Potential Collision Research Articles

A multi-task deep learning model integrating ship trajectory and collision risk prediction

Trajectory prediction can provide position information for ship navigation behavior perception. This is very important for intelligent navigation. However, potential collision risk caused by other ships’ navigation behaviors will directly affect the navigation behavior of own ship. In order to incorporate the potential collision risk caused by the navigation behavior of other ships, this study proposes a Multi-Task Deep Learning Model to exploit the interaction between ships and predict the ship trajectory and potential collision risk simultaneously. Trajectory prediction task can exploit the knowledge contained in collision risk prediction task and the prediction of collision risk can utilize the navigational situation in the future. In the trajectory prediction task, we construct virtual channel center points in a data-driven way to capture the ship behavior in ship traffic flow and use them as constraints in our designed loss function. Furthermore, we design the soft collision risk classification label and the knowledge distillation module to improve the accuracy of the multi-task model. At last, we demonstrate that our method can not only improve the accuracy of trajectory prediction, but also gain reliable potential collision risk results. Our method improves the prediction time scale by an order of magnitude compared with other methods.

Orbital Uncertainty Propagation Based on Adaptive Gaussian Mixture Model under Generalized Equinoctial Orbital Elements

The number of resident space objects (RSOs) has been steadily increasing over time, posing significant risks to the safe operation of on-orbit assets. The accurate prediction of potential collision events and implementation of effective and nonredundant avoidance maneuvers require the precise estimation of the orbit positions of objects of interest and propagation of their associated uncertainties. Previous research mainly focuses on striking a balance between accurate propagation and efficient computation. A recently proposed approach that integrates uncertainty propagation with different coordinate representations has the potential to achieve such a balance. This paper proposes combining the generalized equinoctial orbital elements (GEqOE) representation with an adaptive Gaussian mixture model (GMM) for uncertainty propagation. Specifically, we implement a reformulation for the orbital dynamics so that the underlying state and the moment feature of the GMM are propagated under the GEqOE coordinates. Starting from an initial Gaussian probability distribution function (PDF), the algorithm iteratively propagates the uncertainty distribution using a detection-splitting module. A differential entropy-based nonlinear detector and a splitting library are utilized to adjust the number of GMM components dynamically. Component splitting is triggered when a predefined threshold of differential entropy is violated, generating several GMM components. The final probability density function (PDF) is obtained by a weighted summation of the component distributions at the target time. Benefiting from the nonlinearity reduction caused by the GEqOE representation, the number of triggered events largely decreases, causing the necessary number of components to maintain uncertainty realism also to decrease, which enables the proposed approach to achieve good performance with much more efficiency. As demonstrated by the results of propagation in three scenarios with different degrees of complexity, compared with the Cartesian-based approach, the proposed approach achieves comparable accuracy to the Monte Carlo method while largely reducing the number of components generated during propagation. Our results confirm that a judicious choice of coordinate representation can significantly improve the performance of uncertainty propagation methods in terms of accuracy and computational efficiency.

Genetic Fuzzy Inference System-Based Three-Dimensional Resolution Algorithm for Collision Avoidance of Fixed-Wing UAVs

Fixed-wing Unmanned Aerial Vehicles (UAVs) cannot fly at speeds lower than critical stall speeds. As a result, hovering during a potential collision scenario, like with rotary-wing UAVs, is impossible. Moreover, hovering is not an optimal solution for Collision Avoidance (CA), as it increases mission time and is innately fuel-inefficient. This work proposes a decentralized Fuzzy Inference System (FIS)-based resolution algorithm that modulates the point-to-point mission path while ensuring the continuous motion of UAVs during CA. A simplified kinematic guidance model with coordinated turn conditions is considered to control the UAVs. The model employs a proportional-derivative control of commanded airspeed, bank angle, and flight path angle. The commands are derived from the desired path, characterized by airspeed, heading, and altitude. The desired path is, in turn, obtained using look-ahead points generated for the target point. The FIS aims to mimic human behavior during collision scenarios, generating modulation parameters for the desired path to achieve CA. Notably, it is also scalable, which makes it easy to adjust the algorithm parameters, as per the required missions, and factors specific to a given UAV. A genetic algorithm was used to optimize FIS parameters so that the distance traveled during the mission was minimized despite path modulation. The proposed algorithm was optimized using a pairwise conflict scenario. The effectiveness of the algorithm was evaluated through a Monte Carlo simulation of random conflict scenarios involving multiple UAVs operating in a confined space.

