Automatic Collision Avoidance Research Articles

MASS and COLREGS–Adaptability, Challenges and Coping Strategies

Discussions surrounding Maritime Autonomous Surface Ships (MASS) are occurring in academia, industry, and the International Maritime Organization (IMO). Automatic collision avoidance, as one of the key technologies of MASS, is the core of the autonomous navigation function of MASS, and its role is to solve the autonomous collision avoidance problem during MASS navigation. Convention on the International Regulations for Preventing Collisions at Sea (COLREGS) is a fundamental basis for automatic collision avoidance, and the navigation of MASS should adhere to it. However, the applicability of MASS to COLREGS has not yet been resolved. Responding to these issues, the paper proceeds to analyze the principal challenges of MASS to COLREGS in terms of the application of MASS to good seamanship, the neglect provision, the lookout provision, the insight of one another provision, and the problems of the deviation provision. Furthermore, suggestions are put forth for the revision of COLREGS, including the mode of revision, the reconstruction of MASS collision liability, the long-term coexistence of MASS and traditional ships, and the risk control of COLREGS revision in the context of artificial intelligence. These suggestions aim to establish a foundation for a more effective adaptation to the advent of the MASS era.

Scenarios of Multiple Vessels Encounter for Safety Evaluation for Automatic Collision Avoidance Algorithm using AIS Data

Abstract Interest in Maritime Autonomous Surface Ships (MASS) is growing, and efforts are underway in Japan to realize them. One of the key issues in realizing autonomous operation is automatic collision avoidance. Simulation is effective in developing and evaluating such algorithms. This paper describes the generation of a set of simulation scenarios that consider the actual sea traffic using AIS data, which is traffic flow data in real seas. We assumed that the comprehensiveness of the scenarios could be ensured by generating scenarios by combining typical encounter patterns and collecting difficult situations that are encountered in real situations. First, the characteristics of the target sea area were identified from the AIS data, then difficult traffic situations were extracted from the data, and then a set of scenarios were generated based on them. Considering the presence of manned ships in the test area, we conducted some tests of the generated scenarios not only using fast-time simulations but also using a ship-handling simulator and conducted visual checks from own ship and the target ship.

Brief history and application prospect of robotic spine surgery

Spinal robotics has rounded out twenty years in clinical, is mainly used for pedicle screw placement at present, can significantly increase the accuracy of screw placement and reduce radiation exposure to the patient and the surgeon. In the future, haptic feedback, automatic collision avoidance, and other technologies will further expand its application to complete precise operations such as decompression and correction, providing safety guarantee for the implementation of complex spinal surgery.

The technique for approximation of three-dimensional surfaces in order to synthesize algorithms for preventing aircraft collisions with obstacles

The work marks the beginning of the practical application of algorithms for making the aircraft recovery maneuver from three-dimensional constraint surfaces, which are a combination of terrain and artificial obstacles. An analysis of events leading to aviation accidents was carried out, and a comparison of on-board systems for preliminary notification of aircraft crews about collisions with natural or artificial obstacles was made. It is shown that such systems are insufficient due to their passive-recommendatory nature of issuing warnings. A question has been raised about the need to implement an active automatic collision avoidance system with spatial obstacles. In order to apply existing algorithms for the aircraft recovery maneuver from spatial constraint surfaces, a technique has been developed for approximating three-dimensional surfaces (obstacles) specified on a digital terrain map in the form of discrete height readings with a certain step on a coordinate grid. A paraboloid of revolution was chosen as a continuous 2nd order surface approximating the obstacle, and its characteristic parameters were determined. To determine the characteristic parameters of the paraboloid, an algorithm for determining the intersection of a three-dimensional surface and a plane, based on the principle of determining the intersection of triangles in space, as well as a method for selecting the inflection point of the terrain, based on determining the value of the terrain height gradient, are proposed for use. The construction of an approximating paraboloid using the example of a natural obstacle in the form of a mountain range is given. When synthesizing algorithms for preventing collisions of aircraft with obstacles, the need to take into account not only the parameters of the constraint surfaces and dynamic characteristics of aircraft, but also the accuracy characteristics of data sources about their position is noted. Promising application areas of the developed methodology are shown.

