Intelligence by Design
Exploration of Mechanical Intelligence in Soft Robotics
V.G. Kortman (TU Delft - Mechanical Engineering)
J. Jovanova – Promotor (TU Delft - Mechanical Engineering)
A. Sakes – Promotor (TU Delft - Mechanical Engineering)
P. Breedveld – Promotor (TU Delft - Mechanical Engineering)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
It is currently insufficiently understood how soft robots can be designed for mechanical intelligence. Building on this, the main goal of this thesis is to investigate mechanical intelligence in soft robots, inspired by nature, with the potential to enhance functionality beyond structured environments. Constrained and hard‑to‑reach environments are used as representative application domains, as they place strong demands on robotic embodiment. This means they could benefit from mechanically intelligent designs. To investigate this idea, this thesis focuses on three fundamental robotic interactions: (1) intelligent gripping, (2) intelligent movement and (3) intelligent transport. In each case, the aim is to design bodies that behave intelligently by design. Through various studies on gripping, movement and transport systems, mechanical intelligence is shown to enhance the capabilities of soft robots exploiting their geometry, material composition, local mechanical interactions and integrated actuation. These studies include safe, adaptive grippers functioning across various substrates, artificial muscles that generate complex motions with one simple input and transport mechanisms that function independently of stiffness or geometry. These examples collectively illustrate that mechanical intelligence can be a powerful way to achieve reliable, scalable and context‑aware soft robotic behavior.