Danger Of Collision Research Articles

Feedback neural computation in collision perception: Towards diverse selectivity

Significant strides have been achieved in the biological exploration of the locust’s lobula giant movement detector (LGMD), contributing substantially to the development of collision detection vision systems. Two LGMD neurons, namely LGMD1 and LGMD2, have undergone extensive modeling, each exhibiting distinct collision selectivity toward brighter or darker objects approaching relative to the background. Despite these advancements, a gap exists between biological organisms and the latest models, particularly in implementing diverse collision selectivity and maintaining robustness against objects with varying brightness. To reduce the gap, we introduce a neural model with feedback connections that integrates a feedforward neural network based on ON/OFF channels and feedback loops of ON channels operating merely ON-contrast signals. The instantaneous feedback leads to a fixed-point theorem, establishing the coefficient range in the feedback loop mathematically. This research emphasizes and theoretically analyzes the influence of feedback neural computation on collision perception. To validate the model’s effectiveness, we defined an evaluation criterion, i.e., the time error to collision (TTC), and compared the proposed model with the latest LGMD1 and LGMD2 models. Systematic experiments demonstrated that the proposed model achieves specific collision selectivity comparable to both LGMD1 and LGMD2 while exhibiting enhanced robustness against objects with changing brightness on the surface, outperforming the comparative models. The proposed model predicts collision danger more accurately and robustly, yielding lower TTC. Finally, we carried out on-line robot experiments, which proved the practicality and efficiency of the proposed feedback neural computation in embedded vision system.

Identifying priority sites for whale shark ship collision management globally

The expansion of the world's merchant fleet poses a great threat to the ocean's biodiversity. Collisions between ships and marine megafauna can have population-level consequences for vulnerable species. The Endangered whale shark (Rhincodon typus) shares a circumglobal distribution with this expanding fleet and tracking of movement pathways has shown that large vessel collisions pose a major threat to the species. However, it is not yet known whether they are also at risk within aggregation sites, where up to 400 individuals can gather to feed on seasonal bursts of planktonic productivity. These “constellation” sites are of significant ecological, socio-economic and cultural value. Here, through expert elicitation, we gathered information from most known constellation sites for this species across the world (>50 constellations and >13,000 individual whale sharks). We defined the spatial boundaries of these sites and their overlap with shipping traffic. Sites were then ranked based on relative levels of potential collision danger posed to whale sharks in the area. Our results showed that researchers and resource managers may underestimate the threat posed by large ship collisions due to a lack of direct evidence, such as injuries or witness accounts, which are available for other, sub-lethal threat categories. We found that constellations in the Arabian Sea and adjacent waters, the Gulf of Mexico, the Gulf of California, and Southeast and East Asia, had the greatest level of collision threat. We also identified 39 sites where peaks in shipping activity coincided with peak seasonal occurrences of whale sharks, sometimes across several months. Simulated collision mitigation options estimated potentially minimal impact to industry, as most whale shark core habitat areas were small. Given the threat posed by vessel collisions, a coordinated, multi-national approach to mitigation is needed within priority whale shark habitats to ensure collision protection for the species.

Numerical Study on Hydrodynamic Characteristics of Two Ships Advancing in Parallel for Underway Replenishment of Luxury Cruise Ships

For a long time, seakeeping data has been the basis for judging ship amenities and seaworthiness. Luxury cruise ships, as large passenger ships, put forward higher requirements for seakeeping. To analyze the seakeeping response of luxury cruise ships, AQWA is used to build a model and conduct numerical simulations. The hydrodynamic characteristics of cruise ships and replenishment tankers with different typical sea conditions, various ship spacing and wave directions are studied. According to the results, when two ships are advancing in parallel, the cruise ship should pay attention to the movement of the replenishment tanker while considering its seakeeping to avoid collision danger. The conclusions can avoid dangerous situations in the replenishment and improve the safety of the replenishment operation.

