Simulated Despondency for Robots in Distress

It is widely accepted that increased human interaction with natural systems is responsible for complex environmental issues, with most current thinking centered on the provision of advanced technological solutions. One response emerging from current bioinspired robotics research proposes artificial neural networks (ANNs) enhanced with artificial hormones for increased performance and efficiency. Here the authors discuss their artistic project concept, developed in collaboration with a bioinspired artificial life lab, considering the affordance of emotional robotics to develop despondency in the field.

Learning Based Speed Control of Soft Robotic Fish

Bioinspired robotics takes advantage of biological systems in nature for morphology, action and perception to build advanced robots of compelling performance and wide application. This paper focuses on the design, modeling and control of a bioinspired robotic fish. The design utilizes a recently-developed artificial muscle named super coiled polymer for actuation and a soft material (silicone rubber) for building the robot body. The paper proposes a learning based speed control design approach for bioinspired robotic fish using model-free reinforcement learning. Based on a mathematically tractable dynamic model derived by approximating the robotic fish with a three-link robot, speed control simulation is conducted to demonstrate and validate the control design method. Exampled with a three-link reduced-order dynamic system, the proposed learning based control design approach is applicable to many and various complicated bioinspired robotic systems.

Enabling a Freely Accessible Open Source Remotely Controlled Robotic Articulator with a Neuro-Inspired Control Algorithm

Internet-enabled technologies for robotics education are gaining importance as online platforms promoting skill training. Understanding the use and design of robotics are now introduced at university undergraduate levels, but in developing economies establishing usable hardware and software platforms face several challenges like cost, equipment etc. Remote labs help providing alternatives to some of the challenges. We developed an online laboratory for bioinspired robotics using a low-cost 6 degree-of-freedom robotic articulator with a neuro-inspired controller. Cerebellum-inspired neural network algorithm approximates forward and inverse kinematics for movement coordination. With over 210000 registered users, the remote lab has been perceived as an interactive online learning tool and a practice platform. Direct feedback from 60 students and 100 university teachers indicated that the remote laboratory motivated self-organized learning and was useful as teaching material to aid robotics skill education.

Computational Analysis of Undulatory Batoid Motion for Underwater Robotic Propulsion

Underwater fish of the class Batoidea, commonly known as rays and skates, use large cartilaginous wings to propel themselves through the water. This motion is of great interest in bioinspired robotics as an alternative propulsion mechanism. Prior research has focused primarily on the oscillating kinematics used by some species which resembles flapping; this study investigates undulatory motion induced by propagating sinusoidal waves along the fin. An analytical model of undulatory kinematics is presented and correlated with biological literature, and the model is then simulated via unsteady computational fluid dynamics and multiparticle collision dynamics. A bioinspired robot, Batoid Underwater Robotics Testbed (BURT), was developed to test the kinematics of the undulating propulsion system proposed. Finally, BURT was utilized as a platform to investigate engineering challenges in undulating Batoid robotics.