Collision Avoidance Problem Research Articles

A COLREGs compliance reinforcement learning approach for USV manoeuvring in track-following and collision avoidance problems

The development of new technologies for autonomous platforms has allowed their integration into sea mine countermeasures. This has allowed to remove the personnel from the potential danger by having the mine search task performed by an unmanned surface vessel (USV). Traditional intelligent systems are built by agglomerating hand-coded behaviours that determine how a good manoeuvre looks like. This induces cognitive bias into the pre-defined behaviours that can violate safety and regulatory rules imposed by the COLREGs. To alleviate this issue, this paper proposes a COLREGs compliant reinforcement learning (RL) approach that gives a solution for the autonomous navigation of USVs. A custom simulation environment is developed. The RL agents are trained to deal with path-following problem with obstacle avoidance capabilities. A custom reward function is defined to consider the turning disks for the agent’s decision process. A smoothing decision feature is used to smooth the transitions between consecutive actions. The results demonstrate good convergence and high performance under different scenarios. The collision avoidance with COLREGs compliances shows the effectiveness of the proposed approach under several scenarios with static and moving obstacles.

Balancing Safety and Comfort: A Novel Automatic Braking Control Method Using Seventh-Degree Polynomials

This study reinterprets the rear-end collision avoidance problem as a trajectory planning challenge, introducing an automatic braking control method based on seventh-degree polynomials. This approach effectively balances vehicle safety and comfort. Unlike traditional automatic braking control methods, e.g., time-to-collision or safety distance models, our method incorporates multiple constraints at both the initiation and conclusion of braking. Consequently, it significantly improves the braking comfort while ensuring collision avoidance; specifically, the braking deceleration changes smoothly rather than abruptly, greatly reducing the vehicle’s jerk value. In accordance with the Euro NCAP testing standards, three car-to-car rear (CCR) test scenarios, such as car-to-car rear stationary (CCRs), car-to-car rear moving (CCRm) and car-to-car rear braking (CCRb), were established within the CarSim environment. The proposed algorithm was rigorously evaluated through integrated simulations performed in CarSim and MATLAB/Simulink, demonstrating its effectiveness.

Unmanned aerial vehicle formation control method based on improved artificial potential field and consensus

AbstractFormation coordination can improve the overall performance of unmanned aerial vehicle (UAV) systems, so it is important to realize coordinated formation control. To solve the problems of ineffective internal collision avoidance and communication distance maintenance in existing formation control methods, a UAV formation control algorithm based on an improved artificial potential field and consensus is proposed. First, an improved artificial potential field obstacle avoidance method is used to solve the problems of collision avoidance and communication distance maintenance within the formation by setting a communication risk zone and a collision risk zone and by defining the dynamic adjustment parameters of the inter‐UAV virtual force to improve the traditional artificial potential field method. Second, a time integrating factor is introduced, and an improved consensus‐based formation control method is employed to overcome the problem of the artificial potential field method falling into the local optimum easily. Simulation experiments were designed to analyse the trends of the UAV formation motion trajectory, inter‐UAV relative distance, attitude, and formation time. The analysis results show that the method can make the UAV formation consistent with the flight trajectory of the intended formation, solving the problems of collision avoidance and communication distance maintenance within the UAV formation.

MASS and COLREGS–Adaptability, Challenges and Coping Strategies

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

Distributed fixed-time control for high-order multi-agent systems with FTESO and feasibility constraints

In this study, a fixed-time distributed anti-disturbance control strategy is designed for a class of higher-order multi-agent systems in an undirected static topology. Inspired by the existing literature, the strategy introduces a unique way of defining neighborhood errors during the design process to deal with the connectivity maintenance and collision avoidance problems among the neighbor agents in the system. The control strategy not only solves the full state constraint and transient steady state performance constraint control problems simultaneously, but also considers the effects of internal uncertainties and external disturbances of the system, which enhances the difficulty of controller design. To address these challenges, a fixed-time extended state observer is introduced to obtain the estimation of uncertainty and disturbance . Subsequently, an integrated backstepping control scheme is designed to feed-forward compensate for uncertainties and disturbances, while constraining the transient steady-state performance of the system to remain within a predefined performance boundaries. This is achieved by combining the fixed-time prescribed performance and the barrier Lyapunov function. Finally, a simulation case is presented to verify the effectiveness of the designed control strategy.

