Path Tracking of an Underwater Snake Robot and Locomotion Efficiency Optimization Based on Improved Pigeon-Inspired Algorithm

This paper considers the tracking control of curved paths for an underwater snake robot, and investigates the methods used to improve energy efficiency. Combined with the path-planning method based on PCSI (parametric cubic-spline interpolation), an improved LOS (light of sight) method is proposed to design the controller and guide the robot to move along the desired path. The evaluation of the energy efficiency of robot locomotion is discussed. In particular, a pigeon-inspired optimization algorithm improved by quantum rules (QPIO) is proposed for dynamically selecting the gait parameters that maximize energy efficiency. Simulation results show that the proposed controller enables the robot to accurately follow the curved path and that the QPIO algorithm is effective in improving robot energy efficiency.

A Muscle-Driven Mechanism for Locomotion of Snake-Robots

This paper presents the concept of muscle-driven locomotion for planar snake robots, which combines the advantages of both rigid and soft robotic approaches to enhance the performance of snake robot locomotion. For this purpose, two adjacent links are connected by a pair of pneumatic artificial muscles wherein an alternate actuation of these soft actuators causes a rotational motion at the connecting joints. The muscle-based actuated linkage mechanism, as a closed six-linkage mechanism, was designed and prototyped. The linear motion and force generation of the pneumatic artificial muscle was experimentally characterized using isotonic and isometric contraction experiments. A predictive model was developed based on the experimental data to describe the relationship between the force–length–pressure of the PAMs. Additionally, the muscle-driven mechanism was kinematically and dynamically characterized based on both theoretical and experimental studies. The experimental data generally agreed with our model’s results and the generated joint angle and torque were comparable to the current snake-like robots. A skx-link planar snake robot with five joints, five pairs of antagonistic muscles, and an associated pneumatic controller was prototyped and examined for simple movements on a straight-line. We demonstrated the muscle-driven locomotion of the six-link snake robot, and the results show the feasibility of using the proposed mechanism for future explorations of snake robot locomotion.

NeuroVis: Real-Time Neural Information Measurement and Visualization of Embodied Neural Systems

Understanding the real-time dynamical mechanisms of neural systems remains a significant issue, preventing the development of efficient neural technology and user trust. This is because the mechanisms, involving various neural spatial-temporal ingredients [i.e., neural structure (NS), neural dynamics (ND), neural plasticity (NP), and neural memory (NM)], are too complex to interpret and analyze altogether. While advanced tools have been developed using explainable artificial intelligence (XAI), node-link diagram, topography map, and other visualization techniques, they still fail to monitor and visualize all of these neural ingredients online. Accordingly, we propose here for the first time “NeuroVis,” real-time neural spatial-temporal information measurement and visualization, as a method/tool to measure temporal neural activities and their propagation throughout the network. By using this neural information along with the connection strength and plasticity, NeuroVis can visualize the NS, ND, NM, and NP via i) spatial 2D position and connection, ii) temporal color gradient, iii) connection thickness, and iv) temporal luminous intensity and change of connection thickness, respectively. This study presents three use cases of NeuroVis to evaluate its performance: i) function approximation using a modular neural network with recurrent and feedforward topologies together with supervised learning, ii) robot locomotion control and learning using the same modular network with reinforcement learning, and iii) robot locomotion control and adaptation using another larger-scale adaptive modular neural network. The use cases demonstrate how NeuroVis tracks and analyzes all neural ingredients of various (embodied) neural systems in real-time under the robot operating system (ROS) framework. To this end, it will offer the opportunity to better understand embodied dynamic neural information processes, boost efficient neural technology development, and enhance user trust.

Evolving Multimodal Robot Behavior via Many Stepping Stones with the Combinatorial Multi-Objective Evolutionary Algorithm

An important challenge in reinforcement learning is to solve multimodal problems, where agents have to act in qualitatively different ways depending on the circumstances. Because multimodal problems are often too difficult to solve directly, it is often helpful to define a curriculum, which is an ordered set of sub-tasks that can serve as the stepping stones for solving the overall problem. Unfortunately, choosing an effective ordering for these subtasks is difficult, and a poor ordering can reduce the performance of the learning process. Here, we provide a thorough introduction and investigation of the Combinatorial Multi-Objective Evolutionary Algorithm (CMOEA), which allows all combinations of subtasks to be explored simultaneously. We compare CMOEA against three algorithms that can similarly optimize on multiple subtasks simultaneously: NSGA-II, NSGA-III and ϵ-Lexicase Selection. The algorithms are tested on a function-optimization problem with two subtasks, a simulated multimodal robot locomotion problem with six subtasks and a simulated robot maze navigation problem where a hundred random mazes are treated as subtasks. On these problems, CMOEA either outperforms or is competitive with the controls. As a separate contribution, we show that adding a linear combination over all objectives can improve the ability of the control algorithms to solve these multimodal problems. Lastly, we show that CMOEA can leverage auxiliary objectives more effectively than the controls on the multimodal locomotion task. In general, our experiments suggest that CMOEA is a promising algorithm for solving multimodal problems.

A study of ladder-like silk foothold for the locomotion of bagworms

While walking on horizontal substrates, caterpillars skilfully engage all their legs, including three pairs of thoracic legs and a maximum of five pairs of prolegs, to move in a flexible wave-like motion. Such locomotory behaviours, represented by ‘crawling’ and ‘inching’ motions, have widely inspired the development of locomotion systems in soft robotics. However, bagworms are unable to use their prolegs for walking because these are always accommodated in a portable bag; thus, they are unable to walk using such general locomotory behaviours. Indeed, how they walk with only three pairs of thoracic legs is unknown at present. In this study, we show that bagworms construct a ladder-like foothold using their silk to walk without using prolegs. This enables them to walk not only on horizontal floor surfaces but also on wall and ceiling surfaces, even those with slippery or smooth surfaces. They construct the foothold by spinning a continuous silk thread in a zigzag manner and controlling the discharge of adhesive to attach the folded parts of the silk to a substrate. Discovery of this elaborate silk utilisation technique offers fresh insights into the diversity of silk use in lepidopteran larvae and provides potential designs for robot locomotion systems.