Search Results (82)

Based on the current issues of difficulty in clearing intra-row weeds in orchards, inaccurate sensor detection, and the inability to adjust the row spacing depth, this study designs an intelligent intra-row obstacle avoidance and weeding machine for orchards. We designed the weeding machine’s sensor device, depth-limiting device, row spacing adjustment mechanism, joystick-based obstacle avoidance mechanism, weeding shovel, and hydraulic system. The sensor device integrates non-contact sensors and a mechanical tactile structure, which overcomes the instability of non-contact detection and avoids the risk of collision obstacle avoidance by the weeding parts. The weeding shovel can be adapted to the environments of orchards with small plant spacing. The combination of the sensor device and the obstacle avoidance mechanism realizes flexible obstacle avoidance. We used Ansys Workbench to conduct static and vibration modal analyses on the chassis of the in-field weeding machine. On this basis, through topology optimization, the chassis quality of the weeding machine is reduced by 8%, which realizes the goal of light weight and ensures the stable operation of the machinery. To further optimize the weeding operation parameters, we employed the Box–Behnken design response surface analysis, with weeding coverage as the optimization target. We systematically explored the effects of forward speed, hydraulic cylinder extension speed, and retraction speed on the weeding efficiency. The optimal operational parameter combination determined by this study for the weeding machine is as follows: forward speed of 0.5 m/s, hydraulic cylinder extension speed of 11.5 cm/s, and hydraulic cylinder retraction speed of 8 cm/s. Based on the theoretical analysis and scenario simulations, we validated the performance of the weeding machine through field experiments. The results show that the weeding machine, while exhibiting excellent obstacle avoidance performance, can achieve a maximum weeding coverage of 84.6%. This study provides a theoretical foundation and technical support for the design and development of in-field mechanical weeding, which is of great significance for achieving intelligent orchard management and further improving fruit yield and quality. Full article

Wind is one of the most important resources in the renewable energy basket. However, there are questions regarding wind as a sustainable solution, especially concerning its upfront costs, visual impact, noise pollution, and bird collisions. These challenges arise in commercial windmills, whereas for domestic small-scale windmills, these challenges are limited. On the other hand, accurate wind speed prediction (WSP) is crucial for optimizing power management in renewable energy systems. Existing research focuses on proposing model architectures and optimizing hyperparameters to improve model performance. This approach often results in larger models, which are hosted on cloud servers. Such models face challenges, including bandwidth utilization leading to data delays, increased costs, security risks, concerns about data privacy, and the necessity of continuous internet connectivity. Such resources are not available for domestic windmills. To overcome these obstacles, this work proposes a transformer model integrated with Long Short-Term Memory (LSTM) units, optimized for memory-constrained devices (MCDs). A contribution of this research is the development of a novel cost function that balances the reduction of mean squared error with the constraints of model size. This approach enables model deployment on low-power devices, avoiding the challenges of cloud-based deployment. The model, with its tuned hyperparameters, outperforms recent methodologies in terms of mean squared error, mean absolute error, model size, and R-squared scores across three different datasets. This advancement paves the way for more dynamic and secure on-device wind speed prediction (WSP) applications, representing a step forward in renewable energy management. Full article

