Adaptable robotics: Difference between revisions

Revision as of 15:15, 27 October 2023

Revision as of 00:39, 16 November 2023

Line 1:

'''Adaptable Robotics''' refers to a field of [[robotics]] with a focus on creating robotic systems capable of adjusting their hardware and software components to perform a wide range of tasks while adapting to varying environments. The 1960s introduced robotics into the industrial field.<ref name=":02">P. Thomson, “An Exhaustive History of Robotics,” G2, Aug. 30, 2019. <nowiki>https://www.g2.com/articles/history-of-robots</nowiki> (accessed Oct. 30, 2023).</ref> Since then, the need to make robots with new forms of [[Actuator|actuation]], adaptability, [[Peripheral|sensing and perception]], and even the [[Artificial intelligence|ability to learn]] stemmed the field of adaptable robotics. Significant developments such as the PUMA robot, manipulation research, [[soft robotics]], [[swarm robotics]], [[Artificial intelligence|AI]], [[Cobot|cobots]], bio-inspired approaches, and more ongoing research have advanced the adaptable robotics field tremendously. Adaptable robots are usually associated with their [[Robot kit|development kit,]] typically used to create autonomous mobile robots. In some cases, an adaptable kit will still be functional even when certain components break.<ref>{{Cite news |date=2015-05-27 |title=Adaptable robots 'on their way' to the home |language=en-GB |work=BBC News |url=https://www.bbc.com/news/science-environment-32884768 |access-date=2023-11-09}}</ref>

'''Adaptable robotics''' are generally based in [[robot kit|robot developer kits]]. This technology is distinguished from static [[automation]] due to its capacity to adapt to changing environmental conditions and material features while retaining a degree of predictability required for [[collaboration]] (e.g. human-robot collaboration).<ref>{{Cite book |title=Robotic Fabrication in Architecture, Art and Design 2018 |last=Willmann |first=Jan |last2=Block |first2=Philippe |last3=Hutter |first3=Marco |last4=Byrne |first4=Kendra |last5=Schork|first5=Tim|publisher=Springer|year=2018|isbn=9783319922935|___location=Cham, Switzerland|pages=45}}</ref> The degree of adaptability is demonstrated in the way these can be moved around and used in different tasks.<ref>{{Cite book|title=Industrial Robotics Handbook|last=Hunt|first=V. Daniel|publisher=Industrial Press|year=1983|isbn=0831111488|___location=New York|pages=[https://archive.org/details/industrialroboti0000hunt/page/152 152]|url-access=registration|url=https://archive.org/details/industrialroboti0000hunt/page/152}}</ref>

Adaptable Robotics systems successfully adapt to their environment using techniques such as [[modular design]], [[machine learning]], and [[sensor]] feedback. Using this, they have revolutionized various industries and have the ability tocan address many real-world challenges in the [[medical]], [[industrial]], [[extraterrestrial]], and [[Experiment|experimental]] fields. There are still many challenges to overcome in adaptable robotics, which presents opportunities for growth in the field.

Unlike static or factory robots, which have pre-defined way of operating, adaptable robots can function even if a component breaks, making them useful in cases like caring for the elderly, doing household tasks, and rescue work.<ref>{{Cite news|url=https://www.bbc.com/news/science-environment-32884768|title=Robots adapt to damage in seconds|last=Ghosh|first=Pallab|date=2015-05-27|work=BBC News|access-date=2018-10-04|language=en-GB}}</ref>

== Fundamental Concepts: ==

Adaptable Robotics systems successfully adapt to their environment using techniques such as [[modular design]], [[machine learning]], and sensor feedback. Using this, they have revolutionized various industries and have the ability to address many real-world challenges.

An adaptable robot typically has attributes that distinguish it from robots that perform their task regardless of external factors. Four concepts that adaptable robots utilize to make this distinction are adaptability, sensing and perception, learning and intelligence, and actuation.

