I first found a paper in IEEE that I thought was interesting: Soft, Wearable Robotics and Haptics: Technologies, Trends, and Emerging Applications [1]. This paper discussed current and future technologies for wearable soft robotics technologies considering factors such as functionality, wearability, and ergonomics. Some of these domains include rehabilitation and assistive devices, haptic interfaces, fashion, and design. They list various materials, fabrication methods, and sensing and actuation methods.
From there, I found another paper citing this root paper called Assisting Forearm Function in Children With Movement Disorders via A Soft Wearable Robot With Equilibrium-Point Control [2]. Similar to the root paper, this research focuses on using soft robotics in assistive devices and conducted research with 2 invidiuals to test their mobility using the robot. While the assistive device reduced the amount of effort needed to complete a task on the user’s end, it also increased error. For future research, this could be addressed by improving the device’s coarse nature.
From the same root paper, there was a similar paper discussing motion control with soft robotics. The paper (Towards Adaptive Continuous Control of Soft Robotic Manipulator using Reinforcement Learning) [3], proposes a deep deterministic policy gradient (DDPG)-based control system for the continuous task-space manipulation of soft robots.
[1] M. Zhu, S. Biswas, S. I. Dinulescu, N. Kastor, E. W. Hawkes and Y. Visell, “Soft, Wearable Robotics and Haptics: Technologies, Trends, and Emerging Applications,” in Proceedings of the IEEE, vol. 110, no. 2, pp. 246-272, Feb. 2022, doi: 10.1109/JPROC.2021.3140049.
[2] Realmuto J, Sanger TD. Assisting Forearm Function in Children With Movement Disorders via A Soft Wearable Robot With Equilibrium-Point Control. Front Robot AI. 2022 Jun 15;9:877041. doi: 10.3389/frobt.2022.877041. PMID: 35783026; PMCID: PMC9240630.
[3] Y. Li, X. Wang and K. -W. Kwok, “Towards Adaptive Continuous Control of Soft Robotic Manipulator using Reinforcement Learning,” 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan, 2022, pp. 7074-7081, doi: 10.1109/IROS47612.2022.9981335.