professor School of Mechanical Engineering Sharif University of Technology Tehran, IRAN 11365-9567
More informationHand. Desk 4. Panda research 5. Franka Control Interface (FCI) Robot Model Library. ROS support. 1 technical data is subject to change
TECHNICAL DATA 1, 2 Arm degrees of freedom 7 DOF payload 3 kg sensitivity joint torque sensors in all 7 axes maximum reach 855 mm joint position limits A1: -170/170, A2: -105/105, [ ] A3: -170/170, A4:
More informationComponent Design. Systems Engineering BSc Course. Budapest University of Technology and Economics Department of Measurement and Information Systems
Component Design Systems Engineering BSc Course Budapest University of Technology and Economics Department of Measurement and Information Systems Traceability Platform-based systems design Verification
More informationKINEMATIC AND DYNAMIC SIMULATION OF A 3DOF PARALLEL ROBOT
Bulletin of the Transilvania University of Braşov Vol. 8 (57) No. 2-2015 Series I: Engineering Sciences KINEMATIC AND DYNAMIC SIMULATION OF A 3DOF PARALLEL ROBOT Nadia Ramona CREŢESCU 1 Abstract: This
More informationFunctional Architectures for Cooperative Multiarm Systems
Università di Genova - DIST GRAAL- Genoa Robotic And Automation Lab Functional Architectures for Cooperative Multiarm Systems Prof. Giuseppe Casalino Outline A multilayered hierarchical approach to robot
More informationWhere is the Semantics on the Semantic Web?
Where is the Semantics on the Semantic Web? Ontologies and Agents Workshop Autonomous Agents Montreal, 29 May 2001 Mike Uschold Mathematics and Computing Technology Boeing Phantom Works Acknowledgements
More informationInverse Kinematics Analysis for Manipulator Robot With Wrist Offset Based On the Closed-Form Algorithm
Inverse Kinematics Analysis for Manipulator Robot With Wrist Offset Based On the Closed-Form Algorithm Mohammed Z. Al-Faiz,MIEEE Computer Engineering Dept. Nahrain University Baghdad, Iraq Mohammed S.Saleh
More informationCollision Detection. Jane Li Assistant Professor Mechanical Engineering & Robotics Engineering
RBE 550 MOTION PLANNING BASED ON DR. DMITRY BERENSON S RBE 550 Collision Detection Jane Li Assistant Professor Mechanical Engineering & Robotics Engineering http://users.wpi.edu/~zli11 Euler Angle RBE
More informationÉCOLE POLYTECHNIQUE DE MONTRÉAL
ÉCOLE POLYTECHNIQUE DE MONTRÉAL MODELIZATION OF A 3-PSP 3-DOF PARALLEL MANIPULATOR USED AS FLIGHT SIMULATOR MOVING SEAT. MASTER IN ENGINEERING PROJET III MEC693 SUBMITTED TO: Luc Baron Ph.D. Mechanical
More informationSemantic Web. Ontology Engineering and Evaluation. Morteza Amini. Sharif University of Technology Fall 95-96
ه عا ی Semantic Web Ontology Engineering and Evaluation Morteza Amini Sharif University of Technology Fall 95-96 Outline Ontology Engineering Class and Class Hierarchy Ontology Evaluation 2 Outline Ontology
More informationEEE 187: Robotics Summary 2
1 EEE 187: Robotics Summary 2 09/05/2017 Robotic system components A robotic system has three major components: Actuators: the muscles of the robot Sensors: provide information about the environment and
More informationFlexible Modeling and Simulation Architecture for Haptic Control of Maritime Cranes and Robotic Arms
Flexible Modeling and Simulation Architecture for Haptic Control of Maritime Cranes and Robotic Arms F. Sanfilippo, H. P. Hildre, V. Æsøy and H.X. Zhang Department of Maritime Technology and Operation
More informationMEM380 Applied Autonomous Robots Winter Robot Kinematics
MEM38 Applied Autonomous obots Winter obot Kinematics Coordinate Transformations Motivation Ultimatel, we are interested in the motion of the robot with respect to a global or inertial navigation frame
More informationLesson 1: Introduction to Pro/MECHANICA Motion
Lesson 1: Introduction to Pro/MECHANICA Motion 1.1 Overview of the Lesson The purpose of this lesson is to provide you with a brief overview of Pro/MECHANICA Motion, also called Motion in this book. Motion
More informationDesigning a Pick and Place Robotics Application Using MATLAB and Simulink
Designing a Pick and Place Robotics Application Using MATLAB and Simulink Carlos Santacruz-Rosero, PhD Sr Application Engineer Robotics Pulkit Kapur Sr Industry Marketing Manager Robotics 2017 The MathWorks,
More informationCOPYRIGHTED MATERIAL INTRODUCTION CHAPTER 1
CHAPTER 1 INTRODUCTION Modern mechanical and aerospace systems are often very complex and consist of many components interconnected by joints and force elements such as springs, dampers, and actuators.
