Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The unmanned aerial vehicle (UAV) swarm is regarded as having a significant role in modern warfare. The demand for UAV swarms with the capability of attack-defense confrontation is urgent. The existing decision-making methods of UAV swarm confrontation, such as multi-agent reinforcement learning (MARL), suffer from an exponential increase in traini...
Contexts in source publication
Context 1
... this paper, the attack-defense confrontation problem can be formulated as follows: As Figure 1 shows, it is assumed that our base has detected an enemy UAV approaching. To protect our base, k UAVs are launched to intercept the enemy UAV. ...
Context 3
... As shown in Figure 10, similar to the harassment of the wolf pack, our UAVs induce the enemy UAV to move in a certain direction by constantly alternating between attack and retreat. In the process, our UAVs shrink the size of the encirclement, eventually achieving the capture of the enemy UAV. ...
Context 4
... As shown in Figure 10, similar to the harassment of the wolf pack, our UAVs induce the enemy UAV to move in a certain direction by constantly alternating between attack and retreat. In the process, our UAVs shrink the size of the encirclement, eventually achieving the capture of the enemy UAV. ...
Context 5
... As shown in Figure 11, our UAVs take separation actions to prevent collisions between each other. ...
Context 6
... As shown in Figure 11, our UAVs take separation actions lisions between each other. The control input of the i-th UAV can be calculated as follows: ...
Context 7
... As shown in Figure 13, our UAVs take action to approach each other and facilitate mutual support. The control input of the i-th UAV can be calculated as follows: ...
Context 8
... θ i represents the angle between the line connecting the i-th UAV and the enemy and the line connecting its counter-clockwise neighboring UAV and the enemy, as shown in Figure 14, σ represents the standard deviation of the angles. ...
Context 9
... experiment environment is built using Unity's ML-Agents Toolkit. As shown in Figure 15, the training environment is 100 m long and 100 m wide. The circle on the left represents our base. ...
Context 10
... experiment environment is built using Unity's ML-Agents Toolkit. As shown in Figure 15, the training environment is 100 m long and 100 m wide. The circle on the left represents our base. ...
Context 11
... training parameters of MARL are listed in Table 2. As Figure 16 shows, 12 UAVs are divided into 3 groups, and the environment is 175 m long and 100 m wide. ...
Context 12
... Figure 16 shows, 12 UAVs are divided into 3 groups, and the environment is 175 m long and 100 m wide. ...
Context 13
... original action space contains five actions: up, down, left, right, and void. The curves of the success rates are shown in Figure 17, and the final success rates after 45,000 episodes of training are listed in Table 3. ...
Context 14
... original action space contains five actions: up, down, left, right, and void. The curves of the success rates are shown in Figure 17, and the final success rates after 45,000 episodes of training are listed in Table 3. Figure 17. The curve of success rate per 100 episodes in the training process. ...
Context 15
... the strategy of the attack group is obtained, the success rate of the attack group against enemies with different maximum accelerations is evaluated. The results are shown in Figure 18 and Table 4. Table 3. Final success rates after 45,000 episodes of training. ...
Context 16
... the strategy of the attack group is obtained, the success rate of the against enemies with different maximum accelerations is evaluated. The resul in Figure 18 and Table 4. The strategy is applied to a swarm of 12 UAVs, and the success rate against enemies with different maximum accelerations is obtained. ...
Similar publications
Cross-axis sensitivity is generally undesirable, and lower values are required for the accurate performance of a thermal accelerometer. In this study, errors in devices are utilized to simultaneously measure two physical quantities of an unmanned aerial vehicle (UAV) in the X-, Y-, and Z-directions, i.e., where three accelerations and three rotatio...
Citations
... In [207], distributed decision-making algorithm for UAVs tracking multiple targets based on information fusion strategy and consensus protocol. In [208], a bio-inspired decisionmaking algorithm is proposed for attack defense confrontation purposes. ...
