A method of determining and visualizing safe motion parameters of a ship navigating in restricted waters

Determining and visualizing safe motion parameters of a ship navigating in severe weather conditions

Most ship collisions are caused by human error, making them unpreventable as long as humans operate a ship. Autonomous navigation technology is expected to prevent these accidents. Collision avoidance is a key issue in the realization of autonomous ships. To date, rule- and artificial intelligence (AI)-based collision avoidance algorithms have been studied. However, most of them assumed a simple environment in which other ships maintain their speed and course. During actual navigation in congested waters, safe and efficient collision avoidance are achieved through cooperative maneuvers between ships that obey the COLREGs. To realize cooperative maneuvers of ships, multi-agent deep reinforcement learning was applied to learn collision avoidance maneuvers considering the motions of other ships and COLREGs. Then, the developed multi-agent AI was evaluated with typical one-on-one encounters. The multi-agent AI performed cooperative collision avoidance maneuvers in head-on and crossing situations. Furthermore, the influence of reward setting regarding the degree of compliance with COLREGs on the cooperative collision avoidance was investigated. These results demonstrated that the multi-agent AI was promising for realizing cooperative collision avoidance maneuvers similar to those performed by humans.

Autonomous Landing of Fixed Wing Unmanned Aerial Vehicle with Reactive Collision Avoidance

COLREGs-abiding hybrid collision avoidance algorithm based on deep reinforcement learning for USVs

During the mission of the USV (Unmanned Surface Vehicle), there may be some static or dynamic obstacles on the pre-planned track that are not displayed on the ground station. To avoid these obstacles in time, a model of DCPA (distance to the closest point of approach) between the USV and the obstacle is proposed, which is used to plan the speed of the USV, and adaptively accelerate and decelerate can safely avoid dynamic obstacles. We solved the problem of target unreachable and heading change optimization by planning the heading at IAPF (improved artificial potential field) in the process of sailing, which can effectively avoid static obstacles and respond to collision avoidance in emergencies. The collision avoidance planning outputs a set of behavior vectors (speed, heading), and hands it over to the USV controller to control the navigation of the USV. In this study, an adaptive speed and heading planning method is used to improve the collision avoidance ability of the USV in the mixed scene of dynamic and static obstacles. Through multiple launching experiments, the actual collision avoidance effect of the method is verified, and the safety and reliability of the USV application requirements are met.

Collision avoidance is more and more of importance due to the growing amount of space debris posing a threat not only on satellites in orbit but also on upcoming missions. To avoid a collision between space debris and functioning satellites or even between two functioning satellites collision avoidance manoeuvres can be induced if one of the satellites has a working propulsion system. An alternative method of collision avoidance operations is presented in this study. By changing the satellites attitude, it is possible to obtain an increase or decrease in the semi-major axis in relation to its nominal orbital decay. The change in the semi major axis together with the time until closest approach provokes a change in the relative geometry of the object orbits resulting in a decreasing collision risk. This method enables collision avoidance manoeuvres for satellites in Low Earth Orbits featuring active attitude control and drag-susceptible geometries. Additionally, the probability of a collision can be reduced by changing the satellite attitude so that the minimum effective area is perpendicular to the relative velocity vector at the time of closest approach. Both methods can be applied to satellites without propulsion, which otherwise would be defenceless. A test run for verification of collision avoidance by means of drag-minimization was performed in June 2018 with the Technology Experiment Carrier (TET-1) satellite of the FireBIRD constellation. The experiment planning and results are presented along with the initial flight dynamics analysis and representative examples for collision avoidance scenarios.

An energy efficient IoD static and dynamic collision avoidance approach based on gradient optimization

Autonomous collision avoidance method for MASSs based on precise potential field modelling and COLREGs constraints in complex sailing environments