CAV-enabled data analytics for enhancing adaptive signal control safety environment

Given the connected and autonomous vehicle (CAV) generated trajectories as a “floating sensor” data source to obtain high resolution CAV-generated mobility data at intersections, to ensure maximum safety effect while maintaining efficient operations at the same time is actually a complex task in traffic management. Literature indicates that methods for evaluating the CAV-generated data potentials focusing on safety benefits are still immature. The primary reason lies in lack of underlying mechanism and data models to make the data intelligent to enhance safety environment through adaptive traffic signal control. On top of the developed intelligent CAV-generated mobility data fusion model framework in support of adaptive traffic signal control, parameters and models included in Surrogate Safety Assessment Model (SSAM) are integrated to indicate the risk of near crashes and then evaluate the safety environment. A proof-of-concept study is conducted in Uptown Cincinnati, Ohio to test the developed data fusion models in terms of safety enhancement, along with operational benefits. In the tests, the CAV-generated data supported developed adaptive signal plan is compared with the basic signal plans (i.e., pretimed signal plan, actuated signal plan) that supported by traditional detection systems. The results indicate that the adaptive signal plan has a great potential to decrease at most 91% of total collision risk (measured in probability), 71% of crossing collision risk, 90% of rear end collisions risk and 100% of lane-changing collisions risk, compared with basic signal plans. Meanwhile, it increases up to 6.8% of throughput, and decreases up to 91.49% of average delay, 96.23% of queue length and 75.00% of number of stops. The benefits of operation efficiency include reduced average delay and reduced number of stops; but no improvement in reducing collisions severity that is reflected by high maximum speed and relative speed of two vehicles involved in a potential collision.

Lane Change Trajectory Planning Based on Quadratic Programming in Rainy Weather

To enhance the safety and stability of lane change maneuvers for autonomous vehicles in adverse weather conditions, this paper proposes a quadratic programming−based trajectory planning algorithm for lane changing in rainy weather. Initially, in order to mitigate the risk of potential collisions on wet and slippery road surfaces, we incorporate the concept of road adhesion coefficients and delayed reaction time to refine the establishment of the minimum safety distance. This augmentation establishes constraints on lane change safety distances and delineates the boundaries of viable lane change domains within inclement weather contexts. Subsequently, adopting a hierarchical trajectory planning framework, we incorporate visibility cost functions and safety distance constraints during dynamic programming sampling to ensure the safety of vehicle operation. Furthermore, the vehicle lane change sideslip phenomenon is considered, and the optimal lane change trajectory is obtained based on the quadratic programming algorithm by introducing the maneuverability objective function. In conclusion, to verify the effectiveness of the algorithm, lateral linear quadratic regulator (LQR) and longitudinal double proportional−integral−derivative (DPID) controllers are designed for trajectory tracking. The results demonstrate the algorithm’s capability to produce continuous, stable, and collision−free trajectories. Moreover, the lateral acceleration varies within the range of ±1.5 m/s2, the center of mass lateral deflection angle varies within the range of ±0.15°, and the yaw rate remains within the ±0.1°/s range.

Decision-making algorithm for ship collision avoidance with collision risk map

This paper presents a decision-making algorithm for ship collision avoidance. First, an algorithm for the planar distribution of collision risk is described. The level of collision risk was calculated as a function of the plane coordinates based on the predicted encounter state. It enables the visualization of all the potential collision risks as a collision risk map and the calculation of the integrative collision risk against several ships, considering COLREGs. Second, an optimal route-planning algorithm that can consider the maneuvering characteristics of the ship is proposed. Because a ship cannot change its course and speed suddenly, the nodes and their connections can be set to limit the course and speed change amounts to appropriate ranges. The optimal route was obtained as the minimum-cost route along node connections. Finally, a decision-making algorithm for ship collision avoidance was developed by combining the proposed collision risk mapping and optimal route-planning algorithm. It was applied to representative encounter situations and evaluated by an evaluation method. Further, the proposed algorithm was compared with state-of-art algorithms. Thus, safe and efficient decision-making for collision avoidance can be achieved even in congested situations by appropriately changing both a course and a speed depending on the encounter situation.