Barrier-function based adaptive trajectory tracking control for high-order nonlinear systems with collision avoidance

This paper considers the problem of trajectory tracking and collision avoidance for a class of high-order nonlinear strict feedback systems with unknown nonlinearities. The main issue is how to ensure collision avoidance and tracking performance simultaneously in the presence of unknown nonlinear functions. To address the issue, an integral-multiplicative barrier Lyapunov function (BLF) is integrated into the backstepping procedure to remove the dynamic mismatching issue of the existing SUM-type BLF. It has been proven that the proposed adaptive approach ensures both collision avoidance and tracking performance of high-order nonlinear systems in multi-obstacle environments, and all the signals in the closed-loop system are uniformly ultimately bounded (UUB). Simulation results confirm the effectiveness of the proposed method.

Intelligent sequential multi-impulse collision avoidance method for non-cooperative spacecraft based on an improved search tree algorithm

The problem of collision avoidance for non-cooperative targets has received significant attention from researchers in recent years. Non-cooperative targets exhibit uncertain states and unpredictable behaviors, making collision avoidance significantly more challenging than that for space debris. Much existing research focuses on the continuous thrust model, whereas the impulsive maneuver model is more appropriate for long-duration and long-distance avoidance missions. Additionally, it is important to minimize the impact on the original mission while avoiding non-cooperative targets. On the other hand, the existing avoidance algorithms are computationally complex and time-consuming especially with the limited computing capability of the on-board computer, posing challenges for practical engineering applications. To conquer these difficulties, this paper makes the following key contributions: (A) a turn-based (sequential decision-making) limited-area impulsive collision avoidance model considering the time delay of precision orbit determination is established for the first time; (B) a novel Selection Probability Learning Adaptive Search-depth Search Tree (SPL-ASST) algorithm is proposed for non-cooperative target avoidance, which improves the decision-making efficiency by introducing an adaptive-search-depth mechanism and a neural network into the traditional Monte Carlo Tree Search (MCTS). Numerical simulations confirm the effectiveness and efficiency of the proposed method.

Long-Term Fuel-Optimal Collision Avoidance Maneuvers with Station-Keeping Constraints

This work presents a sequential convex program method to compute fuel-optimal collision avoidance maneuvers for long-term encounters. The low-thrust acceleration model is used to account for the control, but the method can compute high-thrust maneuvers by increasing the maximum available acceleration. Dealing with the long-term conjunction poses additional challenges compared to the short-term problem because the encounter is not instantaneous. Thus, under the assumption of Gaussian statistics, the probability of collision is replaced by a simpler metric, the instantaneous probability of collision (IPoC), and a keep-out zone constraint is formulated as a continuous condition to be respected throughout the time frame of interest. The robustness of the solution is improved by introducing a constraint on the sensitivity of IPoC. Furthermore, the collision avoidance problem is coupled with the classical station-keeping requirement for geostationary Earth orbit satellites and with a return to the nominal orbit condition for low Earth orbit satellites. Even though no guarantee is given for the recovery of the global optimum solution, numerical simulations in different orbital regimes show that the proposed approach can yield a local fuel-optimal solution with a run time suitable for autonomous applications.

Leader-Following Connectivity Preservation and Collision Avoidance Control for Multiple Spacecraft with Bounded Actuation

This paper investigates the distributed formation control of a group of leader-following spacecraft with bounded actuation and limited communication ranges. In particular, connectivity-preserving and collision-avoidance controllers are proposed for the leader with constant or time-varying velocity, respectively. The communication graph between the spacecraft is modeled via a distance-induced proximity graph. By designing a virtual proxy for each spacecraft, the spacecraft–proxy couplings address the actuator saturation constraints. The inter-proxy dynamics incorporated with a bounded artificial potential function fulfill the coordination of all proxies. In addition, the bounded potential function can simultaneously tackle connectivity preservation and collision avoidance problems. The distributed formation controllers are proposed for multiple spacecraft with constant or time-varying velocities relative to the leader. A sliding mode control approach and the proxies’ dynamics are used in the design of a distributed cooperative controller for spacecraft to address the cooperative problem between the followers and the leader. Numerical simulations confirm the effectiveness of the anti-saturation distributed connectivity preservation controller.

Distributed safe formation tracking control of multiquadcopter systems using barrier Lyapunov function.

