On human-in-the-loop optimization of human-robot interaction

• 成果类型: Review
• 署名作者: Slade, Patrick; Atkeson, Christopher; Donelan, J. Maxwell; Houdijk, Han; Ingraham, Kimberly A.; Kim, Myunghee; Kong, Kyoungchul; Poggensee, Katherine L.; Riener, Robert; Steinert, Martin; Zhang, Juanjuan; Collins, Steven H.
• 署名单位: Harvard University; Carnegie Mellon University; Simon Fraser University; University of Groningen; University of Washington; University of Washington Seattle; University of Illinois System; University of Illinois Chicago; University of Illinois Chicago Hospital; Korea Advanced Institute of Science & Technology (KAIST); Erasmus University Rotterdam; Erasmus MC; Delft University of Technology; Swiss Federal Institutes of Technology Domain; ETH Zurich; University of Geneva; University of Zurich; Norwegian University of Science & Technology (NTNU); Nankai University; Stanford University
• 刊物名称: Nature
• ISSN/ISSBN: 0028-6236
• DOI: 10.1038/s41586-024-07697-2
• 发表日期: 2024-09-26
• 页码: 779-788
• 关键词: exoskeleton assistance; metabolic cost; human walking; energy-cost; knee; adaptation; efficient; selection; POWER; work

摘要

From industrial exoskeletons to implantable medical devices, robots that interact closely with people are poised to improve every aspect of our lives. Yet designing these systems is very challenging; humans are incredibly complex and, in many cases, we respond to robotic devices in ways that cannot be modelled or predicted with sufficient accuracy. A new approach, human-in-the-loop optimization, can overcome these challenges by systematically and empirically identifying the device characteristics that result in the best objective performance for a specific user and application. This approach has enabled substantial improvements in human-robot performance in research settings and has the potential to speed development and enhance products. In this Perspective, we describe methods for applying human-in-the-loop optimization to new human-robot interaction problems, addressing each key decision in a variety of contexts. We also identify opportunities to develop new optimization techniques and answer underlying scientific questions. We anticipate that our readers will advance human-in-the-loop optimization and use it to design robotic devices that truly enhance the human experience. A new approach to designing robotic systems that interact closely with people, called human-in-the-loop optimization, can improve human-robot interaction, but many important research questions remain before it can reach its full potential.