Search Results (432)

Event cameras are bio-inspired vision sensors offering low latency, low power consumption, and high dynamic range, capturing motion with microsecond-level precision via a per-event triggering mechanism. Despite these advantages, the inherent sparsity and lack of color in event data hinder direct analysis, necessitating advanced deep learning approaches. To achieve low-latency and high-precision motion segmentation for indoor robotic applications, this paper introduces a dual-branch decoupled CNN framework. Specifically, Principal Component Analysis (PCA) is utilized to project 3D event point clouds into 2D motion trend maps, capturing local motion priors while suppressing ambiguity in structured environments. Concurrently, an Event Leaky Integration (ELI) model, inspired by biological membrane potentials, is designed to enhance the structural representation of sparse events. Within this framework, separate branches respectively perform motion validation and shape extraction and are fused via a Spatial Gated Fusion (SGF) module to suppress static background interference. It is demonstrated experimentally that with an input window of only 10 ms, the proposed method achieves a 77% average mIoU across five indoor test scenarios from the EV-IMO dataset with an inference latency of 10 ms per frame. Compared to state-of-the-art methods like MSRNN and GCN, which required 30–300 ms event slices, our framework achieves a favorable trade-off between computational efficiency and segmentation accuracy, maintaining competitive performance under ultra-short time windows for indoor event-based motion processing. Full article

The biomechanics of frog jumping has been a subject of significant interest in both biology and engineering, driven by the high efficiency of their movement. This study presents the dynamic simulation of a frog’s complete jump cycle, from take-off to landing and re-stabilization, to advance the development of bio-inspired jumping robots for irregular terrains. As a primary contribution, and unlike previous studies that focus exclusively on the propulsion phase, this work addresses all stages, using direct servomotor actuation without mechanical energy storage. Biological joint kinematics were mathematically characterized using Cubic Smoothing Splines. By empirically tuning the smoothing parameter (p), the trajectories achieved the continuous differentiability required for electromechanical actuation. These curves were implemented into a 3D multibody simulation (Altair Inspire), where a PID-based tracking framework managed the mechanically nonlinear multibody dynamics governing the jump (arising from contact forces, impacts, and time-varying inertial effects) to ensure stabilization during the complex landing phase. Validating the model against previous studies, the simulation successfully achieved a maximum horizontal jump distance of 24.12 cm (4.02 body lengths) and a peak velocity of 1.45 m/s. The kinematic fidelity of the model was mathematically validated, yielding a maximum Normalized Root Mean Square Error (NRMSE) of 4.121% relative to biological reference trajectories. Furthermore, the robustness of the landing and re-stabilization phases was demonstrated through a continuous double jump covering a total distance of 45.83 cm. Finally, a dynamic scaling analysis was performed to evaluate the feasibility of implementing real motors. Ultimately, this study establishes a mathematically robust framework for replicating frog-inspired jumping dynamics, contributing a transferable methodology for the design and control of articulated bio-inspired robotic systems. Full article

The selective harvesting of leaves from flexible-stem crops remains a major challenge in agricultural mechanization due to stem compliance, heterogeneous petiole strength, and unstable tool–crop interaction. To address these issues, a bio-inspired ring-cutting and compliant clamping harvesting mechanism is proposed for low-damage selective harvesting under complex terrain conditions. Inspired by the adaptive attachment behavior of octopus suckers, a flexible compliant clamping interface combined with a ring-shaped sliding cutting structure was developed to stabilize flexible stems during harvesting. A coupled kinematic–force analytical model was established to characterize the interaction between tool motion, stem feeding, and cutting behavior. In addition, a sliding cutting mechanics model was introduced to analyze the relationship between cutting force and sliding angle. Dynamic multibody simulations were performed using ADAMS to verify the motion feasibility and trajectory stability of the proposed harvesting mechanism. Bench-scale experiments were conducted using mulberry branches as a representative flexible-stem crop, and a response surface methodology based on a Box–Behnken experimental design was applied to optimize key operational parameters. The optimal parameter combination included a chain linear speed of 0.18 m·s⁻¹, a feeding speed of 0.30 m·s⁻¹, and an installation angle of 36°. Under these conditions, the missed harvest rate was reduced to 9.2–9.8%, demonstrating improved harvesting stability compared with conventional rigid cutting mechanisms. The results indicate that integrating compliant stabilization with sliding cutting provides an effective engineering strategy for selective harvesting of flexible-stem crops in complex agricultural environments. Full article

