The phenomenon of the “traveling wave,” commonly observed in various organisms, involves a wave that propagates along the body, serving as a locomotion mechanism. Particularly, in aquatic environments, organisms such as fish and cetaceans utilize traveling waves to propel themselves through water, minimizing fluid drag and maximizing movement efficiency. Inspired by nature, robotics has extensively explored replicating such locomotion strategies. This work presents a fish robot with an innovative magnetic transmission system. The mechanism transforms the unidirectional rotation of a single motor into an oscillatory, phase-shifted movement across the modules of the kinematic chain, generating a traveling wave along the body. The robot's design and functionality are detailed, highlighting advancements in bio-inspired robotics for underwater applications, such as efficient and non-invasive monitoring and exploration of marine ecosystems. The fish robot achieved a swimming speed of approximately 2 body lengths per second (BL/s) with a tail-beat frequency of 3.24 Hz and a minimum Cost of Transport (CoT) of$5.33 ~\mathrm{J} /(\text{kg} \cdot \mathrm{m})$. Biomimetic robotics can play a key role in sustainable aquafarming, biodiversity conservation, and animal-robot interaction research, offering the potential to minimize ecosystem disruption and advance marine science.

Animal behavior serves as a reliable indicator of the adaptation of organisms to their environment and their overall well-being. Through rigorous observation of animal actions and interactions, researchers and observers can glean valuable insights into diverse facets of their lives, encompassing health, social dynamics, ecological relationships, and neuroethological dimensions. Although state-of-the-art deep learning models have demonstrated remarkable accuracy in classifying various forms of animal data, their adoption in animal behavior studies remains limited. This survey article endeavors to comprehensively explore deep learning architectures and strategies applied to the identification of animal behavior, spanning auditory, visual, and audiovisual methodologies. The survey categorizes techniques into pose estimation-based and non-pose estimation-based methods, analyzing their applications, effectiveness, and limitations. Furthermore, the manuscript scrutinizes extant animal behavior datasets, offering a detailed examination of the principal challenges confronting this research domain. The article culminates in a comprehensive discussion of key research directions within deep learning that hold potential for advancing the field of animal behavior studies.

Underwater monitoring is extremely complex due to the lack of a global localization system, limited communication and environmental factors such as turbidity and darkness that limit visibility, affecting control and situational awareness. Typically, monitoring relies on a single autonomous underwater vehicle (AUV) or a set of independent AUVs; techniques which are prone to failure as they rely only on onboard odometry and sensors, making missions vulnerable to malfunctions, damage, and noise. To address these challenges, we propose a Multi-Agent Reinforcement Learning (MARL) framework to enable cooperation among multiple AUVs, mitigating the limitations of the underwater environment. Our in-silico solution focuses on a group of robots learning a strategy to follow a partially hidden underwater pipe without global localization, while dealing with environmental disturbances affecting sensors and actuators. The numerosity of the agents, and most importantly their collaboration, helps overcome underwater visibility constraints. By sharing relative position information of neighboring agents with respect to the pipe, navigation is improved. By introducing quantitative measures for pipe exploration, we show that cooperation significantly enhances system performance compared to independent agents. Emerging collaboration among robots allows the swarm to complete pipe inspections faster and more efficiently than non-cooperative baseline models of non-interacting agents, even under extremely reduced visibility scenarios. Moreover, single agents also benefit from cooperation, learning effective policies more quickly and covering a longer portion of the pipe. Finally, our model guarantees explainability. We analyze learned strategies and provide a visualization method that allows the interpretation of the learned policies. • Reinforcement learning is applied to pipeline following by underwater robotic agent. • In conditions of poor visibility, a single agent is not able to complete the mission. • In contrast, multi-agent team completes this task using reinforcement learning. • Swarm collaboration enables faster and more efficient task completion. • Collaboration enables agents develop more efficient individual strategies.

