Showing papers on "Collision avoidance system published in 2022"

Collision-Avoidance Decision System for Inland Ships Based on Velocity Obstacle Algorithms

Abstract: Due to the complex hydrology and narrow channels of inland rivers, ship collision accidents occur frequently. The traditional collision-avoidance algorithms are often aimed at sea areas, and not often at inland rivers. To solve the problem of inland-ship collision avoidance, this paper proposes an inland-ship collision-avoidance decision system based on the velocity obstacle algorithm. The system is designed to assist ships in achieving independent collision-avoidance operations under the limitation of maneuverability while meeting inland-ship collision-avoidance regulations. First, the paper improves the Maneuvering Modeling Group (MMG) model suitable for inland rivers. Then, it improves velocity obstacle algorithms based on the dynamic ship domain, which can deal with different obstacles and three encounter situations (head-on, crossing, and overtaking situations). In addition, this paper proposes a method to deal with close-quarters situations. Finally, the simulation environment built by MATLAB software is used to simulate the collision avoidance of inland ships against different obstacles under different situations with a decision-making time of less than 0.1 s. Through the analysis of the simulation results, the effectiveness and practicability of the system are verified, which can provide reasonable collision-avoidance decisions for inland ships.

A Concept of Autonomous Multi-Agent Navigation System for Unmanned Surface Vessels

Abstract: The paper introduces a proposal of an Autonomous Navigation System for Unmanned Surface Vessels. The system architecture is presented with a special emphasis on collision avoidance and maneuver auto-negotiation. For the purpose of maneuver auto-negotiation, the concept of multi-agent systems has been applied. The algorithm developed for the task of collision avoidance is briefly described and the results of the simulation tests, confirming the effectiveness of applied method, are also given. Presented outcomes include solutions of test scenarios from the perspectives of different ships taking part in the considered situations, confirming the applicability of the collision avoidance algorithm in the process of maneuver auto-negotiation.

A Fast Markov Decision Process-Based Algorithm for Collision Avoidance in Urban Air Mobility

Abstract: Multiple aircraft collision avoidance is a challenging problem due to a stochastic environment and uncertainty in the intent of other aircraft. Traditionally a layered approach to collision avoidance has been employed using a centralized air traffic control system, established rules of the road, separation assurance, and last minute pairwise collision avoidance. With the advent of Urban Air Mobility (air taxis), the expected increase in traffic density in urban environments, short time scales, and small distances between aircraft favor decentralized decision making on-board the aircraft. In this paper, we present a Markov Decision Process (MDP) based method, named FastMDP, which can solve a certain subclass of MDPs quickly, and demonstrate using the algorithm online to safely maintain separation and avoid collisions with multiple aircraft (1-on-n) while remaining computationally efficient. We compare the FastMDP algorithm’s performance against two online collision avoidance algorithms that have been shown to be both efficient and scale to large numbers of aircraft: Optimal Reciprocal Collision Avoidance (ORCA) and Monte Carlo Tree Search (MCTS). Our simulation results show that under the assumption that aircraft do not have perfect knowledge of other aircraft intent FastMDP outperforms ORCA and MCTS in collision avoidance behavior in terms of loss of separation and near mid-air collisions while being more computationally efficient. We further show that in our simulation FastMDP behaves nearly as well as MCTS with perfect knowledge of other aircraft intent. Our results show that FastMDP is a promising algorithm for collision avoidance that is also computationally efficient.

Towards Safe Deep Reinforcement Learning for Autonomous Airborne Collision Avoidance Systems

Abstract: In this paper we consider the application of Safe Deep Reinforcement Learning in the context of a trustworthy autonomous Airborne Collision Avoidance System. A simple 2D airspace model is defined, in which a hypothetical air vehicle attempts to fly to a given waypoint while autonomously avoiding Near Mid-Air collisions (NMACs) with non-cooperative traffic. We use Proximal Policy Optimisation for our learning agent, and we propose a reward engineering approach based on a combination of sparse terminal rewards at natural termination points and dense step rewards providing the agent with continuous feedback on its actions, based on relative geometry and motion attributes of its trajectory with respect to the traffic and the target waypoint. The performance of our trained agent is evaluated through Monte-Carlo simulations, and it is demonstrated that it achieves to master the collision avoidance task with respect to safety for a reasonable trade-off in mission performance.