This study employs Monte Carlo (MC) models and thermal-statistical analysis to investigate the production mechanisms of strange ($K_S^0$, $\mathrm{\Lambda }$) and multi-strange ($\mathrm{\Xi }$, $\mathrm{\Omega }$) hadrons in high-multiplicity proton–proton collisions. Through systematic comparisons with experimental data, we evaluate the predictive power of EPOS, PYTHIA8, QGSJETII04, and Sibyll2.3d. EPOS, with its hydrodynamic evolution, successfully reproduces low-$p_T$$K_S^0$ and $\mathrm{\Lambda }$ yields in high-multiplicity classes (MC1–MC3), mirroring quark-gluon plasma (QGP) thermalization effects. PYTHIA8’s rope hadronization partially mitigates mid-$p_T$ multi-strange baryon suppression but underestimates $\mathrm{\Xi }$ and $\mathrm{\Omega }$ yields due to the absence of explicit medium dynamics. QGSJETII04, tailored for cosmic-ray showers, overpredicts soft $K_S^0$ yields from excessive soft Pomeron contributions and lacks multi-strange hadron predictions due to enforced decays. Sibyll2.3d’s forward-phase bias limits its accuracy at midrapidity. No model fully captures $\mathrm{\Xi }$ and $\mathrm{\Omega }$ production, though EPOS remains the closest. Complementary Tsallis distribution analysis reveals a distinct mass-dependent hierarchy in the extracted effective temperature ($T_{\mathrm{eff}}$) and non-extensivity parameter (q). As multiplicity decreases, $T_{\mathrm{eff}}$ rises while q declines—a trend amplified for heavier particles. This suggests faster equilibration of heavier particles compared to lighter species. The interplay of these findings underscores the necessity of incorporating QGP-like medium effects and refined strangeness enhancement mechanisms in MC models to describe small-system collectivity. Full article

Autonomous drifting is an advanced technique that enhances vehicle maneuverability beyond conventional driving limits. This survey provides a comprehensive, systematic review of autonomous drifting research published between 2005 and early 2025, analyzing approximately 80 peer-reviewed studies. We employed a modified PRISMA approach to categorize and evaluate research across two main methodological frameworks: dynamical model-based approaches and deep learning techniques. Our analysis reveals that while dynamical methods offer precise control when accurately modeled, they often struggle with generalization to unknown environments. In contrast, deep learning approaches demonstrate better adaptability but face challenges in safety verification and sample efficiency. We comprehensively examine experimental platforms used in the field—from high-fidelity simulators to full-scale vehicles—along with their sensor configurations and computational requirements. This review uniquely identifies critical research gaps, including real-time performance limitations, environmental generalization challenges, safety validation concerns, and integration issues with broader autonomous systems. Our findings suggest that hybrid approaches combining model-based knowledge with data-driven learning may offer the most promising path forward for robust autonomous drifting capabilities in diverse applications ranging from motorsports to emergency collision avoidance in production vehicles. Full article

The primary challenge is to design feedback controls that enable robots to autonomously reach predetermined destinations while avoiding collisions with obstacles and other robots. Various control algorithms, such as the control barrier function-based quadratic programming (CBF-QP) controller, address collision avoidance problems. Control barrier functions (CBFs) ensure forward invariance, which is critical for guaranteeing safety in robotic collision avoidance within agricultural fields. The goal of this study is to enhance the safety and mitigation of potential collisions in smart agriculture systems. The entire system was simulated in the MATLAB/Simulink environment, and the results demonstrated a 93% improvement in steady-state error over rapidly exploring random tree (RRT). These findings indicate that the proposed controller is highly effective for collision avoidance in smart agricultural systems. Full article

Trajectory prediction is critical for ensuring the safety, reliability, and scalability of Unmanned Aerial Vehicle (UAV) in urban environments. Despite advances in deep learning, existing methods often struggle with dynamic UAV conditions, such as rapid directional changes and limited forecasting horizons, while lacking comprehensive real-time validation and generalization capabilities. This study addresses these challenges by proposing a gated recurrent unit (GRU)-based deep learning framework optimized through Look_Back and Forward_Length labeling to capture complex temporal patterns. The model demonstrated state-of-the-art performance, surpassing existing unmanned aerial vehicles (UAV) and aircraft trajectory prediction approaches, including FlightBERT++, in terms of both accuracy and robustness. It achieved reliable long-range predictions up to 4 s, and its real-time feasibility was validated due to its efficient resource utilization. The model’s generalization capability was confirmed through evaluations on two independent UAV datasets, where it consistently predicted unseen trajectories with high accuracy. These findings highlight the model’s ability to handle rapid maneuvers, extend prediction horizons, and generalize across platforms. This work establishes a robust trajectory prediction framework with practical applications in collision avoidance, mission planning, and anti-drone systems, paving the way for safer and more scalable UAV operations. Full article