Reliable and Accurate Implicit Neural Representation of Multiple Swept Volumes with Application to Safe Human–Robot Interaction

In automated production using collaborative robots in a manufacturing cell, a crucial aspect is to avoid collisions to ensure the safety of workers and robots in human–robot interaction. One approach for detecting collisions is using the swept volume (SV) to identify safe protective space for operation. We learn an accurate and reliable signed distance function (SDF) network from raw point clouds of a pre-computed SV to represent a class of linear joint motion trajectories. The network requires only a set of parameters and constant execution time, thus reducing the computational time and memory of collision checking due to the complexity of explicit geometry during task execution. The distance of collision danger foresaw by the learned SDF is exploited to reduce the frequency of collision detection calls in the dynamic environment and reduce the computational cost further. We assess the relative merits of the implicit neural representation of multiple SVs in terms of F1-score, error distance from the surface of the truth geometry, and 3D visualization by comparing favorably with a binary voxel network for learning a single SV with similar inference time. All the predicted errors of the geometry lie within a distance of 4 voxels from the surface of the truth geometry, and most reconstruction errors are within 3 voxels. A simulation of pick-and-place task execution in the human–robot interaction scenarios by leveraging the learned SDF as an efficient continuous collision detector is performed. The improvement in execution time and collision detection number is validated in the simulation.

Penyuluhan Penggunaan Lampu Navigasi Pada Kapal Nelayan Desa Wawontulap Untuk Menghindari Bahaya Tubrukan di Laut

Risks of transportation safety are still a common issue in Indonesia. Communities living in coastal and marine areas, the majority of whom work as fishermen, still rely on traditional knowledge and skills. Wawontulap Village is located in the Tatapaan District with a total of 80 active fishermen, most of whom use small-scale traditional fishing boats with 50 cc to 80 cc motor engines and without adequate navigation tools, thus impacting visibility for ship maneuvers. fisherman. The position and potential for catching larger fish at night is a challenge for the fishing community in Wawontulap Village. This is because at night many fishing or fishing boats with larger sizes also descend into the sea which can cause a collision hazard between ships. The problem of navigation tools in the form of navigation lights is deemed necessary to find a solution immediately. Navigation lights on board apart from functioning as navigation guides can also be used as lighting and communication tools in the form of light signals if fishermen need help at any time. the method of socialization and delivery of assistance in the form of 3 (three) navigation lights which were handed over symbolically to village officials (the old law). From this community service activity it shows that fishermen's knowledge of the importance of navigation lights becomes clear and the danger of ship collisions when fishermen go outside to catch fish can be avoided.

Study on driver’s active emergency response in dangerous traffic scenes based on driving simulator

Objective A driver’s active emergency response in dangerous traffic scenes consists of two parts, including reaction behavior and physiological state. In dangerous traffic scenes, the driver’s active emergency response has an important impact on human collision injury. Clarifying the driver’s active emergency response is an important prerequisite for the study of human collision injury under nonstandard posture. Therefore, this study investigates the driver’s active emergency response in different inevitable collision scenes using driving simulator. Methods A driving simulator with a high-speed camera system and human physiological signal acquisition system was first built. Then, three typical vehicle dangerous collision scenes were developed, including frontal collision, side collision, and rear-end collision. Finally, twenty participants (15 males and 5 females) were recruited for a driving experiment, and their active emergency responses were recorded and analyzed. Results All subjects would rotate the steering wheel to the left or right in the active emergency state, and the rotation of the hand would also cause the subject’s upper body to tilt in the same direction. The maximum angle for male subjects to rotate the steering wheel was 59.98°, while for the female subjects, it was 44.28°. In addition, the maximum grip force between the male subjects and the steering wheel was 280.5 N, compared to 192.5 N for female subjects. Compared to the female participants, the male participants not only have a greater rotation angle and a greater grip force on the steering wheel, but also have greater pressure on the brake pedal, and the foot moves quickly from the accelerator pedal to the brake pedal and presses the brake pedal. Conclusions Drivers have different active emergency responses to different vehicle collision scenes. Quantitative statistics of driver’s active emergency response will have important guiding significance for the analysis of the impact of human active emergency response on human injury characteristics in subsequent vehicle collision experiments.