=== Adaptability ===

A robot can be defined as adaptive when it has capabilities such as intrinsic safety and performance without compromise, the ability to learn, and the capacity to perform tasks traditional robots are not capable of. These capabilities can be achieved through force control technology, hierarchical intelligence, and other innovative approaches.<ref name=":12">{{Cite web |last=Content |first=Sponsored |date=2019-07-29 |title=Why Adaptive Robots are the Next Big Thing |url=https://www.roboticsbusinessreview.com/content-from-our-sponsor/why-adaptive-robots-are-the-next-big-thing/ |access-date=2023-11-09 |website=Robotics Business Review |language=en-US}}</ref> John Adler’s invention in 1994, the [[Cyberknife (device)|cyberknife]], is a robotic surgery system that is capable of using ultra-fine precision in medical procedures which demonstrates such adaptations.<ref name=":03">P. Thomson, “An Exhaustive History of Robotics,” G2, Aug. 30, 2019. <nowiki>https://www.g2.com/articles/history-of-robots</nowiki> (accessed Oct. 30, 2023).</ref>

=== Sensing and Perception ===

Environmental information gathered through peripherals is processed intelligently in adaptable systems. AI systems can process this data and adjust task primitives accordingly, leading to adapted action.<ref name=":12" /> In 2001, the [[Canadarm 2]] was launched to the [[International Space Station|ISS]] and played a key role in the maintenance of the station, using data from [[Peripheral|peripherals]] to adapt the ISS to environmental changes within it.<ref name=":03" />

=== Learning fromand demonstration (LfD)Intelligence ===

AI, Machine Learning, and [[Deep learning|Deep Learning]] allow systems to learn about the world around them and become progressively more intelligent when executing their tasks.<ref name=":12" />[12] In 1997 the robot [[Sojourner (rover)|Sojourner]] was launched to Mars, with an onboard computer allowing it to adapt to unplanned events and obstacles even with minimal data; a precursor to the addition of AI in adaptable systems. Later that year, IBM’s [[Deep Blue versus Garry Kasparov|Deep Blue]] computer defeated [[Garry Kasparov]] in a game of chess, a landmark for robotic AI’s ability to plan and react.<ref name=":03" />

=== SARActuation ===

Actuation in robotic systems allows the robot to move. Adaptable [[Actuator|actuators]] typically function in response to environmental changes, such as changes in temperature which may change the shape of the actuator. Thus, altering functionality.<ref>{{Cite web |title=Actuators: what is it, definition, types and how does it work |url=https://www.progressiveautomations.com/pages/actuators |access-date=2023-11-09 |website=Progressive Automations |language=en}}</ref> Self-powering (untethered) actuation is achievable, especially in soft robotics where external stimuli can change the shape of an actuator, creating mechanical energy.<ref name=":22">Y. Chi, Y. Zhao, Y. Hong, Y. Li, and J. Yin, “A Perspective on Miniature Soft Robotics: Actuation, Fabrication, Control, and Applications,” Advanced intelligent systems, Apr. 2023, doi: <nowiki>https://doi.org/10.1002/aisy.202300063</nowiki>.\</ref> In 1989 Rodney Brooks created Ghengis, a hexapedal robot capable of traversing difficult terrain.<ref name=":03" /> The Hexapedal model uses six actuators for mobility and has remained prominent with modern hexapedal models like the [[Rhex]].

==Software==

Line 10 ⟶ 23:

The process of modifying a robot to achieve varying capabilities such as collaboration could merely include the selection of a module, the exchange of modules, robotic instruction via software, and execution.<ref>{{Cite book|title=Advances In Cooperative Robotics - Proceedings Of The 19th International Conference On Clawar 2016 |last=Tokhi |first=Mohammad |last2=Gurvinder |first2=Virk |publisher=World Scientific|year=2016|isbn=9789813149120|___location=Hackensack, NJ|pages=159}}</ref>

== Types of Adaptable Robots: ==

=== [[Soft robotics|Soft Robots]] ===

Robotics with soft grippers is an emerging field in the adaptable robotic scene which is based off ofon the [[Venus fly trapflytrap]]. Two soft robotic surfaces provide enveloping and pinching grasp modules. This technology is tested in a variety of environments to determine the effects of diverse objects, errors of object position, and SRS (Soft Robotic Surface) installation on grasping capacity. <ref name=":0">W.{{Cite journal |last=Xiao, C.|first=Wei |last2=Liu, D.|first2=Chang |last3=Hu, G.|first3=Dean |last4=Yang, and X.|first4=Gang |last5=Han, “Soft|first5=Xu |date=2022-04 |title=Soft robotic surface enhances the grasping adaptability and reliability of pneumatic grippers,” ''|url=https://linkinghub.elsevier.com/retrieve/pii/S0020740322000315 |journal=International Journal of Mechanical Sciences'' |language=en |volume=219 |pages=107094 |doi=10.1016/j.ijmecsci.2022.107094}}</ref>Untethered actuation is achievable, volespecially in soft robots with LCPs, a category of stimuli-responsive materials with two way shape memory effect. 219This can allow the LCPs to generate mechanical energy by changing shape in response to external stimuli, phence untethered actuation.<ref 107094name=":23">Y. Chi, Y. Zhao, Y. Hong, Y. Li, and J. Yin, “A Perspective on Miniature Soft Robotics: Actuation, Fabrication, Control, and Applications,” Advanced intelligent systems, Apr. 20222023, doi: <nowiki>https://doi.org/10.10161002/jaisy.ijmecsci.2022.107094202300063</nowiki>.\</ref>

