Transcript Robotics
LEARNING OBJECTIVES 1. Explain what the word robot means and its origins 2. Discuss some of the current uses of robots in society 3. Explain some of the key problems involved in designing and building humanoid robots 4. Understand Asmov’s laws of robotics and discuss the issue they raise for the future development of intelligent robot agents Humans have long dreamed about creating mechanical slaves that effortlessly carry out our daily tasks. Imagine being able to tell a robot to mow the lawn, or paint the fence, or entertain you, or drive you somewhere, or even teach you about something. Will this be a reality? What is the definition of a 'robot'? "A reprogrammable, multifunctional manipulator designed to move material, parts, tools, or specialized devices through various programmed motions for the performance of a variety of tasks" Robot Institute of America, 1979 A dictionary definition: An automatic device that performs functions normally ascribed to humans or a machine in the form of a human The word 'robotics' refers to the study and use of robots. The term was used by the Russian-born American scientist and writer Isaac Asimov. According to Savage (1999, p. 127) a robot is a device that is re-programmable and multi-functional. To be a robot a device must also have some degree of autonomy (the ability to carry on tasks self-sufficiently). Therefore, a dishwasher which carries out a single task cannot be classified as a robot. Similarly, a remote controlled vehicle has no autonomy so it also cannot be classed as a robot. Could the following be classed as robots? TV remote control A security system Traffic lights Alarm clock NO: BECAUSE THEY ALL CARRY OUT A SINGLE FUNCTION HISTORY OF ROBOTICS The word ‘robot’ was created by Karel Capek, a Czech play writer. The word meant forced labour or serf. The use of the word Robot was introduced into Karel Capek’s play R.U.R. (Rossum's Universal Robots) which opened in Prague in January 1921. You may find it interesting to note that the robots Karel Capek wrote about were not mechanical in nature but were created through chemical means. In an essay written in 1935, Capek strongly argued that this idea was very possible. CURRENT ROBOTIC TECHNOLGIES Industrial robots (which can be re-programmed) are used extensively in factories to weld, paint, lift and transport goods in place of humans. The car manufacturing industry is a good example. Robots weld and fit car components to new vehicles. Large organisations and companies reap many benefits from robotic technologies because: Robots are less expensive than paying human workers over the long run and robots are not prone to injure themselves. However, we cannot yet state that industrial robots have any intelligence. They just carry out repetitive mechanical actions in place of humans CURRENT ROBOTIC TECHNOLGIES Robots are currently used for situations where human safety is an issue. Robots are used internationally by Police, Army, Navy and Air force organisations. Robotic technology is used to deal with hazardous situations such as dealing with suspicious packages, riots and for the collection of foreign intelligence. NASA scientists use robotic technologies (Mars Explorer) to explore other planets. EMULATING HUMAN ATTRIBUTES Scientists must overcome some persistent barriers if they are to create competent humanoid robots. Speech synthesis: the ability to get a robotic device to communicate using language. Voice recognition: the ability to get a robot to understand us. Two seconds of speech may contain as much as 100 000 bits of data so it is extremely challenging to create computers powerful enough to process this amount of data. Vision: the ability to get a robot to react as humans do to the physical environment using sophisticated vision systems. Movement: the ability to get a robot to move around in the physical environment as humans can. EMULATING HUMAN ATTRIBUTES: SPEECH SYNTHESIS Speech synthesis Speech synthesis is the artificial production of sounds resembling human speech. It will end our dependence on monitors and allow computers to speak to us. At present speech synthesis is being used to assist people who are speech-impaired. Words can be typed into a computer system and then the computer can be instructed to say these words. Blind people can use a special computer that can recognise letters in a book, then read the book aloud. However, more research and development is required to construct pleasant, human-sounding voices. EMULATING HUMAN ATTRIBUTES: VOICE RECOGNITION Computers are able to listen, as demonstrated by Isolated Word Recognition (IWR). With IWR each word is surrounded by a silence gap so that word boundaries can be understood. Speakers train the system by recording words and sentences. IWR with a 1000 word vocabulary and 95 to 100% accuracy, running on personal computers is not uncommon. Interpreting continuous speech is considerably more difficult because continuous speech is not the same as a string of isolated words. Boundaries between words are not easily defined. Each person’s voice is different. Background noise causes great difficulties. Humans, when interpreting speech, are able to fill in the blanks, read