Automatic modulation recognition (AMR) is increasingly relevant to communication-sensing front ends in robotic and human–robot collaborative systems, where reliable spectrum awareness and adaptive wireless reception are desired. However, existing methods often degrade sharply at low signal-to-noise ratios (SNRs), and large language models (LLMs) are not natively compatible with continuous I/Q signals due to the inherent modality gap. We propose BioLAMR, a GPT-2 adaptation framework for AMR inspired by the auditory system’s parallel time–frequency processing and cortical hierarchy. The framework combines bio-inspired dual-domain feature extraction with parameter-efficient LLM adaptation. BioLAMR includes three components. First, a lightweight dual-domain fusion (LDDF) module extracts complementary time- and frequency-domain features and fuses them through channel and spatial attention. Second, a convolutional embedding module converts continuous I/Q signals into GPT-2-compatible sequences without discrete tokenization. Third, a hierarchical fine-tuning strategy updates only 8.9% of parameters to preserve pretrained knowledge while adapting to modulation recognition. Experiments on the RadioML2016.10a and RadioML2016.10b benchmarks show that BioLAMR achieves overall accuracies of 64.99% and 67.43%, outperforming the strongest competing method by 2.60 and 2.47 percentage points, respectively. Under low-SNR conditions, it reaches 36.78% and 38.14%, the best results among the compared methods. Ablation studies verify the contribution of each component. These results demonstrate that combining dual-domain signal modeling with parameter-efficient GPT-2 adaptation is an effective route to robust AMR in challenging wireless environments. Full article

Collaborative operation of heterogeneous UAV swarms in dense urban environments remains challenging because right-of-way allocation is often rigid, frequent replanning consumes considerable onboard computation, and paths obtained by purely mathematical optimization may not be easy to execute under real dynamic constraints. This paper presents a physics-informed, event-triggered path planning and control framework, termed Physics-Informed SSA-MPC. Its global search layer is built on the Sparrow Search Algorithm (SSA), whose search mechanism originates from sparrow foraging and anti-predatory behaviors. On this basis, the method combines an event-triggered Stackelberg game for airspace coordination, a physically constrained SSA for global path generation, and an event-triggered MPC for local replanning. Battery State of Health (SoH) is incorporated into the adaptive search process, while Lévy-flight updates are limited by the maximum available acceleration to avoid infeasible path mutations. Local replanning is activated only when predicted safety ellipsoids overlap or tracking errors exceed prescribed thresholds, which helps reduce redundant computation. Simulations in a digital twin of Lujiazui, Shanghai, show that the proposed method shortens path length by 3.3% to 14.9%, reduces obstacle-avoidance latency to 45 ms, and achieves a 100% engineering feasibility rate. Full article

In-pipe robots must navigate narrow, curved passages where rigid mechanisms often require bulky steering units. Soft crawlers offer better compliance but typically rely on multiple actuators or reconfigurable contacts to achieve multi-directional motion. Drawing inspiration from biological soft crawlers that exploit directional friction and coordinated anchor–slip patterns, this study focuses on locomotion principles observed in caterpillars, water boatmen, and whirligig beetles. Based on these bioinspired concepts, we present a tendon-driven soft in-pipe robot that combines continuum bending–twisting deformation with modular anisotropic friction pads (AFPs), enabling three locomotion modes using only two motors. AFP inclination, curvature, and ridge geometry were optimized through friction tests, constant-curvature modeling, and finite element analysis to enhance directional adhesion on flat and curved surfaces. A deformation-based locomotion framework was developed to couple tendon actuation with friction orientation, achieving longitudinal crawling, transverse translation, in-place rotation, and smooth transitions via programmed twisting. Driving experiments demonstrated repeatable anchor–slip locomotion with average speeds of 28.6 mm/s, 15.7 mm/s, and 11.5°/s for the three modes. Pipe tests in straight, curved, and T-junction sections further validated stable contact and reliable gait transitions. These findings highlight the potential of friction-programmed continuum robots as compact, bioinspired platforms for advanced in-pipe inspection and diagnostic tasks. Full article

To meet the practical application requirements of underwater biomimetic robots, this paper presents the design of a flexible pectoral fin with integrated sensing and actuation capabilities, based on a “material-structure-function” integrated approach. The sensor film is embedded into the pectoral fin via an embedded cast-molding method, ensuring synchronized deformation and long-term cyclic stability. Experimental results demonstrate that the integrated pectoral fin can accurately perceive its own bending deformation and external environmental disturbances, enabling corresponding obstacle avoidance maneuvers in a manta robot prototype. This design strategy endows the manta robot with environmental adaptability for real-world applications and offers a novel paradigm for the intelligent design of other underwater equipment. Full article

