Avoidance System Research Articles

Improvement in Collision Avoidance in Cut-In Maneuvers Using Time-to-Collision Metrics

This paper proposes a new strategy for a collision avoidance system leveraging time-to-collision (TTC) metrics for handling cut-in scenarios, which are particularly challenging for autonomous vehicles (AVs). By integrating deep learning with TTC calculations, the system predicts potential collisions and determines appropriate evasive actions compared to traditional TTC-based approaches. The methodology is validated through extensive simulations, demonstrating a significant improvement in collision avoidance performance compared to traditional TTC-based approaches. By integrating deep learning models with TTC calculations, the system predicts potential collisions and determines appropriate evasive actions. The use of the Gaussian model to contributes to time-to-collision (TTC) analysis by providing a probabilistic framework to quantify collision risk under uncertainty. It calculates the likelihood that TTC will fall below a critical threshold (TTC_crit), indicating a potential collision. By modeling input variations—such as sensor inaccuracies, fluctuating vehicle velocity, and unpredictable driving behavior—as a Gaussian distribution, the system can handle real-world uncertainties more effectively. This enables continuous, real-time risk prediction, allowing for dynamic and adaptive collision avoidance decisions. The Gaussian approach enhances the robustness of TTC-based systems by improving their ability to predict and prevent collisions in uncertain driving conditions.

PC-CS-YOLO: High-Precision Obstacle Detection for Visually Impaired Safety.

The issue of obstacle avoidance and safety for visually impaired individuals has been a major topic of research. However, complex street environments still pose significant challenges for blind obstacle detection systems. Existing solutions often fail to provide real-time, accurate obstacle avoidance decisions. In this study, we propose a blind obstacle detection system based on the PC-CS-YOLO model. The system improves the backbone network by adopting the partial convolutional feed-forward network (PCFN) to reduce computational redundancy. Additionally, to enhance the network's robustness in multi-scale feature fusion, we introduce the Cross-Scale Attention Fusion (CSAF) mechanism, which integrates features from different sensory domains to achieve superior performance. Compared to state-of-the-art networks, our system shows improvements of 2.0%, 3.9%, and 1.5% in precision, recall, and mAP50, respectively. When evaluated on a GPU, the inference speed is 20.6 ms, which is 15.3 ms faster than YOLO11, meeting the real-time requirements for blind obstacle avoidance systems.

Study on automated guided vehicle collision avoidance mechanism with external computer vision

In industrial automation, safely operating Automated Guided Vehicles (AGVs) in dynamic environments is challenging. Traditional collision avoidance methods, which rely on technologies like LiDAR (Light Detection and Ranging), have limitations in detection range, accuracy, and cost. This study introduces a new method called the Collision Avoidance System with External Computer Vision (CAECV). CAECV uses two cameras which are equipped on the wall in the factory to detect obstacles, and AGV don’t need to equip any obstacle detection sensors. The detection algorithm, combining YOLOv8 with an attention mechanism, excels at identifying obstacles. The system then converts image coordinates to global coordinates using inverse perspective mapping for precise obstacle localization. Experimental comparisons with traditional TIM laser scanning radar show that CAECV outperforms in detection range, response time, accuracy, and cost. CAECV offers a broader detection range, quicker response, and lower error rates. As more AGVs are deployed, CAECV becomes significantly more cost-effective than LiDAR-based systems. Moreover, CAECV can be integrated with LiDAR systems to enhance AGV obstacle avoidance. CAECV represents a scalable, accurate, and economical advancement in AGV collision avoidance technology for modern industrial use.