Autonomous surface crafts (ASCs) have strong potential as platforms for repeat transect oceanographic surveys in coastal and estuarine systems. Good spatial and temporal coverage and resolution could be achieved by an ASC capable of weekslong operations at average speed 5 knots, which is the design goal for the Surveying Coastal Ocean Autonomous Profiler (SCOAP) catamaran ASC. This project addresses operational challenges for long duration ASC deployments, to help minimize risk of collisions: site planning, and on-board collision avoidance (CA) software. In anticipation of a Rhode Island Sound (RIS) SCOAP deployment, a site planning method was developed using archived Automatic Identification System (AIS) data. AIS is a real-time, radio-based system for sharing navigation information among vessels. Archived data were used to determine geographic and seasonal patterns of RIS vessel traffic, and associated frequency of potential collision encounters for various hypothetical repeat transect ASC surveys under consideration. Seasonal-mean AIS vessel traffic varied from as low as 0.01 tracks per day or less in southeastern RIS to about 8 tracks per day in shipping lanes near Narragansett Bay. Corresponding numbers of potential collision encounters for a month-long repeat transect ASC survey in these two areas are about 0-2 and 12-22, respectively, with lower/higher values in winter/summer. Crudely estimated non-AIS traffic suggests up to 3-4 times higher total (AIS and non-AIS vessels) potential encounters. The method provides quantitative information to enable site planning that best balances oceanographic sampling goals against associated collision risks. On-board autonomy software capable of performing collision avoidance (CA) maneuvers is essential for long duration ASC operations. To demonstrate and evaluate its CA performance the Mission Oriented Operation Suite Interval Programming Helm autonomy software, to be implemented on SCOAP, was used to simulate repeat transect ASC surveys with traffic vessels. The CA algorithm used avoids collisions without attempting to comply with Coast Guard (CG) Collision Avoidance Regulations (COLREGS). Three categories of ASC CA maneuver were identified, in which nearly all encounters fall: large deflection, course-reversal, and leave/return to station keeping. ASC path disruptions are substantially reduced when traffic vessels perform CA in addition to the ASC; sensitivity of encounter statistics to other ASC and traffic vessel path configurations, and CA algorithm parameters, is modest. Overall the CA algorithm performed reliably, resolving at least 97% of encounters in 10s of seconds, including interactions with multiple traffic vehicles simultaneously. A framework was developed for how ASCs can best approach compliance with COLREGS, the

Ship berthing operations in restricted waters such as ports requires the accurate use of onboard-vessel equipment such as rudder, thrusters, and main propulsions. For big ships, the assistance of exterior supports such as tugboats are necessary, however with the advancement of technology, we may hypothesize that the use of artificial intelligence to support ship berthing safely at ports without the dependency on the tugboats may be a reality. In this paper we comprehensively assessed and analyzed several literatures regarding this topic. Through this review, we seek out to present a better understanding of the use of artificial intelligence in ship berthing especially neural networks and collision avoidance algorithms. We discovered that the use of global and local path planning combined with Artificial Neural Network (ANN) may help to achieve collision avoidance while completing ship berthing operations.

Constant thrust collision avoidance maneuver under thruster failure

SRM plume: A candidate as space debris braking system for Just-In-Time Collision avoidance maneuver

A significant increase in the number of anthropogenic objects in Earth orbit has necessitated the development of satellite conjunction assessment and collision avoidance capabilities for new spacecraft. Neutral mass density variability in the thermosphere, driven by enhanced geomagnetic activity and solar EUV absorption, is a major source of satellite propagation error. This work investigates the impacts of space weather driver forecasting uncertainty on satellite drag and collision avoidance maneuver decision‐making. Since most operational space weather driver forecasts do not offer an uncertainty assessment, the satellite operator community is left to make dangerous assumptions about the trustworthiness of the forecast models they use to perform satellite state propagation. Climatological persistence‐based forecast models are developed for F10.7 and Kp. These models accurately capture the heteroscedastic and, at times, highly non‐Gaussian uncertainty distribution on forecasts of the drivers of interest. A set of realistic satellite conjunction scenarios is simulated to demonstrate the contributions of space weather driver forecast uncertainty on the probability of collision and maneuver decisions. Improved driver forecasts, especially forecasts of F10.7, are demonstrated to be very useful for enabling durable maneuver decisions with additional lead time (up to 24 hr for the period examined), though the improvement depends on the specific conjunction scenario of interest.

Space debris is an emerging factor in the operation of spacecraft in the Low Earth Orbit regime (LEO) where some altitude bands are densely populated with man-made objects. The consequences are the perturbation of operations through frequent warnings and, casually, collision avoidance manoeuvres. ESA is operating three spacecraft in sunsynchronous orbits. Conjunctions have been monitored since 2004 and the process has been considerably improved and is now significantly assisted by the warning bulletins submitted by the Joint Space Operations Centre (JSpOC). The number of warnings to process and collision avoidance manoeuvres to perform is a function of the probability thresholds used in the various procedures and the object density which again depends on altitude. This paper addresses the number of warning events as a function of the operating altitude for LEO spacecraft. It demonstrates the experience made in ESA with their collision avoidance process and criteria.

Robust Decentralized Supervisory Control in a Leader-Follower Configuration with Obstacle Avoidance