Toward the Optimization of Mining Operations Using an Automatic Unmineable Inclusions Detection System for Bucket Wheel Excavator Collision Prevention: A Synthetic Study

This work introduces a methodology for the automatic unmineable inclusions detection and Bucket Wheel Excavator (BWE) collision prevention, using electromagnetic (EM) inspection and a fuzzy inference system. EM data are collected continuously ahead from the bucket wheel of a BWE and subjected to processing. Two distinct methodologies for data processing were developed and integrated into the MATLAB programming environment. The first approach, named “Simple Mode”, utilizes statistical process control to generate real-time alerts in the event of a potential collision involving the excavator’s bucket and hard rock inclusions. The advanced processing flow (“Advanced Mode”) requires accurate instrument positioning and data from successive EM scans. It incorporates techniques of local resistivity maxima detection (Position Prominence Index) as well as Neural Network-based Pattern Recognition (NNPR). A decision support process based on a Fuzzy Inference System (FIS) has been developed to assist BWE operators in avoiding collision when digging hard rock inclusions. The proposed methodology was extensively tested using synthetic EM data. Limited real data, acquired with a CMD2 (GF Instruments) EM instrument equipped with GPS, were used to control its efficiency. Increased accuracy in the automatic detection of unmineable inclusions was observed using the Advanced Mode. On the other hand, the Simple Mode processing technique offers the advantage of being independent of instrument positioning as well as it provides real-time inspection of the excavated mine slope. This work introduces a methodology for hard rock inclusion detection and can contribute to the optimization of mine operations by improving resource efficiency, safety, cost savings, and environmental sustainability.

CALCULATION OF EARTHQUAKE RESISTANT STRUCTURE OF MEDICAL CENTER BUILDING RUMAH SAKIT UMUM DAERAH (RSUD) SOEDARSO PONTIANAK USING PUSHOVER ANALYSIS

Hospitals are essential in providing health services and must withstand the forces that may occur, even due to an earthquake. RSUD Soedarso is a hospital in Pontianak City that has been around for a long time. However, because it is already quite old, various problems must be addressed. The step taken by the government is to build a new building, namely the Medical Centre and Inpatient Building.The purpose of writing this final project is to evaluate the performance of the earthquake-resistant structure of the Soedarso Hospital Medical Centre building using the pushover analysis method. This method analyses the inelastic behaviour of the system due to the earthquake, where the result is a curve of the relationship between the shear force and the displacement of the roof that occurs. The guidelines for pushover rules used are based on the provisions of ATC-40 and FEMA 356. Further research was carried out on the dilation between the Medical Centre Building and the IRNA Building.The results are that both buildings are still in elastic condition when the performance point is reached. Based on ATC-40 and FEMA 356, the building is classified as in the Immediate Occupancy (IO) performance level, regarding drift ratio and from plastic hinges that occur in column and beam elements. Then the dilatation that arises due to pushover is smaller than the design dilation of 150 mm. Both buildings are protected from potential collisions, which is a relief.

A Hierarchical Motion Planning Method for Mobile Manipulator.

This paper focuses on motion planning for mobile manipulators, which includes planning for both the mobile base and the manipulator. A hierarchical motion planner is proposed that allows the manipulator to change its configuration autonomously in real time as needed. The planner has two levels: global planning for the mobile base in two dimensions and local planning for both the mobile base and the manipulator in three dimensions. The planner first generates a path for the mobile base using an optimized A* algorithm. As the mobile base moves along the path with the manipulator configuration unchanged, potential collisions between the manipulator and the environment are checked using the environment data obtained from the on-board sensors. If the current manipulator configuration is in a potential collision, a new manipulator configuration is searched. A sampling-based heuristic algorithm is used to effectively find a collision-free configuration for the manipulator. The experimental results in simulation environments proved that our heuristic sampling-based algorithm outperforms the conservative random sampling-based method in terms of computation time, percentage of successful attempts, and the quality of the generated configuration. Compared with traditional methods, our motion planning method could deal with 3D obstacles, avoid large memory requirements, and does not require a long time to generate a global plan.

