Robotics - Origin, Myths, Current Trends, and Opportunities

By Prof. Clarence W. de Silva

Clarence W. de Silva, Professor of Mechanical Engineering at the University of British Columbia (UBC), Vancouver, Canada, entered the then University of Ceylon (now University of Peradeniya) from Ananda College, after winning the Dr. Erwin de Silva Gold Medal. He graduated from the University, obtaining First Class Honors and the Dr. C. H. Hewavitarana Prize in Engineering. After working several years as an Assistant Works Engineer, he went overseas. He obtained an MASc degree from University of Toronto, PhD degrees from Massachusetts Institute of Technology (MIT) and University of Cambridge, and the ScD degree, the so-called “Higher Doctorate,” from University of Cambridge. He has attempted to pay back to his motherland through such activities as: providing scholarships to two dozen Sri Lankan students for post-graduate studies in Canada; developing curricula and course material in Mechatronics and conducting courses for educational institutions in Sri Lanka; endowing an award for the top student in Mechatronics; and developing computer facilities, roads, mentoring network, health clinics, and hospital cafeteria in a rural area. In this interview, we have picked his brain to explore the subject of Robotics.

Q: Professor, first let us know how you embarked upon on Robotics.

After completing my PhD at MIT, I was appointed as an Assistant Professor of Mechanical Engineering, at Carnegie Mellon University (CMU) in Pittsburgh, USA, in September 1978. My PhD research has been in the dynamics and control of automated guideway transit (AGT) systems. These vehicles are completely automated, and hence driverless. They run on elevated guideways and don’t interfere with other traffic. So, it had been an attractive area of research at the time.

Robotics was emerging at the same time, yet not properly recognized. I wanted to enter that field as well, but it was clear to me that such research has to be a collaboration of mechanical and electrical engineers and computer scientists. So, I was somewhat hesitant. Fortunately, Raj Reddy, a professor of Computer Science at CMU recognized the importance of Robotics and also collaboration, and contacted some of us (who had appropriate research background) in the departments of mechanical and electrical engineering and computer science, and we were quite excited. To initiate research, we needed funds (for graduate students and equipment in particular). I suggested approaching Westinghouse because it was a leading and very rich company focusing on domestic and heavy equipment and I had done some work with a branch of Westinghouse in Pittsburgh on nuclear power plant equipment. Raj Reddy thought we should approach the Westinghouse office in Winston Salem, North Carolina, who controlled finances and were very powerful. We agreed, and decided to visit Winston Salem and make a presentation with a comprehensive proposal to establish a Robotics Institute at CMU.

Westinghouse gave us two small commuter planes (single-engine and twin-engine Cessna aircraft) for the trip. Raj asked three of us to take the small plane and leave first, and the remaining five including Raj would follow in the bigger plane. We land ed in Winston Salem and waited for the other plane, but it didn’t arrive. There were no cellphones those days. So, we had to find a land phone somewhere and make a call to CMU. That plane had lost an engine and had to return! So, the other group was waiting for a replacement from Westinghouse.

At the end everyone arrived, made an effective presentation to the Westinghouse executives, and the company committed to fund the Robotics Institute. This was the first such institute anywhere, and we grew steadfastly, became world-renowned, and even started granting CMU PhDs in Robotics. The rest is history!

Q: What is a robot?

Commonly, a robot is considered a machine that can perform work or actions normally performed by humans, automatically or by remote control—Teleoperation. The key feature of this definition is the presence of, 1. Mechanical Structure (Machine), 2. Sensors, 3. Actuators (or Effectors), and 4. Controller (or Computer), which is the brain or the decision maker of the robot. In this manner, a robot is able to facilitate “flexible automation,” which is “programmable” automation. Essentially, a digital computer serves as the “brain” of the robot, and it has to be programmed to carry out its actions. As well, there have to be sensors to monitor the operation, and the sensory data are processed by the computer to determine the suitable control actions.