=== Modular Robots ===

Robots designed for the outdoors that adapt to changing landscapes and obstacles. These are constructed like a chain of individual modules with simple hinge joints, enabling modular robots to morph themselves into various shapes to traverse terrain. Some of these forms include configurations like [[spider]], serpentine, and loop.<ref>{{Cite web |title=Modular Robots - IEEE Spectrum |url=https://spectrum.ieee.org/modular-robots |access-date=2023-11-09 |website=spectrum.ieee.org |language=en}}</ref>

=== Swarm Robotics ===

Field of robotics utilizing swarm intelligence to groups of simple homogeneous robots. Swarm robots follow algorithms, usually designed to mimic the behavior of real animals, in order to determine their movements in response to environmental stimuli.<ref>“Swarm Robotics - an overview | ScienceDirect Topics,” www.sciencedirect.com. <nowiki>https://www.sciencedirect.com/topics/engineering/swarm-robotics</nowiki></ref><ref name=":3">A. Iglesias, A. Gálvez, and P. Suárez, “Chapter 15 - Swarm robotics – a case study: bat robotics,” ScienceDirect, Jan. 01, 2020. <nowiki>https://www.sciencedirect.com/science/article/pii/B9780128197141000269#s0100</nowiki> (accessed Nov. 07, 2023).</ref>

=== Biohybrid Robots ===

Biohybrid robotics use living tissues or cells to provide machines with functions that would be difficult to achieve otherwise. For instance, muscle cells have been utilized to allow certain biohybrid robots to move. Swarm robotics combine with biohybrid in certain cases, especially within the medical field <ref name=":3" /><ref name=":4">{{Cite web |last=Conocimiento |first=Ventana al |date=2019-10-21 |title=Biohybrid robots, the next step in the robotic revolution |url=https://www.bbvaopenmind.com/en/technology/robotics/biohybrid-robots-the-robotic-revolution/ |access-date=2023-11-09 |website=OpenMind |language=en-US}}</ref>

== Applications of Adaptable Robotics ==

Adaptable robotics possess capabilities that have made them applicable to many fields including, but not limited to, the medical, industrial, and experimental fields.

[[Reinforcement learning|Learning from demonstration]] (LfD) is a strategy for transferring human motion skills to robots. The primary goal is to identify significant movement primitives (MPs), significant movements humans make, from demonstration and remake these motions to adapt the robot to that motion. There have been a few issues with robots being unable to adapt skills learned through LfD to new environments (a change from the scenario in which the robot was given initial demonstrations). These Issues with LfD have been addressed with a learning model based on a nonlinear dynamic system (DS) which encodes trajectories as dynamic motion primitive (DMP). DMPs are similar to MPs, but they are significant movements represented by a mathematical equation; equation variables change with the changing environment, altering the motion performed. The trajectories recorded through these systems have proven to apply to a wide variety of environments making the robots more effective in their respective spheres. LfD has progressed the applicability of robotics in fields where precision is essential, such as surgical environments.<ref name=":5">{{Cite journal |last=Teng |first=Tao |last2=Gatti |first2=Matteo |last3=Poni |first3=Stefano |last4=Caldwell |first4=Darwin |last5=Chen |first5=Fei |date=2023-06 |title=Fuzzy dynamical system for robot learning motion skills from human demonstration |url=https://linkinghub.elsevier.com/retrieve/pii/S0921889023000453 |journal=Robotics and Autonomous Systems |language=en |volume=164 |pages=104406 |doi=10.1016/j.robot.2023.104406}}</ref>

=== Learning from demonstration (LfD) ===

Learning from demonstration (LfD) is a strategy for transferring human motion skills to robots. The primary goal of this is to identify significant movement primitives (MPs) from human demonstration and remake these motions to adapt the robot to new situations.<ref name=":1">T. Teng, M. Gatti, S. Poni, D. Caldwell, and F. Chen, “Fuzzy dynamical system for robot learning motion skills from human demonstration,” ''Robotics and Autonomous Systems'', vol. 164, p. 104406, Jun. 2023, doi: <nowiki>https://doi.org/10.1016/j.robot.2023.104406</nowiki>.</ref>