More informationPPGEE Robot Dynamics I
PPGEE Electrical Engineering Graduate Program UFMG April 2014 1 Introduction to Robotics 2 3 4 5 What is a Robot? According to RIA Robot Institute of America A Robot is a reprogrammable multifunctional
More informationMobile Robots Locomotion
Mobile Robots Locomotion Institute for Software Technology 1 Course Outline 1. Introduction to Mobile Robots 2. Locomotion 3. Sensors 4. Localization 5. Environment Modelling 6. Reactive Navigation 2 Today
More informationKinematics - Introduction. Robotics. Kinematics - Introduction. Vladimír Smutný
Kinematics - Introduction Robotics Kinematics - Introduction Vladimír Smutný Center for Machine Perception Czech Institute for Informatics, Robotics, and Cybernetics (CIIRC) Czech Technical University
More informationINSTITUTE OF AERONAUTICAL ENGINEERING
Name Code Class Branch Page 1 INSTITUTE OF AERONAUTICAL ENGINEERING : ROBOTICS (Autonomous) Dundigal, Hyderabad - 500 0 MECHANICAL ENGINEERING TUTORIAL QUESTION BANK : A7055 : IV B. Tech I Semester : MECHANICAL
More informationSemantics and Ontologies for Geospatial Information. Dr Kristin Stock
Semantics and Ontologies for Geospatial Information Dr Kristin Stock Introduction The study of semantics addresses the issue of what data means, including: 1. The meaning and nature of basic geospatial
More informationIntroduction to Multi-body Dynamics
division Graduate Course ME 244) Tentative Draft Syllabus 1. Basic concepts in 3-D rigid-body mechanics 1. Rigid body vs flexible body 2. Spatial kinematics (3-D rotation transformations) and Euler theorem
More informationCS283: Robotics Fall 2016: Sensors
CS283: Robotics Fall 2016: Sensors Sören Schwertfeger / 师泽仁 ShanghaiTech University Robotics ShanghaiTech University - SIST - 23.09.2016 2 REVIEW TRANSFORMS Robotics ShanghaiTech University - SIST - 23.09.2016
More informationMETR 4202: Advanced Control & Robotics
Position & Orientation & State t home with Homogenous Transformations METR 4202: dvanced Control & Robotics Drs Surya Singh, Paul Pounds, and Hanna Kurniawati Lecture # 2 July 30, 2012 metr4202@itee.uq.edu.au
More informationKinematics. Kinematics analyzes the geometry of a manipulator, robot or machine motion. The essential concept is a position.
Kinematics Kinematics analyzes the geometry of a manipulator, robot or machine motion. The essential concept is a position. 1/31 Statics deals with the forces and moments which are aplied on the mechanism
More informationNeuro-adaptive Formation Maintenance and Control of Nonholonomic Mobile Robots
Proceedings of the International Conference of Control, Dynamic Systems, and Robotics Ottawa, Ontario, Canada, May 15-16 2014 Paper No. 50 Neuro-adaptive Formation Maintenance and Control of Nonholonomic
More informationINTRODUCTION CHAPTER 1
CHAPTER 1 INTRODUCTION Modern mechanical and aerospace systems are often very complex and consist of many components interconnected by joints and force elements such as springs, dampers, and actuators.
