The Robot's Knowledge Lecture 1

Logic, Ontology and Planning: the Robot’s Knowledge Lecture 1

Stefano Borgo

Laboratory for Applied Ontology (LOA), ISTC-CNR, Trento (IT)

ESSLLI course 2018 Soﬁa, Bulgaria Scope of the course

Robotics: traditional, yet rapidly expanding, research area. It design and develops intelligent autonomous agents like self-driving cars and drones, industrial robots for production, and humanoids for the elderly.

This course focuses on the knowledge a robot needs to act in the environment and to understand what it can possibly do. It introduces and discusses the notions and relationships that are needed to understand a generic scenario and shows how to structure an ontology to organize such knowledge. In particular, it focuses on how to understand and model capacities, actions, contexts and environments. The ﬂow of information between the knowledge module and the planning module in a generic artiﬁcial agent is presented.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 2 / 55 Organization of the lectures (roughly)

Lecture 1: Introduction to robotics – what is robotics about? what is an agent? what are the robot’s components?

Lecture 2: Introduction to ontology – what is an ontology? what is the purpose of ontology? how is an ontology structured?

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 3 / 55 Organization of the lectures (roughly)

Lecture 3: Basic cognition, image schemas and affordance – what is concept creation? what is concept blending? what are image schemas? why do we need them?

Lecture 4: Scenario interpretation, context and knowledge integration – how should one interpret a scenario? how should one distinguish ontological and contextual information? how is heterogeneous information integrated?

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 4 / 55 Organization of the lectures (roughly)

Lecture 5: From knowledge to plans – how to use ontology and knowledge to plan? how to distinguish behavior and function? how to extract new functional information?

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 5 / 55 Course Overview

1 An introduction to Robotics

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 6 / 55 Today’s Lecture

1 An introduction to Robotics Robotics: a bit of history Typical scenarios Deﬁning agents and robots Classifying robots Important topics and trends in robotics

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 7 / 55 First steps – 1

Leonardo Da Vinci (1452-1519) sketched many designs. One of them, drawn around 1495, was about a robot in the form of a medieval knight that could move its arms, head and open its jaws.

With the improvement of mechanics in 1700, a number of automatons ad automatic mechanisms started to appear. These automatons could draw, move, play music and even ﬂy.

The term automaton was the standard one until the publication of “Rossum’s Universal Robots” by Karel Capek (an inﬂuent book about replicants, not mechanical devices as we understand robots today) introduced the term robot. Robot comes from the Czech word “robota” which roughly means slave, forced labour.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 8 / 55 First steps – 2

In 1956 business investor Joseph Engelberger and inventor George Devol started working together leading to the construciton of the Unimate, the very ﬁrst industrial robot (a robotic arm).

Devol’s patent says: The present invention relates to the automatic operation of machinery, particularly the handling apparatus, and to automatic control apparatus suited for such machinery. [wikipedia]

General Motors used Unimate in a die-casting plant. Unimate undertook the job of transporting die castings from an assembly line and welding these parts on auto bodies, a dangerous task for workers, who might be poisoned by toxic fumes or injuried.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 9 / 55 First steps – 3

In those years, William Grey Walter constructed some of the ﬁrst electronic autonomous robots. He wanted to prove that rich connections between a small number of brain cells could give rise to very complex behaviors.

A significant moment in robotics is when robots moved from the factory area to our everyday spaces. Between 1966 and 1972 in Stanford a general-purpose mobile robot, called Shakey, was developed. Shakey is the first robot able to reason about its own actions. It was the first project that integrated logical reasoning and physical action.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 10 / 55 Today’s Lecture

1 An introduction to Robotics Robotics: a bit of history Typical scenarios Deﬁning agents and robots Classifying robots Important topics and trends in robotics

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 11 / 55 Scenario: Robot + Worker

http://www.all-electronics.de

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 12 / 55 Scenario: Robot + Human

http://www.riken.jp

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 13 / 55 Scenario: Robot + Environment

https://i.ytimg.com/vi/jC-AmPfInwU/maxresdefault.jpg

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 14 / 55 Scenario: Robot + Controlled environment

M5 M7 M6 M1

M4 M5 S1

M4 M2 S2 M3 M2

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 15 / 55 Scenario: Robot + Controlled environment /2 RC1 RC1 RC1