A Comparative Study of Rapidly-exploring Random Tree Algorithms Applied to Ship Trajectory Planning and Behavior Generation

Rapidly Exploring Random Tree (RRT) algorithms, notably used for nonholonomic vehicle navigation in complex environments, are often not thoroughly evaluated for their specific challenges. This paper presents a first such comparison study of the variants Potential-Quick RRT* (PQ-RRT*), Informed RRT* (IRRT*), RRT*, and RRT, in maritime single-query nonholonomic motion planning. Additionally, the practicalities of using these algorithms in maritime environments are discussed and outlined. We also contend that these algorithms are beneficial not only for trajectory planning in Collision Avoidance Systems (CAS) but also for CAS verification when used as vessel behavior generators. Optimal RRT variants tend to produce more distance-optimal paths but require more computational time due to complex tree wiring and nearest neighbor searches. Our findings, supported by Welch’s t-test at a significance level of α=0.05, indicate that PQ-RRT* slightly outperform IRRT* and RRT* in achieving shorter trajectory length but at the expense of higher tuning complexity and longer run-times. Based on the results, we argue that these RRT algorithms are better suited for smaller-scale problems or environments with low obstacle congestion ratio. This is attributed to the curse of dimensionality, and trade-off with available memory and computational resources.

Active collision avoidance system based on TimesNet behavioral game model and ABAPF risk quantification map

Active collision avoidance system based on TimesNet behavioral game model and ABAPF risk quantification map

Computational investigation of explosion avoidance system of multi tier Li-ion battery pack

Computational investigation of explosion avoidance system of multi tier Li-ion battery pack

Design and Performance Optimization of Collision Avoidance System for Mechanical Vehicles

A collision avoidance system is designed and optimized in this study. The architecture design, signal processing and data fusion of the system are analyzed in detail, and the sensor selection, control unit integration and algorithm optimization are discussed. In this paper, a performance optimization method based on collision prediction algorithm and real-time and stability of the system is proposed, which solves the problems of system response delay and high false alarm rate, further discusses the optimization strategy of system integration and communication module, and achieves the effect of efficient cooperation and remote monitoring between systems.

Cooperation Dynamics in Multiagent Systems: Modeling Vehicular Cooperation through Game Theory

<div>Cooperation lies at the core of multiagent systems (MAS) and multiagent reinforcement learning (MARL), where agents must navigate between individual interests and collective benefits. Advanced driver assistance systems (ADAS), like collision avoidance systems and adaptive cruise control, exemplify agents striving to optimize personal and collective outcomes in multiagent environments. The study focuses on strategies aimed at fostering cooperation with the aid of game-theoretic scenarios, particularly the iterated prisoner’s dilemma, where agents aim to optimize personal and group outcomes. Existing cooperative strategies, such as tit-for-tat and win-stay lose-shift, while effective in certain contexts, often struggle with scalability and adaptability in dynamic, large-scale environments. The research investigates these limitations and proposes modifications to align individual gains with collective rewards, addressing real-world dilemmas in distributed systems. By analyzing existing cooperative strategies, the research investigates their effectiveness in encouraging group-oriented behavior in repeated games. It suggests modifications to align individual gains with collective rewards, addressing real-world dilemmas in distributed systems. Furthermore, it extends to scenarios with exponentially growing agent populations (<i>N</i> → +∞), addressing computational challenges using mean-field game theory to establish equilibrium solutions and reward structures tailored for infinitely large agent sets. Practical insights are provided by adapting simulation algorithms to create scenarios conducive to cooperation for group rewards. Additionally, the research advocates for incorporating vehicular behavior as a metric to assess the induction of cooperation, bridging theoretical constructs with real-world applications.</div>

Evaluation of collision detection and avoidance methods for urban air mobility through simulation

AbstractUrban Air Mobility is a new concept of regional aviation that has been growing in popularity as a solution to the issue of ever-increasing ground traffic. Electric vehicles with vertical take-off and landing capabilities are developed by numerous market companies as a result of the push toward environmentally sustainable aviation. The next stage in this development process would be to define the concept of operation of these conceptual aircraft and then to integrate them with the existing airspace once they are airborne. In addition to coordinating with conventional air traffic and other Urban Air Mobility vehicles, collision avoidance with uncooperative airspace users has to be addressed. Birds and drones of all sizes pose a serious risk to these low-flying aircraft. Innovative collision detection and avoidance techniques need to be employed due to the non-cooperative nature of these airspace users and different performance characteristics of Urban Air Mobility vehicles compared to classical fixed-wing aircraft. The aim of this study is to evaluate the concept of one such system by means of fast-time simulations. This system builds, similarly to the Airborne Collision Avoidance System, on safety envelopes and rule-based collision avoidance to prevent collisions with non-cooperative airspace members. The system is designed to work with all aircraft configurations used for Urban Air Mobility operations. To assess its influence on safety and capacity, different scenarios are modeled by varying parameters, such as intruder type, location, flight path. The parameters assessed are differences in flight time and closest point of approach with and without the collision avoidance system in place. Moreover, the influence of different configurations of Urban Air Mobility aircraft on these parameters is analyzed. The results show that the separation between the ownship and intruder is increased substantially which leads to safe operations at bearable delay costs.

