Solving problems associated with the efficient distribution and organization of resources has generated increasing interest in the scientific community. One of the most commonly used approaches consists of approximate solution techniques, which have been able to solve complex covering problems within acceptable computational time and cost. One of the benchmarks used to evaluate these approaches is the Set Covering Problem, which is an NP-hard combinatorial optimization problem. Among the techniques that have been investigated, metaheuristics play an important role. These methods are commonly developed for continuous search spaces and, in order to be applied to covering problems, must be modified to operate in discrete domains. This modification presents an important challenge: finding an appropriate transformation method that translates continuous solutions into binary solutions. This issue has been addressed through two main strategies: binarization using two-step schemes, and, in our proposal, the use of repair operators orchestrated according to their performance through an Adaptive Repair Selection Mechanism based on the multi-armed bandit framework. To evaluate our proposal, we selected the Binary Hunger Games Search metaheuristic because the relative quality of each individual determines its hunger level, which in turn regulates the movement of the population and the influence of the best solution found. Infeasible solutions are handled through a set of Tabu Search-based repair operators. Instead of applying a single repair rule throughout the entire execution, the proposed approach dynamically selects among these operators according to their observed contribution during the search. Each repair operator also incorporates Tabu memory to discourage repetitive decisions during feasibility restoration. The experiments were conducted using the classical Beasley benchmark instances for the Set Covering Problem.
Low-cost geared DC motors are widely used in mobile robotics and embedded mechatronic systems; however, their control remains challenging due to dead-zone nonlinearities, friction, low encoder resolution, motor asymmetry, and supply voltage variations. Biological organisms routinely perform motor control in the presence of similar uncertainties by relying on approximate reasoning and adaptive responses rather than precise mathematical models. This paper develops and experimentally validates a practical bio-inspired control architecture for low-cost geared DC motors operating under severe sensing and actuator limitations. The proposed controller combines fuzzy inference, dead-zone compensation, and a ramp-start mechanism to emulate the gradual and adaptive nature of biological motor responses. Instead of relying on an accurate plant model, control actions are generated through linguistic rules that mimic human-like decision-making based on speed error and error variation. The controller is implemented on an Arduino-based differential-drive robotic platform equipped with low-resolution optical encoders. Experimental results demonstrate that the proposed bio-inspired approach effectively mitigates startup stall, reduces oscillatory behavior caused by measurement quantization, and maintains stable speed regulation despite actuator variability and battery voltage fluctuations. The study shows that biologically inspired fuzzy control provides a practical and computationally efficient alternative to conventional PID methods for low-cost robotic systems characterized by significant uncertainty and nonlinear behavior.
Humanoid robots are highly susceptible to structural damage during irrecoverable falls due to high landing velocity, short impact duration, and high peak impact force. Inspired by human protective strategies, namely instinctive postural adjustment and soft-tissue energy absorption, this paper proposes a passive–active cooperative fall-protection method that combines pre-impact motion regulation with post-impact structural energy absorption. On the passive protection side, high-risk contact regions are identified through multi-directional fall simulations, and a multi-region, multilayer protective suit is optimized considering impact energy absorption, peak-force reduction, anti-bottoming safety, added mass, and thickness constraints. On the active protection side, a variable height inverted pendulum (VHIP) model is used to optimize the center of pressure and center of mass trajectories, reducing the terminal impact energy before ground contact. The residual impact energy is then matched with the absorption capacity of the passive protective layers, forming a unified framework that integrates pre-impact motion unloading and post-impact energy absorption. Numerical validation is performed on a MATLAB–CoppeliaSim co-simulation platform, and physical experiments are conducted on the FCR humanoid robot (approx. 50 kg, 1.65 m, 22 DOF). Compared with the unprotected case, the proposed method reduces the peak equivalent impact force from 4819.1 N to 1038.2 N, i.e., a reduction of 78.5%, demonstrating its effectiveness in attenuating impact loads and enhancing protection capability.