F RC1 B B F RC1 B F B CONFIGURATION CONFIGURATION 1 F LC1 B CONFIGURATION CONFIGURATION 1 CONFIGURATION CONFIGURATION 1 LC1 LC1 CONFIGURATION CONFIGURATION 1 LC1 RC2 RC1 CONFIGURATION CONFIGURATION 1 LC1 RC2 RC1 RC2 RC1

RC2

F RC1 B RC2 ! F RC1 B CONFIGURATION CONFIGURATION 2 LC1 LC2 F B LC2 LC1

CONFIGURATION CONFIGURATION 2 F B ! B F LC2 LC1 LC2 CONFIGURATION CONFIGURATION 2 LC1 CONFIGURATION CONFIGURATION 2 ! LC2 LC1 CONFIGURATION CONFIGURATION 2 RC1 RC2 ! LC2 LC1 CONFIGURATION CONFIGURATION 2 !

LC1 CONFIGURATION CONFIGURATION 1

F B RC1 S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 16 / 55 Today’s Lecture

1 An introduction to Robotics Robotics: a bit of history Typical scenarios Deﬁning agents and robots Classifying robots Important topics and trends in robotics

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 17 / 55 Agents

There are three prototypical types of (embodied) agents: human animal artiﬁcial

and then there are the mix-up, e.g., cyborg

centaur

and weaker candidates (e.g. lower biological systems).

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 18 / 55 What is an agent?

For human and animal agents (strong biological systems), the answer is simple: An agent is the offspring of an agent.

This is like to say: A Bulgarian is the offspring of a Bulgarian.

Nothing wrong with this, only that it is not telling us much and, even worse, it is not general: it does not apply to artiﬁcial agents in general.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 19 / 55 What is an agent?

We need to separate three problems:

How can one identify agents?

Dennett’s stances (physical, design, intentional)

What can an agent do?

It discriminates, has preferences, decides, makes changes.

What is an agent?

A perspectival physical entity that persists in time, discriminates, has preferences, decides and acts accordingly in the environment.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 20 / 55 Deﬁnitions of agent /1

1 anything that is seen as “perceiving its environment through sensors and acting upon that environment through effectors.” (Russell and Norvig, 2010, p. 33)

2 “a system that tries to fulﬁll a set of goals in a complex, dynamic environment” (Maes, 1994, p. 136)

3 “any embodied system [that pursues] internal or external goals by its own actions while in continuous long-term interaction with the environment in which it is situated” (Beer, 1995, p. 173)

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 21 / 55 Deﬁnitions of agent /2

Some deﬁnitions of embodied agent from the literature.

(4) “entities which engage in normatively constrained, goal-directed, interaction with their environment” (Christensen and Hooker, 2000, p. 133) (5) (autonomous agent) “a system situated within and apart of an environment that senses that environment and acts on it, over time, in pursuit of its own agenda and so as to effect what it senses in the future.” (Franklin and Graesser, 1996, p. 25).

Commonalities: there is a system, distinguishable from the environment, able to sense and/or perceive that environment, able to act in pursuit of a goal. Note: the deﬁnitions do not refer to intentionality. Why?

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 22 / 55 A more interesting deﬁnition of agent

Recall that our interest is on the notion of embodied agent.

an agent is “a system doing something by itself according to certain goals or norms within a speciﬁc environment.”

Conditions: 1 the system is an individual; 2 the system is the active source of interaction; and 3 the interaction norm is generated by the system (Barandiaran, Di Paolo and Rohde, 2009, p. 374)

Basics: system, distinguishable (the rest is environment), interactive, regulating. (Again, intentionality is not an issue.)

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 23 / 55 Discussion

Is the distinction agent/environment really acceptable? Is it important?

We can identify the typical agents and we know precisely what they do or could do, but isn’t this a limitation of the types of agent we traditionally consider, say in biology and in robotics?

Think in terms of cyborgs or agents connected to the cloud...

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 24 / 55 Desired properties?

Which properties are characterizing agents?

reactivity (maintain an ongoing relationship with the environment and respond to changes),

proactiveness (take the initiative and recognize opportunities),

(social) ability (interact and cooperate with other agents),

rationality,

adaptability.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 25 / 55 Desired properties?

Rationality = For each possible percept sequence, a rational agent should select an action that is expected to maximize its performance measure, given the evidence provided by the percept sequence and whatever built-in knowledge the agent has.