Vehicle Detection and Collision Avoidance System

Abstract: Over past few decades in India, there is drastic increase in vehicle usage for conveyance. Increasement in vehicle usage for transportation routes to traffic congestion and frequent road accidents. Usually not following traffic rules and road abnormalities are the few reasons for accidents. Vehicles encounter into collision due to error done by the drivers and accident occurs due to bad weather related situations. Irrespective of lot of current improvements in technological inventions available for vehicle safety, increase in accidents occurs every day. Hence, a suitable method for vehicle collision detection and avoidance is essential. So, this literature survey impacts the study on various approaches available towards and need for vehicle collision detection and collision avoidance system.

Vehicle-Related Distance Estimation Using Customized YOLOv7

Abstract: AbstractWith the popularity of autonomous driving, the development of ADAS (Advanced Driver Assistance Systems), especially collision avoidance systems, has become an important branch in the field of deep learning. In the face of complex traffic environments, collision avoidance systems need to detect vehicles quickly and accurately in traffic distance to the vehicle in front. Against this background, in this paper, we aim at investigating how to build a fast and robust model for vehicle distance estimation. The theoretical insights are synthesized in the context of odometry and customized YOLOv7 based on what a conceptual framework is proposed. In this paper, KITTI is employed as the dataset for model training and testing. Being one of the pioneer works on distance estimation based on KITTI, the unique value of this research work lies in the first time using YOLOv7 with attention model as a distance estimation model and getting 4.253 on RMSE.KeywordAutonoumous vehicles YOLOv7Vehicle detection Distance estimation Scene understanding

Collision Avoidance in Vehicles Using Ultrasonic Sensor

Abstract: This paper presents the design of collision avoidance in heavy vehicles by using ultrasonic sensors. This project is about vehicle collision avoidance system for vehicles such as cars and trucks, and in particular, this research work utilizes the ultrasonic sensor. Further, the proposed research work utilizes the application of electronic systems embedded in automobile, which is mainly used to save the lives of people and reduce injuries when the accident occurs, and mainly, it reduces or avoids the vehicle accident disaster. This project concentrates on developing a vehicle collision avoidance system model of the rear-end vehicles that contain an LCD display, which will recognize the length between two vehicles that are moving in the same lane, same direction, and when anyone is in danger, a microcontroller will alert the driver. Sensing of object ahead and distance measurement is done by using an ultrasonic sensor.

Collision Risk and Operational Impact of Speed Change Advisories as Aircraft Collision Avoidance Maneuvers

Abstract: Aircraft collision avoidance systems have long been a key factor in keeping our airspace safe. Over the past decade, the FAA has supported the development of a new family of collision avoidance systems called the Airborne Collision Avoidance System X (ACAS X), which model the collision avoidance problem as a Markov decision process (MDP). Variants of ACAS X have been created for both manned (ACAS Xa) and unmanned aircraft (ACAS Xu and ACAS sXu). The variants primarily differ in the types of collision avoidance maneuvers they issue. For example, ACAS Xa issues vertical collision avoidance advisories, while ACAS Xu and ACAS sXu allow for horizontal advisories due to reduced aircraft performance capabilities. Currently, a new variant of ACAS X, called ACAS Xr, is being developed to provide collision avoidance capability to rotorcraft and Advanced Air Mobility (AAM) vehicles. Due to the desire to minimize deviation from the prescribed flight path of these aircraft, speed adjustments have been proposed as a potential collision avoidance maneuver for aircraft using ACAS Xr. In this work, we investigate the effect of speed change advisories on the safety and operational efficiency of collision avoidance systems. We develop an MDP-based collision avoidance logic that issues speed advisories and compare its performance to that of horizontal and vertical logics through Monte Carlo simulation on existing airspace encounter models. Our results show that while speed advisories are able to reduce collision risk, they are neither as safe nor as efficient as their horizontal and vertical counterparts.