Fish-like biomimetic robots increasingly combine compliant structures, soft and variable-stiffness actuation, distributed sensing, and autonomous control, but cross-study comparison remains difficult because biological inspiration, robotic embodiment, test boundaries, and mission definitions are heterogeneous. We synthesize the field through a mechanism-to-evidence framework that links biological mechanisms to measurable descriptors, robotic embodiment, controlled interventions, task-oriented evidence, and conditional design principles. Across the literature, the transferable unit is not external resemblance but a functional mechanism whose advantage remains measurable after robotic integration. Three conclusions recur: dynamic performance depends on matching stiffness, actuation frequency, damping, and fluid loading within the intended operating range; morphology, sensing, control, power, and payload must be co-designed; and component, free-swimming, controlled-task, and field studies support different scopes of inference. We translate these findings into nine evidence-informed conditional design principles with explicit applicability limits and discriminating validation tests. Major gaps remain in wet-state dynamic characterization, complete reporting of power boundaries and kinematics, uncertainty and failures, matched task-level comparisons, and long-duration field validation. The resulting framework shifts evaluation from peak metrics and taxonomic labels toward task-conditioned, evidence-bounded design decisions.
Architectured soft structures have unlocked new possibilities for designing continuum manipulators with tailored mechanical performance. This work introduces a bioinspired soft manipulator based on modular wave spring units, leveraging the high elasticity of wave spring structures to enable compliant deformation and axial extensibility of the soft manipulator. To achieve precise control of the soft manipulator, a neural network-based inverse kinematics framework is developed to establish an efficient mapping from desired end poses to tendon actuation lengths. An iterative learning control strategy is further integrated to compensate for material hysteresis, friction, and external disturbances. A prototype is fabricated using flexible 3D-printable material (TPU), and comprehensive experiments are conducted to validate extensible performance, point positioning accuracy, trajectory-tracking accuracy, and compliant interaction capability. The results demonstrate that the proposed wave spring-based soft manipulator achieves a high extension ratio and reliable control precision.
Metaheuristic algorithms are widely used to solve complex optimization problems, but the trade-off between exploration and exploitation often limits their performance. The Crested Porcupine Optimizer (CPO) employs four bio-inspired defense mechanisms and achieves competitive performance, but it still tends to converge prematurely, initialize populations poorly, and rely on static parameters that cannot adapt to different phases. This paper proposes a Multi-Strategy Enhanced Crested Porcupine Optimizer (MSCPO) with four phase-targeted enhancement strategies: (1) Kent Chaos Opposition-Based Learning Initialization (KCOL) improves the initial population distribution through chaotic-weighted reflection; (2) Arctic Puffin Optimization (APO)-Inspired Dual-Modal Evasion (APO-DME) reduces dependence on the global best solution and increases population diversity through dual-mode differential perturbation; (3) Adaptive Dual-Differential Perturbation (ADDP) refines the search by combining population diversity and elite guidance information; (4) Periodic Dynamic Adaptive Perturbation (PDAP) enhances exploitation through periodic trigonometric perturbation and a fitness-conditioned update rule. These strategies interact across the optimization process to strengthen each defense mechanism at the appropriate phase. On the CEC 2017 and CEC 2022 benchmark suites, MSCPO achieves the best overall mean rank among all compared algorithms, with an overall rank of 2.638 on CEC 2017 and 2.375 on CEC 2022. A full-factorial ablation over all 16 strategy combinations confirms that each strategy contributes positively: removing any single strategy degrades the overall mean rank, and the complete MSCPO achieves the best mean rank (3.34), significantly outperforming all single-strategy variants (Wilcoxon signed-rank test, p < 0.001). To verify the practical applicability of MSCPO, the algorithm is further applied to three engineering design problems: step-cone pulley design, hydrostatic thrust bearing design, and robotic gripper design. MSCPO ranks first on the hydrostatic thrust bearing problem, second on the step-cone pulley problem, and third on the robotic gripper problem. Future work will explore adaptive population sizing to further improve the scalability of MSCPO on very high-dimensional problems.