Flexible automation should be distinguished from “hard automation” or “fixed automation.” In fixed the fixed automation, what is fixed is the control hardware, which is not programmable. It can carry out a specific repetitive task very accurately and at high speed. But since it is not programmable, changing the operation to a different task is not easy, and can be very costly, with significant down time to change the hardware. However, fixed automation, typically, does not require sensors, and the controller can be very simple and straightforward.

A good example of fixed automation is a bottling operation. See: https://youtu.be/HIOINPLdWjk

Note that, we cannot change the type of bottle easily in this system.

Alternative, consider the example of welding robots in an automotive plant: https://youtu.be/0L7Xk5_s3QQ

Here, the vehicle model can be changed very easily and quickly, simply by changing the program. However, the operation itself is not fast albeit quite complex.

A robot that has a human-like body structure is called a “humanoid.” An example is the Honda Asimo: https://asimo.honda.com/

However, a robot need not look like a human. An Unmanned Naval Vehicle (UNV) that we developed (see the picture) is indeed a robot. It is a programmable propelling platform with multiple sensors (to measure the pH value, dissolved oxygen, electrical conductivity, temperature, and the oxidation-reduction potential of water). It is able to autonomously navigate a water body and map out the quality of the water in a particular region, which can be used to provide warnings to the users, determine the source of pollution or contamination, and also take corrective actions.

Q: Who initiated Robotics?

The term “Robot” was introduced in the popular media, well before a physical robot became a reality. In 1920, Czech writer Karel Capek first introduced the term in his play “R.U.R.” or “Rossum’s Universal Robots.” There, it was just a figment of his imagination. Again, in 1942, the Russian-born American science-fiction writer and Boston University Professor Isaac Asimov introduced the term in his fictions. Notably, Asimov was one of “Big Three” in science fiction. The other two were our own Arthur C. Clarke and Robert A. Heinlein. We know that many predictions of Clarke and Asimov have come true today. A device resembling a humanoid robot was designed and built by the ingenious Leonardo Da Vinci, in 1945. It could mechanically move arms, head and jaws, but was not a true robot, in today’s definition. The first true robot arm, the Unimate, was designed by the American inventor George Devol in collaboration with Joseph Engelberger who is often called the “Father of Robotics.” This robot was used in a General Motors (automotive) plant for their manufacturing operations in 1960. It had a primitive digital computer as its brain, and used motion sensors and also dc motors as the actuators. See: https://youtu.be/hxsWeVtb-JQ?t=22. Many different types of robots have been developed and put to operation since.

Q: I am sure, there were many misunderstandings in the general interpretation. Do we have to fear robots?

Indeed, there have been many myths, misnomers, and misunderstandings concerning robots. Some are: 

1. Robots have capabilities that equate or exceed those of humans. This is not true. The intelligence of today’s robots does not exceed even that of a dog!
2. Robots will steal our spouses, and fight wars and defeat us. This is very unrealistic, and will never happen!
3. Robots will create mass unemployment: People said this concerning the first Industrial Revolution as well. But at the end, the industrial revolution (and industrial automation) gave the workers more free time (including the five-day work week), moved them away from hazardous and difficult work, improved the general quality of life, and created higher-paying and more challenging employment (for our friends and relative, if not for us). Many more positive things can be said about robotization. The reasons for the misunderstandings are many. They include: fantasy, movies and popular/social media, unrealistic expectations by the robot enthusiasts, slow developments in the field, inadequate    expertise and capabilities for the necessary developments, the lack of necessary  technologies (mechanical, electronic, and computer science; powerful computers) to achieve the goals, weak collaboration in the beginning (mainly among the electrical and mechanical engineers, and computer scientists, but this culture was changed with the establishment of the Robotics Institute at CMU); and the lack of adequate “robotic intelligence” for various autonomous operations.

See my video interview:   https://youtu.be/rMW32o2QD5E

Q: So, have we achieved what we like to see in Robotics? Are there any shortcomings?

