With the gradual development of Maritime Autonomous Surface Ships (MASS), sea traffic is expected to remain in mixed navigation scenarios where autonomous and conventional ships operate concurrently. General collision avoidance methods and autonomous algorithms resolve encounter situations independently, but disparities in decision-making logic and approaches leave uncoordinated collision risks. This study constructs a bilateral negotiation model that enables autonomous and conventional ships to resolve uncoordinated collision avoidance through negotiation. The Zeuthen strategy is applied to ensure convergence and consensus in bargaining, while unilateral Bayesian learning is embedded to allow autonomous ships to estimate relevant information from conventional ships for improved negotiation capacity. The method exploits the computational capability of autonomous ships while imposing only lightweight information exchange requirements on conventional ships. Simulation experiments in representative mixed navigation scenarios demonstrate that the method resolves previously uncoordinated encounters, eliminates unnecessary evasive maneuvers by autonomous ships, and significantly improves overall navigational safety. This research addresses the limited studies on collaborative collision avoidance in such scenarios, reduces unnecessary active avoidance by autonomous ships, enhances the safety of decision-making for heterogeneous fleets, and provides a reference for the design and optimization of mixed navigation methods.

Flocking collision avoidance for multi-UAVs in restricted scenarios: An event-triggered MAPPO strategy based on task-hierarchical curriculum

Expert-guided and action-compensated deep reinforcement learning for robust multi-ship collision avoidance in dynamic and uncertain maritime environments

The increasing deployment of unmanned aerial vehicles (UAVs) across various fields, from agriculture to disaster management, has raised critical concerns about mid-air collisions in increasingly congested airspaces. While previous research has extensively explored collision avoidance techniques, most solutions focus either on static or low-density dynamic environments, leaving a gap in addressing UAV navigation in densely cluttered, dynamic 3D environments. This paper introduces a novel collision cone-based approach designed to enhance time-efficiency and precision in 3D UAV collision avoidance scenarios, particularly in complex and dynamic environments with multiple obstacles. Through both simulation and real-world experiments, the method demonstrates superior time-efficiency compared to a benchmark method, while maintaining robust performance in unpredictable environments. The contributions of this work include the development of a real-time adaptable algorithm that recalculates optimal paths based on dynamic changes and its practical validation in realistic, high-density scenarios. This work fills a significant research gap by addressing the limitations of previous 2D approaches and static obstacle methods, providing a comprehensive solution for UAVs operating in highly dynamic 3D spaces.

Adaptive target tracking and collision avoidance control of UUV based on limited perception information

The article explores the use of agent-based modelling (ABM) to simulate agent behaviours. The discussion focuses on agents, simulating the behaviour of drones operating in conditions of uncertainty with the environment’s changing parameters. Agent-based modelling makes it possible to customise complex systems by representing entities as autonomous agents that make decisions and interact with both each other and their environment. The primary aim of this paper is to analyse how ABM can be used to simulate drone movement, adaptive behaviours and cooperative actions. In the following sections, the author examines current ABM platforms that use the Python language, identifies algorithms commonly used in drone movement modelling, and proposes an extension of the A* algorithm for implementation on the MESA platform. The final section presents a simulation based on the developed algorithm, which incorporates factors such as collision avoidance, inter-drone communication, and adaptation to changing environmental conditions. The research findings demonstrate that agent-based modelling is an effective tool for analysing and optimising drone operations, providing insights that could contribute to advancements in autonomous systems.

With the development of the automotive industry and road conditions, cars have become essential for daily life and travel. However, the number of traffic accidents is rising rapidly, and rear - end collisions are common, posing a threat to safety. Anti - collision technology is crucial for road traffic, but existing ones can't reduce losses or prevent accidents. This paper focuses on non-contact anti-collision technology based on electromagnetic repulsion and levitation, using relevant conversion technology. Permanent magnet devices like electromagnetic coils are placed around the vehicle. When a collision is about to happen, the magnetic levitation mode is activated; when a collision occurs, emergency levitation braking is triggered to reduce losses and achieve levitation or repulsion. By analyzing previous collision problems, a vehicle-road cooperative collision avoidance method is proposed in combination with the active collision avoidance system. Simulation designs of rear - end collision, active collision avoidance, and magnetic levitation are completed using MATLAB.It's concluded that this technology has high future development value.