In the medical field, SAR technology focuses on taking sensory data from wearable peripherals to perceive the user’s state of being. The information gathered enables the machine to provide personalized monitoring, motivation, and coaching for rehabilitation. Intuitive Physical HRI and interfaces between humans and robots allow functionalities like recording the motions of a surgeon to infer their intent, determining the mechanical parameters of human tissue, and other sensory data to use in medical scenarios.<ref name=":6">{{Cite journal |last=Okamura |first=Allison |last2=Mataric |first2=Maja |last3=Christensen |first3=Henrik |date=2010-09 |title=Medical and Health-Care Robotics |url=http://ieeexplore.ieee.org/document/5569021/ |journal=IEEE Robotics & Automation Magazine |volume=17 |issue=3 |pages=26–37 |doi=10.1109/MRA.2010.937861 |issn=1070-9932}}</ref> Biohybrid robotics have medical applications utilizing biodegradable components to allow robots to function safely within the human body.<ref name=":4" />

Issues with LfD have been addressed with a learning model based on a nonlinear dynamic system (DS) which encodes trajectories as dynamic motion primitive (DMP). The trajectories recorded through these systems have proven to be applicable to a wide variety of environments making the robots more effective in their respective spheres when using this adaptable robotic technology.<ref name=":1" />

AI, Machine Learning, and Deep Learning have allowed advances in adaptable robotics such as autonomous navigation, object recognition and manipulation, natural language processing, and predictive maintenance. These technologies have been essential in the development of cobots (collaborative robots), which are robots capable of working alongside humans capable of adapting to changing environments.<ref name=":7">{{Cite journal |last=Soori |first=Mohsen |last2=Arezoo |first2=Behrooz |last3=Dastres |first3=Roza |date=2023 |title=Artificial intelligence, machine learning and deep learning in advanced robotics, a review |url=https://linkinghub.elsevier.com/retrieve/pii/S2667241323000113 |journal=Cognitive Robotics |language=en |volume=3 |pages=54–70 |doi=10.1016/j.cogr.2023.04.001}}</ref>

=== SAR ===

In the medical field, SAR technology focuses on taking sensory data from wearable [[Peripheral|peripherals]] in order to perceive the user’s state of being. The information gathered enables the machine to provide personalized monitoring, motivation, and coaching for rehabilitation. <ref name=":2">“Medical and Health-Care Robotics,” ''ieeexplore.ieee.org''. <nowiki>https://ieeexplore.ieee.org/document/5569021</nowiki> (accessed Oct. 24, 2023).</ref>

In the industrial field, AI, Machine Learning, and Deep Learning can be used to perform quality control checks on manufactured products, identify defects in products, and alert production teams to make necessary changes in real-time.<ref name=":7" />

Intuitive Physical HRI and interfaces between humans and robots allow functionalities like recording the motions of a surgeon to infer their intent, determining the mechanical parameters of human tissue, and other sensory data to use in medical scenarios. <ref name=":2" />

== Challenges and Limitations ==

Systems whichthat involve physical collaboration between humans and robots are difficult to design well due to human uncertainty. Humans alter the force of their motions regularly due to human factors like emotion, biological processes, and other extraneous factors unknown to a robot. This can make sensory data difficult to quantify for successful adaptation in robots. Furthermore, the specific needs, characteristics, and preferences to whichthat a patient in a medical scenario may need vary from person to person. Adaptable robotic systems need extended time to adapt to the new environment introduced from patient to patient.<ref name=":25" /><ref name=":6" />

The need for reliable data from sensory technology is a challenge for adaptable systems, especially in the AI realm. With AI models becoming rapidly more advanced, the need to develop peripheral technologies able to provide necessary information for these systems becomes increasingly more challenging. Furthermore, the need for dynamic environments to train AI algorithms proves to be challenging as not every scenario a machine may find itself in will be introduced to it during training.<ref name=":7" />

Swarm robots are limited by interference and collisions, uncertainty, lack of specialization, and lack of understanding of the behavioral pattern of the swarm.<ref name=":3" /> Biohybrid robotics have challenges with living cells being delicate even though they are adaptable to a variety of environments due to the properties of the biological material.<ref name=":4" />

==See also==