Achieving fast and agile swimming still remains extremely challenging for a self-propelled robotic fish due to the constraint of actuator's propulsion capability. In this article, we report an untethered bioinspired fish, which combines high-frequency oscillation compliant passive mechanism realize swimming, high pitch maneuvers, even leaping motion. For pursuing explosive propose actuation system with powerful output compact structure. A dynamic model is established indicates that joint...

Biological fish exhibit remarkable adaptability and exceptional swimming performance through their powerful flexible bodies. Therefore, designing a continuum body is significantly important for the development of robotic fish. However, it still challenging to replicate these functions biological due limitations actuation material. In this paper, based on tensegrity structure, we propose bionic design scheme with property stiffness variation. Its detailed structures principles are also...

Developmental robotics is also known as epigenetic robotics. We propose in this paper that there one substantial difference between developmental and robotics, since concentrates primarily on modeling the development of cognitive elements living systems robotic systems, such language, emotion, social skills, while should cover neural morphological single- multirobot systems. With recent rapid advances evolutionary biology biology, increasing genetic cellular principles underlying biological...

Learning-based compression shows competitive ratios for genomics data. It often includes three types of compressors: static, adaptive and semi-adaptive. However, these existing compressors suffer from inferior or throughput, also faces model cold-start problems. To address issues, we propose DeepGeCo, a novel data lossless framework with (s,k)-mer encoding deep neural networks, involving modes (MINI PLUS adaptive, ULTRA semi-adaptive) flexible requirements throughput. In (1) develop BiGRU...

This article proposes the mechanical design and dynamic model of an innovative manta-inspired robot system for both efficient fast swimming high spatial maneuverability. Inspired by some biological studies, a pair unique pectoral fins with six separate degrees freedoms (DOFs) are developed. The novel is characterized improved crank-rocker mechanism distinctive horizontal DOF. former not only endows speed, but also guarantees flapping patterns which close to manta rays. latter employed...

Aquatic animals such as fish and cetaceans can actively modulate their body stiffness with muscle to achieve excellent swimming performance under different situations. However, it is still challenging for a robotic swimmer bionic propulsion mode dynamically adjust its improve the speed due difficulties in designing an effective adjustment structure. In this paper, based on special torque of motor, we propose active variable control method dolphin pursue better speed. Different from structure...

This paper proposes a game-theory based approach in multi–target searching using multi-robot system dynamic environment. It is assumed that rough priori probability map of the targets' distribution within environment given. To consider interaction between robots, dynamic-programming equation proposed to estimate utility function for each robot. Based on this function, cooperative nonzero-sum game generated, where both pure Nash Equilibrium and mixed-strategy solutions are presented achieve...

In this paper, we present a hybrid ant colony optimization/particle swarm optimization (ACO/PSO) control algorithm for distributed robots, where each robot can only communicate with its neighbors within communication range. A virtual pheromone mechanism is proposed as the message passing coordination scheme among robots. This ACO/PSO architecture adopts feedback from environment of ACO and adaptive interplay agents PSO to create dynamic system, it well-suited large scale multi-agent system...

Kinematic analysis of leaping motions can provide meaningful insights into unraveling the efficient and agile propulsive mechanisms in dolphin swimming. However, undisturbed kinematic examination live dolphins has been very scarce due to restriction close-up biological observation with a motion capture system. The main objective this study is quantify self-propelled bionic robotic using combined numerical experimental method. More specifically, dynamic model was established for hydrodynamic...

A new approach to self-calibrate a camera-equipped robot manipulator is proposed in this paper. Self-calibration here means that the camera-robot system capable of determining its geometric parameters without any external measurements and/or ground truth calibration data. With approach, one able identify all rotational and, up scale factor, translational robotic It known from computer vision literature extrinsic and intrinsic camera can be obtained factor by using corresponding points...

Let $\mu$ be a Radon measure on ${{\rr}^d}$ which satisfies the growth condition only namely, there is constant $C>0$ such that for all $x\in{{\rr}^d}$, $r>0$ and some fixed $0<n\le d$, \[ \mu(B(x,r))\le Cr^n, \] where $B(x,r)$ ball centered at $x$ having radius $r$. In this paper, we first give new atomic characterization of Hardy space $H^1(\mu)$ introduced by X. Tolsa. As applications characterization, establish $(H^1(\mu),L^{1,\infty}(\mu))$ estimate commutators generated $RBMO(\mu)$...

Distributed coordination is critical for a multi-robot system in hazardous waste cleanup under dynamic environment. To achieve higher efficiency as well robustness, bio-inspired local interaction via virtual stigmergy (LIVS) approach proposed this paper. This new meta-heuristic integrates two mechanisms - stigmergy-based autocatalytic mechanism and particle swarm optimization cognitive capabilities through into one efficient approach. The LIVS algorithm has been implemented on both...

Most existing robotic fish have a large body size driven by servo motor system, while conventional small-sized actuators hardly generate high swimming performance. This paper reports miniature untethered fish, whose length is 69 mm. In particular, newly designed magnetic actuator system (MAS) equipped, which guarantees both dimension and flexibility of the robot. More specifically, field generated permanent magnet first investigated based on Biot-Savart law. Then, novel tail-beating rhythm...

This paper presents an automatic object detection and tracking algorithm by using particle swarm optimization (PSO) based method, which is a searching inspired the behaviors of social insect in nature. A cascade boosted classifiers on Haar-like features trained employed to detect objects. To improve efficiency, first model projected into high-dimensional feature space, PSO-based applied search over this space converge some global optima, are well-matched candidates terms features. Then,...

In this work, we address the recognition of human activities from a sequence visual data. To end, novel hierarchical probabilistic latent (HPL) model is proposed, which consists four layers bottom-up: spatiotemporal features layer, atomic pattern topic and behavior layer. manner, complicated can be decomposed into low level features, patterns, topics, are much better suited for automatic understanding behaviors. Given video sequence, both spatial temporal interest points extracted as...

Biological systems can generate robust and complex behaviors through limited local interactions in the presence of large amount uncertainties. Inspired by biological organisms, we have proposed a gene regulatory network (GRN) based algorithm for self-organizing multiple robots into different shapes. The self-organization process is optimized using genetic algorithm. This paper focuses on empirical analysis robustness multi-robot system to changes tasks, noise robot environment. We...

Abstract The aquatic-aerial robot with the free interface crossing can enhance adaptability in complex aquatic environments. However, its design is extremely challenging for striking discrepancies propulsion principles. flying fish nature exhibits remarkable multi-modal cross-domain locomotion capability, such as high-maneuvers swimming, agile water-air crossing, and long-distance gliding, providing extensive inspiration. In this paper, we present a unique robotic powerful pair of morphing...

Remora, a bony fish, is well known for the remarkable hitchhiking behavior, by which it can transport itself over large distances without too much effort. In this article, novel robotic remora with stable adhesion system and its motion control methods are proposed transferring behavior to engineered system. terms of mechatronic design, prototype uncoupled planar vertical mechanisms created realize precise agile movement. Furthermore, reliable possessing low preload demand, considerable...

Manta-inspired robots have been increasingly applied in vision-based underwater tasks. However, owing to the refraction effect and motion coupling problem, their accurate target following control is still poorly understood. This letter proposes a scheme for robotic manta. First, an agile manta equipped with binocular camera system constructed. The modes are further detailed based on propulsion analysis flexible pectoral fins. Second, color-based detection localization method conceived....