A Novel Augmentative Backward Reward Function with Deep Reinforcement Learning for Autonomous UAV Navigation

Unmanned aerial vehicle (UAV) technology is a rapidly growing field with tremendous opportunities for research and applications. To achieve true autonomy for UAVs in the absence of remote control, external navigation aids like global navigation satellite systems and radar systems, a minimum energy trajectory planning that considers obstacle avoidance and stability control will be the key. Although this can be formulated as a constrained optimization problem, due to the complicated non-linear relationships between UAV trajectory and thrust control, it is almost impossible to be solved analytically. While deep reinforcement learning is known for its ability to provide model free optimization for complex system through learning, its state space, actions and reward functions must be designed carefully. This paper presents our vision of different layers of autonomy in a UAV system, and our effort in generating and tracking the trajectory both using deep reinforcement learning (DRL). The experimental results show that compared to conventional approaches, the learned trajectory will need 20% less control thrust and 18% less time to reach the target. Furthermore, using the control policy learning by DRL, the UAV will achieve 58.14% less position error and 21.77% less system power.

This paper presents a novel deep reinforcement learning-based system for 3D mapless navigation for Unmanned Aerial Vehicles (UAVs). Instead of using an image-based sensing approach, we propose a simple learning system that uses only a few sparse range data from a distance sensor to train a learning agent. We based our approaches on two state-of-art double critics Deep-RL models: Twin Delayed Deep Deterministic Policy Gradient (TD3) and Soft Actor-Critic (SAC). We show that our two approaches manage to outperform an approach based on the Deep Deterministic Policy Gradient (DDPG) technique and the BUG2 algorithm. Also, our new Deep-RL structure based on Recurrent Neural Networks (RNNs) outperforms the current structure used to perform mapless navigation of mobile robots. Overall, we conclude that Deep-RL approaches based on double critic with Recurrent Neural Networks (RNNs) are better suited to perform mapless navigation and obstacle avoidance of UAVs.

Unmanned Aerial Vehicles (UAVs) have a major issue in autonomous navigation, particularly in dynamic or GPS-denied environments. Conventional rule-based or GPS-dependent strategies lack the flexibility and resilience to support real-time decision-making, especially in difficult terrain. We propose a novel deep learning-based framework, DeepFusion-NavNet, that couples reinforcement learning with semantic segmentation to perform end-to-end autonomous UAV navigation in an attempt to overcome these limitations. It employs a Deep Q-Network (DQN) to learn the optimal trajectory of the UAV based on policies learned once spatial features are extracted from aerial images by a U-Net-based semantic segmentation model. The proposed method was experimented with in both urban and forest environments utilizing the AirSim simulation tool. Relative to existing deep reinforcement learning baselines, experimental validation proves that DeepFusion-NavNet results in a navigation success rate of 97.5%, reduces collision incidents by 91.2%, and improves route efficiency by 22.8%. These results indicate that DeepFusion-NavNet significantly enhances UAV safety and autonomy under challenging operating conditions.

In this chapter, the regulation of an Unmanned Aerial Vehicle (UAV) communication network is investigated in the presence of dynamic changes in the UAV lineup and user distribution. We target an optimal UAV control policy which is capable of identifying the upcoming change in the UAV lineup (quit or join-in) or user distribution, and proactively relocating the UAVs ahead of the change rather than passively dispatching the UAVs after the change. Specifically, a deep reinforcement learning (DRL)-based UAV control framework is developed to maximize the accumulated user satisfaction (US) score for a given time horizon which is able to handle the change in both the UAV lineup and user distribution. The framework accommodates the changed dimension of the state-action space before and after the UAV lineup change by deliberate state transition design. In addition, to handle the continuous state and action space, deep deterministic policy gradient (DDPG) algorithm, which is an actor-critic based DRL method, is exploited. Furthermore, to promote learning exploration around the timing of the change, the original DDPG scheme is adapted into an asynchronous parallel computing (APC) structure which leads to better training performance in both the critic and actor networks. Finally, extensive simulations are conducted to validate the convergence of the proposed learning approach, and demonstrate its capability in jointly handling the dynamics in UAV lineup and user distribution as well as its superiority over a passive reaction method.KeywordsUnmanned aerial vehicle (UAV)UAV-based communication networksDeep reinforcement learningDynamic user spatial distributionUAV trajectory design

Energy-aware control for multiple unmanned aerial vehicles (UAVs) is one of the major research interests in UAV based networking. Yet few existing works have focused on how the network should react around the timing when the UAV lineup is changed. In this work, we study proactive self-remedy of energy-constrained UAV networks when one or more UAVs are short of energy and about to quit for charging. We target at an energy-aware optimal UAV control policy which proactively relocates the UAVs when any UAV is about to quit the network, rather than passively dispatches the remaining UAVs after the quit. Specifically, a deep reinforcement learning (DRL)-based self remedy approach, named SREC-DRL, is proposed to maximize the accumulated user satisfaction scores for a certain period within which at least one UAV will quit the network. To handle the continuous state and action space in the problem, the state-of-the-art algorithm of the actor-critic DRL, i.e., deep deterministic policy gradient (DDPG), is applied with better convergence stability. Numerical results demonstrate that compared with the passive reaction method, the proposed SREC-DRL approach shows a 12.12% gain in accumulative user satisfaction score during the remedy period.