Postsurgical adhesions are common complications of abdominal and pelvic surgeries, often leading to bowel obstruction, chronic pain, and increased risks during reoperation. Although various physical barrier materials have been developed to prevent postsurgical adhesions, retaining anti-adhesive materials at surgical sites is challenging. In this study, we developed thermosensitive injectable gallic acid-conjugated hyaluronic acid (HA-GA) and Pluronic F127 (PluF) composite hydrogels to retain anti-adhesive materials and prevent postsurgical adhesion. The incorporation of HA-GA reduced the critical gelation concentration of PluF from approximately 18 to 12 wt% and decreased the gelation temperature from 28.5 °C for PluF to 25.6 °C for HA-GA (2 wt%)/PluF hydrogels with the left-shift in sol–gel curves. The G′ values increased from 10.1 ± 1.7 kPa for PluF to 24.8 ± 3.6 kPa for HA-GA (2 wt%)/PluF hydrogels at 37 °C. In addition, the HA-GA/PluF hydrogels exhibited enhanced mass retention as a function of time compared to PluF hydrogels alone. HA-GA (2 wt%)/PluF hydrogels retained 33.4 ± 3.5% of their initial mass after 7 d, whereas PluF was completely eroded within 3 d. The anti-adhesion efficacy of the HA-GA/PluF hydrogels was evaluated using a rat cecum abrasion model. Notably, the HA-GA (2 wt%)/PluF hydrogels showed reduced adhesion scores, with an adhesion extent score of 0.67 and 2.33 on postoperative day 7 and 21, respectively, compared with the untreated control group (3 and 3 on postoperative day 7 and 21). In addition, the adhesion severity scores of HA-GA (2 wt%)/PluF hydrogel groups were 0.33 and 1.33 on postoperative day 7 and 21, respectively, compared with the untreated control groups (1.67 and 2.33 on postoperative day 7 and 21). Therefore, HA-GA/PluF hydrogels provide reversible thermosensitive properties with enhanced stability and retention, supporting their potential as injectable physical barriers for postoperative adhesion prevention.
The inherent trade-off between strength and toughness in structural materials remains a critical challenge. Inspired by the hierarchical architecture of fish scales, this study proposes a novel overlapping helical composite structure. Multi-material three dimensional (3D) printing technology was employed to fabricate single-edge notched bending specimens. Quasi-static three-point bending experiment was conducted to investigate the mechanical performance of a fish scale-inspired structure. The results show that compared to the stiff bulk structure, the bio-inspired design exhibits a 60.4% enhancement in apparent fracture toughness and a 157.5% increase in energy absorption despite a reduction in flexural modulus and strength. The significant improvement may be attributed to the synergistic effects of crack deflection, which transform the fracture mode from catastrophic brittle failure to progressive damage with a stable post-peak deformation stage. Furthermore, parametric studies reveal that both the linear helical angle and its nonlinear gradient distribution critically govern the toughening efficiency. An optimal linear angle of 19° provides the best overall performance, while a nonlinear gradient (e = 1.75) further shifts energy dissipation towards the post-peak deformation stage, achieving a higher toughening efficiency. This work establishes a fundamental understanding of an overlapping helical coupling toughening strategy and provides a promising design route for high-damage-tolerance composite structures.
End-of-life (EoL) electric vehicle (EV) batteries comprise numerous interconnected components with complex topological and precedence relationships. These constraints significantly increase the difficulty of disassembly sequence planning (DSP), as feasible sequences must satisfy multiple dependency requirements. Moreover, the large number of possible disassembly alternatives creates a vast search space, making sequence optimisation susceptible to combinatorial explosion and convergence to local optima. Therefore, effective DSP requires both robust constraint-handling mechanisms to ensure sequence feasibility and efficient optimisation strategies to identify high-quality solutions. To address these challenges, this paper proposes a disassembly sequence optimisation method that integrates a hard-constraint rule base, the linear upper confidence bound (LinUCB) algorithm, and the Bees Algorithm (BA). First, a disassembly-oriented hard-constraint rule base is developed to standardise the identification of component topological relationships and precedence constraints, thereby ensuring the generation of feasible disassembly sequences. A LinUCB-based contextual adaptive operator-selection mechanism is subsequently introduced to dynamically select neighbourhood operators according to the current search state. A weighted multi-criteria evaluation function incorporating disassembly time, payment cost, and human–robot utility is integrated into the BA. Two representative EoL-EV battery case studies with different levels of structural complexity are used for validation. Across 50 independent runs, LinUCB-BA reduced the mean normalised weighted objective value by 39.01% and 28.12% relative to simplified swarm optimisation (SSO) and teaching–learning-based optimisation (TLBO), respectively, in the 27-component case, and by 7.19% and 2.33% in the 16-component case. Compared with the enhanced discrete Bees Algorithm (EDBA) ablation baseline, further reductions of 1.98% and 0.43% were achieved, together with lower run-to-run variability. These results indicate that the proposed framework is effective for the two investigated battery disassembly scenarios, while broader validation across additional battery architectures and operating conditions remains necessary.