In the domain of autonomous driving, trajectory prediction plays a pivotal role in ensuring the safety and reliability of autonomous systems, especially when navigating complex environments. Unfortunately, trajectory prediction suffers from uncertainty problems due to the randomness inherent in the driving environment, but uncertainty quantification in trajectory prediction is not widely addressed, and most studies rely on deep ensembles methods. This study presents a novel uncertainty-aware multimodal trajectory prediction (UAMTP) model that quantifies aleatoric and epistemic uncertainties through a single forward inference. Our approach employs deterministic single forward pass methods, optimizing computational efficiency while retaining robust prediction accuracy. By decomposing trajectory prediction into velocity and yaw components and quantifying uncertainty in both, the UAMTP model generates multimodal predictions that account for environmental randomness and intention ambiguity. Evaluation on datasets collected by CARLA simulator demonstrates that our model not only outperforms Deep Ensembles-based multimodal trajectory prediction method in terms of accuracy such as minFDE and miss rate metrics but also offers enhanced time to react for collision avoidance scenarios. This research marks a step forward in integrating efficient uncertainty quantification into multimodal trajectory prediction tasks within resource-constrained autonomous driving platforms. Full article

As the demand for autonomous driving (AD) systems has increased, the enhancement of their safety has become critically important. A fundamental capability of AD systems is object detection and trajectory forecasting of vehicles and pedestrians around the ego-vehicle, which is essential for preventing potential collisions. This study introduces the Deep learning-based Acceleration-aware Trajectory forecasting (DAT) model, a deep learning-based approach for object detection and trajectory forecasting, utilizing raw sensor measurements. DAT is an end-to-end model that processes sequential sensor data to detect objects and forecasts their future trajectories at each time step. The core innovation of DAT lies in its novel forecasting module, which leverages acceleration data to enhance trajectory forecasting, leading to the consideration of a variety of agent motion models. We propose a robust and innovative method for estimating ground-truth acceleration for objects, along with an object detector that predicts acceleration attributes for each detected object and a novel method for trajectory forecasting. DAT is trained and evaluated on the NuScenes dataset, demonstrating its empirical effectiveness through extensive experiments. The results indicate that DAT significantly surpasses state-of-the-art methods, particularly in enhancing forecasting accuracy for objects exhibiting both linear and nonlinear motion patterns, achieving up to a $2\times$ improvement. This advancement highlights the critical role of incorporating acceleration data into predictive models, representing a substantial step forward in the development of safer autonomous driving systems. Full article

This paper introduces an enhanced APF method to address challenges in automatic lane changing and collision avoidance for autonomous vehicles, targeting issues of infeasible target points, local optimization, inadequate safety margins, and instability when using DLQR. By integrating a distance adjustment factor, this research aims to rectify traditional APF limitations. A safety distance model and a sub-target virtual potential field are established to facilitate collision-free path generation for autonomous vehicles. A path tracking system is designed, combining feed-forward control with DLQR. Linearization and discretization of the vehicle’s dynamic state space model, with constraint variables set to minimize control-command costs, aligns with DLQR objectives. The aim is precise steering angle determination for path tracking, negating lateral errors due to external disturbances. A Simulink–CarSim co-simulation platform is utilized for obstacle and speed scenarios, validating the autonomous vehicle’s dynamic hazard avoidance, lane changing, and overtaking capabilities. The refined APF method enhances path safety, smoothness, and stability. Experimental data across three speeds reveal reasonable steering angle and lateral deflection angle variations. The controller ensures stable reference path tracking at 40, 50, and 60 km/h around various obstacles, verifying the controller’s effectiveness and driving stability. Comparative analysis of visual trajectories pre-optimization and post-optimization highlights improvements. Vehicle roll and sideslip angle peaks, roll-angle fluctuation, and front/rear wheel steering vertical support forces are compared with traditional LQR, validating the optimized controller’s enhancement of vehicle performance. Simulation results using MATLAB/Simulink and CarSim demonstrate that the optimized controller reduces steering angles by 5 to 10°, decreases sideslip angles by 3 to 5°, and increases vertical support forces from 1000 to 1450 N, showcasing our algorithm’s superior obstacle avoidance and lane-changing capabilities under dynamic conditions. Full article