Trajectory Planning Framework Combining Replanning and Hierarchical Planning

To enable autonomous vehicles to respond quickly to changes in the surrounding environment and to generate safe and stable trajectory, we propose a safety-based hierarchical trajectory planning method that divides the planning module into two parts: the planner and the replanning monitor. In the planner, we first propose a fast linear trajectory planning method that uses the mass point model instead of the vehicle model and linearizes the collision avoidance constraint using the Big-M method for linear programming (Big-M) to obtain a linear programming model. The complete vehicle kinematic model is then built in the nonlinear programming stage, the collision constraints and cost functions are refined, and the rough solution of the linear programming is brought into it to obtain the exact solution. The replanning monitor is divided into safety and comfort monitors. The safety monitor will always pay attention to the changes in the surrounding environment and calculate whether the vehicle is in danger of collision in the future period, while the comfort monitor is more concerned with the comfort of driving the vehicle; when the monitor requirements are not met, replanning will be carried out. By simulating the driving environment, the proposed algorithm can form a safe and comfortable trajectory, which verifies the rationality of the proposed method.

Robust safety zones for manipulators with uncertain dynamics in collaborative robotics

ABSTRACT In this paper, an approach for computing online safety zones for collaborative robotics in a robust way, despite uncertain robot dynamics, is proposed. The strategy implements the speed and separation monitoring paradigm, and considers human and robot enclosed in bounding volumes. The human-robot collaboration is monitored by a supervisory controller that guides the robot to stop along a path-consistent trajectory in case of collision danger between human and robot. The size of the robot safety zone is minimized online according to the stop time of the manipulator, and the uncertain robot dynamics is considered using interval arithmetic to ensure compliance with the joint torques limits even in case of imperfect knowledge of the dynamic model parameters. The results verify the effectiveness of the proposed approach, and evaluate the influence of dynamics variations on human-robot collaboration.

Research on the Efficient Space Debris Observation Method Based on Optical Satellite Constellations

The increasing amount of space debris poses a major threat to the security of space assets. The timely acquisition of space debris orbital data through observations is essential. We established a mathematical model of optical satellite constellations for space debris observation, designed a high-quality constellation configuration, and designed a space debris tracking observation scheduling algorithm. These tools can realize the efficient networking of space debris from a large number of optical satellite observation facilities. We designed a constellation consisting of more than 20 low-Earth orbit (LEO) satellites, mainly dedicated to the observation of LEO space objects. According to the observation scheduling method, the satellite constellation can track and observe more than 93% of the targets every day, increase the frequency of orbital data updates, and provide support for the realization of orbital space debris cataloguing. Designing optical satellite constellations to observe space debris can help realize the advance perception of dangerous collisions, timely detect dangerous space events, make key observations about high-risk targets, greatly reduce the false alarm rate of collisions, and provide observational data support for space collisions.

Autonomous collision avoidance system in a multi-ship environment based on proximal policy optimization method

To address the challenge of local path planning in a complex, dynamic environment with multiple ships, we built an autonomous collision avoidance system based on deep reinforcement learning in open water. The system switches between path-tracking and collision avoidance modes in real time, during which any collision danger is perceived through encounter identification and risk calculation. Subsequently, the proximal policy optimization method is applied to design the state space, action space, and reward functions. Decision-making offers advantages in terms of continuous action space, perception of global navigation information, compliance with the International Regulations for Preventing Collisions at Sea (COLREGs), and smooth maneuverings. Simulations are performed under multi-ship encounter conditions, considering the ship hydrodynamic model, environmental disturbance force model, COLREGs, and good seamanship. The results indicate the effectiveness and ability of the proposed system to take appropriate action when faced with dangerous situations under rule constraints and diverse scenarios.

Is there a relationship between time pressure and pedestrian non-compliance? A systematic review