Obstacle-avoidance risk threshold control and global discrete keypoint re-entry are critical factors influencing the smooth dynamic obstacle avoidance of unmanned vessels. For underactuated USVs, which operate in planar motion with three degrees of freedom (surge, sway, and yaw) but only two independent control inputs (surge velocity and yaw rate), this paper designs a layered obstacle-avoidance strategy featuring adaptive global path re-entry points, combined with short- and long-term obstacle trajectory prediction and risk perception. This method employs an Interactive Multiple Model (IMM) integrating Constant Velocity (CV), Constant Acceleration (CA), and Constant Turn Rate and Acceleration (CTRA) models to perform long-term spatiotemporal trajectory prediction for dynamic obstacles, constructing a spatiotemporal risk cost map. Long-term dynamic obstacle-avoidance trajectory planning is achieved through optimized adaptive global trajectory re-entry points and an improved A* algorithm. This long-term avoidance trajectory replaces the global path from the avoidance start to the re-entry point, providing a smooth, continuous long-term avoidance prediction. To ensure real-time collision avoidance effectiveness, an improved Dynamic Window Approach (DWA) algorithm uses the long-term avoidance trajectory as a foundation. It integrates the IMM’s short-term spatiotemporal obstacle trajectory prediction, sampling in the velocity and steering angle space to generate short-term avoidance control commands. Finally, the long-term and short-term obstacle-avoidance planning are executed in a receding-horizon manner, where the local DWA planner updates control inputs over a short rolling window without solving a full constrained optimization problem. This establishes a hierarchical avoidance strategy: long-term prediction enables smooth avoidance, while short-term prediction enables real-time avoidance, ensuring the continuity and timeliness of dynamic obstacle avoidance. Simulation results demonstrate that compared with traditional A* planning, the proposed risk-aware A* reduces cumulative collision risk by 62% and increases the minimum obstacle clearance distance by over 32.1%, while maintaining acceptable path length growth. This approach effectively reduces collision risks during navigation, enhances path smoothness, and improves navigation safety.

The development of an intelligent connected monorail transit system offers an effective solution to the mismatch between passenger flow and system capacity at various time intervals within urban rail networks. As the core of such a system lies the virtual coupling (VC) technology, which dynamically adjusts train configurations in response to real-time passenger demand, thereby improving resource utilization. However, during VC operations, severe communication delays between vehicles or the sudden emergence of obstacles ahead may still result in rear-end collisions among coupled vehicles, posing significant safety risks. To address these challenges, this paper focuses on the active collision avoidance control of intelligent connected monorail vehicles operating within the VC environment. At the modeling level, a control model is developed to facilitate VC between leading and following vehicles, and the dynamic characteristics of typical operational scenarios—including station approach coupling, tracking coupling, and departure decoupling—are thoroughly analyzed. Building upon this foundation, the train’s behaviors under collision avoidance during accelerated departures, decelerated arrivals, and unexpected obstacle encounters are further investigated. In terms of control strategy, a Model Predictive Control (MPC) algorithm is introduced to enable efficient coordination and proactive collision avoidance among trains. Ultimately, a simulation platform based on Chongqing Rail Transit Line 3 is established for validating the proposed model and algorithm under representative operating scenarios. The evaluation demonstrates gains in system flexibility and safety and technical foundation for the practical implementation of intelligent rail transit systems.

Formation Tracking with Prescribed Performance and Collision Avoidance

Reverse parking maneuvering of a vehicle with a trailer system is a difficult task to complete for human drivers due to the multi-body nature of the system and the unintuitive controls required to orientate the trailer properly. The problem is complicated with the presence of other vehicles that the trailer and its connected vehicle must avoid during the reverse parking maneuver. While path-planning methods in reverse motion for vehicles with trailers exist, there is a lack of results that also offer collision avoidance as part of the algorithm. This paper hence proposes a modified Hybrid A*-based algorithm that can accommodate the vehicle–trailer system as well as collision avoidance considerations with the other vehicles and obstacles in the parking environment. One of the novelties of this proposed approach is its adaptability to the vehicle with trailer system, where limits of usable steering input that prevent the occurrence of jackknife incidents vary with respect to system configuration. The other contribution is the addition of the collision avoidance functionality which the standard Hybrid A* algorithm lacks. The method is developed and presented first, followed by simulation case studies to demonstrate the efficacy of the proposed approach.

