Collision Avoidance Response Research Articles

Determination of Ship Collision Avoidance Timing Using Machine Learning Method

The accurate timing for collision avoidance actions is crucial for preventing maritime collisions. Traditional methods often rely on collision risk assessments, using quantitative indicators like the Distance to the Closest Point of Approach (DCPA) and the Time to the Closest Point of Approach (TCPA). Ship Officers on Watch (OOWs) are required to execute avoidance maneuvers once these indicators reach or exceed preset safety thresholds. However, the effectiveness of these indicators is limited by uncertainties in the maritime environment and the human behaviors of OOWs. To address these limitations, this study introduces a machine learning method to learn collision avoidance behavior from empirical data of ship collision avoidance, particularly in cross-encounter situations. The research utilizes Automatic Identification System (AIS) data from the open waters around Ningbo Zhoushan Port. After data preprocessing and applying spatio-temporal constraints, this study identifies ship trajectory pairs in crossing scenarios and calculates their relative motion parameters. The Douglas–Peucker algorithm is used to identify the timing of ship collision avoidance actions and a collision avoidance decision dataset is constructed. The Random Forest algorithm was then used to analyze the factors affecting the timing of collision avoidance, and six key factors were identified: the distance, relative speed, relative bearing, DCPA, TCPA, and the ratio of the lengths of the giving-way and stand-on ships. These factors serve as inputs for the XGBoost algorithm model, which is enhanced with Particle Swarm Optimization (PSO), and thus constructing a ship collision avoidance decision model. In addition, considering the inherent errors in any model and the dynamic nature of the ship collision avoidance process, an action time window for collision avoidance is introduced, which provides a more flexible time range for ships to make timely collision avoidance responses based on actual conditions and the specific encounter environment. This model provides OOWs with accurate timing for taking collision avoidance decisions. Case studies have validated the practicality and effectiveness of this model, offering new theoretical foundations and practical guidance for maritime collision avoidance.

Multi-Joint Active Collision Avoidance for Robot Based on Depth Visual Perception

Dear editor, Human-robot collaboration is a research topic that has numerous potential applications, such as in smart cities. An important safety consideration in human-robot collaboration is collision avoidance [1]. Many studies have prioritized collision avoidance of the robot end-effector. However, multi-joint (whole-body) collision avoidance is also very important in complex working scenarios. Several studies have achieved multi-joint collision avoidance by estimating the distance between obstacles and control points placed on the robot body, which adds computational effort to the collision-detection process. Therefore, we combine a robot skeleton with depth visual perception to achieve a fast multi-joint collision avoidance response. This method can be divided into collision detection and collision avoidance strategies, as illustrated in Fig. 1. In collision detection, we use a statistical filtering algorithm to denoise visual data, and propose a real-time obstacle distance-estimation algorithm based on a robot skeleton. In the collision avoidance strategy, a multi-joint repulsive force model is established based on the artificial potential field, and a motion control strategy is developed to obtain a collision-free trajectory. Real-time collision avoidance experiments with a 7-DOF collaborative robot are conducted to verify our approach. The experimental results show that our method enables the robot to have the capability of active collision avoidance for both the end-effector and the whole body. The robot can avoid obstacles and complete desired tasks with a smooth trajectory.

Intelligent Collision Avoidance Method for Motion Obstacles of Unmanned Vehicles

At present, the active technology of automobiles is becoming more and more mature and the emergence of driverless vehicles makes it a hotspot in the field of road safety. A new intelligent collision avoidance method for unmanned vehicle motion obstacles is proposed. The kinematics model of unmanned vehicles is established and linearized to obtain the kinematics linear tracking error model of unmanned vehicles and predict the future behavior of unmanned vehicles. The intelligent collision avoidance can be achieved by improving the artificial potential field model of the unmanned vehicle after understanding the future behavior and obstacle information of the unmanned vehicle. The experimental results show that the method has a high detection rate and success rate of obstacle avoidance and low total time-consuming in the process of behavior selection and path planning. It can quickly make collision avoidance responses and reduce the possibility of collision.

Does the Size-Arrival Effect Occur With an Active Collision-Avoidance Task in an Immersive 3D Virtual Reality Environment?