Time Travel and Collisions

Abstract This paper focuses on problems for time travel that specifically concern continuous time-travel to the past, problems to do with potential collisions with past obstacles such as former time-slices of the time traveler herself. These problems have not been discussed nearly as much as other questions about time travel, such as the Grandfather Paradox. Here I focus on discussions by Bernstein, Dowe, Grey and Le Poidevin. After examination, I conclude that only the problems of turning around in time have any merit and present a new proposal of my own for turning around in time without collisions. I assume a Lewisian framework throughout.

Discovery and physical characterization as the first response to a potential asteroid collision: The case of 2023 DZ2

Context. Near-Earth asteroids (NEAs) that may evolve into impactors deserve detailed threat assessment studies. Early physical characterization of a would-be impactor may help in optimizing impact mitigation plans. We first detected NEA 2023 DZ2 on 27 February 2023. After that, it was found to have a minimum orbit intersection distance (MOID) with Earth of 0.00005 au as well as an unusually high initial probability of becoming a near-term (in 2026) impactor. Aims. We perform a rapid but consistent dynamical and physical characterization of 2023 DZ2 as an example of a key response to mitigating the consequences of a potential impact. Methods. We used a multi-pronged approach, drawing from various methods (observational-computational) and techniques (spectroscopy-photometry from multiple instruments), and bringing the data together to perform a rapid and robust threat assessment. Results. The visible reflectance spectrum of 2023 DZ2 is consistent with that of an X-type asteroid. Light curves of this object obtained on two different nights give a rotation period P = 6.2743 ± 0.0005 min with an amplitude A = 0.57 ± 0.14 mag. We confirm that although its MOID is among the smallest known, 2023 DZ2 will not impact Earth in the foreseeable future as a result of secular near-resonant behaviour. Conclusions. Our investigation shows that coordinated observation and interpretation of disparate data provides a robust approach from discovery to threat assessment when a virtual impactor is identified. We prove that critical information can be obtained within a few days after the announcement of the potential impactor.

An emergency observation method for space debris dangerous conjunction events based on nanosatellite constellation

The amount of space debris is rising rapidly, and the number of satellites launched by humans is also growing. This poses a serious threat to the security of many important space assets including the International Space Station and the China Space Station. Due to the frequent occurrence of hazardous space conjunction (potential collisions) events, we aim to use a constellation composed of a few optical satellites to observe these space dangerous conjunction events, thereby improving the observation accuracy and timeliness of key conjunction events. We consider a variety of factors to establish an optical nanosatellite constellation design model, develop constellation observation efficiency evaluation criteria, construct a constellation configuration evaluation function, and design the performance parameters of space-based optical telescopes. The optimal orbit parameters and constellation configuration are obtained by using the genetic algorithm for optimization calculation. It is determined that a constellation of 6 satellites can track and observe more than 96% of potentially dangerous conjunction objects 24–48 h before a dangerous conjunction occurs. According to the observation data, high-precision orbit information of space objects can be obtained, which can reduce the collision false alarm rate by 99%. As a result, operators are notified to take collision avoidance measures only when the space object is truly in danger. This approach greatly reduces the number of avoidance operations caused by false early warnings, lowers the operating cost of space assets, and ensures the safety of space assets.