Pedestrians are usually referred to as the most vulnerable road users because they lack sound protection against crashes. The danger of collisions for pedestrians increases at intersection crosswalks due to the non-compliance behaviour of pedestrians at such multi-directional traffic locations. To acquire a greater comprehension, it is indeed imperative to understand pedestrian behaviour at such sites. Therefore, this systematic review aims to assess the risk associated with non-compliance behaviour and the primary causes of non-compliance behaviour at intersections. The study also explored the relationship between time pressure and non-compliance road crossing behaviour. The authors searched the Web of Science, Google Scholar, Scopus, and Semantic to identify the required studies. After excluding books, review papers, non-English research, proceedings, duplicates, and irrelevant studies, 73 pieces of literature were identified for the review process. The current study enlisted all the elements that influence the non-compliance behaviour of pedestrians. Many factors, such as time of day, weather conditions, land use, etc., have a substantial effect on non-compliance but have not been sufficiently studied to establish broad conclusions. Consequently, in exploring the fundamental reasons for non-compliance behaviour, it was found that time--saving or being in a hurry is one of the strong influencers for non-compliance behaviour. Hence, these findings indicate a positive correlation between time pressure and the non-compliance behaviour of pedestrians. However, even though time pressure is a primary source of non-compliance, studies illustrating the impact of time pressure on pedestrian decision-making behaviour are extremely limited. Furthermore, because all time pressure studies have been limited to midblock crossings, it is worthwhile to assess the role of time pressure in pedestrian safety in complex intersection scenarios.

Integrating Both Routing and Scheduling Into Motion Planner for Multivehicle System

In multi-automated guided vehicle (AGV) control, optimization and collision avoidance are two of the key issues. To deal with these problems of the AGV fleet, motion planning is a good solution. This method usually comprises two steps as follows: routing and scheduling that are always separately executed in conventional routine. This scheme still exists some drawbacks, such as limitation of candidate paths or lack of flexibility in handling collisions. Besides, with a specific layout, the algorithm needs to be modified to be proper with that application. The warehouse with grid-based layout employed popularly in logistics and supply chain is our concern. To overcome this theme, a time-frame-based routing and scheduling (TFRS) algorithm for motion planning of vehicles is proposed for this warehouse application. In detail, TFRS can also be called an enhanced Dijkstra’s algorithm (EDA) with adaptive weights for every segment and node. It was designed to gain several benefits of time due to the shortest path, free collision, and proper for chessboard layout. The main idea is that while conducting path routing, certain circumstances of potential accidents are detected and dealt by scheduling in every loop. Due to simultaneous policies of routing and scheduling, the optimization and secure operation could be achieved in the AGV system. Numerous situations in danger of collision are experimented to verify the effectiveness, flexibility, and correctness of the proposed algorithm.

Decision-making of active collision avoidance system based on comprehensive evaluation method of dangerous scenarios

Dangerous scenario modeling is of great significance for the development of automatic driving functions, and the active collision avoidance system directly affects the safety of vehicles and the intelligence level of vehicles. However, the current existing collision risk evaluation methods are difficult to comprehensively evaluate different dangerous scenarios, the evaluation methods are complicated and there is no normalized description form. In addition, the traditional decision-making method of active collision avoidance system based on collision time distance will lead to the problems of inconsistent risk evaluation scale and single way of collision avoidance. To solve the above problems, the mechanism analysis of the longitudinal, lateral, and parallel collision risks is carried out respectively, and then the model based on kinematics and dynamics is established. After that, the corresponding expression form of collision risks is derived. Finally, the comprehensive evaluation method of dangerous collision scenarios is proposed. Secondly, based on the comprehensive evaluation method of collision risk, considering longitudinal constraints, lateral constraints, parallel constraints, and road regulations, an active collision avoidance decision-making method that used the cooperative collision avoidance mode of breaking and steering is designed. Thirdly, different simulation experiments are designed based on PanoSim/Simulink. The results show the comprehensive evaluation method can effectively model the collision risk of vehicles in the motion process. At the same time, the decision-making method of the active collision avoidance system achieves the expected working effect, thus improving driving stability and safety.

Collision Avoidance Method for Autonomous Ships Based on Modified Velocity Obstacle and Collision Risk Index

A novel real-time collision avoidance method for autonomous ships based on modified velocity obstacle (VO) algorithm and grey cloud model is proposed. A typical VO algorithm is used to judge whether there is a collision risk for ships in the potential collision area (PCA). Then, in order to quantify the collision risk of ships in different encounter situations within the PCA and trigger a prompt warning of danger of collision, this study sets up a novel collision risk assessment method based on asymmetric grey cloud model (AGC). It can effectively consider the randomness, ambiguity, and incompleteness of the information in the ship collision risk evaluation process. Moreover, reachable collision-free velocity sets under different encounter situations and optimal steering angle model are constructed. A real-time collision avoidance method based on modified VO algorithm and manoeuvring motion characteristics of vessels is put forward. In this model, various constraints are considered including the International Regulations for Preventing Collisions at Sea (COLREGs), ship manoeuvrability, and ordinary practice of seaman. Finally, several case studies are carried out to verify the performance and reliability of the collision avoidance model. The results show that the proposed method can not only effectively identify and quantify the collision risk in real-time but also offer proper collision-free solutions for autonomous ships.