This paper focuses on the acceptance of ADASs in the traffic safety and human factor domain. More specifically, it examines the predictive validity of the Unified Model of Driver Acceptance (UMDA) for an ADAS bundle that includes forward collision warning, headway monitoring and warning, and lane-keeping assistance in Belgium and Vietnam, two substantially different geographical, socio-cultural, and macroeconomic settings. All systems in the studied ADAS bundle are located at the Society of Automotive Engineer (SAE)-level 0 of automation. We found moderate acceptance towards such an ADAS bundle in both countries, and respondents held rather positive opinions about system-specific characteristics. In terms of predictive validity, the UMDA scored quite well in both countries, though better in Belgium than in Vietnam. Macroeconomic factors and socio-cultural characteristics could explain these differences between the two countries. Policymakers are encouraged to prioritise initiatives that stimulate the purchase and use of the ADAS, rather than on measures meant to influence the underlying decisional balance. Full article

Recent progress in autonomous vehicle technology has led to the development of accurate and efficient tools for ensuring safety, which is crucial for verifying the reliability and security of vehicles. These vehicles operate under diverse conditions, necessitating the analysis of varying initial conditions and parameter values. Ensuring the safe operation of the vehicle under all these varying conditions is essential. Reachability analysis is an important tool to certify the safety and stability of the vehicle dynamics. We propose a reachability analysis approach for evaluating the response of the vehicle dynamics, specifically addressing uncertainties in the initial states and model parameters. Reachable sets illustrate all the possible states of a dynamical system that can be obtained from a given set of uncertain initial conditions. The analysis is crucial for understanding how variations in initial conditions or system parameters can lead to outcomes such as vehicle collisions or deviations from desired paths. By mapping out these reachable states, it is possible to design systems that maintain safety and reliability despite uncertainties. These insights help to ensure the stability and reliability of the vehicles, even in unpredictable conditions, by reducing accidents and optimizing performance. The nonlinearity of the model complicates the computation of reachable sets in vehicle dynamics. This paper proposes a Koopman theory-based approach that utilizes the Koopman principal eigenfunctions and the Koopman spectrum. By leveraging the Koopman principal eigenfunction, our method simplifies the computational process and offers a formal approximation for backward and forward reachable sets. First, our method effectively computes backward and forward reachable sets for a nonlinear quarter-car model with fixed parameter values. Furthermore, we applied our approach to analyze the uncertainty response for cases with uncertain parameters of the vehicle model. When compared to time-domain simulations, our proposed Koopman approach provided accurate results and also reduced the computational time by half in most cases. This demonstrates the efficiency and reliability of our proposed approach in dynamic systems uncertainty analysis using the reachable sets. Full article

As the commercialisation of Intelligent Connected Vehicles (ICVs) accelerates, Vehicle-to-Everything (V2X)-based general testing and assessment systems have emerged at the forefront of the research. Current field testing schemes mostly follow the norms of traditional vehicle tests. In contrast, Original Equipment Manufacturers (OEMs) have increasingly focused on the potential influence of V2X communication performance on the application response characteristics. Our previous work resulted in a C-V2X (Cellular-V2X) large-scale testing system (LSTS) for communication performance testing. However, when addressing the need to combine application and communication, the system software faces confronts heightened technical challenges. This paper proposes a layered software architecture for the automated C-V2X LSTS, which is tailored to combined scenarios. This architecture integrates scenario encapsulation technology with a large-scale node array deployment strategy, enabling communication and application testing under diversified scenarios. The experimental results demonstrate the scalability of the system, and a case study of Forward Collision Warning (FCW) validates the effectiveness and reliability of the system. Full article