More informationLecture Telecooperation. D. Fensel Leopold-Franzens- Universität Innsbruck
Lecture Telecooperation D. Fensel Leopold-Franzens- Universität Innsbruck First Lecture: Introduction: Semantic Web & Ontology Introduction Semantic Web and Ontology Part I Introduction into the subject
More informationResearch Subject. Dynamics Computation and Behavior Capture of Human Figures (Nakamura Group)
Research Subject Dynamics Computation and Behavior Capture of Human Figures (Nakamura Group) (1) Goal and summary Introduction Humanoid has less actuators than its movable degrees of freedom (DOF) which
More informationObject-Oriented Design
Object-Oriented Design Lecture 14: Design Workflow Department of Computer Engineering Sharif University of Technology 1 UP iterations and workflow Workflows Requirements Analysis Phases Inception Elaboration
More informationUNIK Multiagent systems Lecture 3. Communication. Jonas Moen
UNIK4950 - Multiagent systems Lecture 3 Communication Jonas Moen Highlights lecture 3 Communication* Communication fundamentals Reproducing data vs. conveying meaning Ontology and knowledgebase Speech
More informationSVG GRAPHICS LANGUAGE AS A DESCRIPTION OF A 2D PATH IN ROBOT PROGRAMMING TASKS
S E L E C T E D E N G I N E E R I N G P R O B L E M S N U M B E R 5 I N S T I T U T E O F E N G I N E E R I N G P R O C E S S E S A U T O M A T I O N A N D I N T E G R A T E D M A N U F A C T U R I N G
More informationWHY WE NEED AN XML STANDARD FOR REPRESENTING BUSINESS RULES. Introduction. Production rules. Christian de Sainte Marie ILOG
WHY WE NEED AN XML STANDARD FOR REPRESENTING BUSINESS RULES Christian de Sainte Marie ILOG Introduction We are interested in the topic of communicating policy decisions to other parties, and, more generally,
More informationSemantic Web Programming
*) Semantic Web Programming John Hebeler Matthew Fisher Ryan Blace Andrew Perez-Lopez WILEY Wiley Publishing, Inc. Contents Foreword Introduction xxiii xxv Part One Introducing Semantic Web Programming
More informationSemantic Web. Ontology Engineering and Evaluation. Morteza Amini. Sharif University of Technology Fall 93-94
ه عا ی Semantic Web Ontology Engineering and Evaluation Morteza Amini Sharif University of Technology Fall 93-94 Outline Ontology Engineering Class and Class Hierarchy Ontology Evaluation 2 Outline Ontology
More informationParallel Robots. Mechanics and Control H AMID D. TAG HI RAD. CRC Press. Taylor & Francis Group. Taylor & Francis Croup, Boca Raton London NewYoric
Parallel Robots Mechanics and Control H AMID D TAG HI RAD CRC Press Taylor & Francis Group Boca Raton London NewYoric CRC Press Is an Imprint of the Taylor & Francis Croup, an informs business Contents
More informationMechanical structure of a robot=skeleton of human body Study of structure of a robot=physical structure of the manipulator structure
UNIT I FUNDAMENTALS OF ROBOT Part A 1. Define Robot. An industrial robot is a re-programmable, multifunctional manipulator designed to move materials, parts, tools, or specialized devices through variable
More informationEstablishing the overall structure of a software system
Architectural Design Establishing the overall structure of a software system Ian Sommerville 1995 Software Engineering, 5th edition. Chapter 13 Slide 1 Objectives To introduce architectural design and
More informationMetamodelling & Metaprogramming. Lena Buffoni
Metamodelling & Metaprogramming Lena Buffoni lena.buffoni@liu.se What is a model? A representation of a concept, phenomenon, relationship, structure, system from the real world Used to communicate, test
More informationRobotics Tasks. CS 188: Artificial Intelligence Spring Manipulator Robots. Mobile Robots. Degrees of Freedom. Sensors and Effectors