Optimization Of The Crew In The Implementation Of The Guard Service To Prevent The Occurrence Of Collision Hazards in KM. TL-IX

Officer has an important role in processing the motion of the ship when sailing to avoid things that are not desirable to avoid the dangers of collision. Formulation of the problem taken by the author in this thesis is the implementation of the guard service to prevent the occurrence of collision hazards in KM.TL-IX optimization of the use of navigation tools to prevent the occurrence of collision hazards. With qualitative research methods that produce descriptive data, the implementation of the guard service can be described clearly and concretely because the data obtained from direct interviews and supported by library methods that provide a clearer picture of a clearer picture of the information presented. The results obtained by the author during the research is the implementation of the guard service on the ship that has not been done properly because Mualim II undisciplined in carrying out guard duty, lack of attention and sense of responsibility of the Guard officer when carrying out guard duty on the bridge and the use of navigation tools that are not optimal. Discussion of the results of the study is the optimization of guard duty must be applied in accordance with STCW 1978 as amended in 2010, Mualim should also be guided by the Collision Regulation 1972 in the face of situations that allow the danger of collision. The use of navigation equipment as a detection of collision hazards should be able to produce maximum results for the Prevention of collision hazards and to avoid emergencies. In this case, it is concluded that the distribution of guard duty on board KM.TL-IX has been in accordance with regulations set internationally but in practice there are irregularities because the Mualim II is not responsible when carrying out his guard duty, a sense of lack of attention of the Guard officer during the bridge guard service and the use of navigation tools that are less than optimal by the mualim cause the results obtained are not optimal. The advice of the author is a senior Mualim should set an example to other mualim in the implementation of the guard service on schedule and must be carried out in a disciplined manner and the captain and the Mualim must have skills in operating navigation equipment.

An analysis of the New York City traffic volume, vehicle collisions, and safety under COVID-19

Introduction and Method: We use the arguably exogenous intensity of COVID-19 as an instrument in order to study the relationship between traffic volume and vehicle collisions in a large metropolitan area. We correlate data from multiple sources and consider a time interval ranging from about one year before to one year after the pandemic breakout, which allows to account for preexisting seasonal patterns as well as the disruption brought by the pandemic. Results: We identify that increased traffic volume is associated with significantly more collisions with a robust elasticity varying between 1.2 and 1.7. At the same time, higher traffic volumes are associated with a significant reduction in casualties. Conversely, low traffic volumes are associated with high speeds and with particularly dangerous collisions. In terms of social cost, we separately calculated the cost of property damage and casualties. We measured that the reduction in the per-day social cost of collisions during the COVID-19 period is approximately $453,000 in property damage. However, the increase in casualties from collisions at lower traffic volumes are worth approximately $2.6 million in injuries and fatalities, entirely offsetting any benefit from reduced collisions. Practical Applications: This research provides valuable insights that policy makers may take into consideration when shifting traffic volume in relation to social cost and safety, such as congestion taxes.

Enhancing fluency and productivity in human-robot collaboration through online scaling of dynamic safety zones

Industrial collaborative robotics is promising for manufacturing activities where the presence of a robot alongside a human operator can improve operator’s working conditions, flexibility, and productivity. A collaborative robotic application has to guarantee not only safety of the human operator, but also fluency in the collaboration, as well as performance in terms of productivity and task time. In this paper, we present an approach to enhance fluency and productivity in human-robot collaboration through online scaling of dynamic safety zones. A supervisory controller runs online safety checks between bounding volumes enclosing robot and human to identify possible collision dangers. To optimize the sizes of safety zones enclosing the manipulator, the method minimizes the time of potential stop trajectories considering the robot dynamics and its torque constraints, and leverages the directed speed of the robot parts with respect to the human. Simulations and experimental tests on a seven-degree-of-freedom robotic arm verify the effectiveness of the proposed approach, and collaborative fluency metrics show the benefits of the method with respect to existing approaches.

