Brief Introduction to HRI Batu Akan batu.akan@mdh.se Mälardalen Högskola September 29, 2008
Overview 1 Introduction What are robots What is HRI Application areas of HRI 2 3 Motivations Proposed Solution
What are robots What is HRI Application areas of HRI What Are Robots and a Short History Etimology The word robot originates from the Czechoslovakian word robota which means work Robot appears to have first been used in Karel Chapeks 1920s play Rossums Universal Robots, Historic appearances Ancient Egypt, Greece and China : Automata and mechanical creatures Iliad refers to golden maids that behave like real people. Golem, an artificial being of Hebrew folklore endowed with life. Chinese legends mention about robot-like creations, such as the story from the West Zhou Dynasty (1066BC-771BC) Leonardo da Vinci sketched a mechanical man around 1495.
What are robots What is HRI Application areas of HRI What Are Robots and a Short History Modern appearances 1926 Fritz Langs movie Metropolis, robot Maria 1936 Alan Turing, Turing Machine 1940 Isaac Asimov, Robbie 1961 Heinrich Ernst MH-1 robot arm 1962 GM Unimate, the first industrial robot 1996 Honda, P3 humonoid 1997 Sojourner, Mars robot 2000 Honda, Asimo
What are robots What is HRI Application areas of HRI Isaac Asimov Aisac Asimov Russian writer Science fiction Robbie written in 1940 I-Robot Robot Laws
What are robots What is HRI Application areas of HRI Robot Laws 1 A robot may not injure a human being or, through inaction, allow a human being to come to harm. 2 A robot must obey orders given to it by human beings, except where such orders would conflict with the First Law. 3 A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.
What are robots What is HRI Application areas of HRI What is HRI Ingredients One or more Humans One or more Robots Some sort of Interaction and Communication between Formal Definition of HRI Human-Robot interaction (HRI) is a field of study dedicated to understanding, designing, and evaluating robotic systems for use by or with humans.
What are robots What is HRI Application areas of HRI Application areas of HRI Application areas of HRI Search and rescue Assistive and educational robotics Entertainment Military and police Space exploration Unmanned Air Vehicles (UAV) reconnaisance and Unmanned Underwater Vehicles (UUV) applications Medical and health care Other Applications
What are robots What is HRI Application areas of HRI Types of Interaction Remote Interaction The human and the robot are not co-located and are separated spatially or even temporally (for example, the Mars Rovers are separated from earth both in space and time). Proximate interaction The humans and the robots are co-located (for example, service robots may be in the same room as humans).
Plan Introduction 1 Introduction What are robots What is HRI Application areas of HRI 2 3 Motivations Proposed Solution
The HRI problem is to understand and shape the interactions between one or more humans and one or more robots. Level of behavior of autonomy, Nature of information exchange, Structure of the team, Adaptation, learning, and training of people and the robot Shape of the task.
Introduction Autonomous robots are robots which can perform desired tasks in unstructured environments without continuous human guidance. Many kinds of robots have some degree of autonomy. Gain information about the environment. Work for an extended period without human intervention. Move either all or part of itself throughout its operating environment without human assistance. Avoid situations that are harmful to people, property, or itself unless those are part of its design specifications. Sense plan and Act paradigm Sense : gather all the information from the sensors Plan : Create the world model using all the information, and plan the next move Act : Set the plan on motion
(2) Introduction Behavior-based robotics Introduced by Brooks and Arkin in the mid 80 s Behavior is generated from a set of carefully designed autonomy modules that are then integrated to create an emergent system These modules generate reactive behaviors that map sensors directly to actions. Hybrid systems Bit of sense plan act and bit of behavior based architecture In these systems low-level reactivity is separated from higher level reasoning about plans and goals
Levels of autonomy Introduction Computer offers no assistance; human does it all. Computer offers a complete set of action alternatives. Computer narrows the selection down to a few choices. Computer suggests a single action. Computer executes that action if human approves. Computer allows the human limited time to veto before auto-matic execution. Computer executes automatically then necessarily informs the human. Computer informs human after automatic execution only if human asks.
Levels of autonomy (2) In order to achieve peer-to-peer collaboration Robot must flexibly exhibit full autonomy at appropriate times. It may need to support social interactions Peer-to-peer collaboration may be considered more difficult to achieve then full autonomy.
Communication Medium 1 Visual displays : typically presented as graphical user inter- faces or augmented reality interfaces. 2 Gestures, including hand and facial movements and by movement-based signaling of intent. 3 Speech and natural language, which include both audi- tory speech and text-based responses. 4 Non-speech audio, frequently used in alerting 5 Physical interaction and haptics, frequently used remotely in augmented reality or in teleoperation to invoke a sense of presence 6 Neuroscience and Brain Computer Interface (BCI)
Introduction HRI problems are not restricted to a single human and a single robot,though this is certainly one important type of interaction. How many robots required to operate a robot How many robots can be operated by a single human Organization of the team Who has the authority to make certain decisions? Robot? Interface Software? or Human? Who has the authority to issue instructions or commands to the robot? How conflicts are resolved, especially when robots are placed in peer-like relationships with multiple humans? How roles are defined and supported?
Minimizing operator training Service robots are typically designed to be manageable by a wide variety of humans ROOMBA (Automatic vacuum cleaner) Efforts to train humans Some application domains involving remote robots require careful training because operator workload or risk is so high Military and police Space applications Search and rescue operations
(2) Training Designers These robots are typically designed to be manageable by a wide variety of humans, Training Robots In HRI robots are also learning both offline and online Improve perceptual abilities Improve reasoning and planing capabilities Improve autonomous capabilities
(3) Approaches to robot learning Teaching by demostration Task learning Skill learning Social skills Cognitive skills Locomotion skills Biologicaly inspired learning models
Introduction Task-shaping is a term that emphasizes the importance of considering how the task should be done and will be done when new technology is introduced.
Roles of robots Introduction Roles of robots Supervisor Operator Mechanic Peer Bystander Mentor : the robot is in a teaching or leadership role for the human, and Information Consumer : the human does not control the robot, but the human uses information coming from the robot in, for example, a reconnaissance task.
Motivations Proposed Solution Plan 1 Introduction What are robots What is HRI Application areas of HRI 2 3 Motivations Proposed Solution
Motivations Proposed Solution Intelligent Human(e) Robot Interaction - Robotics for SME s Motivations Robot automation investments are considered to be technically challenging as well as costly by small and medium sized enterprises (SME). No matter how simple the production process might be, to integrate the robot, one has to rely on a robot programming expert. Software department?? or out source?? An optimal human-robot interaction solution is strongly demanded. Constraints No traditional programming Ease of operability and intuitiveness Precision
Motivations Proposed Solution Proposed Solution Proposed Solution A high level language for intelligent human robot interaction that relies on multi-sensor inputs providing an abstract instructional environment for the user
Motivations Proposed Solution Proposed Solution (2) Proposed Solution Interaction through vision and gesture The robot gives feedback through speech, pointing device Robot senses the environment through visual and audio Other sensory inputs maybe added
Motivations Proposed Solution Proposed Solution (3) Proposed Solution µ-language and µ-cognition µ-language will provide natural language (NLP) processing Has to be intuitive µ-cognition will provide the necessary cognitive abilities
Motivations Proposed Solution Thank you for listening Any questions?