Artificial Intelligence guidance for Unmanned Aerial Vehicles in three dimensional space
01 Nov 2014-pp 1256-1261
TL;DR: This research proposes use of Artificial Intelligence for dynamic target tracking capability of an UAV and the AI guidance algorithm performance is compared against standard guidance algorithm like Proportional Navigation Guidance (PNG) algorithm.
Abstract: Unmanned Aerial Vehicle(UAV) are used in various applications like visual surveillance of natural resources, product delivery, armed attacks, disaster relief etc. This research proposes use of Artificial Intelligence (AI) for dynamic target tracking capability of an UAV. The AI guidance algorithm performance is compared against standard guidance algorithm like Proportional Navigation Guidance (PNG) algorithm.
Citations
More filters
TL;DR: The intelligent air combat learning system proposed in this paper is more flexible in situation assessment and in the prediction of opponents’ actions, and although it cannot be deployed quickly, it has a continuous learning ability.
Abstract: Unmanned aerial vehicles (UAVs) have played an important role in recent high-tech local wars. Seizing air control rights with UAVs will undoubtedly be a popular topic in future military development. Autonomous air combat is complex, antagonistic and mutable, and consequently, the decision-making that depends on unmanned systems is extremely challenging with very little research having been conducted on it. An intelligent air combat learning system inspired by the learning mechanisms of the brain is proposed in this paper. In accordance with research on learning, knowledge and memory, we constructed a cognitive mechanism model of the brain. Based on this model and the inferential abilities of humans, a long short-term hierarchical multi-line learning system is established. Then, the bio-inspired architecture and the basic learning principle of the system are clarified. Taking advantage of the conclusions of studies on information theory, the relationship between the knowledge updating cycle and the system learning performance is analysed. The updating cycle length adjustment problem is transformed into an optimization problem optimization problem, and system performance improvement is guaranteed. Experiments show that the system designed in this paper can acquire confrontation abilities through self-learning without prior rules; the parallel universe mechanism can significantly improve the system’s learning speed when the number of parallels is within 40, and the performance of the system improves gradually and continuously. The system can master actions similar to classical tactical manoeuvres such as the high yo-yo and the barrel-roll-attack without prior knowledge. Compared with the Bayesian inference and moving horizon optimization (BI&MHO) method, the learning system proposed in this paper is more flexible in situation assessment and in the prediction of opponents’ actions. Although it cannot be deployed quickly, it has a continuous learning ability.
14 citations
Cites methods from "Artificial Intelligence guidance fo..."
...[27], [28] developed a new guidance scheme using Q-learning....
[...]
TL;DR: A novel approach to the autonomous generation of trajectories for multiple aerial vehicles is presented, whereby an artificial kinematic field provides autonomous control in a distributed and highly scalable manner.
14 citations
TL;DR: In this article, the authors investigate the narrowband properties of the air-to-ground channel for 5G communications and beyond by means of GPU accelerated ray launching simulations, with a special focus on the extension of coverage and capacity of mobile radio networks.
Abstract: Unmanned Aerial Vehicles (UAV), also known as “drones”, are attracting increasing attention as enablers for many technical applications and services, and this trend is likely to continue in the next future. When compared to conventional terrestrial communications, those making use of UAVs as base- or relay-stations can definitely be more useful and flexible in reaction to specific events, like natural disasters and terrorist attacks. Among the many and different fields, UAV enabled communications emerge as one of the most promising solutions for next-generation mobile networks, with a special focus on the extension of coverage and capacity of mobile radio networks. Motivated by the air-to-ground (A2G) propagation conditions which are likely to be different than those experienced by traditional ground communication systems, this paper aims at investigating the narrowband properties of the air-to-ground channel for 5G communications and beyond by means of GPU accelerated ray launching simulations. Line of sight probability as well as path loss exponent and shadowing standard deviations are analysed for different UAV flight levels, frequencies and dense urban scenarios, and for different types of on board antennas. Thanks to the flexibility of the ray approach, the role played by the different electromagnetic interactions, namely reflection, diffraction and diffuse scattering, in the air-to-ground propagation process is also investigated. Computation time is reported as well to show that designing UAV communication networks and optimising their performances in a fast and reliable manner, might avoid exhausting – multiple - measurement campaigns.