Li-Fi Technology for Vehicle-To-Vehicle

The integration of Light Fidelity (Li-Fi) technology within Smart Cities to enhance vehicle-to-vehicle (V2V) communication systems. Highlighting the limitations of traditional radio frequency (RF) methods in managing increasing traffic and potential ecosystem impacts, the abstract introduces Li-Fi as a promising alternative. Li-Fi utilizes visible light to achieve high-speed data transfer rates, offering advantages such as enhanced efficiency, reduced latency, improved reliability, and heightened security. The objectives of implementing Li-Fi in V2V communication are delineated, emphasizing its potential to facilitate real-time data exchange crucial for autonomous driving and safety applications. The abstract further details the methodology and architecture of Li-Fi technology, illustrating its utilization of LED bulbs and photo detectors for data transmission and reception. Practical implementation strategies for integrating Li-Fi into V2V communication systems, including sensor-based distance measurement and automated collision avoidance mechanisms, are discussed. Ultimately, the abstract concludes by emphasizing Li-Fi's potential as a cost-effective solution to mitigate traffic accidents and enhance communication efficiency in Smart Cities. Keywords — Li-Fi, Illumination, Wi-Fi, LED, Photo Diode, Radio Frequency

Collision avoidance for formation of autonomous ships using separation and recovery mechanism combine artificial potential field method

ABSTRACT It is essential to investigate the path planning and tracking problem for maritime autonomous surface ships (MASS). This study proposed an automatic collision avoidance method based on the separation and recovery mechanism with formation of MASS (F-MASS). First, the marine environment model utilized S-57 electric navigation chart (ENC) data for construction. The Scan-searching method was proposed for multipath and path-optimized redistribution method was developed to address MASS congestion. The formation pattern transformation was settled by separation and recovery mechanism. Considered the ‘unmanned–manned’ encounter situation, formulated avoidance strategies for both the MASS formation and manned ships encounters. Finally, the simulation experiment was carried out in the sea near Zhoushan port to verify the effectiveness of the algorithm. The results indicated that the method can satisfy the integrated operation of collision avoidance in a complex environment and can offer effective collision avoidance strategies for F-MASSs navigating in complex marine environments.

A Review on Highway Network System - Samruddhi Expressway

Highway networks serve as critical arteries of transportation infrastructure, facilitating the movement of goods and people across vast geographical regions. As traffic volumes continue to increase and technological advancements reshape transportation systems, there is a pressing need to optimize the efficiency, safety, and sustainability of highway networks. This abstract presents a comprehensive system approach aimed at addressing these challenges. The proposed highway network system integrates advanced technologies such as intelligent transportation systems (ITS), real-time traffic monitoring, data analytics, and machine learning algorithms to optimize traffic flow, minimize congestion, and enhance safety. By leveraging data from various sources including sensors, cameras, and connected vehicles, the system enables proactive traffic management and congestion prediction, allowing authorities to implement timely interventions and mitigate potential disruptions. Furthermore, the integration of artificial intelligence and machine learning algorithms enables predictive maintenance of infrastructure, identifying potential issues before they escalate into critical failures. This proactive approach not only reduces maintenance costs but also enhances the reliability and lifespan of highway assets. Moreover, the system prioritizes safety through the implementation of automated collision avoidance systems, adaptive speed control, and real-time incident management. By leveraging vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communication technologies, the system enables vehicles to exchange critical information, such as hazardous road conditions or impending collisions, thereby reducing the risk of accidents and improving overall safety. Additionally, the system incorporates sustainability principles by optimizing traffic flow patterns to minimize fuel consumption and emissions, promoting eco-friendly transportation practices, and facilitating the integration of electric and autonomous vehicles into the existing infrastructure.

Framework of safety evaluation and scenarios for automatic collision avoidance algorithm

This paper proposes a novel method to design a scenario set for evaluating automatic collision avoidance algorithms. While many automatic collision avoidance methods have been proposed recently, they have been verified using different methods and scenarios. This study aims to construct a scenario set that covers all possible encounter situations between ships. Based on risks, rules such as the COLREGs and characteristics of encounter angle of ships, the scenario sets of one-on-one and one-on-two encounter situations are built. For the evaluation of collision avoidance maneuvers, the authors provide the analytical solution in the time domain of evaluation indices using the position and velocity vectors of two ships. The authors also present the design method of the additional scenario to evaluate the automatic ship avoidance maneuvering algorithm, for the safety verification of autonomous and unmanned ships.