Autonomy = An autonomous agent has the ability to generate novel behavior, i.e. it can non-trivially and purposively change its behavior (interaction with the environment). An autonomous agent learns from experience and uses this new knowledge to make decisions. Autonomous agents operate without the direct intervention of humans or others, and have some kind of control over their actions and internal state.

Proactivity = A proactive agent has the capacity to take the initiative. Proactive agents are not driven solely by events, they are capable of generating new goals and of acting to achieve them.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 26 / 55 Problem: How to deﬁne robotic agent?

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 27 / 55 What is a robot?

Robots can have different forms and functions but the scientiﬁc and engineering principles and algorithms that control them remain the same.

Although the term is used commonly and we have clear intuitions about it, it is hard to give a precise deﬁnition of what a robot is. Generally people start from two core ideas:

Carrying out actions automatically (washing machine? airplane autopilot?) Being programmable (by a computer) (heating system? teller machine?)

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 28 / 55 Deﬁning robots

There is no accepted deﬁnition of robot even though several proposals have been made.

“A robot is a machine –especially one programmable by a computer– capable of carrying out a complex series of actions automatically.” [Wikipedia] “A machine capable of carrying out a complex series of actions automatically, especially one programmable by a computer.” [Oxford English Dict]

A crucial element, already seen for agents but not explicitly stated here, is adaptability which requires the use of sensors. Most automata do not have sensors and cannot adapt their actions to their environment. Sensors enable a robot to verify the ongoing execution of complex tasks in a changing environment.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 29 / 55 Deﬁning robots

another attempt...

Robotics Institute of America (RIA):

A robot is a reprogrammable, multifunctional, manipulator designed to move material, parts, tools or specialised devices through variable programmed motions for the performance of a variety of tasks. The robot is automatically operating equipment, adaptable to complex conditions of the environment in which it operates, by means of reprogramming managing to prolong, amplify and replace one or more human functions in its interactions with the environment.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 30 / 55 Deﬁning robots

And another...

IEEE Standard for Ontologies for Robotics and Automation

An agentive device [...] in a broad sense, purposed to act in the physical world in order to accomplish one or more tasks. In some cases, the actions of a robot might be subordinated to actions of other agents [...], such as software agents (bots) or humans. A robot is composed of suitable mechanical and electronic parts. Robots might form social groups, where they interact to achieve a common goal. A robot (or a group of robots) can form robotic systems together with special environments geared to facilitate their work.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 31 / 55 Today’s Lecture

1 An introduction to Robotics Robotics: a bit of history Typical scenarios Deﬁning agents and robots Classifying robots Important topics and trends in robotics

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 32 / 55 Classifying robots – 1

Classiﬁcation of robots by environment and mechanism of interaction

Fixed robots are mostly industrial robotic manipulators. They are attached to a stable mount on the ground, so they can compute their position based on their internal state. Mobile robots need to rely on their perception of the environment. Mobile robots need to deal with situations that are not precisely known in advance and that change over time (robotic vacuum cleaner, self-driving cars). Environments require signiﬁcantly different design principles. [From “Elements of Robotics” 2018, pg.2]

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 33 / 55 Classifying robots – 2

Classiﬁcation of robots by intended application ﬁeld and the tasks they perform.

Industrial robots work in well-deﬁned environments. Additional ﬂexibility is required when industrial robots interact with humans and this introduces strong safety requirements, both for robotic arms and for mobile robots. The advantage of humans working with robots is that each can perform what they do best. [[From “Elements of Robotics” 2018, pg.3]

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 34 / 55 Classifying robots – 3.1 [The following is from “Robotics: History, Trends and Future Directions”, 2018]

The Japanese Industrial Robot Association (JIRA) divides robots in six categories which we will see in order.

1 Manipulators – A manipulator is physically anchored to its workplace. Manipulators are subdivided in: manual – machines slaved to a human operator; sequential – device that performs a series of tasks in the same sequence every time they are activated; and programmable – deﬁne operation through computer commands based on tasks or objectives.

