Robotics in the Era of Artificial Intelligence

Robots are typically defined as physical agents that perform a variety of tasks by manipulating the physical world. The term is said to have been derived from the Czech word 'robota' meaning 'forced labour' and was used first in K. Capek's play, R.U.R. 'Rossum's Universal Robots', which appeared in 1920.

Robots are equipped with effectors like legs, wheels, arms & grippers. The single purpose of effectors is to exert physical force on the environment. Present day robots also use a whole range of sensors including cameras, Sonars, LiDARs, Radars and Lasers to assess and measure their environment as well as gyroscopes and accelerometers to measure their own motion.

Mostly, today's robots fall into one of three primary categories. These are Manipulators, Mobile Robots and Mobile Manipulators. Let's take a closer look at each of these categories.

Manipulators: Often referred to as robot arms, manipulators are physically anchored to their workplace. They can be found in a variety of places including factory assembly lines and space stations. Manipulator motion usually involves a chain of controllable joints, enabling them to place their effectors in any position within the workplace. Most industrial robots are of this category. They can be found in hospitals at times, assisting surgeons and in cars.

Mobile robots: Mobile robots have the ability to move about using wheels or robotic legs. Unmanned Ground Vehicles (UGVs) can drive autonomously on streets, highways and also off-roads. Unmanned Air Vehicles (UAVs aka drones) are commonly used for surveillance, military operations, crop spraying and even deliveries. Autonomous Underwater Vehicles (AUVs) are used in deep-sea explorations and underwater searches. Mobile robots can also be found delivering food in hospitals, moving containers in loading docks, delivering packages to customers and vacuuming floors in offices and homes. 

Mobile Manipulators: Sometimes referred to as Humanoid Robots, these typically mimic the human torso. Mobile manipulators can apply their effectors over a much larger area than typical manipulators, which are anchored. However their task is made more difficult since they lack the rigidity that anchors provide. 

Real robots must cope with environments that are partially observable, stochastic, dynamic and continuous. Practical robotic systems need to build in prior knowledge about the robot, its physical environment and the tasks that the robot may be called upon to perform so that the robot can learn quickly and perform safely. 

Robotics today brings together several concepts from AI and Machine Learning like probabilistic state estimation, perception, unsupervised learning and reinforcement learning, among others. The success of robots depends quite a bit on the design of sensors and effectors that are appopriate for the task for which the robot is being deployed.

Let us briefly look at some of the more popular and common application domains for robotic technology.

Industry & Agriculture: Heavy machines used for harvesting, mining or excavating earth are increasingly robots. Robots have been used to strip paint off ships at least 50 times faster than humans with much reduced resultant environmental impacts. Robots have been used to generate high-precision maps of abandoned mines and sewer systems. They have also been found to be much faster than humans in transporting ore from underground mines. 

Healthcare: Robots are frequently used to assist surgeons with instrument placement when operating on intricate organs like brains, hearts and eyes. Owing to their high precision, they have become indispensable aids in surgical procedures like hip replacements. Outside the operating theatre they can be deployed as aides for elderly & handicapped people such as intelligent robotic walkers and intelligent devices that remind people to take their medication on time and provide comfort to them. 

Personal Services: Service robots assist individuals in performing daily tasks like vacuuming offices or homes, mowing lawns or acting as caddies of golfers. Service robots in public places act as information kiosks in shopping malls, trade fairs and museums. These not only interact with humans but possess the ability to cope with unpredictable and dynamic environments. 

Human augmentation: Robotic devices are making it easier for people to walk or move their arms by providing additional forces at the appropriate places. Robotic tele-operation involves carrying out tasks over long distances with the aid of robotic devices. A popular configuration is the master-slave one, where a robot manipulator emulates the motion of a remote human operator, measured through a haptic interface. Tele-operated underwater vehicles are sent to depths considered dangerous for humans. Humanoid robots are available through several companies in Japan and South Korea.

Here are some of the more interesting projections about the future of robotics:
  • A significant percentage of commercial robotic applications will be in the form of 'robot-as-a-service' (RaaS). This will help to significantly lower the cost for robot deployment.
  • A significant percentage of all robotic deployments will be smart collaborative robots that will operate three times faster than many robots being used today and will be safe for work around humans.
  • Over 50 percent of robots will depend on cloud-based software to define new skills, cognitive abilities and application programs, leading to the formation of a robotics cloud marketplace.
  • In the very near future, 50 percent of the 200 leading global ecommerce and omni-channel commerce companies will deploy robotic systems in their order fulfillment, warehousing and delivery operations.
  • By 2020, over 40 percent of commercial robots will become connected to a mesh of shared intelligence, resulting in 200 percent improvement in overall robotic operational efficiency.

-- Raja Mitra