Optimizing Multi-Vessel Collision Avoidance Decision Making for Autonomous Surface Vessels: A COLREGs-Compliant Deep Reinforcement Learning Approach

Automatic collision avoidance decision making for vessels is a critical challenge in the development of autonomous ships and has become a central point of research in the maritime safety domain. Effective and systematic collision avoidance strategies significantly reduce the risk of vessel collisions, ensuring safe navigation. This study develops a multi-vessel automatic collision avoidance decision-making method based on deep reinforcement learning (DRL) and establishes a vessel behavior decision model. When designing the reward function for continuous action spaces, the criteria of the “Convention on the International Regulations for Preventing Collisions at Sea” (COLREGs) were adhered to, taking into account the vessel’s collision risk under various encounter situations, real-world navigation practices, and navigational complexities. Furthermore, to enable the algorithm to precisely differentiate between collision avoidance and the navigation resumption phase in varied vessel encounter situations, this paper incorporated “collision avoidance decision making” and “course recovery decision making” as state parameters in the state set design, from which the respective objective functions were defined. To further enhance the algorithm’s performance, techniques such as behavior cloning, residual networks, and CPU-GPU dual-core parallel processing modules were integrated. Through simulation experiments in the enhanced Imazu training environment, the practicality of the method, taking into account the effects of wind and ocean currents, was corroborated. The results demonstrate that the proposed algorithm can perform effective collision avoidance decision making in a range of vessel encounter situations, indicating its efficiency and robust generalization capabilities.

Integrated Four-Wheel Steering and Direct Yaw-Moment Control for Autonomous Collision Avoidance on Curved Road

<div>An automatic collision avoidance control method integrating optimal four-wheel steering (4WS) and direct yaw-moment control (DYC) for autonomous vehicles on curved road is proposed in this study. Optimal four-wheel steering is used to track a predetermined trajectory, and DYC is adopted for vehicle stability. Two single lane change collision avoidance scenarios, i.e., a stationary obstacle in front and a moving obstacle at a lower speed in the same lane, are constructed to verify the proposed control method. The main contributions of this article include (1) a quintic polynomial lane change trajectory for collision avoidance on curved road is proposed and (2) four different kinds of control method for autonomous collision avoidance, namely 2WS, 2WS+DYC, 4WS, and 4WS+DYC, are compared. In the design of DYC controller, two different feedback control methods are adopted for comparison, i.e., sideslip angle feedback and yaw rate feedback. The simulation results demonstrate significant improvements in the path tracking performance and stability of the 4WS+DYC control system compared to other control systems. Furthermore, the performance of the DYC control system with yaw rate feedback outperforms that of the DYC control system with sideslip angle feedback.</div>

Overtaking collision avoidance for small autonomous uncrewed aircraft using geometric keep-out zones

Autonomous uncrewed aircraft will require collision avoidance systems (CASs) designed with autonomy in mind as they integrate into the increasingly crowded national airspace system. Current uncrewed aircraft CASs typically require a remote pilot to execute avoidance or to provide poorly defined guidance that does not benefit autonomous systems. The Path Recovery Automated Collision Avoidance System (PRACAS) re-plans flight paths to autonomously adjust for collisions using path planners and keep-out zones (KOZs), but it does not currently detect or mitigate overtaking collisions. This work investigates the effect of geometric KOZs on overtaking scenarios for autonomous uncrewed aircraft. KOZ shapes were developed by relating relative velocities and turn rates of aircraft in overtaking scenarios and were tested using PRACAS. The operational ranges for approach heading, relative velocity, and look-ahead time were then determined. The set of KOZs that were developed prevented intruder aircraft from entering the minimum separation distance of one wingspan from the mission aircraft in overtaking scenarios with look-ahead times between 5 and 12 s, relative velocities of 2–20, and approach angles between 110° and −110° measured from the heading of the main UAS. Minimum separation was maintained for low-speed encounters with relative velocities between 1.1 and 2.0 for look-ahead times between 2 and 8 s for all approach angles. With look-ahead times ranging from 5 to 8 s, overtaking collisions of all tested approach angles and relative speeds are handled with more than twice the separation required for success, showing that the KOZs developed are feasible in possible autonomous CASs.