With the ongoing advancement of electric power Internet of Things (IoT), traditional power inspection methods face challenges such as low efficiency and high risk. Unmanned aerial vehicles (UAVs) have emerged as a more efficient solution for inspecting power facilities due to their high maneuverability, excellent line-of-sight communication capabilities, and strong adaptability. However, UAVs typically grapple with limited computational power and energy resources, which constrain their effectiveness in handling computationally intensive and latency-sensitive inspection tasks. In response to this issue, we propose a UAV task offloading strategy based on deep reinforcement learning (DRL), which is designed for power inspection scenarios consisting of mobile edge computing (MEC) servers and multiple UAVs. Firstly, we propose an innovative UAV-Edge server collaborative computing architecture to fully exploit the mobility of UAVs and the high-performance computing capabilities of MEC servers. Secondly, we established a computational model concerning energy consumption and task processing latency in the UAV power inspection system, enhancing our understanding of the trade-offs involved in UAV offloading strategies. Finally, we formalize the task offloading problem as a multi-objective optimization issue and simultaneously model it as a Markov Decision Process (MDP). Subsequently, we proposed a task offloading algorithm based on a Deep Deterministic Policy Gradient (OTDDPG) to obtain the optimal task offloading strategy for UAVs. The simulation results demonstrated that this approach outperforms baseline methods with significant improvements in task processing latency and energy consumption.

Unmanned Aerial Vehicles (UAVs) based delivery is thriving. In this paper, we model autonomous navigation of UAV in large-scale unknown complex environment as a discrete-time continuous control problem and solve it using deep reinforcement learning. Without path planning or map construction, our method enables UAVs to navigate from arbitrary departure places to destinations using only sensory information of local environment and GPS signal. We argue the navigation task is a partially observable Markov decision process (POMDP) and extant recurrent deterministic policy gradient algorithm is less efficient. Consequently, we derive a faster policy learning algorithm for POMDP based on actor-critic architecture. To validate our ideas, we simulate five virtual environments and a virtual UAV flying at a fixed altitude with constant speed. Cognition of local environment is achieved by measuring distances from UAV to obstacles in multiple directions. Simulation results demonstrate the effectiveness of our method.

The path planning of Unmanned Aerial Vehicle (UAV) is a critical component of rescue operation. As impacted by the continuity of the task space and the high dynamics of the aircraft, conventional approaches cannot find the optimal control strategy. Accordingly, in this study, a deep reinforcement learning (DRL)-based UAV path planning method is proposed, enabling the UAV to complete the path planning in a 3D continuous environment. The deep deterministic policy gradient (DDPG) algorithm is employed to enable UAV to autonomously make decisions. Besides, to avoid obstacles, the concepts of connected area and threat function are proposed and adopted in the reward shaping. Lastly, an environment with static obstacles is built, and the agent is trained using the proposed method. As has been proved by the experiments, the proposed algorithm can fit a range of scenarios.

With the improvement in the intelligence level of UAVs and the development of cluster control technology, the intelligent decision-making method of UAV cluster confrontation will become the key technology of UAV combat in the future. The UAV cluster confrontation learning environment is of complex characteristics of high dimension, non-linearity, incomplete information, continuous action space, and so on. Recently, artificial intelligence technology represented by deep learning and reinforcement learning has made a great breakthrough. Deep reinforcement learning has shown a great ability to solve intelligent decision-making problems in complex environments. In this paper, enlightened by the multi-agent centralized training distributed execution framework and the idea of maximum policy entropy, we propose a deep reinforcement learning method of the multi-agent soft actor-critic (MASAC) with incomplete information. A game model for UAV cluster confrontation based on multi-agent deep reinforcement learning is established, and a continuous space multiple UAV combat environment is constructed. Simulation experiments are performed on the asymmetric confrontation of UAV clusters with red and blue teams. The experimental results show that MASAC outperforms the existing popular multi-agent deep reinforcement learning methods, making the game players converge to a higher return equilibrium point of the game. Moreover, the convergence of MASAC is investigated and analyzed extensively, and the results show that MASAC is of good convergence and stability, ensuring the practicability of MASAC in intelligent decision-making regarding UAV cluster confrontation.

Study on deep reinforcement learning techniques for building energy consumption forecasting

This paper discusses the algorithms of vision systems for automatic UAV (Unmanned Aerial Vehicle) landing. The basic algorithms for finding helipad and adapting the UAV control system to an autonomous UAV landing are presented. The authors consider algorithms to solve navigation problems, building block diagrams of automatic UAV control. Also, the developed algorithms make it possible to implement an automatic landing system for UAVs using technical vision systems, using various camera parameters, algorithms allowing research, as part of the autonomous navigation of unmanned aerial vehicles. The article discusses the developed algorithm that allows you to highlight certain characteristic points for visual navigation. Also, a search system for characteristic points has been developed that allows automatic UAV landing. These algorithms may be useful for the autonomous landing UAV systems. Algorithms can also be used to track a trajectory of the UAV system.