Soft robots show compliance and have infinite degrees of freedom. Thanks to these properties, such robots can be leveraged for surgery, rehabilitation, biomimetics, unstructured environment exploring, and industrial grippers. In this case, they attract scholars from a variety of areas. However, nonlinearity and hysteresis effects also bring a burden to robot modeling. Moreover, following their flexibility and adaptation, soft robot control is more challenging than rigid robot control. In order to model and control soft robots, a large number of data-driven methods are utilized in pairs or separately. This review first briefly introduces two foundations for data-driven approaches, which are physical models and the Jacobian matrix, then summarizes three kinds of data-driven approaches, which are statistical method, neural network, and reinforcement learning. This review compares the modeling and controller features, e.g., model dynamics, data requirement, and target task, within and among these categories. Finally, we summarize the features of each method. A discussion about the advantages and limitations of the existing modeling and control approaches is presented, and we forecast the future of data-driven approaches in soft robots. A website (https://sites.google.com/view/23zcb) is built for this review and will be updated frequently.Note to Practitioners—This work is motivated by the need for a review introducing soft robot modeling and control methods in parallel. Modeling and control play significant roles in robot research, and they are challenging especially for soft robots. The nonlinear and complex deformation of such robots necessitates specific modeling and control approaches. We introduce the state-of-the-art data-driven methods and survey three approaches widely utilized. This review also compares the performance of these methods, considering some important features like data amount requirement, control frequency, and target task. The features of each approach are summarized, and we discuss the possible future of this area.

Deformable object manipulation is a challenging problem due to its complex deformable properties. With the development of artificial intelligence, learning-based methods have shown outstanding performance in robotic manipulation. Previous works have investigated the manipulation of deformable objects via Reinforcement Learning (RL) in simulation. However, they approximate object deformation with particles, using particle states as observations, which are unavailable in reality. To address these issues, we utilize Vision-Based Tactile Sensors (VBTSs) as the end-effector to manipulate and observe the deformable objects. In this work, we develop a new contact simulation environment for deformable objects, including elastic, plastic, and elastoplastic. We utilize RL strategies and expert demonstrations to train agents in the simulation. Finally, we build a real experimental platform to complete the sim-to-real tasks and robustness testing. Our work introduces an innovative strategy that utilizes high-resolution VBTSs for contact simulation and manipulation of deformable objects. The experimental results show superior performances of deformable object manipulation with the proposed method.

In this article, we introduce the Game Boy Learning Environment (GLE), an innovative suite based on Nintendo Game Boy games, crafted to advance and evaluate deep reinforcement learning algorithms on rich and varied gameplay tasks. GLE offers a comprehensive selection of eleven Game Boy environments, spanning nine distinct titles. These environments represent a significant leap in complexity compared to previous endeavors, like the Arcade Learning Environment, presenting challenges for reinforcement learning like intricate long-term planning, strategic foresight, and hierarchical decision-making, posing substantial difficulties even for proficient human players. We delineate the spectrum of available environments and furnish initial baseline results obtained through the development and assessment of intelligent agents, employing established AI methodologies to address individual levels or subtasks within these environments. All software is openly accessible to the public viahttps://github.com/edofazza/GameBoyLearningEnvironment.

Modular soft robot arms (MSRAs) are composed of multiple modules connected in a sequence, and they can bend at different angles in various directions. This capability allows MSRAs to perform more intricate tasks than single-module robots. However, the modular structure also induces challenges in accurate planning and control. Nonlinearity and hysteresis complicate the physical model, while the modular structure and increased DOFs further lead to cumulative errors along the sequence. To address these challenges, we propose a versatile configuration space planning and control strategy for MSRAs, named$S2C2A$(State to Configuration to Action). Our approach formulates an optimization problem,$S2C$(State to Configuration planning), which integrates various loss functions and a forward model based on biLSTM to generate configuration trajectories based on target states. A configuration controller$C2A$(Configuration to Action control) based on biLSTM is implemented to follow the planned configuration trajectories, leveraging only inaccurate internal sensing feedback. We validate our strategy using a cable-driven MSRA, demonstrating its ability to perform diverse offline tasks such as position and orientation control and obstacle avoidance. Furthermore, our strategy endows MSRA with online interaction capability with targets and obstacles. Future work focuses on addressing MSRA challenges, such as more accurate physical models.