The influence and development of artificial intelligence on automobile emergency system

In the automobile industry, the application of artificial intelligence is more and more extensive, among which the emergency hedging system of automobile is one of the important fields of artificial intelligence application. With the increasing growth of automobiles, traffic road safety has become a topic often talked about in People's Daily life. With the rapid development of artificial intelligence, many automobile companies begin to use artificial intelligence to help the car emergency hedging system. Artificial intelligence will greatly enhance the timeliness, accuracy and safety of the automobile emergency system. This paper aims to discuss the influence and development of artificial intelligence on automobile emergency avoidance system, and analyze its advantages and disadvantages and future development trend. Which has a very obvious help to the automatic driving technology, but also laid the development of automatic driving technology.

Off-Highway Collision Avoidance System Leveraging Cellular Vehicle-to-Everything and Software-Defined Vehicle Architecture

<div>The off-highway industry witnesses a vast growth in integrating new technologies such as advance driver assistance systems (ADAS/ADS) and connectivity to the vehicles. This is primarily due to the need for providing a safe operational domain for the operators and other people. Having a full perception of the vehicle’s surrounding can be challenging due to the unstructured nature of the field of operation. This research proposes a novel collective perception system that utilizes a C-V2X Roadside Unit (RSU)-based object detection system as well as an onboard perception system. The vehicle uses the input from both systems to maneuver the operational field safely. This article also explored implementing a software-defined vehicle (SDV) architecture on an off-highway vehicle aiming to consolidate the ADAS system hardware and enable over-the-air (OTA) software update capability. Test results showed that FEV’s collective perception system was able to provide the necessary nearby and non-line-of-sight detections to the vehicle’s controls algorithms and the vehicle was able to navigate the environment safely.</div>

Fuzzy Inference-Based Adaptive Sonar Control for Collision Avoidance in Autonomous Underwater Vehicles

Abstract This article discusses the use of adaptive control in the sonar scanning sector within an obstacle detection system, to improve the effectiveness of collision avoidance for autonomous underwater vehicles (AUVs). An adaptive network-based fuzzy inference system (ANFIS) was used for dynamic calculations of the sonar scanning sector. Based on 100 simulation scenarios containing various trajectories created by the mission planner, with various shapes, dimensions and arrangements of static obstacles, and various arrangements and displacement vectors of dynamic obstacles, the effectiveness of the proposed system was tested in comparison with other classical approaches such as a single echosounder and sonar with a fixed scanning sector width. The above sensor configurations were evaluated in terms of the percentage of collision-free trials, the average percentage of trajectory completion, and the average number of activations of the collision avoidance system. Simulations conducted based on the mathematical model of the AUV confirmed that the proposed approach increased the effectiveness of collision avoidance systems for AUVs compared to classical echosounder and sonar-based systems.

Optimizing Consider-Covariance Models for Realistic Orbit Errors and Application to Collision Avoidance

Precise knowledge about the orbit state vectors and the associated uncertainties are crucial for reliable conjunction assessment and efficient mitigation of on-orbit collision risks through collision avoidance maneuvers by active satellites. The decision-making process heavily relies on the orbit accuracy and the uncertainty realism of the encountering objects, primarily space debris, and the maneuvering satellite itself. The process of determining an orbit creates an estimate of the orbit state and its associated state covariance matrix. This estimate serves as the initial value for predicting the orbit’s uncertainty at the time of closest approach. To determine and numerically propagate realistic orbit errors, the uncertainties of the dynamic model must be taken into account. One method that fulfils this purpose is consider covariance propagation, provided that suitable consider parameters and their variances have been established. This paper presents a novel method for optimizing the consider covariance parameters from past mission data. Real orbit data from multiple low Earth orbit satellites controlled by the DLR, German Aerospace Center’s German Space Operations Center are used to calibrate and evaluate different error models, including covariance parameters and other error terms. The results demonstrate improved uncertainty realism in orbit predictions and subsequent benefits for collision avoidance. Finally, this paper presents the required steps for integrating the new method into the existing collision avoidance system, along with initial results from conjunction assessment.