We have not yet achieved what the engineers and technologists reasonably expect in Robotics, not to mention the robot enthusiasts. The common capabilities of the existing robots include: Navigation with obstacle avoidance (SLAM—Simultaneous Localization and Mapping), visual and verbal communication with humans, operation of some appliances, grasping and carrying of objects (including conformable grasping and tactile sensing), multi-robot cooperation, and haptic teleoperation (with force feedback).

Some obvious shortcomings of today’s robots include: Poor human-like interaction (and poor interaction with humans), slow speed, poor dexterity and the sequential nature in grasping and handling of objects (e.g., the robotic hand slowly moves to the object and subsequently the fingers are closed around the object. Instead, the human observes the object to be grasped and simultaneously moves the hand and the body in coordination until the object is reached and the grasping is complete. A human can easily sense possible slipping of the object), possible safety problems for humans (due to the shortcomings of the current robotic mechanical components and control), sensory limitations (particularly related to smell and taste or chemical and biological sensing; transparency in teleoperation), limited mechanical capability (in dexterity, flexibility, adaptability, etc., unlike humans), and limited robotic intelligence.   Concerning the safety in human-robot Interaction, robot-inflicted injuries include accidents involving: Sharp objects and tools, large forces, fast motions and quick changes of magnitude and direction, and malfunctions in the robotic equipment.

Q: What are some of the immediate needs in Robotics?

The autonomous operation (i.e., operating on its own, without outside help) of robots is essential. Some needs for this autonomy are: Greater robotic intelligence (better learning; operating in dynamic, partially structured, and partially known environments; use of enhanced characteristics of intelligence); Greater accuracy, speed, dexterity, etc.; Increased safety (better object handling, accident/obstacle avoidance, etc.); More human-friendly and human-like communication and operation; and the redesigning of household appliances for easy operation by robots (and humans).

Consider the required basic caregiver tasks (of humans), for example: Verbal and visual communication; Assistance for movement/mobility; Identifying, grasping, and handling of needed objects properly and safely; Safe and quick assistance in the mobility of the care-receiver, in the presence of obstacles (both static and dynamic such as furniture, appliances, other humans and pets); Monitoring of objects and the environment for carrying out the caregiver tasks (under normal and emergency situations); Operating household appliances; and Provision of assistive devices. Then, similar operational requirements from robotic caregivers include: Faster yet safe operation; Human-friendly and human-like interaction and communication; Autonomous assistance for 24-hr, routine and basic care (mobility, bathing, dressing, toileting, meal preparation, providing medicine, etc.); Effective monitoring and detection of emergency situations; and Adequate emergency assistance (possibly incorporating remote monitoring, teleoperation, etc.) until regular help arrives. In this context, some needs in haptic teleoperation (teleoperation with feedback from the slave robot to the human master) are: Improvements to autonomous robotics as in non-teleoperation situations; Improved transparency (better/faster tactile/visual/auditory feedback to the remote human operator, for realistic creation of remote presence); Stability under (and compensation for) time delays (which are common in teleoperation. See the video:https://youtu.be/sl5ckyY7Zao?t=9);

Human-like manipulation; Improved design and control (for accuracy, speed, robustness, reliability, and safety); and 3-D virtual reality for the remote operator (for improved transparency).

Q: With such needs and shortcomings, I believe one must plan possible directions for advancing the state-of-the-art of Robotics. Can you suggest some?

We need to focus on several aspects, to improve the state-of-the-art. They include: Autonomous operation; Improved learning and intelligence (for autonomous operation); Self-awareness for robots (i.e., knowing the own capabilities of robot); Improved dexterity of handling (e.g., compliant grasping, parallel not sequential, and in coordination. Providing the adequate degrees of freedom for manipulation of the handled object); Improved robot-human interaction (in particular, working “with” a human rather than working “for” a human); Improved speed, stability, robustness, reliability, and safety; Improved sensing (particularly, chemical and biological sensing; transparency of remote operations; dynamic sensor networks; intelligent sensor fusion); and Significant improvement of the “mechanical” capabilities. Note particularly, the needs in software, mechanical capabilities, and instrumentation. Possible developments in Sri Lanka as well should focus on these, as appropriate. We will talk about this later.

