Two degree-of-freedom robotic eye: design, modeling, and learning-based control in foveation and smooth pursuit
Source abstract
Abstract
Abstract With increasing ocular motility disorders affecting human eye movement, the need to understand the biomechanics of the human eye rises constantly. A robotic eye system that physically mimics the human eye can serve as a useful tool for biomedical researchers to obtain an intuitive understanding of the functions and defects of the extraocular muscles and the eye. This paper presents the design, modeling, and control of a two degree-of-freedom (2-DOF) robotic eye, driven by artificial muscles, in particular, made of super-coiled polymers (SCPs). Considering the highly nonlinear dynamics of the robotic eye system, this paper applies deep deterministic policy gradient (DDPG), a machine learning algorithm to solve the control design problem in foveation and smooth pursuit of the robotic eye. To the best of our knowledge, this paper presents the first modeling effort to establish the dynamics of a robotic eye driven by SCP actuators, as well as the first control design effort for robotic eyes using a DDPG-based control strategy. A linear quadratic regulator-type reward function is proposed to achieve a balance between system performances (convergence speed and tracking accuracy) and control efforts. Simulation results are presented to demonstrate the effectiveness of the proposed control strategy for the 2-DOF robotic eye.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Control and Dynamics of Mobile Robots · Zebrafish Biomedical Research Applications · Adaptive Control of Nonlinear Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (28)
Show source-provided references
1. Spaeth · 2011 · 462
2. Ichhpujani · 2015 · 841
3. Orbit 1.8 gaze mechanics simulation
4. Design and control of 3-DoF spherical parallel mechanism robot eyes inspired by the binocular vestibule-ocular reflex10.1007/s10846-014-0078-x ↗
5. Simulation and design of 3-DOF eye mechanism using listing’s law
6. Models for the design of bioinspired robot eyes10.1109/tro.2007.906270 ↗
7. Mac-eye: a tendon driven fully embedded robot eye
8. Design of the robot-cub (icub) head
9. Agile eye: a high-performance three-degree-of-freedom camera-orienting device
10. A biomimetic eye with a hemispherical perovskite nanowire array retina10.1038/s41586-020-2285-x ↗
11. Design and kinematic analysis of a novel humanoid robot eye using pneumatic artificial muscles10.1016/s1672-6529(08)60034-7 ↗
12. Dynamic modeling of mckibben pneumatic artificial muscles for antagonistic actuation
13. Operating characteristics of antagonistic actuator with pneumatic artificial muscles10.4028/www.scientific.net/amm.616.101 ↗
14. On the control and properties of supercoiled polymer artificial muscles10.1109/tro.2017.2664885 ↗
15. Foveation control of a robotic eye using deep reinforcement learning
16. Cannata · 2007
17. Biomimetic eye-neck coordination
18. Human-level control through deep reinforcement learning10.1038/nature14236 ↗
19. Continuous control with deep reinforcement learning
20. Project L.E.N.S—a robotic eye system using artificial muscles
21. Remington · 2012 · vol 244 · 184
22. 3D kinematics using dual quaternions: theory and applications in neuroscience10.3389/fnbeh.2013.00007 ↗
23. Geometry and control of human eye movements10.1109/tac.2006.887902 ↗
24. Modeling and inverse compensation of hysteresis in supercoiled polymer artificial muscles10.1109/lra.2017.2651401 ↗
25. Forsyth · 2012 · p 203
26. The normal visual field on the Humphrey field analyzer10.1159/000309679 ↗
27. Comparison of visual field sensitivities between the medmont automated perimeter and the Humphrey field analyser10.1111/j.1442-9071.2010.02246.x ↗
28. Weighted random sampling with a reservoir10.1016/j.ipl.2005.11.003 ↗