Implementation and Evaluation of Load Balancing Mechanism With Multiple Edge Server Cooperation for Dynamic Map System

In recent years, research has been conducted on dynamic map systems, which are information and communication platforms that manage vehicle sensor information and run applications. However, there is a concern about scalability in the dynamic map system, which operates on a cloud on the Internet, when the number of vehicles that transmit and receive sensor information increases. Therefore, it is considered that the application load can be distributed by distributing multiple edge servers geographically and having the information managed in the cloud by the edge servers. However, the edge server that controls the vehicle information and the edge server that receives the data do not always match depending on the actual radio wave conditions. Therefore, some applications are difficult to manage, such as intersection collision danger warning and merging arbitration when edge servers are assigned in the same way as base stations that receive data from vehicles. Such an application should receive all vehicle data for the target road area. Therefore, we divide the area on the road where a vehicle travels as “lane section ID” and assign an edge server to each lane section ID on the basis of that area. In addition, we implemented a dynamic map system that connects vehicles and edge servers by linking multiple edge servers. This enables the edge server to aggregate vehicle data without being affected by radio traffic conditions. We evaluated the scalability of the dynamic map system and verified the effectiveness of the load balancing mechanism using multiple edge servers.

Vehicle Safety-Assisted Driving Technology Based on Computer Artificial Intelligence Environment.

In this paper, we propose an assisted driving system implemented with a Jetson nano-high-performance embedded platform by using machine vision and deep learning technologies. The vehicle dynamics model is established under multiconditional assumptions, the path planner and path tracking controller are designed based on the model predictive control algorithm, and the local desired path is reasonably planned in combination with the behavioral decision system. The behavioral decision algorithm based on finite state machine reasonably transforms the driving state according to the environmental changes, realizes the following of the target vehicle speed, and can take effective emergency braking in time when there is a collision danger. The system can complete the motion planning by the model predictive control algorithm and control the autonomous vehicle to smoothly track the replanned local desired path to complete the lane change overtaking action, which can meet the demand of ADAS. The path planner is designed based on the MPC algorithm, solving the objective function with obstacle avoidance function, planning the optimal path that can avoid a collision, and using 5th order polynomial to fit the output local desired path points. In 5∼8 s time, the target vehicle decelerates to 48 km/h; the autonomous vehicle immediately makes a deceleration action and gradually reduces the speed difference between the two vehicles until it reaches the target speed, at which time the distance between the two vehicles is close to the safe distance, obtained by the simulation test results. The system can still accurately track the target when the vehicle is driving on a curve and timely control the desired speed change of the vehicle, and the target vehicle always maintains a safe distance. The system can be used within 50 meters.

A COLREGs-compliant guidance strategy for an underactuated unmanned surface vehicle combining potential field with grid map

A guidance strategy conforming to the International Regulations for Preventing Collisions at Sea (COLREGs) is introduced in this paper such that its objective effectively combines unmanned surface vehicle (USV) dynamics with the obstacle avoidance process. The strategy is divided into the global path-guided and local reactive layers based on expanded Theta* (ETheta*) and improved artificial potential field (IAPF). The global layer constructs a nominal mapping relation (NMR) through running the ETheta* reversely. The USV is guided by sub-targets extracted from the NMR to steer clear of all stationary obstacles and reach the destination. The local layer generates the double-attractive potential of adjacent sub-targets and grid-based repulsive potential of irregular shape stationary obstacles. A COLREGs-compliant repulsive potential is additionally created when the USV detects the danger of collision. Taking the gradient of steepest descent in total potential field as the desired heading, PID method is used to control the USV navigation and realize the autonomous obstacle avoidance. The whole guidance strategy is modeled and simulated on unblocked and real maps respectively for some complicated scenarios. The results show that, with this guidance strategy, the vehicle avoids other target ships and obeys COLREGs with appropriate USV dynamics.