Due to their potential to accomplish complicated missions more effectively, UAV swarms have attracted a lot of attention lately. UAV swarm offers enhanced intelligence, improved coordination, increased flexibility, survivability, and reconfigurability. It is a multi-disciplinary system that necessitates a tight integration of several sub-systems, including optimal trajectory planning, localization, task coordination, etc. This review covers the important aspects of UAV swarms including swarm formation control, communication, swarm path planning, autonomy, coordination, and security. It additionally explores recent technical advancements in UAV swarm algorithms that have made the development of complex UAV swarm systems possible. This paper also provides insight into ethical aspects and the use cases of UAV swarms in various military, civilian, and entertainment applications. This paper is concluded by highlighting the potential future directions and challenges of UAV swarm technology and the need for more research and development to exploit their potential fully. Overall, this paper presents a comprehensive review of UAV swarm technology, addressing its potential for revolutionizing many fields and supporting advancements in the future.
... The NavMesh navigation system [40] is adopted in this paper, which calculates v t and ω t for the tank according to the navigation path. Similar to [8,26,27,37,[41][42][43], in this paper, it is assumed that the information of the confrontation is complete, i.e., that the tanks can access Tanks attack opponents by firing shells, and a tank will be destroyed once it is hit by a shell. The range of the shell is set to be d f ire = 1200 m, and the shell reloading time is set to be t rld = 5 s. ...
This paper considers the confrontation problem for two tank swarms of equal size and capability in a complex urban scenario. Based on the Unity platform (2022.3.20f1c1), the confrontation scenario is constructed featuring multiple crossing roads. Through the analysis of a substantial amount of biological data and wildlife videos regarding animal behavioral strategies during confrontations for hunting or food competition, two strategies are been utilized to design a novel bio-inspired intelligent swarm confrontation algorithm. The first one is the “fire concentration” strategy, which assigns a target for each tank in a way that the isolated opponent will be preferentially attacked with concentrated firepower. The second one is the “back and forth maneuver” strategy, which makes the tank tactically retreat after firing in order to avoid being hit when the shell is reloading. Two state-of-the-art swarm confrontation algorithms, namely the reinforcement learning algorithm and the assign nearest algorithm, are chosen as the opponents for the bio-inspired swarm confrontation algorithm proposed in this paper. Data of comprehensive confrontation tests show that the bio-inspired swarm confrontation algorithm has significant advantages over its opponents from the aspects of both win rate and efficiency. Moreover, we discuss how vital algorithm parameters would influence the performance indices.
... Article [40] proposes the use of LiDAR as a means for obstacle recognition and physical space intrusion detection. A model proposed by authors in [41] takes inspiration from shoal formations in the real world, such as bees and fish, to demonstrate a cooperative hunting strategy for a swarm. Such techniques can be used to both hunt targets, evade enemy agents, and address multiple swarm components and modules. ...
... Area coverage [45] Agent security (physical) [40, 42,44] Path planning, collision avoidance [40,43] Agent property (heterogeneity) [44,45,47] Resource allocation/task reassignment [44,45] Formation control [41,46] Network security [50] This technique can also be scaled and applied to swarm systems to track cooperative swarm agents for collision avoidance and external dynamic and static obstacle avoidance. A similar technique using visual sensing has been used in [43] to detect cooperative UAVs in swarms. ...
The number of real-world scenarios where the use of an unmanned aerial vehicle (UAV) swarm is beneficial has greatly increased in recent years. From precision agriculture to forest fire monitoring, post-disaster search and rescue applications, to military use, the applications are widespread. While it is a perceived requirement that all UAV swarms be inherently resilient, in reality, it is often not so. The incorporation of resilient mechanisms depends on an application usage scenario. This study examines a comprehensive range of application scenarios for UAV swarms to bring forward the multitude of components that work together to provide a measure of resilience to the overall swarm. A three-category scheme is used to classify swarm applications. While systemic resilience is an interconnected concept, most real-world applications of UAV swarm research focus on making certain components resilient to disturbances. A broad categorization of UAV swarm applications, categorized by recognized components and modules, is presented, and prevalent approaches for novel resilience mechanisms in each category are discussed.