Endoscopic Submucosal Dissection (ESD) is a minimally invasive procedure designed to remove precancerous and cancerous lesions from the gastrointestinal (GI) tract. Given the GI tract’s tortuous and narrow shape, along with the need for varied movements during dissection, this requires highly flexible and compact instruments, making flexible continuum robots suitable candidates. In this paper, we propose a novel two-segment continuum robot system named DESectBot, featuring a diameter of 5.5 mm and a total length of the active bending module of 48 mm, while the robot’s total length exceeds 1 m. We designed a novel joint combination structure called the spatial cross-curved disk skeleton for the robot, which addresses the mechanical coupling problem between flexible robot actuators. The DESectBot boasts six degrees of freedom, and its kinematic modeling has been derived and utilized in the closed-loop control of the DESectBot. The validation of the DESectBot was conducted through a two-stage test: first, the decoupling performance of the DESectBot was validated. The results show that when one active bending segment bends, the other segment remains almost uninfluenced, with a maximum variation of 1.15 degrees, demonstrating the robot’s effective decoupling capability. Secondly, the accuracy of DESectBot was validated through trajectory-following experiments. The results reveal that the average tracking error for both trajectories is less than 2 mm, and the maximum tracking error is below 2.5 mm. Taking marking, one of the ESD procedures with a 5mm tolerance, as an example, the DESectBot has the potential to be utilized for ESD procedure.

Biomimetic robotics can help support underwater exploration and monitoring while minimizing ecosystem distur-bance. It also has potential applications in sustainable aqua-farming management, biodiversity preservation, and animal-robot interaction studies. This study proposes a bio-inspired control strategy for an underactuated robotic fish, which utilizes a single DC motor to drive a mechanism that converts the motor's oscillating motion into an oscillatory motion of the robotic fishtail through a magnetic coupling and a wire-driven system. The proposed control strategy for the robotic fish is based on central pattern generators (CPGs) and incorporates proprioceptive sensory feedback. The torque exerted on the fishtail is adjusted based on its position, allowing for increased or decreased body speed and steering with different angular speeds and radii of curvature despite the underactuated design. The robotic fish can vary the swimming speed of 0.08 body lengths per second (BL/s) with a related change in the tail-beating frequency up to 2.3 Hz, and it can vary the steering angular speed in the range of 0.08 rad/s with a relative change in the curvature radius of 0.25 m. The controller can adapt to changes in tail structure, weight, or the surrounding environment based on the proprioceptive feedback. Design changes to the modular design can improve speed and steering performances, maintaining the control strategy developed.

Prokaryotic flagellum is considered as the only known example of a biological “wheel,” a system capable of converting the action of rotatory actuator into a continuous propulsive force. For this reason, flagella are an interesting case study in soft robotics and they represent an appealing source of inspiration for the design of underwater robots. A great number of flagellum-inspired devices exists, but these are all characterized by a size ranging in the micrometer scale and mostly realized with rigid materials. Here, we present the design and development of a novel generation of macroscale underwater propellers that draw their inspiration from flagellated organisms. Through a simple rotatory actuation and exploiting the capability of the soft material to store energy when interacting with the surrounding fluid, the propellers attain different helical shapes that generate a propulsive thrust. A theoretical model is presented, accurately describing and predicting the kinematic and the propulsive capabilities of the proposed solution. Different experimental trials are presented to validate the accuracy of the model and to investigate the performance of the proposed design. Finally, an underwater robot prototype propelled by four flagellar modules is presented.

Flagellated micro-organism are regarded as excellent swimmers within their size scales. This, along with the simplicity of their actuation and the richness of their dynamics makes them a valuable source of inspiration to design continuum, self-propelled underwater robots. Here we introduce a soft, flagellum-inspired system which exploits the compliance of its own body to passively attain a range of geometrical configurations from the interaction with the surrounding fluid. The spontaneous formation of stable helical waves along the length of the flagellum is responsible for the generation of positive net thrust. We investigate the relationship between actuation frequency and material elasticity in determining the steady-state configuration of the system and its thrust output. This is ultimately used to perform a parameter identification procedure of an elastodynamic model aimed at investigating the scaling laws in the propulsion of flagellated robots.

Due to extreme and unpredictable conditions, oceanic missions are still a persistent challenge in robotics. With the aim of improving decision autonomy and robustness against unforeseen circumstances, the EU-funded CoCoRo project is developing a cognitive swarm of underwater robots. Swarm and cognition algorithms will be studied and validated with a large number of miniaturized and affordable AUVs, named Jeff, whose custom mechanical design is described in this paper. Jeff is conceived for high-mobility in 3D cluttered environments and has distributed sensors for multi-directional perception and communication. The propulsion and the buoyancy systems are designed with watertight and energetically efficient solutions to improve system reliability and energetic autonomy. The manuscript also describes the design of a docking system that allows Jeff to passively align and connect to a submerged docking station for battery charging.