Establishing “norms of behavior” for satellite collision avoidance maneuver planning

Several commercial companies, as well as various nations, have proposed to deploy or are deploying many satellites in Low Earth Orbit (LEO). These large constellations will greatly increase the number of satellites operating in relatively narrow altitude regions of space. The added space traffic in these regions will create many close approaches between the members of the large constellations and other space operators. These close approach situations can necessitate maneuver(s) to avoid a potential collision. Should both satellites have maneuvering capability, the question of how the overall collision avoidance procedures should be executed is raised. Some constellations may employ automated collision avoidance systems which interact differently than conventional human-in-the-loop systems. Interactions between an automated system and another operational satellite, between two automated systems or two nonautonomous systems present new challenges for executing effective collision avoidance. Additionally, the existence of non-maneuverable satellites and space debris continues to pose additional challenges. This paper is the first of several papers that will be documenting an International Academy of Astronautics study on this topic.

A novel route-plan-guided artificial potential field method for ship collision avoidance: Modeling, integration and test

To address the technical difficulties of artificial potential filed (APF)-based automatic collision avoidance (CA) algorithms, a stable and reliable technological framework was established for autonomous CA from the perspectives of navigation practice and real-ship application. First, an improved route-plan-guided APF (RPGAPF) approach was introduced, considering the ship motion and constraints by the International Regulations for Preventing Collisions at Sea (COLREGS). Second, a simulation-based real-ship accompanying test system (SRSATS) was well-designed for the intelligent navigation projects and installed on a 45.0 m length ship. Third, various real-ship open-loop CA tests were conducted under different encountering situations, and concurrently, simulation testing in both open-loop and closed-loop were carried out. The results indicated that simulation tests may be used as precursors before real-ship trials, and that the proposed SRSATS can be employed as a practical verification method for real-ship testing to generate variety of complex encountering situations. The CA procedures and results for the corresponding real-ship and simulation tests produced similar trends, and the improved RPGAPF approach can be applied in real-ship automatic CA systems owing to its dependability, determinism, and repeatability. This study proposes a complete solution for the APF-base CA approach, including system modelling, integration and testing. The findings provide valuable insights into the ship CA research and contribute to the improvement of ship intelligence.

Automatic Collision Avoidance Route Planning Method in Complex Navigation Environments

Efficient collision avoidance (CA) route planning is one of the important technologies for ensuring the safety of autonomous ships. Many CA route planning studies have been developed for the open sea, but few studies have been conducted for ships in complex navigation environments. A complex navigation environment refers to water encompassing various factors, such as multiple obstacles, varying water depths, ships collision risk, and other maritime challenges. These factors collectively contribute to the complexity of the environment. CA planning in this type of environment is a special type of route planning. To address CA in complex navigation environments, firstly, the route binary tree algorithm is utilized for conducting global route planning in order to determine the optimal path. Secondly, this paper proposes a dynamic generation of local collision avoidance trajectories along the optimal path, seamlessly integrating global route optimization and local collision avoidance. Finally, a comparative analysis is conducted using classical techniques to verify the effectiveness of the proposed method. Numerical simulation results reveal that when a ship is taken as the object of CA in the open sea, the route generated using the proposed method exhibits a remarkable level of unity with the one generated by the benchmark method of improved Artificial Potential Field (APF), particularly in terms of collision avoidance strategy selection, collision avoidance trends, and the actual trajectory. The former’s computational efficiency is improved by at least 30%. When dealing with CA at sea, with complex navigation obstacles, the proposed method considers static complex navigation obstacles, dynamic ships, and their unpredictable strategies to timeously generate a safe path which considers some key rules from the COLREGS (International Regulations for Preventing Collisions at Sea) (IMO, 1972).

국제해상충돌예방규칙을 고려한 Event Triggered NMPC 기반의 선박 충돌 회피 알고리즘

About 75% of vessel collision accidents are caused by human error, which causes enormous economic loss, environmental pollution, and human casualties, thus research on automatic collision avoidance of vessels is being actively conducted. In addition, vessels must comply with the COLREGs rules stipulated by IMO when performing collision avoidance with other vessels in motion. In this study, the collision risk was calculated by estimating the position and velocity of other vessels through the Probabilistic Data Association Filter (PDAF) algorithm based on RADAR sensor data. When a collision risk is detected, we propose an event-triggered Nonlinear Model Predict Control (NMPC) algorithm that geometrically creates waypoints that satisfy COLREGs and follows them. To verify the proposed algorithm, simulations through MATLAB are performed.

