Published March 21, 2019 | Version v1
Journal article Open

Editorial on Advances in Machine Learning and Robotics

  • 1. University of Bridgeport

Description

Machine Learning is opening door to entirely new automation possibilities. It is set to disrupt practically every industry imaginable. Presently, machine learning are being applied in limited methods and are enhancing the abilities of industrial robotic systems. There is always room for improvement for the full potential of robotics and machine learning but applications are advantageous. There are four major areas for robotic process and machine learning are impacting to make current applications more efficient and beneficial. It includes Vision – machine learning is aiding robots to detect items that they have never seen before and analyze objects with greater detail. Grasping – robots are also gripping objects that they have never seen before with machine learning it is assisting them to determine the best position and orientation to hold the object. Motion Control – with the assistance of machine learning robots are able to have dynamic interaction and obstacle avoidance to maintain productivity. Data – with the help of machine learning and artificial intelligence robot can understand physical and logistical data patterns to be proactive and act appropriately.

Files

Algorithms and Machine Learning.pdf

Files (423.1 kB)

Name Size Download all
md5:bc7d2ece39410a7039152635464ed366
423.1 kB Preview Download

Additional details

Related works

References

  • Robotics Online. (2018, June 26). Industrial Robotics and Automation Blog. Retrieved from https://www.1. robotics.org/blog-article.cfm/Applying-Artificial-Intelligence-and-Machine-Learning-in-Robotics/
  • Subham S. Sahoo, Christoph H. Lampert, Georg Martius. Learning Equations for Extrapolation and Control. 2. 35th International Conference on Machine Learning, 2018
  • Institute of Science and Technology Austria. (2018, July 12). First machine learning method capable of 3. accurate extrapolation. ScienceDaily. Retrieved March 7, 2019 from www.sciencedaily.com/releases/ 2018/07/180712123938.htm
  • Robert Kwiatkowski, Hod Lipson. Task-agnostic self-modeling machines. Science Robotics, 2019; 4 (26): 4. eaau9354 DOI: 10.1126/scirobotics.aau9354
  • Columbia University School of Engineering and Applied Science. (2019, January 30). Engineers create 5. a robot that can 'imagine' itself. ScienceDaily. Retrieved March 7, 2019 from www.sciencedaily.com/releases/2019/01/190130175621.htm
  • Georgia Institute of Technology. (2017, June 14). Robot uses deep learning and big data to write 6. and play its own music. ScienceDaily. Retrieved March 7, 2019 from www.sciencedaily.com/releases/2017/06/170614120407.htm
  • Salma Kassem, Alan T. L. Lee, David A. Leigh, Vanesa Marcos, Leoni I. Palmer, Simone Pisano. Stereodivergent 7. synthesis with a programmable molecular machine. Nature, 2017; 549 (7672): 374 DOI: 10.1038/nature23677
  • University of Manchester. (2017, September 20). World's first 'molecular robot' capable of building molecules. 8. ScienceDaily. Retrieved March 7, 2019 from www.sciencedaily.com/releases/2017/09/170920131744.htm
  • Jonathan Kanevsky, Jason Corban, Richard Gaster, Ari Kanevsky, Samuel Lin, MirkoGilardino. Big Data and 9. Machine Learning in Plastic Surgery. Plastic and Reconstructive Surgery, 2016; 137 (5): 890e DOI: 10.1097/PRS.0000000000002088
  • Wolters Kluwer Health. (2016, April 29). 'Machine learning' may contribute to new advances in plastic surgery. 10. ScienceDaily. Retrieved March 6, 2019 from www.sciencedaily.com/releases/2016/04/160429192812.htm