In this context, the question can be posed whether to put our effort in developing universal robots having unlimited capabilities and functions, which will of course be very costly and complex. In other words should we focus on developing luxury and very expensive Cadillacs or use existing Marutis, cooperatively? It is not wise to put much effort in the development of complex and costly robots with numerous features and multi-function capabilities. As a scenario, consider the use of existing low-cost robots that have been developed for just one specific task (e.g., security, human assistance and guidance, street cleaning). If an emergency occurs (e.g., an explosion), can we call upon them to join, in cooperation (if available) to perhaps put together simple devices and help in the situation (e.g., evacuation of the injured)?

Q: You mentioned the need for improved robotic intelligence. Many people talk about artificial intelligence (AI), and say it can make robots challenging (and dangerous?) to humans. What is your opinion?

The importance of intelligence in Robotics is quite clear. Intelligence is essential for the autonomous operation of a robot. In fact, realization of expectations (including some fantasies?) of robotics depends on improved robotic intelligence and similarly improved mechanical capability. Today’s robots don’t have even “primitive” intelligence. Without significantly improved intelligence, robots cannot achieve human-like capabilities; for example, emotions, common sense, and inventiveness are quite farfetched! Improved intelligence renders the robots to acquire some characteristics of human intelligence. However, it is simply “fear mongering” to say that the future robots will be a danger to the human kind because of their high level of intelligence.

Typically, robots improve their intelligence through learning, and the foundation of AI is indeed machine learning. Some claim that since a chess playing computer has defeated a human champion, it is possible that intelligent robots will defeat humans in many activities. Here we have to realize that the capabilities of a robot depend on their control program, which is developed by humans. It is true that due to learning, robot intelligence (the decision making ability related to the learned knowledge) improves. Unlike humans whose level of intelligence can depreciate for many reasons (physiology, lack of practice, new knowledge, new and complex environments, etc.), machine learning will always improve the robotic intelligence. This means, a chess playing robot will continuously improve its skills through learning (practice) and can thereby defeat a chess champion. However, we have to realize that such intelligence is provided to robots by humans, through the control programs. Furthermore, we should question whether a chess playing robot can also perform other tasks (e.g., caring for an elderly, carrying out medical surgery) as well. Very unlikely. Also, can a robot ever acquire such characteristics as common sense or emotions?

We should remember that humans develop robots and we program their controller (brain). We can set limitations, checks and balances, regulations, and guidelines, as we wish. We should collaborate with social scientists, and develop proper guidelines and regulations for the development and the safe and ethical use of robots. Since a proper ethical evaluation and certification are essential for any technology that is used by humans, this should be properly adhered for robots as well, and should be strictly applied in Sri Lanka too! In medical surgery, for example, a robot will facilitate the surgical procedures, but they should be performed under the supervision of a human surgeon, who must have the capability to abort the robotic procedure immediately, if necessary. 

In fact, people who fear AI simply fear a black box! Do they know: What is in the AI black box? What methodologies are used in that black box? And, how are those methodologies implemented and operated? So, instead of simply fear mongering, they should explore the black box carefully and in detail (through experts who are knowledgeable in the subject) and only then indicate what methodologies in the AI black box might be dangerous, in their opinion. Then other experts will be able to respond intelligently and in an informative manner. Unfortunately, that is not happening now.     

Q: Professor, this is somewhat reassuring. But for a lay person, can you explain what AI is?