Coordinating the movements of a robotic fleet using consensus-based techniques is an important problem in achieving the desired goal of a specific task. Although most available techniques developed for consensus-based control ignore the collision of robots in the transient phase, they are either computationally expensive or cannot be applied in environments with dynamic obstacles. Therefore, we propose a new distributed collision-free formation tracking control scheme for multiquadcopter systems by exploiting the properties of the barrier Lyapunov function (BLF). Accordingly, the problem is formulated in a backstepping setting, and a distributed control law that guarantees collision-free formation tracking of the quads is derived. In other words, the problems of both tracking and interagent collision avoidance with a predefined accuracy are formulated using the proposed BLF for position subsystems, and the controllers are designed through augmentation of a quadratic Lyapunov function. Owing to the underactuated nature of the quadcopter system, virtual control inputs are considered for the translational (x and y axes) subsystems that are then used to generate the desired values for the roll and pitch angles for the attitude control subsystem. This provides a hierarchical controller structure for each quadcopter. The attitude controller is designed for each quadcopter locally by taking into account a predetermined error limit by another BLF. Finally, simulation results from the MATLAB-Simulink environment are provided to show the accuracy of the proposed method. A numerical comparison with an optimization-based technique is also provided to prove the superiority of the proposed method in terms of the computational cost, steady-state error, and response time.

Motion Planning for the Robotic Fiber Positioners of the Large Sky Area Multiobject Fiber Spectrocopy Telescope

The Large Sky Area Multi-Object Fiber Spectroscopy Telescope (LAMOST) is one of the most effective multiobject spectroscopic instruments. Its survey efficiency is guaranteed by simultaneously positioning multiple fibers via 4000 robotic fiber positioners (RFPs). With the further updates to LAMOST, the new-generation RFPs will be smaller, and the number of RFPs will increase to 5000. The RFPs are densely packed with shared working space. Thus, they may collide with each other, leading to them damaged and reducing the survey speed. In this study, we propose a new motion planning algorithm that prevents the collision of RFPs. To simplify the collision avoidance problem, we transform the motion planning process from a dynamic one into a static one by selecting one of the RFPs in each collision pair as the waiting robot. Accordingly, we design a method for choosing the waiting robot, and use a rapidly exploring random tree to plan a collision-free path for the waiting robot. However, there may be blocks between the waiting robots and their neighbors. Therefore, we also design methods to resolve these blocks. Simulations suggest that the proposed algorithm can prevent 98.4% of the collisions. About 99.9% of the positioners can reach their targets without collisions. Although developed for LAMOST, we believe that our algorithm can also be used for other instruments with equal-arm theta-phi positioners, such as the Dark Energy Spectroscopic Instrument.

Autonomous spacecraft collision avoidance with a variable number of space debris based on safe reinforcement learning

The avoidance of multiple space debris collisions by autonomous spacecraft has garnered significant interests worldwide. Applying deep reinforcement learning (DRL) to autonomous spacecraft collision avoidance problems is still difficult because of limitations on constraint satisfaction and environment state perception, even if DRL is a suitable model-free and data-driven framework. In this research, a state-of-the-art penalized proximal policy optimization (P3O) method is applied to address the spacecraft's autonomous collision avoidance problem, which is formalized as a constrained Markov decision process (CMDP). In contrast with traditional DRL methods, P3O promises to satisfy multiple constraints in actual spaceship operations while also facilitating efficient learning in multi-dimensional, continuous state and action spaces. The scalability of the P3O algorithm is enhanced by combining the feature extraction capabilities and variable-length input capabilities of the long short-term memory (LSTM) networks, enabling the P3O to adapt to a variable number of space debris without the need for network retraining. The performance of the proposed method is compared with other five methods through simulation cases, which verifies the superior performance of the proposed method in terms of scalability, energy consumption, collision probability and constraint satisfaction.

Autonomous Vehicle Traffic Accident Prevention using Mobile-Integrated Deep Reinforcement Learning Technique

When it concerns autonomous traffic management, the most effective decision-making reinforcement learning methods are often utilized for vehicle control. Surprisingly demanding circumstances, however, aggravate the collisions and, as a consequence, the chain collisions. In order to potentially offer guidance on eliminating and decreasing the danger of chain collision malfunctions, we first evaluate the main types of chain collisions and the chain events typically proceed. In an emergency, this study proposes mobile-integrated deep reinforcement learning (DRL) for autonomous vehicles to control collisions. Three essential influencing substances are completely taken into consideration and ultimately achieved by the offered strategy: accuracy, efficiency, and passenger comfort. Following this, we investigate the safety performance currently employed in security-driving solutions by interpreting the chain collision avoidance problem as a Markov Decision Process problem and offering a decision-making strategy based on mobile-integrated reinforcement learning. All of the analysis's findings have the objective of aid academics and policymakers to appreciate the positive aspects of a more reliable autonomous traffic infrastructure and to smooth out the way for the actual adoption of a driverless traffic scenario.