Prototype Collision-Avoidance System for Small Multirotor Unmanned Aircraft at Low Altitude

Abstract: The increasing number and type of unmanned aircraft system (UAS) operations provide a clear need for safe and efficient integration of UAS into the National Airspace System. The main obstacle in integration is the lack of certified collision avoidance solutions. Traffic Alert and Collision Avoidance System II has limitations to meet the requirements for UASs and has shown to lack the adaptability to future operational environments. The Airborne Collision Avoidance System X (ACAS X) has been developed to address these issues and increase surveillance, alerting, and resolution performance. This research investigates and assesses the performance of a prototype collision avoidance algorithm for low-level application tailored to the unique dynamic capabilities of multirotor small UASs (SUASs) based on the ACAS X framework. These unique capabilities of SUAS platforms allow them to hover, laterally deviate from the flight path, and use speed commands to resolve a conflict with potentially limited maneuvering space. The algorithm supports resolutions for both the horizontal and vertical domains. This paper describes the development and functioning of the prototype system, and it provides insight into the possible tailoring to specific operational and safety requirements for multirotor SUASs.

Application of Echolocation Signal Processing for Collision Avoidance of a Remote Controlled Reconnaissance System

Abstract: Low visibility in disaster sites hinders rescuers from successful rescue operations without casualties. A remote-controlled reconnaissance system is proposed in this research. Compared to traditional surveying of the area, UAVs are easier to use and can quickly survey the area by having an aerial view. The reconnaissance system was designed using Arduino Mega and UNO modules and achieved a collision-avoidance system. Four (4) ultrasonic sensors were used for the four directions: north, south, east, and west, all calibrated with an average error percentage of 1.75%. The data from the ultrasonic sensors will go straight through the drone’s remote control, which will automatically evade the drone when it encounters a collision. Results have shown that the collision avoidance system is applicable in low-visibility rescue operations.

Real-Time Drone Anti-Collision Avoidance Systems: an Edge Artificial Intelligence Application

Abstract: Collision Avoidance (CA) is one of the most challenging and fundamental problems in the Unmanned Aerial Vehicle (UAV) ecosystem. The unmanned version of Airborne Collisions Avoidance Systems (ACAS-Xu) detects collision threats and informs pilots of avoidance maneuvers to perform. It makes decisions based on an optimized cost tables. However, these tables are too large and heavy (~5GB) to be integrated on the current certified avionic hardware. In this paper, we present a machine learning (ML) based approach to reduce the memory footprint of the cost tables by approximating them using a deep neural network (DNN). Training results show that the proposed approach reduces the memory footprint drastically by a factor of 500 from 5GB to 10MB while maintaining the same level of safety. Additionally, we embedded the DNN based approach on an edge artificial intelligence (AI) device and demonstrated its ability to operate on limited hardware with low processing time.

Effectiveness of the Autonomous Braking and Evasive Steering System OPREVU-AES in Real World Vehicle-to-pedestrian collisions