Robotic piano playing is a challenging benchmark for biomimetic dexterous manipulation, requiring precise timing, coordinated multi-finger motion, and stable key contact. This study proposes a robotic piano-playing framework based on a two-stage reinforcement learning curriculum. Musical Instrument Digital Interface (MIDI) data are converted into target-key and fingering grids to provide future musical goals for policy learning in a parallel MJLab simulation environment. A Soft Actor–Critic (SAC) agent takes a 2106-dimensional observation vector, including joint states, previous actions, musical phase, future key targets, fingering assignments, and piano-key states, and outputs a 21-dimensional continuous action vector for wrist, finger, and global hand-positioning control. Stage 1 weakens physical regularization to facilitate key-pressing acquisition, whereas Stage 2 strengthens power, velocity, acceleration, collision, posture, and finger-speed constraints to improve the regularity of policy outputs and readiness for real-world deployment. Simulation experiments on 30 s right-hand excerpts from Für Elise, Canon, and Beethoven’s Symphony No. 5 achieve frame-wise key-state F1 scores above 0.99 on the first two excerpts and approximately 0.945 on Beethoven. Real-world deployment uses open-loop playback of policy-generated high-level trajectories with low-level joint-position feedback and achieves F1 scores of 0.95, 0.91, and 0.83, respectively, while reproducing representative piano techniques such as chords, octaves, mixed black-and-white-key patterns, overlapping finger actions, and rapid sequential movements. These physical results demonstrate the feasibility of the proposed sim-to-real pipeline for complete 30 s executions; they are not intended as a statistical repeatability study. The results further show that biomimetic robotic hands can learn complex piano-playing skills from MIDI-based task objectives without relying on human motion demonstration trajectories.
The legs of flying insects play a critical role in enabling seamless transitions between aerial and terrestrial environments. These appendages serve multiple functions, including landing, walking, jumping, and transitioning from jumping to flight (takeoff). Such capabilities have inspired engineers to seek similar multimodal mechanisms in Flapping-Wing Aerial Robots (FWARs) to expand their operational versatility across diverse environments. However, designing multimodal mechanisms with distinct kinematic and propulsive characteristics remains challenging, particularly in the domain of autonomous jump takeoff for FWARs, where research remains relatively sparse. In this study, inspired by the jumping takeoff strategy and hindleg kinematics of the Asian migratory locust (Locusta migratoria), we propose a functional bio-inspired jumping takeoff mechanism that extracts selected mechanical principles of the locust jumping system, including elastic energy accumulation, temporary mechanical locking, and rapid energy release. The mechanism employs a gear–crank–slider transmission system and utilizes one-way bearings to regulate the locking and disengaging states, enabling the storage and rapid release of energy for jump takeoff, thereby achieving autonomous takeoff of the robot. Adams dynamic simulations show that at a torsion spring angle of 40°, the mechanism achieves a maximum resultant velocity of 1.955 m/s, a jump height of 168.2 mm, and a horizontal displacement upon landing of 134.6 mm. Ansys Fluent (2024 R2) simulations under multiple operating conditions further confirm that the aerodynamic performance is optimal at a takeoff angle of attack(α) of 5° with a torsion spring angle(β) of 40°, yielding a lift-to-drag ratio of 3.005. This work presents a functional bio-inspired jumping takeoff mechanism based on selected mechanical principles of locust jumping, providing a potential approach for improving the autonomous takeoff capability of small-scale FWARs.