Deep operator and SSA collaboration for space sustainability

The space data association (SDA) has been providing reliable flight safety products for approximately 30 spacecraft operators for 14 years now. The service provides conjunction warnings and operator points of contact for around 700 spacecraft occupying all orbital regimes. The SDA's Space Data Center (SDC), built by AGI and maintained and operated by COMSPOC Corporation, has a proven track record of providing high availability space traffic coordination (STC) products since becoming operational on 15 July 2010.Earlier this year, the SDA, and its chief technical consultant, COMSPOC Corporation, supported the U.S. Department of Commerce (DOC) Geosynchronous Earth Orbit (GEO) and Middle Earth Orbit (MEO) Pilot project by providing comprehensively fused orbit solutions, ten-day orbit ephemeris and covariance predictions, and smoothed reference ephemerides for 100 active spacecraft. Most of these spacecraft are operated by SDA members and participants, allowing the operators to collaboratively contribute their maneuver plans, GPS NavSol measurements, active ranging, and passive RF observations, and authoritative spacecraft dimensions to the DOC Pilot project. For its part, COMSPOC employed its Space Situational Awareness (SSA) Software Suite (SSS)to comprehensively fuse this diverse set of spacecraft operator observations with COMSPOC's own observations from its global network of optical sensors.The first phase of this collaborative data fusion required the establishment of accounts, data connectivity, file transfer methods, and sensor calibration. This required about one month of technical interchange, provision of operator sensor locations and specifics, and COMSPOC SSS operator calibration of those sensors for each spacecraft.But once the data flows, sensor calibrations, and maneuver readers were completed, the second phase drew upon a nearly continuous stream of fused observations and maneuvers to yield accurate and timely predictive ephemerides and covariance time histories. These data products are well-suited to the collision avoidance problem.

Multi-ship encounter situation graph structure learning for ship collision avoidance based on AIS big data with spatio-temporal edge and node attention graph convolutional networks

With the increasing number of ships on the sea, the frequency multi-ship encounters situation was becoming more common than two-ship encounter. The complexity and risk of the navigation will exponentially increase with the more ships involved. Relying solely on the International Regulations for Preventing Collisions at Sea (COLREGS) (objective knowledge) was insufficient to handle the multi-ship intelligent collision avoidance problem, also needed the ship officer's good seamanship (subjective knowledge). In this study, we propose a methodology that combines subjective insights from AIS big data with objective analysis through multi-ship encounters recognition with graph convolutional networks (GCN). (1) The ship encounter 8-azimuths map was utilized to identify the two-ship encounter situation (25 types) from the AIS data. (2) Identify the multi-ship encounters trajectory data by cross-matching the two-ship encounter data. (3) To handle the intricate relationship information between the multiple ships which were transformed into a graph structure using graph theory. (4) Finally, a spatial-temporal edge and node attention graph convolutional network (ST-ENAGCN) was proposed with the graph convolutional unit and long short-term memory (LSTM) unit. The 2022 Ningbo Sea area AIS big data was utilized to achieve graph-structured learning regarding human experiences during the multi-ship encounters situation. The results indicate that the ST-ENAGCN model can understand the complex marine traffic situation to make the own ship collision avoidance decisions. This study contributes significantly to the increased efficiency and safety of sea operations in complex marine traffic conditions and support autonomous navigation of swarm of MASSs under the human-machine hybrid (HMH) conditions to better understand the collision avoidance intention of the ship officer in the multi-ship encounters situation.

Parallel distributed collision avoidance with intention consensus based on ADMM

This paper presents an approach to the problem of collaborative collision avoidance of autonomous inland ships. We propose a distributed model predictive control algorithm that allows ships to negotiate their intention to collaboratively avoid collisions directly. Furthermore, a new method is introduced to better shape ships’ behavior in order to follow Traffic regulations. The simulation results illustrate that the proposed algorithm could significantly increase ship safety navigation. Moreover, it also shows that the solution proposed by our algorithm complies with waterway Traffic regulations except in complex situations when other safe solutions are negotiated.

Reduction of Necessary Conditions for the Variational Collision Avoidance Problem

In this work, we study the reduction by a Lie group of symmetries of variational collision avoidance probelms of multiple agents evolving on a Riemannian manifold and derive necessary conditions for the reduced extremals. The problem consists of finding non-intersecting trajectories of a given number of agents, among a set of admissible curves, to reach a specified configuration, based on minimizing an energy functional that depends on the velocity, covariant acceleration and an artificial potential function used to prevent collision among the agents.