Business Case for Transit Bus Automated Collision Avoidance Systems

Although the National Transportation Safety Board has strongly recommended the application of collision avoidance warning systems and automated emergency braking (CAWS/AEB), the transit industry has lagged behind autos and trucks. CAWS/AEB for buses is more complex than for cars and trucks and represents a niche market. If bus manufacturers and suppliers are to invest in developing this technology, they will need to be convinced there is a market for it. Transit agencies also will need to be convinced that the technology works and is affordable. For both vendors and purchasers, a business case could be made that some or all of the expense of procuring and deploying the technology can be recovered through savings from reduced insurance premiums and claims payouts by preventing or mitigating collisions. This paper describes two methods for estimating the business case for equipping transit buses with CAWS/AEB. First, industrywide data on the numbers of collisions and casualty and liability expenses incurred by transit agencies were examined, and statistical relationships were modeled to determine whether reducing the numbers of collisions would reduce casualty and liability expenses. Second, individual collision claims records for specific transit agencies were examined to determine whether the collisions could have been prevented by CAWS/AEB, and the potential savings.

Human-like route planning for automatic collision avoidance using generative adversarial imitation learning

Automatic collision avoidance systems are expected to eliminate maritime accidents caused by human error. Recent studies have shown that ships can prevent collisions in complex situations by using deep reinforcement learning (DRL). However, rewards must be designed to implement DRL, which can be challenging for ambiguous tasks, such as following the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). While some studies have used inverse reinforcement learning (IRL) to derive an appropriate reward for limited problems with small, discrete state spaces, this study introduced generative adversarial imitation learning (GAIL) and proposed a route planning algorithm that addresses the above limitations. We applied DRL to generate sample collision avoidance trajectories and demonstrate that the imitative route planner based on GAIL can reproduce these trajectories. Also, expert trajectories were collected in simulation experiments involving a well-experienced captain, and we attempted to generate collision avoidance routes that mimic human expert performance. By applying a convolutional neural network and other techniques to improve the planner's imitation capability, we established a sophisticated route planner that is consistent with captain's risk assessments and tolerant of noise.

Automatic collision avoidance algorithm based on route-plan-guided artificial potential field method

With respect to navigation practices and real-ship applications, this study provided a stable and reliable technical program for automatic ship navigation. First, an improved route-plan-guided artificial potential field (APF) method was presented by balancing the attractive and repulsive forces, resolving the irrationality and swaying of the collision avoidance (CA) strategy, and extending the applicability of the International Regulations for Preventing Collisions at Sea (COLREGS). Second, a fast local path planning (FLPP) method was proposed based on the high-precision ship motion model to obtain the expected CA results in advance, and to promote its acceptance and application by the navigators. Third, a dynamic goal-guided APF method was proposed to navigate a ship to return to its route plan upon completing the CA procedure. A series of CA experiments for different ships and encountering situations were conduct in a simulated environment. Although the varying maneuverability influenced the CA procedure and results, the CA processes and trends were identical, and the track zone width was within 0.10 nm in restricted waters. The real-time CA track sufficiently aligned with the FLPP results, and the ship was able to rapidly return to its route plan and remained within the cross track limit (XTL) according to the set return parameters.

Generalized Behavior Decision-Making Model for Ship Collision Avoidance via Reinforcement Learning Method

Due to the increasing number of transportation vessels, marine traffic has become more congested. According to the statistics, 89% to 95% of maritime accidents are related to human factors. In order to reduce marine incidents, ship automatic collision avoidance has become one of the most important research issues in the field of ocean engineering. A generalized behavior decision-making (GBDM) model, trained via a reinforcement learning (RL) algorithm, is proposed in this paper, and it can be used for ship autonomous driving in multi-ship encounter situations. Firstly, the obstacle zone by target (OZT) is used to calculate the area of future collisions based on the dynamic information of ships. Meanwhile, a virtual sensor called a grid sensor is taken as the input of the observation state. Then, International Regulations for Preventing Collision at Sea (COLREGs) is introduced into the reward function to make the decision-making fully comply with COLREGs. Different from the previous RL-based collision avoidance model, the interaction between the ship and the environment only works in the collision avoidance decision-making stage. Finally, 60 complex multi-ship encounter scenarios clustered by the COLREGs are taken as the ship’s GBDM model training environments. The simulation results show that the proposed GBDM model and training method has flexible scalability in solving the multi-ship collision avoidance problem complying with COLREGs in different scenarios.

Influence of Running Position in Lane on Automatic Collision Avoidance in Personal Mobility Vehicle

Influence of Running Position in Lane on Automatic Collision Avoidance in Personal Mobility Vehicle