Biological systems regulate motion and suppress unwanted vibrations through learning, adaptation, and predictive control under uncertainty. Inspired by these principles, Bayesian system identification has emerged as a powerful framework for modeling and estimation, particularly in the presence of uncertainty in structural systems. Flexible structures in aerospace and robotics require advanced control to mitigate vibrations under model uncertainty. This paper proposes a data-driven strategy leveraging a Gaussian Process (GP) integrated within a Nonlinear Model Predictive Control (NMPC) framework. The core innovation lies in using a Gaussian Process Nonlinear AutoRegressive model with eXogenous input (GP-NARX) as a probabilistic predictor to capture structural dynamics while quantifying uncertainty. The operational mechanism involves a tight coupling where the GP provides multi-step-ahead forecasts that the NMPC optimizer uses to minimize a cost function subject to constraints. Validated through simulations on Duffing oscillators, linear oscillators, and cantilever beams, the GP-NMPC achieved an 88.2% reduction in displacement amplitude compared to uncontrolled systems. Quantitative analysis shows high predictive accuracy, with a Root Mean Square Error (RMSE) of 0.0031 and a Standardized Mean-Squared Error (SMSE) below 0.05. Furthermore, Mean Standardized Log Loss (MSLL) evaluations confirm the reliability of the predictive uncertainty within the control loop. These results demonstrate strong performance in both regulation and tracking tasks, justifying this Bayesian-predictive coupling as a powerful approach for high-performance structural vibration control and a potential foundation for bio-inspired mechanical design. Full article

Micro air vehicles (MAVs) operating at low Reynolds numbers face aerodynamic and structural challenges that differ significantly from those encountered by conventional aircrafts. Nature provides effective solutions to these constraints, as insects, birds, and bats demonstrate highly efficient flight through integrated interactions between morphology, kinematics, and unsteady aerodynamic mechanisms. This review examines how biological flight principles can inform the design of next-generation MAVs. The study first analyzes biological flight strategies across insects, birds, and bats, with emphasis on scaling laws and physiological adaptations relevant to small-scale flight. It then reviews key unsteady aerodynamic phenomena governing low-Reynolds-number flight, including leading-edge vortex stability, wing–wake interactions, tandem-wing effects, and ground influence, as well as current modeling approaches ranging from quasi-steady methods to high-fidelity Navier–Stokes simulations. Building on these principles, the paper discusses biomimetic design strategies for MAV wings, structural–aerodynamic coupling, and actuation technologies used to replicate flapping flight. Existing MAV demonstrators inspired by biological flyers are analyzed, including concepts relevant to planetary exploration environments. Finally, the review identifies current technological limitations and research gaps in materials, actuation, aerodynamic modeling, and system integration. By synthesizing insights from biology and engineering, this work highlights key directions for the development of efficient, adaptable biomimetic MAV platforms capable of operating in complex environments. Full article

Bio-inspired quadrupedal robots exhibit superior adaptability and mobility in unstructured environments, making them suitable for complex task scenarios such as navigation, obstacle avoidance, and tracking in a variety of environments. Visual perception plays a critical role in enabling autonomous behavior, offering a cost-effective alternative to multi-sensor systems. This paper proposes an image segmentation-guided visual tracking framework to enhance both perception and motion control in quadruped robots. On the perception side, a cascaded convolutional neural network is introduced, integrating a global information guidance module to fuse low-level textures and high-level semantic features. This architecture effectively addresses limitations in single-scale feature extraction and improves segmentation accuracy under visually degraded conditions. On the control side, segmentation outputs are embedded into a biologically inspired central pattern generator (CPG), enabling coordinated generation of limb and spinal trajectories. This integration facilitates a closed-loop visual-motor system that adapts dynamically to environmental changes. Experimental evaluations on benchmark image segmentation datasets and robotic locomotion tasks demonstrate that the proposed framework achieves enhanced segmentation precision and motion flexibility, outperforming existing methods. The results highlight the effectiveness of vision-guided control strategies and their potential for deployment in real-time robotic navigation. Full article