For autonomous systems operating in complex environments, it is a critical challenge to develop effective MAS path planning control mechanism that enables agents to collaborate and avoid collisions with each other. In response to this crucial need, this paper introduces a novel hybrid algorithm for MAS path planning called Crow Swarm Optimization (CSO). This solution leverages the strengths of two distinct metaheuristic approaches, the Crow Search algorithm (CSA) and the Particle Swarm Optimization (PSO). Although CSA is effective during search space exploration, it has slower convergence and weaknesses in finding global optima due to random location updates. To enhance the local search capability of the CSA, this research leverages the strength of PSO in exploitation. To accomplish this, the primary objective of this paper is to leverage the functionally segregated mechanism to overcome the inherent weaknesses of single-approach algorithms, thereby achieving optimal MAS path planning. Beyond path optimization, the presented work addresses collision prevention employing a velocity adjustment technique. This approach minimizes the agent’s velocity to prevent collisions with other agents. To validate the findings, the study conducted a comparative analysis against various versions of both CSA and PSO. The results clearly demonstrate the efficacy of the proposed approach in solving the path-planning problem with collision avoidance.

This article introduces the architecture and real-world deployment of a collision avoidance system based on shared perception between vehicles and infrastructure in autonomous mobility. It employs microservices on both the infrastructure and vehicle platforms to integrate data from multiple sensors and distributed computing units. By leveraging Vehicle to Infrastructure (V2I) communication, the system autonomously interfaces with vehicle’s systems in critical emergency scenarios, such as executing an emergency stop triggered by the presence of Vulnerable Road Users (VRUs), signaled by a roadside unit. Edge computing at key points enhances the system’s capabilities, enabling swift object detection through computer vision and real-time integration with the vehicle’s interfaces via V2I message exchanges. The system is integrated in both fully autonomous and semi-autonomous vehicles, performing emergency stops when a hazard is detected. Depending on the vehicle, it either returns control to the driver or allows the autonomous control system to resume operation. The integration with Autoware, the autonomous control system for the fully autonomous vehicle used in this work, highlights the system’s ability to seamlessly integrate vehicular communications into autonomous mobility. It cooperates with Autoware using information from surrounding entities to execute emergency stop maneuvers without disrupting autonomous driving. Once the maneuver is completed and the hazard is cleared, the vehicle resumes its path without manual intervention. The experimental results with both fully autonomous and semi-autonomous vehicles, in the presence of VRU, demonstrate the system’s ability to deliver timely alerts and ensure successful vehicle responses. Additionally, a comprehensive timing analysis of the system’s performance is conducted across both vehicles and infrastructure.

Practical prescribed-time formation control of nonholonomic mobile robots with connectivity maintenance and collision avoidance

Adaptive robust constraint-following control for a class of nonlinear multiagent systems: Collision avoidance and uncertainty suppression

Collision avoidance for unmanned surface vehicles via adversarial inverse reinforcement learning with diffusion model

Equivalent obstacle star method for collision avoidance of unmanned surface vehicles in restricted waters

The aim was to evaluate the efficiency of cooperative route planning for autonomous drones operating in densely built-up urban environments, with a particular focus on system resilience and positioning accuracy. Experiments were conducted between April and June 2025 at the Intelligent Unmanned Systems Laboratory of the School of Aeronautics at Beihang University (Shunyi District, Beijing, China). The methodology included 60 flights involving multidrone groups using Da Jiang Innovations Matrice 300 Real-Time Kinematics and Yuneec H520 platforms, both operating on multi-agent route cooperative planning (MARCP) and rapidly exploring random tree star (RRT*) algorithms. Data analysis was performed using Python. The results indicated that the MARCP algorithm significantly outperformed RRT* across all navigation metrics: the mean positional error was 0.83 m compared to 1.41 m, and maximum deviations were 2.03 m versus 3.56 m, respectively. MARCP showed superior route adherence at altitudes up to 60 m and in narrow corridors. It achieved 96.6% collision avoidance versus RRT*’s 82.8% through early conflict prediction and dynamic trajectory reallocation. Drone coordination was more reliable with consistent interdrone distances of 6.7–8.9 m, while RRT* showed significant inconsistencies. MARCP recorded only 19 failures (3 critical) compared to RRT*’s 47 failures (20 involving synchronization loss). Buffering and predictive models provided resilience under communication disruptions.

Advanced APF-based collision avoidance and route restoration for large commercial ships under COLREGs

Decentralized cooperative collision avoidance strategies for conventional and intelligent ships in mixed scenarios