CS 188: Artificial Intelligence Spring 2006 Lecture 5: Robot Motion Planning 1/31/2006 Dan Klein UC Berkeley Many slides from either Stuart Russell or Andrew Moore Motion planning (today) How to move from
More informationArchGenTool: A System-Independent Collaborative Tool for Robotic Architecture Design
ArchGenTool: A System-Independent Collaborative Tool for Robotic Architecture Design Emanuele Ruffaldi (SSSA) I. Kostavelis, D. Giakoumis, D. Tzovaras (CERTH) Overview Problem Statement Existing Solutions
More informationSelf-Collision Detection and Prevention for Humanoid Robots. Talk Overview
Self-Collision Detection and Prevention for Humanoid Robots James Kuffner, Jr. Carnegie Mellon University Koichi Nishiwaki The University of Tokyo Satoshi Kagami Digital Human Lab (AIST) Masayuki Inaba
More informationKinematics and Orientations
Kinematics and Orientations Hierarchies Forward Kinematics Transformations (review) Euler angles Quaternions Yaw and evaluation function for assignment 2 Building a character Just translate, rotate, and
More informationCMPUT 412 Motion Control Wheeled robots. Csaba Szepesvári University of Alberta
CMPUT 412 Motion Control Wheeled robots Csaba Szepesvári University of Alberta 1 Motion Control (wheeled robots) Requirements Kinematic/dynamic model of the robot Model of the interaction between the wheel
More informationMCE/EEC 647/747: Robot Dynamics and Control. Lecture 3: Forward and Inverse Kinematics
MCE/EEC 647/747: Robot Dynamics and Control Lecture 3: Forward and Inverse Kinematics Denavit-Hartenberg Convention Reading: SHV Chapter 3 Mechanical Engineering Hanz Richter, PhD MCE503 p.1/12 Aims of
More informationProperties of Hyper-Redundant Manipulators
Properties of Hyper-Redundant Manipulators A hyper-redundant manipulator has unconventional features such as the ability to enter a narrow space while avoiding obstacles. Thus, it is suitable for applications:
More informationNeuro Fuzzy Controller for Position Control of Robot Arm
Neuro Fuzzy Controller for Position Control of Robot Arm Jafar Tavoosi, Majid Alaei, Behrouz Jahani Faculty of Electrical and Computer Engineering University of Tabriz Tabriz, Iran jtavoosii88@ms.tabrizu.ac.ir,
More informationManipulation: Mechanisms, Grasping and Inverse Kinematics
Manipulation: Mechanisms, Grasping and Inverse Kinematics RSS Lectures 14 & 15 Monday & Wednesday, 1 & 3 April 2013 Prof. Seth Teller Overview Mobility and Manipulation Manipulation Strategies Mechanism
More informationLecture «Robot Dynamics»: Kinematics 3
Lecture «Robot Dynamics»: Kinematics 3 151-0851-00 V lecture: CAB G11 Tuesday 10:15 12:00, every week exercise: HG E1.2 Wednesday 8:15 10:00, according to schedule (about every 2nd week) office hour: LEE
More informationWritten exams of Robotics 1
Written exams of Robotics 1 http://www.diag.uniroma1.it/~deluca/rob1_en.php All materials are in English, unless indicated (oldies are in Year Date (mm.dd) Number of exercises Topics 2018 06.11 2 Planar
More informationSerial Manipulator Statics. Robotics. Serial Manipulator Statics. Vladimír Smutný
Serial Manipulator Statics Robotics Serial Manipulator Statics Vladimír Smutný Center for Machine Perception Czech Institute for Informatics, Robotics, and Cybernetics (CIIRC) Czech Technical University
More informationCALCULATING TRANSFORMATIONS OF KINEMATIC CHAINS USING HOMOGENEOUS COORDINATES
CALCULATING TRANSFORMATIONS OF KINEMATIC CHAINS USING HOMOGENEOUS COORDINATES YINGYING REN Abstract. In this paper, the applications of homogeneous coordinates are discussed to obtain an efficient model
More informationLecture «Robot Dynamics»: Kinematics 3
Lecture «Robot Dynamics»: Kinematics 3 151-0851-00 V lecture: CAB G11 Tuesday 10:15 12:00, every week exercise: HG E1.2 Wednesday 8:15 10:00, according to schedule (about every 2nd week) Marco Hutter,