6 citations
04 Jun 2020
TL;DR: A proposal referred to as the “Guard Masking” has been offered in the following paper, to provide an alternative for securing Artificial Intelligence.
Abstract: Artificial Intelligence also often referred to as machine learning is being labelled to as the future has been into light since more than a decade. Artificial Intelligence designated by the acronym AI has a vast scope of development and the developers have been working on with it constantly. AI is being associated with the existing objects in the world as well as with the ones that are about to arrive to improve them and make them more reliable. AI as it states in its name is intelligence, intelligence shown by the machines to work similar to humans and work on achieving the goals they are being provided with. Another application of AI could be to provide defenses against the present cyber threats, vehicle overrides etc. Also, AI might be intelligence but, in the end, it’s still a bunch of codes, hence it is prone to be corrupted or misused by the world. To prevent the misuse of the technologies, it is necessary to deploy them with a sustainable defensive system as well. Obviously, there is going to be a default defense system but it is prone to be corrupted by the hackers or malfunctioning of the intelligence in certain scenarios which can result disastrous especially in case of Robotics. A proposal referred to as the “Guard Masking” has been offered in the following paper, to provide an alternative for securing Artificial Intelligence.
1 citations
Cites background from "Artificial Intelligence guidance fo..."
...The new UAV’s are being encrypted by the Artificial Intelligence, so that they are able to access the new regions with more ease and work efficiently [6]....
[...]
24 Nov 2022
TL;DR: In this article , the authors focused on the analysis of the introduction of artificial intelligence in the control of unmanned aerial vehicles (UAVs) and provided a comparative analysis of scientific papers that are dealing with artificial intelligence for UAVs.
Abstract: Recently, the demand for unmanned aerial vehicles has been growing at an exponential rate and unmanned aerial vehicles are being used in many industries for many purposes. By adding artificial intelligence, the potential of these devices increases. Artificial intelligence itself can make operation of unmanned aircraft easier and more efficient, but it does not have only positive aspects. Artificial intelligence in drones requires more energy and also much more computing power. The paper is focused on the analysis of the introduction of artificial intelligence in the control of unmanned aerial vehicles. The paper contains comparative analysis of scientific papers that are dealing with artificial intelligence in the control of unmanned aerial vehicles.
References
More filters
Book•
01 Jan 2020TL;DR: In this article, the authors present a comprehensive introduction to the theory and practice of artificial intelligence for modern applications, including game playing, planning and acting, and reinforcement learning with neural networks.
Abstract: The long-anticipated revision of this #1 selling book offers the most comprehensive, state of the art introduction to the theory and practice of artificial intelligence for modern applications. Intelligent Agents. Solving Problems by Searching. Informed Search Methods. Game Playing. Agents that Reason Logically. First-order Logic. Building a Knowledge Base. Inference in First-Order Logic. Logical Reasoning Systems. Practical Planning. Planning and Acting. Uncertainty. Probabilistic Reasoning Systems. Making Simple Decisions. Making Complex Decisions. Learning from Observations. Learning with Neural Networks. Reinforcement Learning. Knowledge in Learning. Agents that Communicate. Practical Communication in English. Perception. Robotics. For computer professionals, linguists, and cognitive scientists interested in artificial intelligence.
16,983 citations
26 Dec 2007
TL;DR: In this article, a method of collision avoidance for point mass UAVs (own and intruder) with constant velocity is described in 3D, where en route aircraft are assumed to be linked by real-time data bases like ADS-B and can be considered as a constant velocity motion.