Before exploring AI, let us examine intelligence itself. No precise definition exists for intelligence. It is the external characteristics and capabilities that we observe from actions that enable us to claim a person (or robot) to be intelligent.  Essentially, the outward characteristics define intelligence. Let us examine what some of those characteristics are.

The characteristics of intelligence include: Sensory perception; Pattern recognition; Learning (i.e., knowledge acquisition, which is extremely important for intelligence); Inference (i.e., making decisions) from incomplete information; Inference from qualitative or approximate information (this is commonly used in “qualitative reasoning” as in fuzzy logic or fuzzy reasoning); Ability to deal with unfamiliar situations; Adaptability to new, yet related situations (through “expectational knowledge.” For example, a human is able to expect the nature of an environment, like a classroom, even when encountering that environment for the first time); Inductive reasoning (people must have done this in high school mathematics, when proving a mathematical result “by induction”); Common sense; Display of emotions; Inventiveness; and Self-awareness (i.e., knowing their own capabilities).           

AI uses formal techniques to acquire some characteristics of intelligence. In fact, appropriate models of AI are used for this purpose, based on one or more of the mentioned characteristics. Such approaches (or models) of AI include Machine Learning, which is a very popular approach of AI. The conventional models of AI include Knowledge-based Systems, Neural Networks—NN, Fuzzy Systems, Evolutionary Computing, and Swarm Intelligence. A knowledge-based system, typically, consists of a knowledge base (or a rule base), a data base, and an inference engine (the decision maker). The decisions are made as follows: Some data in the data base (including what is acquired recently through sensors) is matched with the (context of the) rules in the knowledge base, by the inference engine, and the inferences (or actions) are determined accordingly (i.e., rules are fired). Popular “Expert Systems” are based on this model. Of course, the knowledge base will be improved and enhanced continuously through “learning” and experience (so, machine learning is used here as well). Deep learning uses deep NN including Convolutional NN. They have a structure of multiple layers (convolution layers) incorporating the “dynamic” learning ability, and ending with a “Softmax” layer, which is the classification layer. First the NN is trained using “labeled data” (i.e., input data whose proper outcomes are known a priori). After the network is trained properly, unlabeled data (or new data) may be used for the actual decision making. Massive amounts of data, including sensed data (a mixture of labeled and unlabeled data) may be effectively used in a deep NN. Reinforcement learning relies on rewarding the correct decisions and penalizing the wrong decisions, to learn the proper decision strategies. AI agents are capable of providing explanations for their decisions (similar to Expert Systems). In Edge AI, AI algorithms are processed locally on a hardware device. The algorithm uses data that are created on the device (e.g., data generated by the algorithm itself) in addition to other data (external data, including from sensors and through the system interface). Hence, Edge AI functions at the “edge of the system network.” Fuzzy logic attempts to be similar to human decision making, by incorporating “fuzzy” or “qualitative” or “approximate” data, such as those that use qualifiers like fast, small, better, and close.   Qualitative or fuzzy reasoning is used in the decision making (inference) process. Swarm Intelligence behaves like a swarm of animals or insects. They are distributed (no hierarchical) and interact with each other to learn and make decisions.  The members in a swarm use very simple rules, yet leading to "intelligent" global behavior, even though an individual member is not quite intelligent, which will improve with time. Evolutionary computing relies on genetic algorithms or genetic computing to realize “optimized” behavior through learning. The basis of this methodology is the biological evolution (or survival of the fittest). Fuzzy logic, NN, and evolutionary computing belong to the area of “soft computing.”  

Q: Where are robots used today? What are the opportunities in this field?

