Towards using Musculoskeletal Models for Intelligent Control of Physically Assistive Robots

The Printing House
Publication Type:
Conference Proceeding
International Conference of the IEEE Engineering in Medicine and Biology Society, 2011, pp. 8162 - 8165
Issue Date:
Full metadata record
Files in This Item:
Filename Description SizeFormat
2010005486.pdf549.3 kBAdobe PDF
With the increasing number of robots being developed to physically assist humans in tasks such as rehabilitation and assistive living, more intelligent and personalized control systems are desired. In this paper we propose the use of a musculoskeletal model to estimate the strength of the user, from which information can be utilized to improve control schemes in which robots physically assist humans. An optimization model is developed utilizing a musculoskeletal model to estimate human strength in a specified dynamic state. Results of this optimization as well as methods of using it to observe muscle-based weaknesses in task space are presented. Lastly potential methods and problems in incorporating this model into a robot control system are discussed.
Please use this identifier to cite or link to this item: