Collision Avoidance Performance Research Articles

Change in the collision avoidance performance of autonomous emergency braking systems

Objective This study quantifies the change in collision avoidance performance of autonomous emergency braking (AEB) systems for traffic accidents in Japan since 2015. Method This study used data on Japanese traffic accidents compiled by Japan’s National Police Agency. The data included only accidents involving loss of or injury to human life; accidents involving only property damage were excluded. We restricted our analysis to collisions between two 4-wheel vehicles and considered only collisions for which we could determine whether the primary party’s car was equipped with an AEB system. Both Poisson and negative binomial mixed-effects regression analyses were conducted using the data for 2021 and 2022 to measure the collision avoidance performance of first registered cars in 2015 to 2020 equipped with AEB systems compared with cars without AEB systems first registered in 2015. Collision avoidance performance was measured for 2 types of intervehicle collisions: rear-end collisions and right-turn collisions. Collision avoidance performance for rear-end collisions was also measured for each of the 3 car types—Standard, small, and light cars. Results The collision reduction rate for rear-end collisions increases with the year of first registration and for cars equipped with AEB systems first registered in 2020 compared with non-AEB-equipped cars first registered in 2015 is 69.2% (95% confidence interval [CI] 67.0%–71.1%), indicating that the performance of AEB systems has dramatically improved in terms of preventing rear-end collisions. For right-turn collisions, the rate increased to 20.4% (95% CI 5.9%–32.6%) for cars equipped with AEB systems first registered in 2019. However, no clear trend is observed. Conclusions This study evaluated a time series of the collision reduction performance of AEB systems using an original methodology. Japan’s New Car Assessment Program (JNCAP) has included AEB’s effectiveness in reducing damage from traffic collisions as an evaluation item since FY2014. The results could demonstrate the effectiveness of JNCAP.

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.

CSS for CVR: A Reciprocal Velocity Obstacle-Based Crowd Simulation System for Non-Playable Character Movement of Campus Virtual Reality

Along with the development of multimedia technology, an overview of the campus environment for prospective new visitors can be visualized through a 3D virtual environment based on virtual reality. A crowd simulation system is needed to provide an overview of the crowds in campus virtual reality (CVR). The simulation helps make it easier for individuals to predict crowds in certain areas virtually. In this study, we propose using the Reciprocal Velocity Obstacle (RVO) method to support the simulation of Non-Playable Character (NPC) crowds in a visualized virtual environment. RVO implements multi-agent navigation by estimating the possibility of moving without communication between agents and being able to perform collision avoidance. The use of RVO in this study aims to contribute to the collision detection development process for each NPC. The application of RVO is carried out in the development of virtual reality by using Unity3D and Blender asset support tools. The results of this study indicate that the RVO method can be applied in multi-agent navigation. These results were confirmed by the success of the NPC as a simulation agent in selecting routes and independently navigating to avoid collisions between agents without the need for communication. In every simulation, collisions will occur within a set of agents due to high density, which causes complex computations. The development of CSS can help every CVR user experience a virtual environment. In addition, each user can experience a more natural experience with the presence of 3D objects and virtual reality with RVO-based CSS. Furthermore, this research material is expected to be developed from various perspectives and themes related to crowd simulation for games and other simulation media.

Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety

The application of autonomous driving system (ADS) technology can significantly reduce potential accidents involving vulnerable road users (VRUs) due to driver error. This paper proposes a novel hierarchical deep reinforcement learning (DRL) framework for high-performance collision avoidance, which enables the automated driving agent to perform collision avoidance maneuvers while maintaining appropriate speeds and acceptable social distancing. The novelty of the DRL method proposed here is its ability to accommodate dynamic obstacle avoidance, which is necessary as pedestrians are moving dynamically in their interactions with nearby ADSs. This is an improvement over existing DRL frameworks that have only been developed and demonstrated for stationary obstacle avoidance problems. The hybrid A* path searching algorithm is first applied to calculate a pre-defined path marked by waypoints, and a low-level path-following controller is used under cases where no VRUs are detected. Upon detection of any VRUs, however, a high-level DRL collision avoidance controller is activated to prompt the vehicle to either decelerate or change its trajectory to prevent potential collisions. The CARLA simulator is used to train the proposed DRL collision avoidance controller, and virtual raw sensor data are utilized to enhance the realism of the simulations. The model-in-the-loop (MIL) methodology is utilized to assess the efficacy of the proposed DRL ADS routine. In comparison to the traditional DRL end-to-end approach, which combines high-level decision making with low-level control, the proposed hierarchical DRL agents demonstrate superior performance.

Relative navigation with Bayesian range estimation

The applications of multiple unmanned aerial vehicles (UAVs) require high-precision and reliable relative navigation for flight formation, collision avoidance, and mission performance. Providing high-precision relative navigation is possible by fusing the observations of inertial measurement units, global navigation satellite system receivers, and radio-ranging modules. However, radio-ranging is vulnerable to various types of interference, including additive noise, nonlinear propagation, and multi-user interference. At the same time, UAVs strict energy constraints force us to look for ways to increase interference immunity without increasing the transmitting power of radio-ranging modules. This work is about improving the noise immunity of relative navigation by using a scheme tightly coupled with radio ranging and Bayesian range estimation. We describe the proposed scheme and also carry out a comparative simulation of tightly coupled and conventional, loosely coupled schemes. According to the simulation, a tightly coupled scheme has a quarter smaller RMS error compared to a loosely coupled one at an SNR below -7 dB. The obtained results demonstrate the prospects for further development of the proposed scheme.

Synthetic Maritime Traffic Generation System for Performance Verification of Maritime Autonomous Surface Ships

With the global advancement of maritime autonomous surface ships (MASS), the critical task of verifying their key technologies, particularly in challenging conditions, becomes paramount. This study introduces a synthetic maritime traffic generation system (S-MTGS) designed for the efficient and safe verification of these technologies. The S-MTGS encompasses a maritime traffic generator integrating a generator based on absolute position (GAP) and a generator based on relative position (GRP). This innovative system leverages historical maritime data to create various scenarios or generate virtual ships based on their interactions with and proximity to other ships. The virtual ships adeptly navigate and perform collision avoidance maneuvers with nearby vessels enabled by the integrated collision avoidance algorithm. The S-MTGS’s ability to generate a wide range of maritime traffic information mirroring actual maritime conditions is pivotal for thoroughly verifying the performance of MASS technology under both standard and extreme situations. The development of the S-MTGS represents a significant advancement in maritime safety and technology. It can evaluate collision avoidance and navigation systems in MASS, featuring a virtual environment for realistic scenario testing and an intelligent navigation system focused on route tracking and collision avoidance.

Collision avoidance trajectory planning for a dual-robot system: using a modified APF method

AbstractDual-robot system has been widely applied to the field of handling and palletizing for its high efficiency and large workspace. It is one of the key problems of the trajectory planning to determine the collision avoidance method of the dual-robot system. In the present study, a collision avoidance trajectory planning method for the dual-robot system was proposed on the basis of a modified artificial potential field (APF) algorithm. The interference and collision criterion of the dual-robot system was given firstly, which was established based on the method of kinematic analysis in robotics. And then, in consideration of the problem of excessive virtual potential field force induced by using the traditional APF algorithm in the process of dual-robot trajectory planning, a modified APF algorithm was proposed. Finally, the modified APF algorithm was used for motion control of a dual-robot palletizing process, and the collision avoidance performance of the proposed collision avoidance algorithm was studied through a dual-robot palletizing simulation and experiment. The results have shown that with the proposed collision avoidance trajectory planning algorithm, the two robots in dual-robot system can maintain a safe distance at all times during palletizing process. Compared with the traditional APF and rapidly-exploring random tree (RRT) algorithm, the trajectory solution time of the modified APF algorithm is greatly reduced. And the modified APF algorithm’s convergence time is 14.2% shorter than that of the traditional APF algorithm.

Application of fuzzy reinforcement learning in IoT-based robotics for autonomous navigation and collision avoidance

In this study, we investigate the viability of applying fuzzy reinforcement learning (FRL) to Internet of Things-based robots for purposes of autonomous navigation and collision avoidance. The proposed approach utilises FRL, IoT, and a sensor network to give the robot the ability to learn from its environment and act in accordance with those policies. The authors used FRL to train a mobile robot with wheels to move around and avoid obstacles, and then they put the robot through its paces in a virtual world. Results showed that the FRL-based technique improved the robot’s navigation and collision avoidance performance compared to traditional rule-based approaches. The results of this study indicate that FRL may be a viable technique for enabling autonomous navigation and obstacle avoidance in IoT-based robotics.

Method for collision avoidance based on deep reinforcement learning with path-speed control for an autonomous ship

In this paper, we propose a collision avoidance method based on deep reinforcement learning (DRL) that simultaneously controls the path and speed of a ship. The DRL is actively applied in machine control and artificial intelligence. To verify the proposed method, we applied it to the Imazu problem. It provides benchmark scenarios for collision avoidance. In particular, we compared and analyzed the collision avoidance performance according to the level of learning and various parameters to ensure that the proposed method displays optimal avoidance performance. The results indicated that the proposed method can determine a safe avoidance path for a given situation. Finally, to compare the performance of the proposed method, we compared the collision avoidance method based on the path–speed control of the OS proposed in this study with the collision avoidance method that controls only the path of the OS (Chun et al., 2021). We observed that the proposed method failed in 6 out of 20 scenarios of the Imazu problem when only the path of the OS was controlled. However, it succeeded in collision avoidance in all the 20 scenarios when both path and speed were controlled simultaneously.

Deep reinforcement learning based collision avoidance system for autonomous ships

Autonomous ships is a key to avoid accidents caused by human errors and improve maritime safety. However, unlike the autonomous vehicles counterpart, collision avoidance for autonomous ships faces many challenges due to the hash driving environments, difficult ship control and large stopping distance. In this paper, we investigate a collision avoidance system for autonomous ships under complex encounter scenarios, such as busy ports. In the system various sensors are used to detect objects and perceive the maritime environments. To help the autonomous ships handle the complex and dynamic scenarios that may be encountered, a collision map used to describe the ships encounter scenarios is generated and utilized as the input of a deep reinforcement learning (DRL) model. The DRL model is applied to make collision avoidance and safe driving decisions. New reward functions are proposed to train the DRL model to generate safe ship maneuver actions to reduce collisions and ensure compliance with the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). Furthermore, a self-adaptive parameters sharing approach is designed for fast convergence and collision avoidance performance of the DRL model, where the parameters of the fully connected layers are shared and the correlation layers are self adapted for the DRL critic and actor networks. Simulation results show that the proposed system has high DRL convergence speed and excellent collision avoidance.

Formation Control for UAV-USVs Heterogeneous System with Collision Avoidance Performance

This paper investigates the cooperative formation trajectory tracking problem for heterogeneous unmanned aerial vehicle (UAV) and multiple unmanned surface vessel (USV) systems with collision avoidance performance. Firstly, a formation control protocol based on extended state observer (ESO) is proposed to ensure that the UAV and the USVs track the target trajectory simultaneously in the XY plane. Then, the collision avoidance control strategy of USV formation based on artificial potential field (APF) theory is designed. Specifically, the APF method is improved by reconstructing the repulsive potential field to make the collision avoidance action of USVs more in line with the requirements of International Regulations for Preventing Collisions at Sea (COLREGs). Following that, an altitude controller for the UAV is proposed to maintain the cooperative formation of the heterogeneous systems. Based on the input-to-state stability, the stability of the proposed control structure is proven, and all the signals in the closed-loop system are ultimately bounded. Finally, a simulation study is provided to show the efficacy of the proposed strategy.

Enhancing IoT Connectivity and Services for Worldwide Ships through Multi-Region Fog Cloud Architecture Platforms

As technologies such as eco-friendly ships, electric propulsion vessels, and multi-fuel propulsion systems advance, the scope of IoT applications in maritime fields is expanding, resulting in increased complexity in control factors. The gradual progression towards Maritime Autonomous Surface Ships (MASS) is further driving the evolution of ship-based IoT applications. These advancements underscore the necessity for a platform capable of ensuring reliable connectivity between ships and onshore. The limitations of the existing single cloud architecture become evident in this context. In response to these emerging challenges, this paper presents a cloud-based data platform structure anchored in the architecture of a multi-region fog cloud. Concurrently, we propose a strategic approach aimed at enhancing collision avoidance performance. This is achieved through the seamless sharing of navigation plan data among ships facilitated by the proposed platform structure. In regions densely populated with ships, there looms a potential for packet loss as data traffic sharing intensifies through the platform. To address this concern, we devised a traffic model based on the AIS data generation cycle and proposed an algorithm for subscription decision. Subsequently, we conducted comparative analyses of packet loss probabilities between the single cloud structure and the multi-region fog cloud structure. This was achieved through experimental packet loss data collected via the AWS cloud. Simulation results underscored a notable difference: with 100 subscribed ships, the packet loss probability in regions assuming a single cloud was about 28 times higher compared to the same region within the multi-region fog cloud structure. These simulations affirm the stable and effective implementation of the proposed collision avoidance performance enhancement method within the multi-region fog cloud structure. Furthermore, feasibility was corroborated through the successful implementation of the proposed platform via the AWS Cloud.

Supporting human supervision in autonomous collision avoidance through agent transparency

Ongoing trends in society point towards the adoption of intelligent agents across safety critical industries. In the maritime domain, artificially intelligent agents may soon be capable of autonomously performing collision and grounding avoidance (CAGA); a task traditionally performed by humans. Consequently, the role of humans is anticipated to change from those performing collision avoidance to those supervising an agent performing collision avoidance. One of the key concerns with regards to human factors is avoiding the out-of-the-loop performance problem where humans lose situation awareness (SA) and become susceptible to misinterpreting the agent’s decisions and planned actions. Despite previous research addressing human factors in autonomous shipping and remote control, few studies have focused on how to support the humans’ mental processes in this new role. Therefore, this study performed a goal-directed task analysis addressing goals, decisions, and SA requirements for human-supervised collision avoidance. Data was obtained from in situ observations and interviews with nine navigators onboard passenger ferries, an appraisal of the collision regulations, and of relevant company documentation. The task analysis identified specific SA requirements to make agents, capable of collision and grounding avoidance, transparent to their users. The results further indicate a change towards increased cognitive activities required to verify agent performance. Therefore, providing insight into the agents’ internal reasoning and actions becomes a key consideration in supporting future supervisors. Given the trends towards the application of artificially intelligent agents capable of autonomous behaviour, this study anticipates that transparency becomes an essential prerequisite for safe and effective human-autonomy system oversight.

A novel intelligent collision avoidance algorithm based on deep reinforcement learning approach for USV

Enhancing the efficiency of unmanned surface vehicles (USVs) collision avoidance can yield a significant impact, as it can result in safer navigation and lower energy consumption. This paper introduces a robust approach employing deep reinforcement learning theory to facilitate informed collision avoidance decisions within intricate maritime environments. The restrictions on USV maneuverability and international regulations for preventing collisions at sea are studied and quantified, particularly focusing on the shape and size changes of the ship’s domain caused by USV speed. Based on the deep Q network, an improved methodology is designed, incorporating a noisy network, prioritized experience replay, dueling neural network architecture, and double Q learning, resulting in a highly efficient sampling, exploration, and learning process. To curtail computational expenses associated with USVs, a novel dynamic area restriction technique is proposed. Furthermore, an innovative USV state clipping method is introduced to mitigate training complexities. By utilizing the Unity platform, a virtual environment characterized by complexity and stochasticity is constructed for training and testing the collision avoidance of USVs This novel approach surpasses the performance of the pre-improvement algorithm across multiple collision avoidance effectiveness indicators and performance metrics.

Generation of naturalistic and adversarial sailing environment (NASE) for intelligent test of autonomous ships

—Intelligence testing and verification of autonomous sailing capability is crucial to the development and deployment of autonomous ships. The prevailing approach is to establish a real test site on the sea or create a life-like simulator to test the autonomous sailing functions. However, due to the high dimensionality of the naturalistic sailing environment and the rareness of encounter events, hundreds of millions of miles and long test cycles would be required to demonstrate the collision avoidance performance of autonomous ships, which results in huge consumption. A novel approach is presented to generate the naturalistic and adversarial sailing environment by employing the sparse but adversarial adjustments into the naturalistic sailing environment. Our method can be used to enhance the existing sailing environment simulations to accelerate the autonomous ship test process. Firstly, the naturalistic probabilistic distributions of ship sailing behaviors are analyzed. Then, the naturalistic sailing environment (NSE) is generated to achieve real-world renderings. Moreover, the characteristics of ship maneuvering behavior at different encountered situations are identified. Furthermore, the naturalistic and adversarial sailing environment (NASE) is established by sampling maneuvers of the background ships (BS) from the importance functions at critical moments. It ensures the authenticity of the scenarios and increases the generation probability of encounter scenarios. The effectiveness of the proposed naturalistic and adversarial sailing environment model in the simulation of narrow waterway environment is proved. Compared with the naturalistic sailing environment, the proposed model can accelerate the generation speed of the critical scenarios and improve the generation efficiency of encounter scenarios.

Distributed Weighted Coverage for Multi-Robot Systems in Non-Convex Environment

Multi-robot coverage systems are widely used in operations such as environmental monitoring, disaster rescue, and pollution prevention. This study considers inherent positioning errors in positioning systems and ground mobile robots with limited communication distance and poor quality in practice. A centroidal Voronoi tessellation algorithm-based formation control technology for multi-robots is optimized. First, by constructing buffered Voronoi cells (BUVCs) for each robot, the collision avoidance ability of the multi-robot formation movement is improved. Next, the formation control problem of multi-robots in a limited communication range and non-convex environment is realized via discrete Voronoi partitioning, a communication distance constraint, and an obstacle avoidance strategy. Simulation and experiment results demonstrate that the proposed method can effectively solve the position generation problem of multi-robot coverage systems in a non-convex environment with actual sizes of the robots and positioning system errors and can further improve the collision avoidance performance of robots and the robustness of BUVC algorithms.

국제해상충돌예방규칙을 고려한 Event Triggered NMPC 기반의 선박 충돌 회피 알고리즘

About 75% of vessel collision accidents are caused by human error, which causes enormous economic loss, environmental pollution, and human casualties, thus research on automatic collision avoidance of vessels is being actively conducted. In addition, vessels must comply with the COLREGs rules stipulated by IMO when performing collision avoidance with other vessels in motion. In this study, the collision risk was calculated by estimating the position and velocity of other vessels through the Probabilistic Data Association Filter (PDAF) algorithm based on RADAR sensor data. When a collision risk is detected, we propose an event-triggered Nonlinear Model Predict Control (NMPC) algorithm that geometrically creates waypoints that satisfy COLREGs and follows them. To verify the proposed algorithm, simulations through MATLAB are performed.

Digital twin empowered cooperative trajectory planning of platoon vehicles for collision avoidance with unexpected obstacles

Road obstacles that unexpectedly appear such as vehicle breakdowns and accidents, are major causes of fatal road accidents. Connected Autonomous Vehicles (CAVs) can be used to avoid collisions to ensure road safety through cooperative sensing and driving. However, the collision avoidance performance of CAVs with unexpected obstacles has not been studied in the existing works. In this paper, we first design a platoon-based collision avoidance framework for CAVs. In this framework, we deploy a Digital Twin (DT) system at the head vehicle in a platoon to reduce communication overhead and decision-making delay based on a proposed trajectory planning scheme. In addition, an DT-assistant system is deployed on the assistant vehicle to monitor vehicles out of the sensing range of the head vehicle for the maintenance of the DT system. In this case, the transmission frequency of kinetic states of platoon members to ensure low-overhead communication. Moreover, we design a variable resource reservation interval that can ensure DT synchronization between DT and the assistant system with high reliability. To further improve road safety, an urgency level-based trajectory planning algorithm is proposed to avoid unexpected obstacles considering different levels of emergency risks. Simulation results show that our DT system-based scheme can achieve significant performance gains in unexpected obstacle avoidance. Compared to the existing schemes, it can reduce collisions by 95% and is faster by about 10% passing by the unexpected obstacle.

Deep reinforcement learning-based model-free path planning and collision avoidance for UAVs: A soft actor–critic with hindsight experience replay approach

In this paper, we propose a soft actor–critic (SAC) algorithm with hindsight experience replay (HER), called SACHER, which is a class of deep reinforcement learning (DRL) algorithm. SAC is an off-policy model-free DRL algorithm that outperforms earlier DRL algorithms in terms of exploration and robustness. However, in SAC, maximizing the entropy-augmented objective degrades the optimality of learning outcomes. We propose SACHER to improve the learning performance of SAC. We apply SACHER to the path planning and collision avoidance control of unmanned aerial vehicles (UAVs). We demonstrate the effectiveness of SACHER in terms of the success rate, learning speed, and collision avoidance performance of UAV operation.

Distributed dynamic matrix control with constrained optimization for collision and obstacle avoidance of simulated multiple quadcopters

AbstractA system of fast moving quadcopters has a high risk of collisions with neighboring quadcopters or obstacles. The objective of this work is to develop a control strategy for collision and obstacle avoidance of multiple quadcopters. In this paper, the problem of distributed dynamic matrix control (DMC) for collision avoidance among a team of multiple quadcopters attempting to reach consensus in the horizontal plane and yaw direction ( , and ) is investigated. Violations of a predetermined safety radius generates output constraints on the DMC optimization function, which has not been dealt with in the literature. Different from past works, the proposed strategy can perform collision avoidance in the , , and ‐directions. In addition, logarithmic barrier functions are implemented as input rate constraints on the control actions. Extensive simulation studies for a team of quadcopters illustrate promising results of the proposed control strategy and case variations. In addition, DMC parameter effects on the system performance are studied, and a successful study for obstacle avoidance is presented.