Determine whether the size-arrival effect (SAE) occurs with immersive, 3D visual experiences and active collision-avoidance responses. When a small near object and a large far object approach the observer at the same speeds, the large object appears to arrive before the small object, known as the size-arrival effect (SAE), which may contribute to crashes between motorcycles and cars. Prior studies of the SAE were limited because they used two dimensional displays and asked participants to make passive judgments. Participants viewed approaching objects using a virtual reality (VR) headset. In an active task, participants ducked before the object hit them. In a passive prediction-motion (PM) judgment, the approaching object disappeared, and participants pressed a button when they thought the object would hit them. In a passive relative TTC judgment, participants reported which of two approaching objects would reach them first. The SAE occurred with the PM and relative TTC tasks but not with the ducking task. The SAE can occur in immersive 3D environments but is limited by the nature of the task and display. Certain traffic situations may be more prone to the SAE and have higher risk for collisions. For example, in left-turn scenarios (e.g., see Levulis, 2018), drivers make passive judgments when oncoming vehicles are far and optical expansion is slow, and binocular disparity putatively is ineffective. Collision-avoidance warning systems may be needed more in such scenarios than when vehicles are near and drivers' judgments of TTC may be more accurate (DeLucia, 2008).

Research on waterborne collision avoidance and early warning algorithm based on location data

Zhenjiang Dagang Ferry, located in the middle and upper reaches of the Yangtze River Jiangsu section, is full of different types of ships. The steam ferry crosses the waterway and frequently meets with the passing ships, inducing water collision accidents. This article, taking cross-river ferrys and normal navigation ships as research subjects, proposes an algorithm for water navigation collision avoidance based on position data. First, by analyzing the dynamic coordinate of the ferry and navigation vessel, their navigation trajectories are predicted respectively. Second, the time when they arrive at the possible collision point is calculated, the type of traffic conflict is determined, the drive’s collision avoidance response time is considered, and a warning criterion for early warning is established. Finally, the proposed warning algorithm is analyzed to check to what extent the warning can help the ship avoid the collision. Sixteen sets of data showing the navigation of the ships are selected to compare the effect of the warning algorithm with the radar warning method. The research results show that the application of the algorithm can avoid unnecessary alarm, false alarm, and alarm failure the radar warnings have, improving the accuracy and helping avoid the collision accidents.

Validation of Essential Acoustic Parameters for Highly Urgent In-Vehicle Collision Warnings.

Objective The aim of this study was to validate the importance of key acoustic criteria for use as in-vehicle forward collision warning (FCW) systems. Background Despite recent advances in vehicle safety, automobile crashes remain one of the leading causes of death. As automation allows for more control of noncritical functions by the vehicle, the potential for disengagement and distraction from the driving task also increases. It is, therefore, as important as ever that in-vehicle safety-critical interfaces are intuitive and unambiguous, promoting effective collision avoidance responses upon first exposure even under divided-attention conditions. Method The current study used a driving simulator to assess the effectiveness of two warnings, one that met all essential acoustic parameters, one that met only some essential parameters, and a no-warning control in the context of a lead vehicle-following task in conjunction with a cognitive distractor task and collision event. Results Participants receiving an FCW comprising five essential acoustic components had improved collision avoidance responses relative to a no-warning condition and an FCW missing essential elements on their first exposure. Responses to a consistently good warning (GMU Prime) improved with subsequent exposures, whereas continued exposure to the less optimal FCW (GMU Sub-Prime) resulted in poorer performance even relative to receiving no warning at all. Conclusions This study provides support for previous warning design studies and for the validity of five key acoustic parameters essential for the design of effective in-vehicle FCWs. Application Results from this study have implications for the design of auditory FCWs and in-vehicle display design.

Coming back into the loop: Drivers’ perceptual-motor performance in critical events after automated driving

This driving simulator study, conducted as part of the EU AdaptIVe project, investigated drivers’ performance in critical traffic events, during the resumption of control from an automated driving system. Prior to the critical events, using a between-participant design, 75 drivers were exposed to various screen manipulations that varied the amount of available visual information from the road environment and automation state, which aimed to take them progressively further ‘out-of-the-loop’ (OoTL). The current paper presents an analysis of the timing, type, and rate of drivers’ collision avoidance response, also investigating how these were influenced by the criticality of the unfolding situation. Results showed that the amount of visual information available to drivers during automation impacted on how quickly they resumed manual control, with less information associated with slower take-over times, however, this did not influence the timing of when drivers began a collision avoidance manoeuvre. Instead, the observed behaviour is in line with recent accounts emphasising the role of scenario kinematics in the timing of driver avoidance response. When considering collision incidents in particular, avoidance manoeuvres were initiated when the situation criticality exceeded an Inverse Time To Collision value of ≈0.3s−1. Our results suggest that take-over time and timing and quality of avoidance response appear to be largely independent, and while long take-over time did not predict collision outcome, kinematically late initiation of avoidance did. Hence, system design should focus on achieving kinematically early avoidance initiation, rather than short take-over times.