body language, eliminate background noise and appreciate the context. Interpretation of continuous speech requires the use of an immense knowledge base and immense comparison operations. Alternatives to von Neumann architecture are needed to provide the required computer processing power. EMULATING HUMAN ATTRIBUTES: HUMAN VISION POSITIVES: Humans can distinguish and identify different objects around us in the physical world in just a fraction of a second. NEGATIVES: Humans cannot see outside the visible spectrum below infra red or beyond ultra violet. We cannot see forms of radiation, X-rays or microwaves. We need microscopes and telescopes to increase our visual ability. Humans need sunglasses to protect our vision during the bright daylight and artificial light to see in the dark. EMULATING HUMAN ATTRIBUTES: VISION SYSTEMS Scientific research into vision systems has focused on three main areas: Image input: Television based sensors which can distinguish between visible or non-visible light break an image into rows and columns using numbers. Each pixel element can be described. Numbers are used to define an image’s brightness, contrast, colour, texture etc. Digital cameras are one example of an input technology. Computers are able to read, as demonstrated by the use of scanners with optical character recognition. Image manipulations: Correcting brightness, contrast, gamma levels, noise reduction, colour, zooming, enhancing, rotating, etc. This area is progressing very rapidly. Image recognition: Converting an image’s content into knowledge about the world. A computer is able to store an image of a scene but has difficulty interpreting the image. This is an extremely challenging area for artificial intelligence researchers. Understanding the meaning of the letters and words is a natural language processing problem. EMULATING HUMAN ATTRIBUTES: VISION SYSTEMS The major problems which exist for vision systems and image recognition are: Interpreting what an image means using pattern recognition technologies. The vision system must recognise what the pattern formed by the image is. Determining the distance of an object (its proximity) in the environment. Cameras fitted with stereo technology have been used successfully to work out distance and depth. EMULATING HUMAN ATTRIBUTES: MOVEMENT The major difficulty creating robots which can walk has been making them stable and able to move in a variety of directions (motion planning). Various terrains require different types of mobility. Humans have many degrees of freedom with movement. To understand ‘degrees of freedom’ place your arm straight up in the air and point your index finger at the roof. DO NOT BEND YOUR ELBOW. In how many directions can you move your arm? 1. You can move up and down – this is known as ‘pitch’. 2. You can move right to left – this is known as ‘yaw’. 3. You can roll your arm in a circular motion – this is known as ‘roll’. This gives you ‘3 degrees of freedom’ – pitch, yaw and roll. Degrees of freedom define the number of independent motions a robot can make In your opinion will our society need to create special laws governing robotic technologies? Asimov's Laws of Robotics Laws 1-3 were published in I, Robot, 1950 Law 0 was added by Asimov later. 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 the 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 Laws. 0. A robot may not injure humanity or, through inaction, allow humanity to come to harm. The following sections of this presentation involve watching several small movie clips and visiting web sites so the use of headphones is advised. EMULATING HUMAN ATTRIBUTES: MOVEMENT FUJITSU recently unveiled HOAP-2, a new humanoid robot with movement abilities similar to humans. Review HOAP-2 movies. HOAP-2 navigating stairs HOAP-2 navigating a curve HOAP-2 navigating a slope ASIMO is another humanoid robot created by HONDA Click here to review a brochure about ASIMO. Click here to go to the ASIMO educational web site ROBOTICS Robotics in the home Hardware Movie Take a look at Robosapien Review media coverage. Emotions Affective Intent Expression Examples What makes Robosapien special? Is Robosapien actually useful? Is Robosapien as intelligent as they claim? Kismet is a socially intelligent robot created by MIT’s Humanoid Robotics Group. Their aim is to create humanoid robots that rely on humans for knowledge, functioning and social interaction. Why is this important? Go to the kismet site to read about Kismet’s speech & vision systems. HISTORY OF ROBOTICS If you have time - go to the following site and find out more about the history of robots. http://www.thetech.org/exhibits/onlin e/robotics/universal/ Links Artificial Intelligence - MIT KISMET http://www.ai.mit.edu/projects/humanoid-robotics-group/kismet/ Kismet movies – downloaded from http://www.ai.mit.edu/projects/sociable/videos.html More about kismet http://www.inel.gov/adaptiverobotics/humanoidrobotics/anthropopathic.shtml HOAP-2 http://www.automation.fujitsu.com/en/products/products09.html ASIMO http://asimo.honda.com/inside_asimo.asp Speech recognition http://www.dalmed.u-net.com/home7.html Robotics & AI http://library.thinkquest.org/18242/robotics.shtml THE END