Metaheuristics require sustained global search without sacrificing local refinement, yet many variable-structure methods change operators through one-way iteration schedules. We introduce the Weather State Ants Optimizer (WSAO), in which a discrete-time Markov chain recurrently selects one of three population updates. Sunny, cloudy, and rainy states correspond to global exploration, movement toward nests, and local refinement, respectively. An archive-based mechanism also maintains several spatially separated nests as concurrent search centers. Thirty independent runs compared WSAO with 11 algorithms on 29 CEC2017 and 12 CEC2022 functions. WSAO achieved the lowest Friedman mean rank on both suites, at 2.48 and 2.33. Across five constrained design cases, it joined the leading group by mean objective value on four cases and ranked second on pressure-vessel design. Targeted CEC2022 controls showed that no alternative transition matrix dominated the baseline. Eliminating the trial perturbation worsened every selected function, whereas the contribution of multiple nests depended on the landscape structure. The combined evidence supports recurrent state-controlled search as a competitive framework for continuous numerical and constrained optimization.
Bionic intelligent robots operating in unstructured dynamic environments require perception systems that regulate uncertain observations according to their reliability and avoid converting transient disturbances into persistent spatial references. Inspired by reliability-weighted multisensory integration and by a functional abstraction of persistence-based evidence consolidation in biological navigation, this paper proposes a bio-inspired reliability-constrained LiDAR–inertial odometry framework. Each point-to-map observation is evaluated using residual consistency, local geometric quality, and voxel-level temporal stability. The fused reliability score regulates both the ESIKF state update and incremental map maintenance: low-confidence observations are continuously down-weighted, highly reliable points are admitted to the persistent map, ambiguous points are retained in short-term candidate memory for multi-frame verification, and unreliable points are rejected. The framework translates biological design principles into an engineering perception–memory architecture rather than reproducing a specific neural circuit. Repeated experiments on public datasets and a wheeled mobile robot platform show comparable accuracy in two normal sequences. Across five dynamic sequences, the complete method reduces localization RMSE by 14.08–28.88% relative to Fast-LIO2 and achieves lower mean RMSE than Dynamic-LIO on all five evaluated dynamic sequences. Frozen-map evaluation further yields 7.77–15.71% lower point-to-map RMSE together with higher consistent-correspondence ratios and coverage, while the maximum mean RMSE deviation in the parameter-sensitivity study remains below 7.2%. The maximum measured processing time is 18.69 ms per scan, maintaining real-time operation for a 10 Hz LiDAR.
Human augmentation is an important branch of robotics research aimed at reducing metabolic energy consumption, delaying fatigue, and increasing body speed. However, existing evaluation protocols lack systematic frameworks for unpowered hip devices. This study aims to reduce the energy consumption of human movement without providing additional power and to develop a hip-assisted exoskeleton device. Through gait, plantar pressure, and electromyography tests, the system studied the assistance performance of exoskeletons in three wearing states: “No exo.”, “Exo. on”, and “Exo. off”. A comprehensive evaluation method of unpowered lower limb wearable exoskeleton (CE-ULLWE) is established, featuring the novel three-condition design that isolates the structural mass effect from true assistance via the “Exo. off” condition, and integrates multi-indicator metrics including kinematics, dynamics, plantar pressure, EMG, and metabolic simulations. Combining wearing and exercise testing to obtain the human–machine compatibility of exoskeletons and the subjective comfort of users when wearing exoskeletons. Experimental results demonstrate that wearing the exoskeleton increases peak hip and knee angular velocities by 18.5% and 9.0%, reduces joint power, decreases plantar pressure center excursion by 32.3%, and lowers total metabolic energy consumption by 16.0%, confirming its effectiveness in reducing metabolic cost and delaying fatigue. This achievement has important theoretical guidance and practical application value for the design, function, and performance evaluation of wearable assistive exoskeleton products. The proposed CE-ULLWE offers a replicable, multi-indicator framework that clarifies assistive efficacy and guides future exoskeleton optimization.
