A Survey on Soft Robot Adaptability: Implementations, Applications, and Prospects

TL;DR

Soft robotics leverage intrinsic compliance to enable high adaptability, categorized as external (environmental and object interactions) and internal (robustness to hardware variations and cross-platform transfer). The paper surveys design, sensing, and control approaches that realize this adaptability and analyzes applications in surgery, wearables, locomotion, and manipulation, highlighting architectural strategies for stiffness modulation, robust sensing, and learning-based control. It emphasizes spatial, temporal, and dynamic compliance regulation in design, transferable sensing calibration, and model-based and model-free control methods, including hybrid and embodied-intelligence-inspired approaches. The work underscores the practical impact of adaptable soft robots and outlines modular, multi-agent, and cross-domain strategies as key directions to achieve safe, scalable, and versatile systems in real-world settings.

Abstract

Soft robots, compared to rigid robots, possess inherent advantages, including higher degrees of freedom, compliance, and enhanced safety, which have contributed to their increasing application across various fields. Among these benefits, adaptability is particularly noteworthy. In this paper, adaptability in soft robots is categorized into external and internal adaptability. External adaptability refers to the robot's ability to adjust, either passively or actively, to variations in environments, object properties, geometries, and task dynamics. Internal adaptability refers to the robot's ability to cope with internal variations, such as manufacturing tolerances or material aging, and to generalize control strategies across different robots. As the field of soft robotics continues to evolve, the significance of adaptability has become increasingly pronounced. In this review, we summarize various approaches to enhancing the adaptability of soft robots, including design, sensing, and control strategies. Additionally, we assess the impact of adaptability on applications such as surgery, wearable devices, locomotion, and manipulation. We also discuss the limitations of soft robotics adaptability and prospective directions for future research. By analyzing adaptability through the lenses of implementation, application, and challenges, this paper aims to provide a comprehensive understanding of this essential characteristic in soft robotics and its implications for diverse applications.

Figures (4)

• Figure 1: (A) Adaptability in soft robotics can be categorized into external and internal adaptability. External adaptability refers to a soft robot’s ability to adjust to dynamic and varied environments. Internal adaptability refers to the ability of software to remain effective across soft robots with different parameters or configurations. (From kim2024extremelytrumic2021adaptivedel2024growingpolzin2025roboticruotolo2021grasping; used with permission) (B) The classification of external and internal adaptability: Passive adaptability refers to the robot’s natural response to environmental changes and object interactions, primarily enabled by its inherent material properties or compliant structural design. In contrast, active adaptability involves deliberate, control-driven behaviors guided by intelligent algorithms to dynamically respond to external variations. Internal adaptability encompasses the capacity of adaptive algorithms to maintain performance despite hardware variations resulting from material aging or manufacturing tolerances and to transfer effectively across robots with differing physical parameters or material compositions.
• Figure 2: The number of publications containing the keywords "Soft Robot" (red) and "Soft Robot Adaptability" (dashed red), along with their ratio (blue). The data is based on search results from the Scopus database, limited to article title, abstract, and keywords. The figure illustrates the growing research interest in soft robotics, along with the increasing emphasis on adaptability as a key characteristic of soft robots.
• Figure 3: Robot adaptability based on the body: Compliance regulation and Embodied Intelligence. Global soft crawling robot shepherd2011multigait, Soft arm with varied spatial compliance guan2023trimmed, variable stiffness base on phase change materials hwang2022shape and antagonistic actuation bruder2023increasing, fast crawling based on bistable spine tang2020leveraging, auto gait based on ring oscillators drotman2021electronics; All figures used with permission.
• Figure 4: Key areas for adaptability in the sensory system of a soft robotic manipulator.