Autonomous Robots
Autonomous robots are intelligent machines capable of performing tasks in the world independently of either direct human control or fixed programming. Examples range from autonomous drones, to industrial production robots, to your robotic vacuum cleaner. They combine expertise from the fields of Artificial Intelligence, robotics, and information science.The autonomous robot must have the ability to perceive its environment, analyze situational data in order to make decisions based on what it perceives, and then modify its actions based on these decisions. For example, the scope of autonomy could include starting, stopping, maneuvering around obstacles, communicating to obstacles, and using appendages to manipulate obstacles. There are few autonomous robots in operation today. Even most sophisticated, dynamic robots such as those used in an automotive factory perform according to static programming. And most autonomous robots are only semi-autonomous and will likely remain so even as more fundamental autonomy becomes technically feasible. For example, the Roomba vacuum cleaner does not move according to a pre-programmed route and can modify its route dynamically as its environment changes. However, it has a very limited degree of freedom that is determined by its programming.
- INDUSTRIES
-
Automotive Equipment & Machinery Heavy Vehicle - FUNCTIONS
-
Discrete Manufacturing - CASE STUDIES
-
Siemens: Siemens | Using Machine Learning to Get Machines to Mimic IntuitionThe ability to learn is a precondition for autonomy. With this in mind, Siemens researchers are developing knowledge networks based on deep learning-related simulated neurons and connections. Such networks can be used to generalize information by identifying associations between extraordinarily complex realms, such as the publicly accessible Internet and a company’s internal information systems. Far-reaching and generic, this technology appears to hold the potential of mimicking what humans call intuition.
RoboDK: Accurate Robot MachiningIndustrial robots are highly repeatable but not very accurate. However, through a robot calibration process the accuracy of a robot arm can be improved to the point where it is close to its repeatability, usually under the 0.100 mm mark. This is becoming very attractive to small and medium enterprises as robot arms are very affordable and can be used for multiple manufacturing applications, including machining materials such as wood, plastic or marble.
ABB: Metal FabricationAs each mast section needs a total of 222 reliable welds, manufacturing them is an extremely labor intensive process.Until recently, STROS had to use highly skilled welders to make these sections. Although it has been using robots for 25 years, these machines could not manage the complex arc welds in narrow spaces needed for these particular components. Consequently, in order to produce a satisfactory number of mast sections it had to employ three welders per shift at three separate workstations to make these pieces. Apart from the obvious outlay this required in terms of manpower and space, STROS found it increasingly difficult to recruit the highly qualified welders needed for this work. That's why in 2007 the company decided to hold a tender for the complete robotization of its manufacturing process for mast sections. Of the four firms who participated, only the ABB group could fulfill all its requirements. - MARKET SIZE
-
The Boston Consulting Group is conservatively projecting that the market will reach USD 87 billion by 2025.
Source: The Robot Report
Electrical engineering company Siemens predicts the global market for autonomous robots to grow to USD 3.6 billion in 2019, and USD 13.9 billion in 2023.
Source: Siemens
The global autonomous robot market was valued at around USD 4.6 billion in 2016 and it is expected to reach more than USD 11.9 billion million by 2024. It is expected to grow at a CAGR of over 14% between 2017 and 2024.
Source: Global Newswire
- BUSINESS VIEWPOINT
-
When are autonomous robots practical?
Autonomous robots are particularly useful when one of the two criteria are met:
1. The environment is either dangerous or expensive for humans to operate in. For example, spaceflight and mine sweeping are both dangerous fields of human activity. Spaceflight is also extremely expensive due to the cost of supporting human life in space.
2. The task requires simple, routine action in high volume with a modest level of dynamic adjustment. For example, store-to-door goods delivery and highway trucking are both routine activities yet require the ability to react to unexpected situations within a range of possibilities. Likewise, in a production environment, a robot performs a largely repetitive action but must respond to unpredicted variables such as the precise orientation of a component it is assembling, or modification of the task in order to customize orders.
What are the core functionalities of an autonomous robot?
The concept of an autonomous robot is broad and can include a wide range of devices with very different capabilities. However, any autonomous robot should have some ability to perform these basic functions:
1. Gather and process information about the environment.
2. Work for an extended period without human intervention under unpredictable stimuli.
3. Move through its operating environment without human assistance (but with pre-determined constraints).
4. Avoid situations that it has been programmed to identify as undesirable, such as harm to people, property, or itself.
More advanced robots may be capable of optimizing their efficiency or adding new capabilities as they 'learn' through by processing data. The capabilities of robots can also be improved through system upgrades enabled by collective data processing. For example, a fleet of vehicles could receive regular updates that incrementally improve fuel efficiency based on the processing of their collective operational data under diverse driving conditions.
- STAKEHOLDER VIEWPOINT
-
- TECHNOLOGY VIEWPOINT
-
- DATA VIEWPOINT
-
- DEPLOYMENT CHALLENGES
-