The commercial applications of Intelligent Robotics (with AI) include: Autonomous agents such as self-driving vehicles (aerial, ground, and underwater), which are indeed mobile robots;  Assistive devices (Active and adaptive prostheses, wearables, hand-held smart devices); Advisory Systems (or, expert systems, which are used in such areas as medical, legal, business, service, and social); Monitoring/Security Systems (they are applicable in such areas as machine fault detection, prediction and diagnosis; and for human health monitoring, in telemedicine, homecare, etc.; Video Analysis; Cyber security; Human-machine interaction (including natural language processing, facial expression detection, speech recognition, communication, and intelligent connectivity; Industrial application (including manufacturing and the assessment of production quality, cost, and efficiency); Consumer, Service, and Entertainment sectors (retail, domestic, social, etc.); Agriculture (growing, fertilizing, weed removal, and harvesting); Smart buildings (Heating Ventilation, and Air Conditioning—HVAC; smart metering, safety, smart appliances, automated lighting, and achieving energy efficiency); Education (“Intelligent” Learning Management System or LMS, collaboration among students and with teachers—this approach may be quite beneficial in the current epidemic situation of Covid-19); and Energy and Environment (Distribution, exploration, monitoring, planning, and utilization of energy). Some of these applications have been implemented today. Some will provide diverse future opportunities.

Q: Are our universities in Sri Lanka doing enough in Robotics, in particular?

Many universities in Sri Lanka are active in the area of Robotics (teaching, research and industrial collaboration). For example, your group at the Open University of Sri Lanka (OUSL) is doing excellent work in “Soft Robotics.” Others including University of Moratuwa (UM) have undertaken very practical projects such as mine clearing robots. Even University of Uva Welassa has a good group in Mechatronics and Robotics. Certainly, they should collaborate, rather than working in isolation, particularly because Robotics is a field that can benefit greatly through multidisciplinary collaboration (see what I mentioned before, particularly under the Robotics Institute of CMU).

As you know, I have collaborated with OUSL, UM, and SLIIT. In particular, I have provided scholarships for their faculty members to carry out Master’s, Doctoral, and Post-doctoral research in my laboratory at UBC. They collaborate with others in my laboratory and outside, in their research, and gain significant expertise before leaving my group. Fortunately, some of them have returned to Sri Lanka, and are carrying out good research and development.

Q: Professor, in conclusion, please indicate some opportunities that Robotics provide for our country?

What I say here is equally applicable to other developing countries as well. Opportunities for us exist in all the areas that I mentioned before. However, we should not blindly decide on our activities, just for the sake of being involved in Robotics or AI. We must explore and determine what is in the “black box.” Otherwise we can be dissuaded through fear mongering, as I mentioned before, or make wrong choices for robotic activities. We must first question whether Robotics is needed for a specific application (in Si Lanka). Then we must explore which robotic approaches are relevant for the considered task. Very importantly, we must examine what is in the existing Black Box, before implementing it.

I suggest that Sri Lankans should concentrate on “robot development” not their application for automation of local industries. We can market such robots to other countries. Since we have an excessive and smart labor force, using robots for such applications as agriculture and industrial automation is not generally suitable here. Nevertheless, we may consider the development of simple and low-cost robots for local use (e.g., for service and household applications). We must focus on the development of advanced software, in particular, to incorporate other forms of intelligence into robots and efficient software, and the use of advanced tools like Flexible Cloud, Real-time Internet of Things (IoT), and Edge AI. Software developments can be accomplished without much capital investment, as they do in India, for example, particularly because we have a highly educated and smart group of engineers, technicians, and computer scientists in Sri Lanka. Also, we should focus on advancing the “Mechanical Capabilities” of robots, which are essential as I had indicated before, but not necessarily for the local market. As well, we should consider the needs that result from a particular situation (e.g., Covid-19). Very importantly, we should develop our own guidelines and regulations for robotic ethics and safety, which can be done by modifying the existing guidelines and regulations in other jurisdictions.

Contributed by Nimali Medagedara
BSc Eng (Hons) (Peradeniya), MPhil (UK), MIE (SL), C.Eng., MIEEE
Senior Lecturer, Department of Mechanical Engineering
The Open University of Sri Lanka.

 

Prof. Clarence W. de Silva

https://mech.ubc.ca/clarence-de-silva/