Reaction Time and Glance Behavior of Visually Distracted Drivers to an Imminent Forward Collision as a Function of Training, Auditory Warning, and Gender

Forward Collision Warning (FCW) systems are intended to alert drivers to an imminent forward collision threat to reduce the frequency and severity of rear-end collisions and mitigate injury and property damage for occupants of both vehicles. This between-subjects driving simulator study examined the effects of three variables – FCW system training, auditory warning type, and gender – on a visually distracted driver's response to an unexpected, imminent, forward collision threat. First, only half of the participants were provided with a brief description of the FCW system. Second, four different auditory warning conditions were compared: no-auditory warning (baseline), average-urgency warning, highest-urgency warning, and an auditory icon car horn. Drivers who received FCW system training had faster reaction times and 68% fewer collisions than drivers who did not receive training. While the highest-urgency warning produced the fastest initial glance to the forward scene, it was the car horn warning that produced robust reaction time, glance behavior, and collision benefits. Unexpectedly, 34.7% of distracted drivers glanced back to the center console display, following their initial forward glance, prior to braking. This unanticipated behavior resulted in longer reaction times, shorter minimum time-to-collision, and a 63.7% increase in collisions as compared with drivers who did not glance back to the console display. Results suggest that even brief system training can aid interaction with an FCW system and glance behavior, reaction times can improve with an auditory icon car horn as the auditory warning, and that uninterrupted forward attention upon detection of a collision threat is imperative for an effective collision avoidance response.

Force Measurements on Locusts during Visually-Evoked Collision Avoidance Maneuvers

The collision avoidance behavior of the locust, Schistocerca americana, in response to simulated approaching objects, also called looming stimuli, was investigated in a low speed wind tunnel. The animals were mounted using a sting on a sensitive six-component microbalance custom-designed for the experiments. Forces and moments were measured as a function of time during the simulated approach and interpreted in the context of collision avoidance behaviors. The stimuli presented from the side effectively evoked robust and discernible collision avoidance responses. Locusts attempted to avoid collision by either flying over or under the looming object, or alternatively by steering around it. These efforts appeared in the form of changes in aerodynamic forces and moments as a function of time. It was also observed that the locusts increased the wing flapping frequency in response to the stimulus.

Neural mechanisms underlying the collision avoidance behavior in the African Clawed frog tadpole

Event Abstract Back to Event Neural mechanisms underlying the collision avoidance behavior in the African Clawed frog tadpole Arseny S. Khakhalin1, David Koren1 and Carlos D. Aizenman1* 1 Brown University, Department of Neuroscience, United States The tadpole of the African Clawed frog Xenopus laevis is a broadly used experimental preparation in developmental and cellular neuroscience research. Premetamorphic Xenopus tadpoles are known to be suction feeders and do not track prey, however they do exhibit a range of orienting behaviors such as schooling, collision avoidance, and escape responses. It is assumed that in the tadpole most of these behaviors are mediated by the optic tectum, which is a structure that serves as a higher multisensory integrative center in these animals, and which is homologous to the mammalian superior colliculus. While a lot is known about the development and cellular organization of the optic tectal circuitry, it is still unclear how the information coming from the environment is encoded in the activity of the tectal cells, and how the necessary computations are performed in this structure. Here we describe a collision avoidance behavior in Xenopus laevis tadpoles, and through a series of sequentially reduced preparations we illustrate the mechanisms underlying this behavior. In the first set of experiments we presented freely swimming animals with computer-generated two-dimensional objects, approaching them at either collision or non-collision trajectories. By tracking the animals, and by reconstructing the geometry of approaches, and the projections computer-generated objects would have on the retinas, we identified temporal and spatial properties of those stimuli that successfully triggered the collision avoidance response. Then, in the second set of experiments, we presented partially immobilized animals with computer generated stimuli that were projected on a microfiber screen placed near one of the eyes. The stimuli were specifically designed so that their retinal projections mimicked our reconstructions from the first set of experiments. A high speed camera was used to track the movements of the tail, and we show that different stimuli induced different sub-variants of the avoidance motor program, with different latencies, and probabilities. Finally, we presented the same set of stimuli to fully immobilized animals, recording either the spiking activity, or the inhibitory and excitatory postsynaptic currents from individual cells in the optic tectum. We show that the spatial and temporal computations that are required for the identification of behaviorally relevant stimuli start at the level of the ganglion cells in the retina, and continue in the optic tectum, where they rely on the temporal interaction between excitatory and inhibitory drive to the tectal cells. Keywords: collision avoidance, Frog, navigation, optic tectum, superior colliculus, Vision, Xenopus Conference: Tenth International Congress of Neuroethology, College Park. Maryland USA, United States, 5 Aug - 10 Aug, 2012. Presentation Type: Poster (but consider for participant symposium and student poster award) Topic: Orientation and Navigation Citation: Khakhalin AS, Koren D and Aizenman CD (2012). Neural mechanisms underlying the collision avoidance behavior in the African Clawed frog tadpole. Conference Abstract: Tenth International Congress of Neuroethology. doi: 10.3389/conf.fnbeh.2012.27.00168 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 27 Apr 2012; Published Online: 07 Jul 2012. * Correspondence: Dr. Carlos D Aizenman, Brown University, Department of Neuroscience, Providence, RI, 02912, United States, Carlos_Aizenman@brown.edu Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Arseny S Khakhalin David Koren Carlos D Aizenman Google Arseny S Khakhalin David Koren Carlos D Aizenman Google Scholar Arseny S Khakhalin David Koren Carlos D Aizenman PubMed Arseny S Khakhalin David Koren Carlos D Aizenman Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