Of the above, only a programmable manipulator would qualify as robot outside of Japan.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 35 / 55 Classifying robots – 3.2

Japanese Industrial Robot Association (JIRA):

2 Numerical control (NC) machines: these robots are programmable automata instructed to perform tasks through information on sequences and positions (using alphanumeric data). The data represent relative positions between a tool and other processing element often referred to as a work-head and the work-part, i.e., the object being processed. Three important components merge to create a numerical control system: (a) part program, (b) machine control unit, and (c) processing equipment. Part program refers to the detailed set of commands to be followed by the processing equipment. The machine control unit is usually a microcomputer that stores and executes the program. An operation is sequential with one command being processed at a time.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 36 / 55 Classifying robots – 3.3

Japanese Industrial Robot Association (JIRA):

3 Sensate – by “sensate robots” one usually means embodied machines with the unique capability to sense human body language, thus enabling these machines to better comprehend and respond to their human companions in a natural way. The family of robots that incorporate touch sensors, proximity sensors, vision systems, and so forth predominantly for human-machine societal interaction is referred to as sensate robots.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 37 / 55 Classifying robots – 3.4

Japanese Industrial Robot Association (JIRA):

4 Adaptive – Advances in sensor technology coupled with artiﬁcial intelligence have infused new directions to robotics leading to multi-purpose, adaptive workers. Robots that can change the way they function in response to their environment are termed as adaptive robots.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 38 / 55 Classifying robots – 3.5

Japanese Industrial Robot Association (JIRA):

5 Smart – Robots that are considered to possess artiﬁcial intelligence leading to cognitive capabilities are smart.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 39 / 55 Classifying robots – 3.6

Japanese Industrial Robot Association (JIRA):

6 Intelligent Mechatronic System – Tetsuro Mori from the Yaskawa Electric Cooperation coined the term “Mechatronics” to mean the intersection and synergy of mechanical/electrical and computer control systems. Mechatronics refers to embedment of smart devices into systems already in place leading to Intelligent Mechatronic System.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 40 / 55 Today’s Lecture

1 An introduction to Robotics Robotics: a bit of history Typical scenarios Deﬁning agents and robots Classifying robots Important topics and trends in robotics

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 41 / 55 Important topics

The ﬁeld of robotics has many topics and four of these are particularly important today:

mechanical manipulation (functionality) locomotion (functionality) computer vision (sensor) artiﬁcial intelligence (information management)

The following discussion is broadly set along these lines.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 42 / 55 Important topics: Joints and Links

Robotic manipulators are composed of (rigid) links connected by joints. Joints allow relative motion of neighboring links. A serial manipulator is a set of bodies connected in a chain by joints. The joints in a robotic manipulator are restricted to one degree of freedom. Two types of joints are common: (a) revolute joints and (b) prismatic joints. Convention: number the links from the immobile base (link 1) till the free end of the arm (link n). Degrees of freedom (DoF): the number of independent movements an object can have in 3-D space. A rigid body free in space can have six independent movements, three translations and three rotations, leading to six DoFs. The end-effector is at the free end, farthest away from the base (the distal end).

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 43 / 55 Serial manipulator and (revolute, prismatic) joints

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 44 / 55 Important topics: Actuators

Actuators are like the muscles of the robot. Actuators convert energy to mechanical form determining force, torque, speed of operation, accuracy, precision, and power consumption; any device that accomplishes this conversion is an actuator. Types of actuators: electrical (electrical motor; solenoid), pneumatic ﬂuid power (using pressurized air), and hydraulic ﬂuid power (hydraulic actuators use oil instead of air). Sensors measure the stimuli from the environment and the robot’s parts. Actuators and sensors together with a feedback control system are the most basic requirements for a robot to interact with the environment. Motion Convertors: mechanical power transmission systems required to convert actuator outputs to type of motions required by the system. For example, convertors are required for speed reduction or conversion from rotary to linear motion.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 45 / 55 An actuator

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 46 / 55 Important topics: Sensors

Sensors convert physical stimuli into a form suitable to measurement. Examples: active and passive IR sensors; sound and voice sensors; ultrasonic range sensors, positional encoders on arm joints, head and wheels; compasses, navigational and GPS sensors; active and passive light and laser sensors; a number of bumper switches; and sensors to detect acceleration, turning, tilt, odor detection, magnetic ﬁelds, ionizing radiation, temperature, tactile, force, torque, visual sensors (CCD cameras). Any robotic system has two distinct categories of sensors: Proprioceptors: they measure the kinematic and dynamic parameters of the robot. Proprioceptive sensors are responsible for controlling internal status and monitoring self-maintenance. Exteroceptors: they sense the environment to estimate the location/position and force interaction with the environment. Exteroceptors are broadly categorized into: (a) contact sensors [mechanical switches; tactile sensors], (b) range sensors [laser range ﬁnders and sonar], and (c) vision sensors [cameras].