Abstract: A method of collision avoidance for point mass UAVs (own and intruder) with constant velocity is described in 3-D. This paper discusses en route aircraft which are assumed to be linked by real time data bases like ADS-B and can be considered as a constant velocity motion. The proposed approach uses probabilistic trajectory model supposed to have uncertain information so that possible trajectory deviations can be tackled in a series of Monte Carlo simulations. The simulations are used to estimate the probability of conflict in which own aircraft should operate resolution maneuvers. From the probability of conflict, 'Threat Level' is determined between two aircraft on conflict situation, then, the best one of some possible resolution maneuver candidates is chosen so that the effective resolution maneuver can be commanded. In this paper, several 'collision avoidance/guidance' examples are shown by simulation and the simulation results are discussed.
47 citations
TL;DR: It is observed that in the presence of line-of-sight rate delay, increasing the effective navigation constant of the PN guidance law deteriorates its performance.
Abstract: This brief discusses the convergence analysis of proportional navigation (PN) guidance law in the presence of delayed line-of-sight (LOS) rate information. The delay in the LOS rate is introduced by the missile guidance system that uses a low cost sensor to obtain LOS rate information by image processing techniques. A Lyapunov-like function is used to analyze the convergence of the delay differential equation (DDE) governing the evolution of the LOS rate. The time-to-go until which decreasing behaviour of the Lyapunov-like function can be guaranteed is obtained. Conditions on the delay for finite time convergence of the LOS rate are presented for the linearized engagement equation. It is observed that in the presence of line-of-sight rate delay, increasing the effective navigation constant of the PN guidance law deteriorates its performance. Numerical simulations are presented to validate the results.
23 citations
"Artificial Intelligence guidance fo..." refers methods in this paper
...The PNG scheme is a well used guidance scheme, used to guide an UAV to a maneuvering target....
[...]
27 Jun 2012
TL;DR: A modified ACBPNG (MACBPNG) where the required bias term is derived in a closed form considering non-linear equations of motion, which is capable of achieving a wide range of impact angles.
Abstract: Impact angle constrained guidance laws are important in many applications such as guidance of torpedoes, anti-ballistic missiles and reentry vehicles. In this paper, we design a guidance law which is capable of achieving a wide range of impact angles. Biased proportional navigation guidance uses a bias term in addition to the basic PN command to satisfy additional constraints. Angle constrained BPNG (ACBPNG) uses small angle approximations to derive the bias term for impact angle requirement. We design a modified ACBPNG (MACBPNG) where the required bias term is derived in a closed form considering non-linear equations of motion. Simulations are carried out for a wide range of impact angle requirements. We also analyze capturability from different initial positions and also the launch angles possible at each initial position. The performance of the proposed law is compared with an existing law.
19 citations
"Artificial Intelligence guidance fo..." refers methods in this paper
...The PNG scheme is a well used guidance scheme, used to guide an UAV to a maneuvering target....
[...]
TL;DR: In this paper, a 3D modified proportional navigation (PN)-based guidance law based on the total demand vector concept is presented, which can maintain the navigation constant to the designer-selected value for any 3D engagement scenario with associated lead angles and any velocity profile with missile longitudinal accelerations/decelerations.
Abstract: Different proportional navigation (PN)-based guidance laws-pure proportional navigation (PPN), true proportional navigation (TPN), and proportional navigation with boost acceleration compensation generally used cannot maintain fundamental parameter of proportional navigation, viz, Navigation constant to the desired value in the presence of significantly high lead angles and missile longitudinal accelerations/decelerations In a real-life situation with sensor noises and hardware constraints, this navigation constant should be maintained tightly at the selected value, which is generally between 3 and 4, for optimum performance In this paper; a new 3-D modified PN guidance law based on a total demand vector concept is presented, which can maintain the navigation constant to the designer-selected value for any 3-D engagement scenario with associated lead angles and any velocity profile with missile longitudinal accelerations1 decelerations Generality of this guidance law is brought out and superiority of this guidance law over the commonly used proportional navigation-based laws like PPN, TPN and PN with boost acceleration compensation has been demonstrated by applying it to the real-life 3-D engagement scenarios of different hypothetical missiles
8 citations
"Artificial Intelligence guidance fo..." refers methods in this paper
...The PNG scheme is a well used guidance scheme, used to guide an UAV to a maneuvering target....
[...]