Abstract: Among the possible improvements of Autonomous Emergency Braking (AEB) systems, reducing the intensity of the automatic braking process by studying the kinematics and general behavior of the pedestrian while crossing is crucial to determine the progressiveness of the braking, or replacing part of the braking process by an evasive maneuver when a collision is imminent. This paper proposes the integration of an autonomous avoidance system (Automatic Emergency Steering, AES) that acts directly on the steering system to generate an evasive maneuver and avoid a possible pedestrian collision (OPREVU-AES system), as well as the assessment of its effectiveness compared to a commercial AEB system. OPREVU and VULNEUREA are research projects in which INSIA and CEDINT have cooperated to improve driving assistance systems and the safety of pedestrians and cyclists through Virtual Reality (VR) techniques. The analysis of the kinematic and dynamic response of the OPREVU-AES system is conducted in CarSim© software. The effectiveness evaluation procedure is based on the reconstruction of a sample of road vehicle-to-pedestrian crashes (INSIA-UPM database), using the PCCrash® software, and taking as an indicator the probability of head injury severity (ISP). The results show that the AEB system would have prevented part of the collisions, especially after the incorporation of the OPREVU-AES system. In most of the cases where avoidance is not possible, a significant reduction of the ISP is achieved.

Pedestrian – Vehicle Collision Avoidance Support System for Many Pedestrians

Abstract: We have been studying a pedestrian-vehicle collision avoidance support system (P-VCASS) using wireless communications. However, the conventional system can only support up to three pedestrians, and it does not work when the number of pedestrians changes. In this paper, we propose a system to solve the above problem. The effectiveness of the proposed system is demonstrated through experiments and simulations that are modeled for actual road conditions.

Performance Evaluation of Collision Avoidance in Last Slot Algorithm for IEEE 802.11 DCF

Abstract: This paper presents the collision avoidance algorithms to enhance the IEEE 802.11 DCF performance and the previously proposed algorithm, the reducing wasted slots at the end of each frame (REF) algorithm. From the results, it was found that when the collision avoidance in the last slot algorithm is applied to the IEEE 802.11 DCF and the REF algorithms, it can improve the performance of both algorithms. We also found that the $\text{REF} + \text{CAS}$ algorithm performs best in all traffic load conditions. In addition, the number of slots per frame must be cautiously selected in order to optimize the system performance.

Roadkill Avoidance System Using YOLOv5

Abstract: Roadkills due to collisions have been on the rise lately, and many endangered animal species are on the affected radar. Traditional animal-vehicle collision avoidance systems use object detection for detecting animals, but often these systems fail due to innumerous reasons, one of them being lack of training on appropriate data. In this paper, we identify and overcome the failure spot of most animal detection systems to present a fast, efficient, and reliable animal-vehicle collision avoidance framework. It is based on a custom collected dataset containing preprocessed, augmented, and annotated images belonging to 20 categories of animals most frequently encountered on roads. Further, the model is trained over the YOLOv5 deep learning architecture that gives a detection processing speed of 140 fps and renders an exceptional mAP of 91.27%.

Intelligent Control of a Driverless Energy Vehicle Based on an Environment Sensing Sensor

Abstract: In order to solve the complex environment in the process of vehicle driving and the complexity of self-vehicle structure, intelligent vehicles are prone to rear end collision, lateral collision, and other safety accidents in the presence of tall trees, mountains, and other road environments, endangering the safety of people on board. According to parameters such as the speed of the vehicle, the movement of the blind spot, and the relationship between the vehicle and the blind spot, the model is based on the safety mode of the preceding vehicle. Based on the static obstacles that may exist in the sensing blind area, a sensor sensing blind area safety distance model is established. Based on the possible dynamic obstacles, the active collision avoidance algorithm based on the sensor perceived blind area is studied and simulated. The experimental results show that the selected sensor sensing blind area active collision avoidance controller can well adapt to a variety of special and emergency working conditions, can accurately complete the accurate control of sensor sensing blind area active collision avoidance, and avoid collision accidents to the greatest extent. Compared with the control group, the system designed in this paper can avoid more than 80% of the collision scenes compared with the previous anticollision system. It provides a reference for the future research of sensor sensing blind area-related topics and sensor sensing blind area active collision avoidance system. To a certain extent, it can improve the ability of intelligent vehicle environmental perception and reduce the incidence of rear end collision accidents.