Morphology, perception and locomotion are three key features highly inter-dependent in robotics. This paper gives an overview of an underwater modular robotic platform equipped with a bio-inspired electric sense. The platform is reconfigurable in the sense that it can split into independent rigid modules and vice-versa. Composed of 9 modules, the longer entity can swim like an eel over long distances, while once detached, each of its modules is efficient for small displacements with a high accuracy. Challenges are to mechanically ensure the morphology changes and to do it automatically. Electric sense is used to guide the modules during docking phases and to navigate in unknown scenes. Several aspects of the design of the robot are described and a particular attention is paid to the inter-module docking system. The feasibility of the design is assessed through experiments.

In this paper the development of a bio-robotic platform is described. The robot design exploits biomechanical and neuroscientific knowledge on the lamprey, an eel-like swimmer well studied and characterized thanks to the reduced complexity of its anatomy. The robot is untethered, has a compliant body, muscle-like high efficiency actuators, proprioceptive sensors to detect stretch and stereoscopic vision. Experiments on the platform are reported, including robust and autonomous goal-directed swimming. Extensive experiments have been possible thanks to very high energy efficiency (around five hour continuous operating) the platform is ready to be used as investigation tool for high level motor tasks.

This paper describes the design of a fast long-jumping robot conceived to move in unstructured environments through simple feed-forward control laws. Despite the apparent similarities with hopping, jumping dynamics is peculiar and involve non-trivial issues on actuation powering, energy saving and stability. The "Grillo" robot described here is a quadruped, 50-mm robot that weights about 15 grams and is suited for a long-jumping gait. Inspired by frog locomotion, a tiny motor load the springs connected to the hind limbs. At take-off, an escapement mechanism releases the loaded springs. This provides a peak power output that can exceed several times the maximum motor power. In this way, the actuation and energy systems can be significantly reduced in weight and size. On the other hand, passive dynamics is exploited by compliant forelegs, that let to partially recover the impact energy in their elastic recoil. Equipped with a 0.2W DC motor, the robot is dimensioned to achieve a forward speed of 1.5 m/s, which corresponds to about 30 body length per second.

The biomedical application this paper refers to is the neuroendoscopy of the sub-arachnoid spinal space. Such a kind of endoscopy is strongly challenging due to the tiny space to be explored and to the delicate anatomical structures which lie into it. In order to enhance the degree of safety of the endoscopic intervention, a robotic system for neuroendoscopy has been developed, so as to obtain a robot-assisted exploration which aims to lower the risks for the patient and to ease the catheter maneuvering task. This paper explains how robot sensory feedbacks can be exploited to provide the surgeon with useful information for the navigation and to implement automatic control strategies. It is described how sensory feedbacks processing can improve the safety of the operation by implementing a human-robot cooperation for the understanding of the anatomical environment and the monitoring of physiological parameters. The focus of the paper is on vision and pressure sensory feedbacks. Experimental results prove the reliability and the effectiveness of the proposed algorithms and their suitability to be employed in real time operation

This paper presents a bioinspired concept of locomotion for small autonomous robots. Scale effects in locomotion highly influence gait efficiency and in lightweight micro-robots jumping can be more energetically efficient than just walking or climbing. In addition, a jump can make the robot overcome obstacles and uneven terrains. Inspired by nature, the actuation of the proposed robot is entrusted to loaded springs. During the flight phase, energy from an electric micro-motor is collected in springs, while it is released by a click mechanism during take-off. In this way instant power delivered by rear legs (about 5 W) is much higher than the one provided by the motor (0.3 W). Passive compliant legs and low-power actuation result in light, efficient micro-robot, designed to have long autonomy for environment exploration and monitoring. In order to verify these assumptions, a quadruped prototype was developed, with two active rear limbs and passive elastic forelegs. Robot Grillo is 50 mm long and weighs about 10 grams. In conservative simulations the microrobot reaches a forward speed of 1.5 m/s, which corresponds to about 30 body length s-1

This paper introduces the main objectives of the neurobotics project aimed at designing and developing innovative hybrid bionic systems (HBSs) by fusing neuroscience and robotics. Eight different HBSs have been jointly designed and are being developed. This paper presents in detail the telepresence platform. The neurobotics artificial lamprey model has been designed to validate a number of neuroscience models and to investigate new telepresence strategies

This paper describes the development of an active clamping mechanism to be integrated into a swallowable pill for the diagnosis of the gastrointestinal (GI) tract. The clamping system allows to stop the pill in desired sites of the GI tract for long monitoring purposes. After discussing the major technical constraints, the design of the clamping system, based on FEA (Finite Element Analysis), is illustrated as well as its fabrication process. The clamping unit is actuated exploiting Shape Memory Alloys (SMA), in wires and spring configuration, and it is driven by a dedicated electrical interface. A fine tuning has been performed in order to limit the power consumption. Then a working prototype is fabricated and preliminarily tested, pointing out a capability of the grasping system over 40 g.