Examples for the application of rule-based algorithms in the simulation modeling of the physical separation of automated guided vehicles

Nowadays, in parallel with the rapid spread of modern automation and digitalization solutions, different autonomous systems are playing an increasingly important role in the field of industry and logistics, a classic example of which is the case of automated guided vehicles (AGVs). Although these devices have been in use for a long time in the aforementioned areas, at the same time, in parallel with the progress of automation in the recent period, in many cases they can be seen more and more as autonomous mobile robots (AMRs), which perform the tasks assigned to them with a high degree of independence. At the same time, issues such as the problem of preventing collisions between individual freely moving vehicles in industrial environments naturally come to the fore. The purpose of this publication is to provide an example for the structure of some simpler rule-based algorithms in response to the former question, which may be relevant in terms of avoiding some potential collision situations of lower complexity. The operation of the algorithms was represented using the Siemens Tecnomatix Plant Simulation discrete event simulation software.

Driver distraction and in-vehicle interventions: A driving simulator study on visual attention and driving performance

Driving simulator studies are popular means to investigate driving behaviour in a controlled environment and test safety-critical events that would otherwise not be possible in real-world driving conditions. While several factors affect driving performance, driving distraction has been emphasised as a safety-critical issue across the globe. In this context, this study explores the impact of distraction imposed by mobile phone usage, i.e., writing and reading text messages, on driver behaviour. As part of the greater i-DREAMS project, this study uses a car driving simulator experimental design in Germany to investigate driver behaviour under various conditions: (I) monitoring scenario representing normal driving conditions, (II) intervention scenario in which drivers receive fixed timing in-vehicle intervention in case of unsafe driving manoeuvres, and (III) distraction scenario in which drivers receive in-vehicle interventions based on task completion capability, where mobile phone distraction is imposed. Besides, eye-tracking glasses are used to further explore drivers’ attention allocation and eye movement behaviour. This research focuses on driver response to risky traffic events (i.e., potential pedestrian collisions, and tailgating) and the impact of distraction on driving performance, by analysing a set of eye movement and driving performance measures of 58 participants. The results reveal a significant change in drivers’ gaze patterns during the distraction drives with significantly higher gaze points towards the i-DREAMS intervention display (the utilised advanced driver assistance systems in this study). The overall statistical analysis of driving performance measures suggests nearly similar impacts on driver behaviour during distraction drives; a higher deviation of lateral positioning was noted irrespective of the event risk levels and lower longitudinal acceleration rates were observed for pedestrian collisions and non-critical events during distracted driving.

AN APPLICATION OF AGENT-BASED TRAFFIC FLOW MODEL FOR MARITIME SAFETY MANAGEMENT EVALUATION

This paper aims to analyse maritime traffic safety assessment via a traffic flow simulation model. The model developed via NetLogo platform, agent-based modelling and simulation approach. And it is implemented on an open sea area, at the Aegean Sea to show its applicability. The model is verified through experiments conducted in the area. The simulation outputs give the risky locations and scores. Risky locations and risk scores in the area are determined as the outputs of the simulation runs. A traffic separation scheme is established to prove the suitability of the model as adaptable and updatable. After the scheme is implemented, it shows that the potential collision locations and scores change considerably. The developed model is convenient to simulate various conditions by changing the input parameters on maritime traffic safety

Privacy-Preserving AGV Collision-Resistance at the Edge Using Location-Based Encryption

Edge computing fundamentally changes the architecture in which applications are deployed and how resources are managed, especially in the 5G/6G era. Automated guided vehicles (AGV) are critical means of transportation in future society. We aim at investigating a privacy-preserving AGV collision-resistance paradigm leveraging edge computing. We define a model containing all potential collision occasions and propose a method to handle collisions using “virtual” traffic lights generated by edge servers. The proposed paradigm is AGV-centered, for AGVs ought not to care about where the nearby edge servers are in a broadcasting environment. In case of privacy leakage, we incorporate ciphertext-policy attribute-based encryption (CP-ABE) to protect AGV information. Besides, the use of CP-ABE leads to a location-based encryption (LBE) scheme, where AGV encrypts its running state information leveraging its current position rather than an edge server's public key. That is achievable due to the support of integer comparison in the CP-ABE access policy. To our knowledge, we are the first to implement an LBE scheme based on CP-ABE. Part of the paradigm has been deployed in a wharf yard in Shanghai. Throughout the paper, we take a yard as an example and conduct concrete experiments to highlight the feasibility and efficiency.