Compliant muscle–tendon mechanics can improve terrain adaptation in musculoskeletal robots, but heterogeneous terrains impose competing requirements on compliance, propulsion, foot clearance, and support transfer. This paper proposes Value-Gradient Generalist Design (VGGD), a framework for selecting one fixed physiological muscle–tendon parameterization for cross-terrain locomotion while preserving skeletal topology and muscle routing. VGGD searches a compact PCA-based manifold that coordinates bounded scale factors for muscle strength, contraction-velocity capacity, and passive elastic response. A design- and terrain-conditioned value proxy is learned from sampled latent designs and then optimized by proximity-regularized projected value-gradient ascent under a soft-worst objective. Independent proxy validation uses 50 random designs solely for calibration and 100 separately sampled test designs excluded from fitting and Stage-B optimization. On the 100-design test set, the proxy shows positive agreement with mean cross-terrain return (Pearson r=0.580, Spearman ρ=0.565) and worst-terrain return (r=0.583, ρ=0.551), with all bootstrap intervals above zero and Holm-adjusted permutation p=0.0006. A separate paired local-direction test uses 60 previously unused evaluation seeds and equal feasible-space perturbation radii; at the nominal, midpoint, and selected designs, the proxy-gradient direction agrees with improvements in mean and seed-wise worst-terrain rollout return. After design selection, the muscle–tendon parameters are fixed, and a terrain-aware controller is trained with variational information-bottleneck regularization and auxiliary expert distillation. Checkpoint-resolved evaluation records identify 216/300 successes and an overall mean distance of 12.14 m for the complete pipeline, compared with 57/300 and 6.20 m for nominal-body PPO. The three checkpoint success rates are 84%, 78%, and 54% for Proposed and 49%, 0%, and 8% for PPO; exact two-sided policy-level permutation tests yield p=0.10 for success rate and p=0.20 for mean distance. All methods receive the same nominal 100-million-step final-controller budget per training run, while the 10 M Stage-A budget and expert-pretraining costs are reported separately.
Long-horizon robotic manipulation requires coordinating multiple motor primitives under uncertainty, especially in contact-rich and changing environments. Existing end-to-end visuomotor policies often lack explicit temporal structure, causing brittle execution and limited recovery after disturbances. Inspired by biological motor control, where reusable primitives are organized through phase decomposition and feedback-dependent transitions, we propose a bio-inspired phase-aware framework that represents execution as structured transitions over perception-grounded motor phases. The framework integrates three modules: a Multimodal Phase-and-Primitive Detector that extracts semantically and physically consistent phases from visual, proprioceptive, and force–torque signals; a Multimodal Perception Skill Graph (MPSG) that encodes feasible phase transitions and supports skipping, rollback, and recovery; and Promptable Phase Control, which converts language instructions into graph-level ordering constraints for task reordering without retraining low-level policies. Experiments on four multi-stage tasks show improved robustness, increasing the average disturbed-condition success rate from 25.0% to 73.8% relative to the monolithic Action Chunking with Transformers (ACT) baseline.
Developmental and adult neurotoxicity are hard to assess with conventional in vitro assays, which rarely account for how a chemical actually distributes once inside the body. Biomimetic chromatography offers a practical way to fill that gap, using stationary phases that mimic phospholipid membranes and major plasma proteins to yield experimental descriptors of lipophilicity, membrane affinity, and protein binding without needing radiolabeled compounds or large sample amounts. Working within the Partnership for the Assessment of Risk from Chemicals, we profiled 67 neurotoxicology-relevant chemicals on immobilized artificial membrane, human serum albumin, and alpha-1-acid glycoprotein columns alongside lipophilicity measured at three pH values. The chromatographic lipophilicity scale matched literature log p values closely. Principal component and hierarchical cluster analyses of the seven descriptors pointed to one dominant hydrophobicity axis and a smaller, second axis tied to ionization and albumin binding. The panel’s overall chromatographic profile did not separate neurotoxic from non-neurotoxic reference compounds, but the most membrane- and protein-avid compounds were disproportionately positive controls and warrant closer attention. The resulting dataset gives New Approach Methodologies a ready, experimentally grounded input for in vitro-to-in vivo extrapolation and baseline toxicity assessment.