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 47 / 55 Sensors

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 48 / 55 Important topics: Kinematics

Kinematics is the study of position, velocity, acceleration, and other higher order derivatives of the position variables without considering forces causing these effects. It includes the study of the geometrical and time-based properties of motion of the manipulator. It is fundamental to describing an end-effector’s position, orientation as well as motion of all the joints. Denavit-Hartenberg Notation: used for the kinematic description of a robot. Forward Kinematics: the problem of computing the position and orientation of the end-effector given the set of joint angles. Inverse Kinematics: the problem of computing all possible sets of joint angles to attain the given position and orientation. For any practical use of the manipulator such as a pick-and-place operation or line-following operation, inverse kinematics is the fundamental problem to be solved. Velocities and Singularities: kinematic analysis may involve manipulators in motion. A matrix called the Jacobian of the manipulator is deﬁned to undertake velocity analysis.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 49 / 55 Important topics: Dynamics

Motion is caused by forces acting on a body. Dynamics is the study of the forces required at the joints to cause motion of the end-effector. It includes kinematics and kinetics. A manipulator at rest is accelerated and made to move at a constant end-effector velocity; later, it needs to decelerate and stop. The joint actuators accomplish this through a complex set of joint torques. The actuator torque not only depends on path through which the end-effector moves but also on the mass properties of the links and payload. Forward Dynamics: finding end-effector motion for known joint torques/forces (important in simulation). Inverse Dynamics: finding joint torques/forces for given joint motions and end-effector moment/force. For a desired path of the end-effector, using the dynamic equations of motion of a manipulator, actuator torque can be estimated. This in turn can be used to control a manipulator. Trajectory Generation: the locus of points which the manipulator has to follow is the path. A path further qualified with specification of a timing law is referred to as trajectory.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 50 / 55 Important topics: Planning and Control

Planning and control are fundamental components of robot systems. Motion planning is particularly important for autonomous robots. Forces or torques are usually supplied to actuators to drive the manipulators. Inverse dynamics computes the required torques that will cause the desired motion. Even though the problem of dynamics forms a basis of a framework for control of a manipulator, in itself it does not sufﬁce. Position Control Force Control Hybrid Control

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 51 / 55 Artiﬁcial Intelligence

To perform at par with a human, the robot needs to have the capability of “rational” decision making. Intelligent robots are equipped with a myriad of sensors, particularly for knowledge of the external world. In line with the use of visual and qualitative information for everyday commonsense reasoning, a robot in an unstructured environment (i.e. not known a priori) makes use of “qualitative spatial reasoning” and “robotic vision.” Interpretation of a scene and learning from vision are difﬁcult phases in the whole pipeline of visual image processing. This requires intelligence that in turn demands huge volume of knowledge. Learning techniques, through evolving paradigms such as deep learning, are essential.

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 52 / 55 Applications

The predominant use still remains in the ﬁeld of automation in manufacturing. Automation replaces the worker with intelligent control systems, thereby contributing to increase in productivity, speed, and repeatability. Automation using robotic technologies exploiting advances in computing, particularly machine learning and artiﬁcial intelligence, has been the trend. Manufacturing robots Space robots Service robots Medical Robots Rehabilitation and assistive robots Entertainment Robotics

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 53 / 55 Trends

Social robot: “a physically embodied, autonomous agent that communicates and interacts with humans on an emotional level” Biomimetic robot: a robot built based on principles extracted from biological systems. Cloud robotics: robotics based on ubiquitous, convenient, on-demand network access to a shared pool of conﬁgurable resources that can be rapidly provisioned and released with minimal management effort or service provider interaction. Embodied cognition: most of AI within robotics takes the symbolic approach where Sense-Plan-Act cycles are clearly separated. In another view intelligence, including cognitive functions such as decision making, perception, and language, is grounded in our physical presence rather than on abstract symbolic models. (Grasping and walking have been explored as embodied, non-symbolic intelligence). robotics and IOT robotics through synthetic biology (self-replicating machines, machines capable of producing a detached, functional copy of themselves).

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 54 / 55 End of Lecture 1

Pls, download Protégé from: https://protege.stanford.edu/

S. Borgo (LOA ISTC-CNR Trento) The Robot’s Knowledge - Lecture 1 ESSLLI – Soﬁa, 2018 55 / 55