More informationSemantic Web. Ontology Pattern. Gerd Gröner, Matthias Thimm. Institute for Web Science and Technologies (WeST) University of Koblenz-Landau
Semantic Web Ontology Pattern Gerd Gröner, Matthias Thimm {groener,thimm}@uni-koblenz.de Institute for Web Science and Technologies (WeST) University of Koblenz-Landau July 18, 2013 Gerd Gröner, Matthias
More informationUsing Classical Mechanism Concepts to Motivate Modern Mechanism Analysis and Synthesis Methods
Using Classical Mechanism Concepts to Motivate Modern Mechanism Analysis and Synthesis Methods Robert LeMaster, Ph.D. 1 Abstract This paper describes a methodology by which fundamental concepts in the
More informationLecture «Robot Dynamics»: Multi-body Kinematics
Lecture «Robot Dynamics»: Multi-body Kinematics 151-0851-00 V lecture: CAB G11 Tuesday 10:15 12:00, every week exercise: HG E1.2 Wednesday 8:15 10:00, according to schedule (about every 2nd week) Marco
More informationMotor control learning and modular control architectures. Francesco Nori
Motor control learning and modular control architectures Francesco Nori Italian Institute of Technology, Genova, ITALY Robotics Brain and Cognitive Sciences Department, (former) member of LIRA-Lab Giorgio
More informationMobile Robots: An Introduction.
Mobile Robots: An Introduction Amirkabir University of Technology Computer Engineering & Information Technology Department http://ce.aut.ac.ir/~shiry/lecture/robotics-2004/robotics04.html Introduction
More informationROBOTICS 01PEEQW Laboratory Project #1. Basilio Bona DAUIN Politecnico di Torino
ROBOTICS 01PEEQW Laboratory Project #1 Basilio Bona DAUIN Politecnico di Torino The structure to be simulated 2 Lab Simulation Project #1: Pan-Tilt (PT) structure (2dof) This system is composed by two
More informationThe Conceptual Design of Robotic Architectures using Complexity Rules
The Conceptual Design of Robotic Architectures using Complexity Rules Waseem A. Khan and J. Angeles Centre for Intelligent Machines & Department of Mechanical Engineering McGill University Montreal, Quebec,
More informationCancer Biology 2017;7(3) A New Method for Position Control of a 2-DOF Robot Arm Using Neuro Fuzzy Controller
A New Method for Position Control of a 2-DOF Robot Arm Using Neuro Fuzzy Controller Jafar Tavoosi*, Majid Alaei*, Behrouz Jahani 1, Muhammad Amin Daneshwar 2 1 Faculty of Electrical and Computer Engineering,
More informationSimulation-Based Design of Robotic Systems
Simulation-Based Design of Robotic Systems Shadi Mohammad Munshi* & Erik Van Voorthuysen School of Mechanical and Manufacturing Engineering, The University of New South Wales, Sydney, NSW 2052 shadimunshi@hotmail.com,
More informationArchitectural Styles. Software Architecture Lecture 5. Copyright Richard N. Taylor, Nenad Medvidovic, and Eric M. Dashofy. All rights reserved.
Architectural Styles Software Architecture Lecture 5 Copyright Richard N. Taylor, Nenad Medvidovic, and Eric M. Dashofy. All rights reserved. Object-Oriented Style Components are objects Data and associated
More informationAnnouncements. CS 188: Artificial Intelligence Fall Robot motion planning! Today. Robotics Tasks. Mobile Robots
CS 188: Artificial Intelligence Fall 2007 Lecture 6: Robot Motion Planning 9/13/2007 Announcements Project 1 due (yesterday)! Project 2 (Pacman with ghosts) up in a few days Reminder: you are allowed to
More informationCS 188: Artificial Intelligence Fall Announcements
CS 188: Artificial Intelligence Fall 2007 Lecture 6: Robot Motion Planning 9/13/2007 Dan Klein UC Berkeley Many slides over the course adapted from either Stuart Russell or Andrew Moore Announcements Project
More information