Animals utilize their well-evolved dynamic vision systems to perceive and evade collision threats. Driven by biological research, bio-inspired models based on lobula giant movement detectors (LGMDs) address certain gaps in constructing artificial collision-detecting vision systems with robust selectivity, offering reliable, low-cost, and miniaturized collision sensors across various scenes. Recent progress in neuroscience has revealed the energetic advantages of dendritic arrangements presynaptic to the LGMDs, which receive contrast polarity-specific signals on separate dendritic fields. Specifically, feed-forward inhibitory inputs arise from parallel ON/OFF pathways interacting with excitation. However, none of the previous research has investigated the evolution of a computational LGMD model with feed-forward inhibition (FFI) separated by opposite polarity. This study fills this vacancy by presenting an optimized neuronal model where FFI is divided into ON/OFF channels, each with distinct synaptic connections. To align with the energy efficiency of biological systems, we introduce an activation function associated with neural computation of FFI and interactions between local excitation and lateral inhibition within ON/OFF channels, ignoring non-active signal processing. This approach significantly improves the time efficiency of the LGMD model, focusing only on substantial luminance changes in image streams. The proposed neuronal model not only accelerates visual processing in relatively stationary scenes but also maintains robust selectivity to ON/OFF-contrast looming stimuli. Additionally, it can suppress translational motion to a moderate extent. Comparative testing with state-of-the-art based on ON/OFF channels was conducted systematically using a range of visual stimuli, including indoor structured and complex outdoor scenes. The results demonstrated significant time savings in silico while retaining original collision selectivity. Furthermore, the optimized model was implemented in the embedded vision system of a micro-mobile robot, achieving the highest success ratio of collision avoidance at 97.51% while nearly halving the processing time compared with previous models. This highlights a robust and parsimonious collision-sensing mode that effectively addresses real-world challenges. Full article

The development of autonomous driving vehicles has increased the global demand for robust and efficient automotive radar systems. This study proposes an automotive radar-based ego-vehicle speed detection network (AVSD Net) model using convolutional neural networks for estimating the speed of the ego vehicle. The preprocessing and postprocessing methods used for vehicle speed correction are presented in detail. The AVSD Net model exhibits characteristics that are independent of the angular performance of the radar system and its mounting angle on the vehicle, thereby reducing the loss of the maximum detection range without requiring a downward or wide beam for the elevation angle. The ego-vehicle speed is effectively estimated when the range–velocity spectrum data are input into the model. Moreover, preprocessing and postprocessing facilitate an accurate correction of the ego-vehicle speed while reducing the complexity of the model, enabling its application to embedded systems. The proposed ego-vehicle speed correction method can improve safety in various applications, such as autonomous emergency braking systems, forward collision avoidance assist, adaptive cruise control, rear cross-traffic alert, and blind spot detection systems. Full article

The Cislunar economy is thriving with innovative space systems and operation techniques to enhance and uplift the traditional approaches significantly. This paper brings about an approach for sustainable small satellite constellations to retain autonomy for long-term missions in the Cislunar space. The methodology presented is to align the hybrid model of the constellation for Earth and Moon as an integral portion of the Cislunar operations. These hybrid constellations can provide a breakthrough in optimally utilizing the Cislunar space to efficiently deploy prominent missions to be operated and avoid conjunction or collisions forming additional debris. Flower and walker constellation patterns have been combined to form a well-defined orientation for these small satellites to operate and deliver the tasks satisfying the mission objectives. The autonomous multi-parametric analysis for each constellation based in Earth and Moon’s environment has been attained with due consideration to local environments. Specifically, the Solar Radiation Pressure (SRP) is a critical constraint in Cislunar operations and is observed during simulations. These are supported by conjunction analysis using the Monte Carlo technique and also the effect of the SRP on the operating small satellites in real-time scenarios. This is followed by the observed conclusions and the way forward in this fiercely competent Cislunar operation. Full article