Towards safer general aviation operations using a vision-based decision support system for weather threat avoidance

The commercial aviation sector has achieved significant advancements in safety owing to robust Air Traffic Management technologies and rigorous regulatory measures. In contrast, General Aviation (GA) operations present unique safety challenges that demand focused attention. This study proposes an innovative decision support system tailored for GA pilots to augment their situational awareness. Our approach leverages on-board camera data in conjunction with semantic weather descriptors to construct an uncertainty-aware neural network model. The model provides predictions with quantified uncertainties while handling multiple labels and categories across diverse weather conditions. To validate the effectiveness of our framework, extensive experiments were conducted utilizing a flight simulator as a data collection platform. The results demonstrate that our model showcased significant improvements over the multiple baselines. We also found that a cost-sensitive learning approach can provide more conservative predictions while yielding performance improvements. Ultimately, our decision support framework aims to complement existing weather data sources, such as Next Generation Weather Radar (NEXRAD) data and Meteorological Aerodrome Reports (METAR) from airports, without imposing the burden of mounting expensive and bulky on-board weather radar systems.

Review of Recent Supreme Court Rulings on the Interpretation of the Korea-China Tax Treaty: Focusing on the Foreign Tax Credit System for Avoidance of Double Taxation and the Interpretation Principles of the OECD Model Tax Convention

Review of Recent Supreme Court Rulings on the Interpretation of the Korea-China Tax Treaty: Focusing on the Foreign Tax Credit System for Avoidance of Double Taxation and the Interpretation Principles of the OECD Model Tax Convention

The Summary of Artificial Intelligence Vehicle Obstacle Avoidance System

With the rapid increase in the global number of vehicles, frequent traffic accidents and urban traffic congestion have become urgent social problems that need to be solved. As an innovative solution, autonomous driving technology is gradually demonstrating its potential, and in this cutting-edge field, automatic obstacle avoidance technology is undoubtedly the core. It deeply integrates advanced sensing technology and intelligent control algorithms, aiming to enable vehicles to quickly make safe and accurate evasive actions when encountering potential obstacles. The evolution of automatic obstacle avoidance technology has gone beyond simple functional pursuits and shifted towards deep integration of various cutting-edge technologies to optimize obstacle avoidance efficiency. In summary, the innovation and development of automatic obstacle avoidance technology are leading the technological revolution in the field of autonomous driving, not only profoundly changing the mode of human vehicle interaction, but also having a profound impact on the vision of future smart city transportation systems.

Dynamic Obstacle Avoidance Technology Based on Multi-Sensor Fusion in Autonomous Driving

With the booming development of artificial intelligence and sensor technology, various types of devices are widely used in daily life and industry. This paper reviews the current state and prospects of multi-sensor fusion technology for dynamic obstacle avoidance in autonomous systems. The purpose of this paper is to discuss the application status and future development direction of multi-sensor fusion technology in dynamic obstacle avoidance. By analyzing the current research results and technical challenges, this paper will summarize how multi-sensor fusion technology can improve the performance of dynamic obstacle avoidance systems, and discuss the application of intelligent algorithms and future research directions The limitations of traditional single-sensor approaches are demonstrated through a single-sensor versus multi-sensor comparison, emphasizing the advantages of combining data from various sensors (e.g. lidar, cameras, and IMUs) to enhance environmental perception. This fusion improves obstacle detection accuracy and system robustness, particularly in complex urban environments. Despite significant advancements, challenges remain, including data management, real-time processing, and computational efficiency.