Enhanced Global Optimization With Parallel Global and Local Structures for Real-Time Control Systems

In practice, objective functions of real-time control systems can have multiple local minimums or can dramatically change over the function space, making them hard to optimize. To efficiently optimize such systems, in this paper, we develop a parallel global optimization framework that combines direct search methods with parallel Bayesian optimization. It consists of an iterative global and local search that searches broadly through the entire global space for promising regions and then efficiently exploits each local promising region. We prove the asymptotic convergence properties of the proposed framework and conduct several numerical experiments to illustrate its empirical performance. We also provide a real-time control problem to illustrate the efficiency of our proposed algorithm. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This work is motivated by a collision avoidance problem of vessels aided with onboard agent-based simulations. The simulation on one vessel can predict potential conflicts with other vessels on a pre-defined trajectory. In heavy congestion regions, the environment is highly dynamic and thus it is difficult to find a much safer alternative trajectory if collision is predicted on the current one. Moreover, for such real-time decisions, the control system should be quick in response to improve safety. The proposed metamodel based algorithm is designed for quick decision in such highly dynamic systems. The algorithm employs a decomposition of the response surface to better handle the multi-modal surface resulting from the highly dynamic environment. Specifically, it first looks at the large-scale trend globally (filter out the many local fluctuations that may otherwise trap the algorithm) to locate potential promising regions and then proceeds to this local regions for more detailed local search. To make quick decisions, it uses fast direct search algorithms in the local search phase and applies a parallel search scheme to enjoy the abundant computing power. Both the theoretical analysis and the simulation studies demonstrate that the proposed algorithm can provide better decisions quickly. We also note that this algorithm is not limited to real-time control or simulation-based system. In the case where each run of the experiment is expensive and the budget is limited for the final decision and when the response function is multi-modal, this algorithm can hopefully become a quite efficient and competitive approach. The multi-modal responses have broad applications in the area of control, planning and operations research, such as robot navigating and reinforcement learning.

COLREGs-Based Path Planning for USVs Using the Deep Reinforcement Learning Strategy

This research introduces a two-stage deep reinforcement learning approach for the cooperative path planning of unmanned surface vehicles (USVs). The method is designed to address cooperative collision-avoidance path planning while adhering to the International Regulations for Preventing Collisions at Sea (COLREGs) and considering the collision-avoidance problem within the USV fleet and between USVs and target ships (TSs). To achieve this, the study presents a dual COLREGs-compliant action-selection strategy to effectively manage the vessel-avoidance problem. Firstly, we construct a COLREGs-compliant action-evaluation network that utilizes a deep learning network trained on pre-recorded TS avoidance trajectories by USVs in compliance with COLREGs. Then, the COLREGs-compliant reward-function-based action-selection network is proposed by considering various TS encountering scenarios. Consequently, the results of the two networks are fused to select actions for cooperative path-planning processes. The path-planning model is established using the multi-agent proximal policy optimization (MAPPO) method. The action space, observation space, and reward function are tailored for the policy network. Additionally, a TS detection method is introduced to detect the motion intentions of TSs. The study conducted Monte Carlo simulations to demonstrate the strong performance of the planning method. Furthermore, experiments focusing on COLREGs-based TS avoidance were carried out to validate the feasibility of the approach. The proposed TS detection model exhibited robust performance within the defined task.

Adaptive Neuroevolution With Genetic Operator Control and Two-Way Complexity Variation

Topology and weight evolving artificial neural network (TWEANN) algorithms optimize the structure and weights of artificial neural networks (ANNs) simultaneously. The resulting networks are typically used as policy models for solving control and reinforcement learning (RL) type problems. This paper presents a neuroevolution algorithm that aims to address the typical stagnation and sluggish convergence issues present in other neuroevolution algorithms. These issues are often caused by inadequacies in population diversity preservation, exploration/exploitation balance, and search flexibility. This new algorithm, called the Adaptive Genomic Evolution of Neural-Network Topologies (AGENT), builds on the neuroevolution of augmenting topologies (NEAT) concept. Novel mechanisms for adapting the selection and mutation operations are proposed to favorably control population diversity and exploration/exploitation balance. The former is founded on a fundamentally new way of quantifying diversity by taking a graph-theoretic perspective of the population of genomes and inter-genomic differences. Further advancements to the NEAT paradigm occur through the incorporation of variable neuronal properties and new mutation operations that uniquely allow both the growth and pruning of ANN topologies during evolution. Numerical experiments with benchmark control problems adopted from the OpenAI Gym illustrate the competitive performance of AGENT against standard RL methods and adaptive HyperNEAT, and superiority over the original NEAT algorithm. Further parametric analysis provides key insights into the impact of the new features in AGENT. This is followed by evaluation on an unmanned aerial vehicle collision avoidance problem where maneuver planning models are learnt by AGENT with 33% reward improvement over 15 generations.