Path planning refers to that the mobile robot can obtain the surrounding environment information and its own state information through the sensor carried by itself, which can avoid obstacles and move towards the target point. Deep reinforcement learning consists of two parts: reinforcement learning and deep learning, mainly used to deal with perception and decision-making problems, has become an important research branch in the field of artificial intelligence. This paper first introduces the basic knowledge of deep learning and reinforcement learning. Then, the research status of deep reinforcement learning algorithm based on value function and strategy gradient in path planning is described, and the application research of deep reinforcement learning in computer game, video game and autonomous navigation is described. Finally, I made a brief summary and outlook on the algorithms and applications of deep reinforcement learning.

In recent years, unmanned aerial vehicles (UAVs) have been widely used in wireless communication, attracting intensive attentions. UAVs can not only serve as relays, but also serve as aerial base station for ground users (GUs). However, limited energy means that they cannot work for long and cover a limited area of services. In this paper, we investigate 2D UAV trajectory design and power allocation in order to maximize the UAV's service time and downlink throughput. Based on deep reinforcement learning, we propose a deep deterministic policy gradient (DDPG) algorithm for trajectory design and power allocation (TDPA) to solve the energy efficient and communication service quality problem. The simulation results show that TDPA can extend the service time of UAV, improve the communication service quality, and realize the maximization of downlink throughput, which are significantly improved compared with existing methods.

In this paper, we propose a novel deep reinforcement learning (DRL) method for optimal path planning for mobile robots using dynamic programming (DP)-based data collection. The proposed method can overcome the slow learning process and improve training data quality inherently in DRL algorithms. The main idea of our approach is as follows. First, we mapped the dynamic programming method to typical optimal path planning problems for mobile robots, and created a new efficient DP-based method to find an exact, analytical, optimal solution for the path planning problem. Then, we used high-quality training data gathered using the DP method for DRL, which greatly improves training data quality and learning efficiency. Next, we established a two-stage reinforcement learning method where, prior to the DRL, we employed extreme learning machines (ELM) to initialize the parameters of actor and critic neural networks to a near-optimal solution in order to significantly improve the learning performance. Finally, we illustrated our method using some typical path planning tasks. The experimental results show that our DRL method can converge much easier and faster than other methods. The resulting action neural network is able to successfully guide robots from any start position in the environment to the goal position while following the optimal path and avoiding collision with obstacles.

Learning ability is the basic characteristic of human intelligence. The July 1, 2005 issue of Science published a list of 125 important questions in science. Among them, the question 94 “What are the limits of learning by machines?”. The annotation “Computers can already beat the world’s best chess players, and they have a wealth of information on the Web to draw on. But abstract reasoning is still beyond any machine”. In recent artificial intelligence has made great progresses. In 1997, the rise of the man-machine war, IBM Supercomputer Deep Blue defeated the chess master Garry Kasparov. On February 14, 2011, IBM’s Watson supercomputer won a practice round against Jeopardy champions Ken Jennings and Brad Rutter. In March 2016, Google DeepMind’s AlphaGo sealed a 4-1 victory over a South Korean Go grandmaster Lee Se-dol. This paper focuses on the machine learning methods of AlphaGo, including reinforcement learning, deep learning, deep reinforcement learning, analysis of the existing problems and the latest research progress. Deep reinforcement learning is the combination of deep learning and reinforcement learning, which can realize the learning algorithm from the perception to action. Simply said, this is the same as human behavior, input sensing information such as vision, and then, direct output action through the deep neural network. Deep reinforcement learning has the potential to learn a variety of skills for the robot to achieve full autonomy. Even though reinforcement learning is practiced successfully, but feature states need to manually set, for complex scene is a difficult thing, especially easy to cause the dimension disaster, and expression is not good. In 2010, Sascha Lange and Martin Riedmiller proposed deep auto-encoder neural networks in reinforcement learning to extract feature, which is used to control the visual correlation. In 2013, DeepMind proposed deep Q-network (DQN) in NIPS 2013, using convolution neural network to extract features, and then applied in reinforcement learning. They continue to improve and published an improved version of DQN on Nature in 2015, which has aroused widespread concern. In order to break through the limits of learning by machines, cognitive machine learning is proposed, which is the combination of machine learning and brain cognition, so that the machine intelligence is constantly evolving, and gradually reaches the human level of artificial intelligence. A cognitive model entitled Consciousness And Memory (CAM) is proposed by author, which consists of memory, consciousness, high-level cognitive functions, perception and motor. High-level cognitive functions of the brain include learning, language, thinking, decision making, emotion, and so on. Learning is a course to accept the stimulus through the nervous system and obtain new behavior, habits and accumulation experience. According to the current research progress of brain science and cognitive science, cognitive machine learning may be interested in learning emergence, procedural memory knowledge learning, learning evolution and so on. For intelligence, so-called evolution is refers to the learning of learning and the structure also follows the change. It is important to record the learning result by structure changing and improve the learning method.