This work presents an adaptive segmentation algorithm for endoscopic images. It is part of a complete system for robot-assisted endoscopy of the human sub-arachnoid spinal space. The role of the vision system is to provide a feedback for assisting the navigation of the endoscope and helping avoid damages to delicate tissues. Due to the presence of small blood vessels, nerves, and possible fibrosis, a multi-step approach has been followed for segmentation of the lumen (corresponding to free space for navigation) and the other tissues. Histogram analysis, together with blob analysis and a modified implementation of the convex hull algorithm bring to the isolation of the lumen; by means of adaptive thresholding nerves are isolated; thresholding on the hue and saturation helps in recognizing the vessels. A special condition of dirty lumen helps in managing doubtful situations. Experimental trials have been conducted on video streams from endoscopic explorations of animal (pig) spinal cord in-vivo. Experimental results show that membranes, vessels, nerves, and lumen are recognized in a reliable way, so as to contribute to robot-assisted endoscopy. The speed of the processing resulted compatible with an envisaged use in real tune support of endoscopic navigation.

This paper illustrates the analysis of locomotion in the gastrointestinal tract obtainable by a legged capsule for diagnostic and therapeutic purposes. A preliminary simulation of the legged locomotion onto slippery and deformable substrates has been performed and -simultaneously - mechanisms for on board actuation of the legs have been developed and tested. Moreover, an engineering translation of medical needs in endoscopy is presented, with some ad hoc solutions for improving diagnostic capabilities.

This paper presents the design, development and preliminary test of a new active microendoscope for neuroendoscopy and therapy of the spinal cord. Endoscopy of the spinal sub-arachnoid space is useful for some pathologies, but it is a very challenging task for several reasons: the navigation space is very narrow, there are many blood vessels and delicate structures which could be damaged by maneuvers and large forces and, finally, the CerebroSpinal Fluid (CSF) is a peculiar environment which must be preserved. An innovative method for active safe navigation in the sub-arachnoid space has been devised, based on hydrojets sustentation of the endoscope. The hydrojets, if appropriately tuned and oriented, allow the tip of the endoscope to avoid the delicate structures of the spinal cord and could also assist propulsion. A MATLAB simulation of the hydrojets is illustrated and a digital controller for the regulation of the hydrojets is demonstrated. The pressure ripple is about 5%, as tested experimentally on a 2D simulator. A prototype of steerable microendoscope whose tip is equipped with hydrojets has been fabricated and tested in an artificial path simulating the sub-arachnoid space. Performance are quite interesting.

This paper presents a new miniature gripper design, suitable for endoscopic surgery and similar applications. The gripper is based on a mechanism fabricated in-situ via a rapid prototyping process that permits multiple materials and the addition of embedded components. The gripper is actuated using a tuned vibrating mass and impact mechanism. The mechanism relies on close tolerances and clearances, obtained by depositing and subsequently removing thin films of sacrificial material. The gripper design and fabrication process are scalable, and future versions of the gripper can be made at a fraction of the size of the first 15 mm prototype without incurring manufacturing difficulty. Tests on the first prototype reveal the importance of controlling friction and preload at the sliding interface.

This paper describes a teleoperated mobile microrobot incorporating a novel type of electromagnetic micromotor. The overall dimensions of the microrobot are 10 mm/spl times/10 mm/spl times/10 mm. Two micromotors are used to actuate the two wheels of the microrobot. The micromotor is based on variable reluctance working principle and moves step by step. The micromotor is driven by a sequence of current pulses and performs about 200 steps per revolution. The micromotor generates a torque of 350.10/sup -6/ Nm at each step and a maximum speed of about 180 rpm. The heart of the control circuitry is the PIC16C73 microcontroller, that implements the control algorithm which allows the microrobot to move forward, backward and turn left or right. The operator controls the microrobot by a remote joystick and flexible ultraminiature wires. The microrobot has a maximum speed of 10 cm/s and can climb a slope of 15 degrees. The paper describes the design, fabrication and performance of the microrobot and of its components.