Activity of descending contralateral movement detector neurons and collision avoidance behaviour in response to head-on visual stimuli in locusts

We recorded the activity of the right and left descending contralateral movement detectors responding to 10-cm (small) or 20-cm (large) computer-generated spheres approaching along different trajectories in the locust's frontal field of view. In separate experiments we examined the steering responses of tethered flying locusts to identical stimuli. The descending contralateral movement detectors were more sensitive to variations in target trajectory in the horizontal plane than in the vertical plane. Descending contralateral movement detector activity was related to target trajectory and to target size and was most sensitive to small objects converging on a direct collision course from above and to one side. Small objects failed to induce collision avoidance manoeuvres whereas large objects produced reliable collision avoidance responses. Large targets approaching along a converging trajectory produced steering responses that were either away from or toward the side of approach of the object, whereas targets approaching along trajectories that were offset from the locust's mid-longitudinal body axis primarily evoked responses away from the target. We detected no differences in the discharge properties of the descending contralateral movement detector pair that could account for the different collision avoidance behaviours evoked by varying the target size and trajectories. We suggest that descending contralateral movement detector properties are better suited to predator evasion than collision avoidance.

Using a mobile robot to study locust collision avoidance responses.

The visual systems of insects perform complex processing using remarkably compact neural circuits, yet these circuits are often studied using simplified stimuli which fail to reveal their behaviour in more complex visual environments. We address this issue by testing models of these circuits in real-world visual environments using a mobile robot. In this paper we focus on the lobula giant movement detector (LGMD) system of the locust which responds selectively to objects which approach the animal on a collision course and is thought to trigger escape behaviours. We show that a neural network model of the LGMD system shares the preference for approaching objects and detects obstacles over a range of speeds. Our results highlight aspects of the basic response properties of the biological system which have important implications for the behavioural role of the LGMD.

The Role of Situational Factors and Display Cues on Collision Detection and Avoidance Using a Terrain Enhanced Primary Flight Display

The present research examines situation factors and display cues that contribute to the effectiveness of using a terrain enhanced primary flight display (TE-PFD) for detecting and avoiding potential Controlled Flight Into Terrain (CFIT) accidents. Specifically, the relative importance of the terrain distance, altitude, and presence of an artificial horizon line were investigated. One of the crucial features of the TE-PFD is the inclusion of an artificial horizon line in addition to the natural horizon line provided by the terrain. The present research compared collision detection and avoidance decisions using a TE-PFD both with and without an artificial horizon line. Performance was assessed using the signal detection theory (SDT) parameters of sensitivity and response bias as well as the more traditional analysis of RT. Results indicated that removal of the artificial horizon line not only reduced the perceptual ease in detecting collisions but also altered the decision criterion used to make a collision avoidance response.

Collision Avoidance Response Stereotypes in Pilots and Nonpilots

A two-part study was conducted to investigate the effects of target variables upon pilot and nonpilot collision avoidance responses to simulated approaches which were head-on or nearly so. Part I investigated the effect of bearing and found that nonpilots preferred to turn left in a head-on approach. Although pilots generally turned right under the same conditions, 25% exhibited the nonpilot left-turn response. The nonpilot response bias seemed related to the type of control used for aircraft pilotage. Part II examined the effects of bearing and collision index (a geometric construct representing an index for optimal response selection) upon the responses of 24 pilots. Two subgroups were identified, one apparently attending primarily to bearing while the other attended to aspect. Only one subject appeared to use the optimal collision-index construct for response selection.