Additive manufacturing is enabling soft robots with increasingly complex geometries, creating a demand for sensing solutions that remain compatible with single-material, one-step fabrication. Optical soft sensors are attractive for monolithic printing, but their performance is often degraded by uncontrolled light propagation (ambient coupling, leakage, scattering), while common miti- gation strategies typically require multimaterial interfaces. Here, we present an approach for 3D printed soft optical sensing (SOLen), in which a printed lens is placed in front of an emitter within a Y-shaped waveguide. The sensing mechanism relies on deformation-induced lens rotation and focal-spot translation, redistributing optical power between the two branches to generate a differential output that encodes both motion direction and amplitude. An acrylate polyurethane resin was modified with lauryl acrylate to improve compliance and optical transmittance, and single-layer optical characterization was used to derive wavelength-dependent refractive index and transmittance while minimizing DLP layer-related artifacts. The measured refractive index was used in simulations to design a lens profile for a target focal distance, which was then printed with sub-millimeter fidelity. Rotational tests demonstrated reproducible branch-selective signal switching over multiple cycles. These results establish a transferable material-to-optics workflow for soft optical sensors with lens with new functionalities for next-generation soft robots
Figures & tables
Figure 1: (A) Acrylate soft polyurethane was 3D printed via UV-based DLP to fabricate (B) SOLen sensor, with post-assembled emitter and photoreceiver. (C) Microscope image of the 3D printed lens, which is the basis of the (D) working principle of the SOLen. On the left, the sensor in the undeformed state, on the right, the sensor under rotation. The focal spot point moves with the lens, guiding the light.
Figure 2: UV-Vis spectra of (A) Transmittance T and (B) Absorbance A of one-layer of ma-PU (C) the analytical refractive index, measured by modeling the printed layer as a slab of thickness h. λ is the wavelength of the incident light, and R is the reflectance.
Figure 3: (A). Graph three different lens profiles obtained with different RI parameters in the Cartesian oval’s equation. (B). Zoom on the lens (RI=1.44) during the simulation. (C). Simulation after the lens rotation of −3∘ . (D). Simulation after the lens rotation of +3∘ . (E-G) Printed lens microscope images compared with the Cartesian ovals for the different refractive index (RI in the figure).
Figure 4: Figure 4. Experimental validation of lens-driven focal switching in the Y-shaped optical sensor. (A) Initial configuration of the test, where the emitter is aligned with the centerline between the two branches, placing the focal spot between ReceiverL and ReceiverR. (B) Right-rotation state (-3°), achieved by tilting the emitter/lens assembly to shift the focal spot into the right branch toward ReceiverR. (C) Left-rotation state (+3°), where the focal spot is redirected into the left branch toward ReceiverL. (D) Measured receiver signals plotted as voltage versus rotation angle for three sensors equipped with lenses over five consecutive cycles (mean curve with shaded standard deviation). A clear intensity redistribution is observed between the two receivers: during right rotation, ReceiverR shows a voltage decrease (higher intensity) while ReceiverL shows a voltage increase (lower intensity), with the opposite trend during left rotation.
Figure 5: Conceptual example of SOLen integration in a monolithic soft robot architecture. Selected structural elements act as waveguides, while printed lenses focus and steer light toward predefined directions to enable distributed sensing.
All authors are with the MIT Computer Science & Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar St, Cambridge, MA 02139, USA.