Nighttime driving safety remains a critical challenge in modern transportation systems: insufficient ambient lighting significantly degrades visual perception quality, adversely affecting both human drivers and advanced driver-assistance systems (ADAS) and directly threatening road users’ safety. Traditional image enhancement methods often suffer from color distortion and visual artifacts, whereas existing deep learning approaches typically require paired training data and incur substantial computational overhead. To address these limitations, this paper presents BLEN (bio-inspired low-light enhancement network), a zero-reference deep learning framework that integrates biological vision principles with efficient convolutional architectures. Specifically, BLEN leverages Retinex theory for illumination–reflectance decomposition, is inspired by and functionally approximates lateral inhibition mechanisms for edge enhancement, and incorporates a Large-Kernel Convolution with Attention (LKCA) module that reduces the parameter count of the LKCA encoder block by 76% (0.56 M vs. 2.34 M for a standard 13 × 13 convolution) relative to standard large-kernel operations. Extensive experiments on the SICE and LOL benchmarks demonstrate that BLEN achieves state-of-the-art performance among real-time, edge-deployable zero-reference methods on the SICE benchmark, yielding a peak signal-to-noise ratio (PSNR) of 23.67 ± 0.14 dB and a structural similarity index measure (SSIM) of 0.891 ± 0.004 on SICE while maintaining 2.10 M parameters (2.1 MB in INT8, 8.4 MB in FP32). Furthermore, the proposed method enables real-time inference at 31 frames per second (FPS) on embedded platforms, including the HiSilicon SS928 and Jetson Nano, demonstrating that the proposed method is an efficient and effective front-end for camera-based ADAS perception on automotive-grade edge hardware.
Replicating the nonlinear, pressure-dependent mechanical behavior of native arteries remains a central challenge in small-diameter vascular graft design, where compliance mismatch between synthetic grafts and host vessels is strongly linked to graft failure. Building on a silk fiber-reinforced alginate-polyacrylamide interpenetrating polymer network (IPN) hydrogel platform, we investigated whether biomimetic vascular structural motifs, specifically fiber reorientation and crimp, can be used as programmable design parameters to tune the tensile and pressure-dependent mechanical response of tubular constructs toward native coronary artery behavior. Three architectures were fabricated: a cross-plied (CP) baseline, a 25° reoriented configuration, and a crimped CP configuration. Under internal pressurization, fiber reorientation and crimp significantly increased compliance at low physiological pressures, with a consistent directional trend across the full pressure range, by extending the low-stiffness toe region preceding fiber recruitment while preserving tensile stiffness. Across the investigated pressure range, all architectures exhibited compliance within the reported range of native coronary arteries, with crimped constructs producing pressure-diameter behavior that most closely resembled young coronary arteries, whereas the CP baseline more closely resembled aged coronary arteries. These findings demonstrate that biomimetic structural motifs, without altering material composition, can serve as programmable design parameters for engineering vascular mechanics, enabling a single material platform to reproduce distinct physiological mechanical phenotypes through architecture alone.
This paper presents a load-capacity-constrained arm-angle planning method for a centrally driven humanoid robotic arm. Joint-range and singularity constraints are projected into the one-dimensional arm-angle domain to form a geometric feasible set. A static load-capacity constraint is derived from gravity torque, the Jacobian-transpose mapping of a known endpoint load, and individual actuator-torque limits, and is projected into the same domain. Continuous arm-angle values are then selected along a prescribed Cartesian path within the intersection of the geometric and mechanical feasible sets. In a heavy-load simulation, the maximum output-power metric decreased by 13.3%, and the energy value decreased from 30.60 J to 22.95 J (25.0%). In a prototype proof-of-principle test with a 13 N payload (approximately 1.33 kg), each trajectory was executed three times; the controller-recorded shoulder peak was approximately 1.83% lower, and the recorded energy value decreased from 30.378 J to 28.85 J (5.03%). The prototype values are descriptive because run-level statistics and measurement uncertainty are unavailable, and the experiment covers only one payload and one path. The results support the proposed static, load-capacity-aware planning principle for the tested slow-motion conditions but do not establish general performance or real-time suitability.