Reward Function Optimization of a Deep Reinforcement Learning Collision Avoidance System

Abstract: The proliferation of unmanned aircraft systems (UAS) has caused airspace regulation authorities to examine the interoperability of these aircraft with collision avoidance systems initially designed for large transport category aircraft. Limitations in the currently mandated TCAS led the Federal Aviation Administration to commission the development of a new solution, the Airborne Collision Avoidance System X (ACAS X), designed to enable a collision avoidance capability for multiple aircraft platforms, including UAS. While prior research explored using deep reinforcement learning algorithms (DRL) for collision avoidance, DRL did not perform as well as existing solutions. This work explores the benefits of using a DRL collision avoidance system whose parameters are tuned using a surrogate optimizer. We show the use of a surrogate optimizer leads to DRL approach that can increase safety and operational viability and support future capability development for UAS collision avoidance.

Design of multi-AGV intelligent collision avoidance system based on dynamic priority strategy

Abstract: With the development of industrial automation, there are urgent requirements for adaptive multi-AGV intelligent collision avoidance in logistics warehousing. In this paper, an intelligent collision avoidance method of AGV system based on dynamic priority strategy is proposed, which uses the A* algorithm for initial optimal path planning, uses the positioning navigation method combining inertial navigation and visual navigation algorithm, uses visual sensors to identify AGVs and obstacles, and adjusts the speed and distance between AGVs and AGV and obstacles in time according to the priority size to achieve intelligent collision avoidance. The numerical analysis of the data results is carried out through simulation experiments, and the results show that this method can achieve intelligent collision avoidance, which initially verifies the feasibility of system design.

Collision Risk and Operational Impact of Speed Change Advisories as Aircraft Collision Avoidance Maneuvers

Abstract: Aircraft collision avoidance systems have long been a key factor in keeping our airspace safe. Over the past decade, the FAA has supported the development of a new family of collision avoidance systems called the Airborne Collision Avoidance System X (ACAS X), which model the collision avoidance problem as a Markov decision process (MDP). Variants of ACAS X have been created for both manned (ACAS Xa) and unmanned aircraft (ACAS Xu and ACAS sXu). The variants primarily differ in the types of collision avoidance maneuvers they issue. For example, ACAS Xa issues vertical collision avoidance advisories, while ACAS Xu and ACAS sXu allow for horizontal advisories due to reduced aircraft performance capabilities. Currently, a new variant of ACAS X, called ACAS Xr, is being developed to provide collision avoidance capability to rotorcraft and Advanced Air Mobility (AAM) vehicles. Due to the desire to minimize deviation from the prescribed flight path of these aircraft, speed adjustments have been proposed as a potential collision avoidance maneuver for aircraft using ACAS Xr. In this work, we investigate the effect of speed change advisories on the safety and operational efficiency of collision avoidance systems. We develop an MDP-based collision avoidance logic that issues speed advisories and compare its performance to that of horizontal and vertical logics through Monte Carlo simulation on existing airspace encounter models. Our results show that while speed advisories are able to reduce collision risk, they are neither as safe nor as efficient as their horizontal and vertical counterparts.

A Practical Method for Assessing Collision Avoidance Strategies Based on Marine Simulator

Abstract: To ensure collision avoidance strategy can be used onboard, it's vital to make a thorough assessment on it. In this paper, an assessment method is proposed to evaluate the compliance of collision avoidance strategies in case of two ships in sight of one another at open sea. Based on the International Regulations for Collision Avoidance at Sea, the quantification formulates of metrics, such as safety indexes and different rule clauses, etc., are firstly obtained. After that, the compliance of ship avoidance strategies in different avoidance stages are determined by ship's behaviors on typical encounter situations according to the quantification formulates. Finally, simulation tests of proposed method are carried out with a full mission marine simulator. The score of the assessed collision avoidance strategies in a typical encounter situation is calculated. Test results show that the assessment results of the present method are consistent with the practical performance of the ship's collision avoidance strategy on typical encounter situations, which verifies the effectiveness of the proposed method.