Proposed Outlook based on Different Obstacle Avoidance and Pathfinding Algorithms

Abstract. Currently, a variety of papers explore various directions in automated pathfinding and obstacle avoidance, with scholars developing diverse algorithmic models to address different theoretical frameworks. These models often enhance existing optimization algorithms or combine two distinct approaches to achieve improved results. In practical applications, it is common that no single paper can fully encompass the necessary background knowledge, which highlights the urgent need for a comprehensive article that integrates and enriches this knowledge base. Such a work would effectively address most path planning and obstacle avoidance challenges. This paper employs a literature review method to study automated pathfinding algorithms and obstacle avoidance systems. Its primary aim is to analyze cutting-edge research in these areas, providing a detailed examination and explanation of each relevant paper. Additionally, the paper critiques the current literature and the field as a whole, while also offering insights and prospects for future research directions in automated pathfinding and obstacle avoidance, ultimately contributing to advancements in the discipline.

A pursuit-evasion game robot controller design based on a neural network with an improved optimization algorithm

A pursuit-evasion game (PEG) is a type of game that utilizes one or several cooperative pursuers to capture one or several evaders. The PEG game concept has been used in different multi-robot applications such as transportation or navigation applications, search and rescue, surveillance applications such as collision avoidance and air traffic control systems, multi-defense applications such as missile guidance systems, and medical applications such as analyzing biological behaviors. Regardless of the benefits of PEG, one of the main drawbacks of such systems is the computational burden and the immense time required to learn such systems. For this reason, this work proposes a neural network game based on the pursuit-evasion game, where the leader (evader) robot tries to eat several particles/apples distributed inside a closed game environment with boundary and inner obstacles. In contrast, a follower (pursuer) robot tries to capture the leader robot and stop the particle-eating process. The leader and follower robots were designed based on a differential two-wheel robot (DTWR). The neural network is presented to control and learn the leader and follower robot directions with respect to the boundary and inside obstacles in the game environment. The neural network weights are learned using an improved sine cosine algorithm based on chaotic theory (ISCACT). The ISCACT is proposed to solve and avoid the proposed game of being trapped in the local minimum problem. The ISCACT is tested based on five multimodal benchmark functions. The ISCACT has been used in two cases, the first case arises when ISCACT is used in the follower robot’s learning process. In the second case, the ISCACT has been used in the leader robot’s learning process. The results for the first and second cases prove the superiority of the ISCACT compared with other existing works in enhancing the PEG performance time and reducing the computational burden for multi-robot applications.

Development of a Machine stereo vision-based autonomous navigation system for orchard speed sprayers

In orchards, radio frequency scintillation caused by high vegetation density can hinder the effectiveness of machinery auto guidance based on the Global Navigation Satellite System (GNSS). Signal interference not only leads to poor quality of machine operation but can also pose operational risks. In this work, we propose an alternative trajectory positioning system to supplement traditional GNSS-based navigation for machinery used in orchards. The aim of this research was to develop a deep learning machine stereo vision guidance system onboard an orchard speed sprayer. The developed system combines a collision avoidance methodology along with deep learning-driven machine vision for interrow positioning and a dead reckoning set of rules for alternating U-turns. The developed methodology was tested in 4 rows of an artificial orchard. The results show that it is possible for the embedded EfficientDet target detection algorithm to guide the equipment at 1, 1.5 and 2 km × h−1 with minimum average root-mean-square errors (RMSEs) of 0.24 m, 0.20 m, and 0.31 m, respectively. When the system navigation was performed using YOLOv7, the minimum average RMSEs for each row were 0.40 m, 0.48 m, and 0.43 m, respectively, for the abovementioned speeds. The U-turn by dead reckoning showed minimum average RMSE values of 0.56 m, 0.22 m, and 0.35 m for row navigation based on EfficientDet at 1, 1.5 and 2 km × h−1, respectively. For YOLOv7-based navigation in rows, the minimum average RMSE values at these speeds were 0.35 m, 0.81 m, and 0.44 m, respectively. This study contributes to the field by proposing an alternative navigation system for orchard machines that operates without the limitations associated with GNSS. In addition, our proposed guidance methodology introduces an RGB-D collision avoidance system with a demonstrated safety capacity for navigation under real scenario conditions.