Classical contact mechanics typically relies on simplifying assumptions such as linear elasticity and frictionless interfaces. A notable example is the Westergaard model, a rigorous theoretical solution for the contact between a rigid sinusoidal surface and an elastic half-space with a flat surface. This configuration captures the features of surface roughness at a single characteristic scale. Such modeling is particularly relevant since most natural and engineered surfaces exhibit roughness, significantly influencing their contact behavior. In this work, we present a nonlinear analytical contact model, which overcomes the main limitations of the Westergaard solution. Specifically, we formulate the contact problem within a finite elasticity framework and include interfacial friction. The analytical model is derived from the results of dedicated finite element simulations and subsequently validated against experimental data from the literature, demonstrating improved predictive accuracy in estimating the contact area as a function of the applied mean pressure. This work lays the foundation for the development of weakly nonlinear multiscale models, where solutions for single-scale roughness can be superimposed to approximate the behavior of more complex, fractal surface geometries. Such an approach holds promise for applications in areas such as tactile human–device interactions, soft robotics, and the design of bioinspired surfaces. Full article

Biological fish possess the intrinsic ability to dynamically modulate body stiffness to adapt to varying fluid environments, thereby optimizing propulsive efficiency, swimming speed, and maneuverability. In contrast, this capability remains a significant challenge for most existing robotic fish, which typically rely on fixed-stiffness configurations. This article presents a comprehensive review of variable stiffness structures and their applications in biomimetic robotic fish. The associated technologies are systematically classified into four categories: smart material-driven, bio-inspired, fluid-driven, and hybrid-driven mechanisms. A comparative analysis of state-of-the-art prototypes is conducted, evaluating critical performance metrics including physical dimensions, maximum swimming speed, minimum turning radius, maximum turning rate, and Strouhal number. Furthermore, the specific advantages and technical limitations of each variable stiffness category are critically assessed. Finally, existing challenges in current research are identified, and prospective directions are proposed. The review demonstrates that variable stiffness technology offers significant potential to advance the hydrodynamic performance of robotic fish and facilitate their deployment in practical engineering applications. Full article

Vision-based robot control remains a significant challenge due to the sample inefficiency and prolonged training times associated with traditional deep reinforcement learning methods. We propose a novel approach inspired by biological gene regulation, leveraging Gene Regulatory Networks (GRNs) for efficient and robust robot control. In our approach, robot states are encoded as gene expression levels, and evolutionary optimization is used to learn GRN parameters that map raw visual inputs to motor commands. We evaluate this method on the KukaDiverseObjectEnv benchmark, where robots must grasp diverse objects using only RGB images. Our GRN-based controller achieves a $57.5\%$ success rate while reducing training time by $13.7\times$ compared to Proximal Policy Optimization baselines. It also outperforms NEAT, standard reinforcement learning algorithms, and deep Q-learning in terms of both efficiency and performance. The controller maintains $91.8\%$ performance under noisy visual conditions. This bio-inspired design naturally enables hierarchical control via expression cascades, computational efficiency through bounded dynamics, and temporal reasoning without explicit memory modules. Full article

While walking robots possess significantpotential for various real-world applications, the reliance on high-performance sensors and complex control architectures for precise gait control remains a significant barrier to commercialization and lightweight design. To overcome these engineering limitations and lay the groundwork for a sensing paradigm adaptable to complex terrains, this study proposes an AI-based sensorless feedback control framework that incorporates the biological principles of proprioception. To this end, a walking robot leveraging the morphological intelligence of the Klann linkage was developed. We constructed a time-series dataset by defining motor current signals as ‘interoceptive sensing’ information—analogous to biological muscle feedback—and synchronizing them with absolute angular data. This dataset was used to train an Attention-LSTM (A-LSTM) model, which predicts future motor states in real-time by decoding nonlinear physical information embedded within internal current data, independent of external environmental sensors. By integrating the proposed model into a PI controller, a stable biomimetic walking loop was successfully implemented without the need for additional position sensors. Full article

Biarticular actuators can enhance efficiency and stability in legged locomotion by transferring energy between joints. Their effectiveness depends strongly on the lever arm ratio—the ratio of the actuator’s moment arm at one joint to its moment arm at another—which governs how torque is distributed across joints during movement. Inspired by biomechanics, early robotic studies implemented biarticular actuators to improve energy efficiency, joint coordination, and positional control, primarily in planar or single-joint systems, leaving a gap in fully 3D robotic legs. Here, we present a geometry optimization framework for a robotic leg incorporating both biarticular and monoarticular actuators. Using human motion capture and joint torque data, we optimized the linkage mechanisms so that the system can maintain the required joint torques while keeping biarticular actuator moment arm ratios near their optimal values during walking and running. The optimized leg achieved a minimum achievable cost of transport of approximately $0.41 \mathrm{J}/(\mathrm{kg}·\mathrm{m})$ for walking and $0.62 \mathrm{J}/(\mathrm{kg}·\mathrm{m})$ for running. Full article