Planning of Mobile Crane Walking Operations in Congested Industrial Construction Sites

The trend toward more compact designs and congested site layouts makes it challenging for lift planners to provide feasible lift paths for mobile cranes, confronting the added risk of potential collisions when maneuvering through on-site obstacles. In some cases, particularly in congested industrial modular projects, it is inevitable for mobile cranes to walk with loads to a position with sufficient clearance to perform the lifts and place the objects in their final set position. This study contributes to the body of knowledge by introducing a comprehensive lift planning framework to plan complicated lifts involving mobile crane walking operations. Due to the lack of reliable and accurate plans for such lifts in practice and the added complexities, they are often eluded by practitioners compared with the more straightforward pick-and-set scenarios. This study proposes an algorithm for optimized planning of crane walking–involved lift operations borrowing an obstacle avoidance technique from robotics. The proposed path planner thoroughly considers site constraints and crane configurations to prevent collision between the crane body and the load with preinstalled objects. Actual case studies are presented to validate the efficiency of the proposed algorithm. The system generated the presented real-world lift in less than 5 min, satisfying the operations’ optimality, safety, and feasibility.

A framework of marine collision risk identification strategy using AIS data

AbstractCollisions are one of the major accidents in the shipping industry, causing significant losses. In this work, a framework of marine collision risk identification strategy was developed to quantitatively analyse collision risks and provide an easy and convenient way to monitor traffic flow in relevant waters to mitigate the chances of collision. The model was verified by using automatic identification system data obtained from Tianjin Port. When compared to previous research, the proposed model can identify risks earlier and give people more time to analyse and take action. The results indicate that it also can provide a visual display to alert relevant personnel. The model can be used as a reference to identify potential collision risks or as an information source for future research.

A Safety Control Method of Car-Following Trajectory Planning Based on LSTM

This paper focuses on the potential safety hazards of collision in car-following behaviour generated by deep learning models. Based on an intelligent LSTM model, combined with a Gipps model of safe collision avoidance, a new, Gipps-LSTM model is constructed, which can not only learn the intelligent behaviour of people but also ensure the safety of vehicles. The idea of the Gipps-LSTM model combination is as follows: the concept of a potential collision point (PCP) is introduced, and the LSTM model or Gipps model is controlled and started through a risk judgment algorithm. Dataset 1 and dataset 2 are used to train and simulate the LSTM model and Gipps-LSTM model. The simulation results show that the Gipps-LSTM can solve the problem of partial trajectory collision in the LSTM model simulation. Moreover, the risk level of all trajectories is lower than that of the LSTM model. The safety and stability of the model are verified by multi-vehicle loop simulation and multi-vehicle linear simulation. Compared with the LSTM model, the safety of the Gipps-LSTM model is improved by 42.02%, and the convergence time is reduced by 25 seconds.

MBC-SS: A multi-band cooperative sidelink scheme for NR V2X networks

Vehicle-to-everything (V2X) sidelink (SL) communication at mmWave frequency is envisioned to satisfy the exchange of massive sensor data among vehicles. However, directional deafness due to inherent highly directional transmissions results in transmission collisions. Moreover, the high mobility of vehicles incurs significant beam training overhead for beam alignment and tracking. These issues cause performance degradation and pose challenges to SL scheme design. In this paper, we propose a multi-band cooperative SL scheme (MBC-SS) with the concurrent support of resource scheduling and beamforming, which offloads partial mmWave control signals to sub-6 GHz control channels and exploits spatial correlations between multiple frequencies. To enable such multi-band cooperation, centralized and distributed modes are developed for in-coverage and out-of-coverage deployments, respectively, whose advantages are twofold. First, centralized scheduling or receiver-side directional sensing in certain directions is adopted to avoid potential collisions during resource selection phase. Second, we take into account the spatial congruence and temporal dependence of channels to adaptively design training beams and select alignment beams. In addition, the performances of the proposed protocol are investigated theoretically and verified by simulations. Compared with the existing sub-6 GHz assisted scheme, the proposed distributed MBC-SS has an improvement of transmission reliability by 15% and throughput by 12.5% in highly dense scenarios. Meanwhile, lower delay and training overhead are achieved.