Deep reinforcement learning for drone delivery. This work is supported by NSF Award No.
Deep reinforcement learning for drone delivery. Apr 22, 2021 · Unmanned Aerial Vehicles (UAVs) are increasingly being used in many challenging and diversified applications. We advocate for a Deep Reinforcement Learning (DRL)-based guidance mechanism, utilising the Twin Delayed Deep Deterministic Policy Gradient algorithm. As sensors, the drone only has a stereo-vision front camera, from which depth information is obtained. Autonomous navigation of drones is a challenging problem that is yet to be fully solved. Sep 10, 2019 · In this work, reinforcement learning is studied for drone delivery. Jul 6, 2023 · Deep Reinforcement Learning for Truck-Drone Delivery Problem July 2023 Drones 7 (7):445 DOI: 10. Sep 5, 2024 · Recently, machine learning has been very useful in solving diverse tasks with drones, such as autonomous navigation, visual surveillance, communication, disaster management, and agriculture. The ongoing growth of e-commerce heightens the need for advanced UAV technologies to overcome urban logistics challenges, including navigation and package delivery. (2024) put forward an effective solution for the last-mile delivery with the machine learning approach. 2020 Deep drone racing and navigation are emerging applications of deep learning which may be used in competitions and potentially to automatize a multitude of tasks accomplished by drones. Researchers prefer to use supervised learning Oct 1, 2025 · This paper presents a comprehensive review of MARL-based truck–drone logistics, categorizing recent advancements in value-based, policy-based, and hybrid learning approaches, including Deep Q-learning, proximal policy optimization, and multi-agent deep deterministic policy gradient, and meta-reinforcement learning. DeliverSense: Eficient Delivery Drone Schedul-ing for Crowdsensing with Deep Reinforcement Learning. In this Feb 20, 2024 · This work proposes an approach that improves the performance of Deep Q-Networks on multi-agent delivery by drone problems by utilizing state decompositions for lowering the problem complexity To address this challenge, we propose a machine learning model that leverages public transportation vehicles as carriers to extend the range of drones, integrating Hybrid Pointer Networks (HPNs) and Deep Reinforcement Learning (DRL) to solve the complex routing problem. To address this problem, we present a reinforcement learning model using Double Deep-Q Network (DDQN) to handle both task scheduling with a dynamic number of drones and drone employment simultaneously. To name a few; infrastructure inspection, traffic patrolling, remote sensing, mapping, surveillance, rescuing humans and animals, environment monitoring, and Intelligence, Surveillance, Target Acquisition, and Mar 5, 2021 · With the freight delivery demands and shipping costs increasing rapidly, intelligent control of fleets to enable efficient and cost-conscious solutions becomes an important problem. Through testing multiple algorithms, we implemented a solution to the truck-drone delivery problem based on deep reinforcement learning. Sep 10, 2019 · The application of reinforcement learning to drones will provide them with more intelligence, eventually converting drones in fully-autonomous machines. 3390/drones7070445 License CC BY 4. In this work, reinforcement learning is studied for drone delivery. 2022. Mar 1, 2023 · Therefore, combining the drone and truck is a promising tandem to improve the efficiency of last-mile delivery. This survey investigates the convergence of deep learning (DL) and reinforcement learning (RL) for unmanned aerial vehicle (UAV) applications, particularly in autonomous last-mile delivery. For the truck–drone routing problem, deep reinforcement learning found an optimal routing among all constrained clusters. Sep 21, 2022 · DeliverSense: Efficient Delivery Drone Scheduling for Crowdsensing with Deep Reinforcement Learning Jun 1, 2025 · Routing heuristics determine route feasibility by vehicle or drone, and deep reinforcement learning is then used to determine if a vehicle or a drone should be dispatched. It proposes a structured taxonomy based on learning strategies, optimization Sep 10, 2019 · The application of reinforcement learning to drones will provide them with more intelligence, eventually converting drones in fully-autonomous machines. 0 In this study, we utilized the characteristics of deep reinforcement learning and the high generality offered by the Gym environment. Oct 3, 2025 · This study introduces an end-to-end Reinforcement Learning (RL) approach for controlling Unmanned Aerial Vehicles (UAVs) with slung loads, addressing both navigation and obstacle avoidance in real Jul 6, 2023 · In this study, reinforcement learning was used to solve a truck-drone combined logistics delivery problem, and the effectiveness of the results was enhanced by introducing different reinforcement learning algorithms for comparison. Nov 20, 2023 · To address this problem, we present a reinforcement learning model using Double Deep-Q Network (DDQN) to handle both task scheduling with a dynamic number of drones and drone employment simultaneously. Jan 1, 2025 · In summary, this study contributes to the field of same-day delivery by formulating a new problem with vehicles and drones, introducing a novel hierarchical decision approach based on deep reinforcement learning, and demonstrating effectiveness through extensive experiments. Indeed, UPS has started testing combining the drone and the truck to deliver goods (Business Insider, 2017). Dec 1, 2024 · Deep learning delivery sequences Yilmaz et al. Traditional navigation approaches frequently struggle to acclimatize to these complications. Tests used a very realistic simulator and a neighborhood scenario. This exploration paper investigates the operation of deep underpinning literacy(DRL) for enabling independent drone navigation in cluttered surroundings. These applications belong to the civilian and the military fields. Among these machine learning, two representative paradigms have been widely utilized in such applications: supervised learning and reinforcement learning. Nov 20, 2023 · This article proposes an architecture for drone navigation and target interception, utilizing a self-supervised, model-free deep reinforcement learning approach. To improve the efficiency of Mar 1, 2025 · In the truck-drone collaborative mode, as each truck performs the delivery services and serves as a mobile depot for the drone associated with it, the drone launches from its associated truck at a node, delivers relief resources to one affected area, and returns to rendezvous with the truck at the node or another node along the truck route. DL and RL offer promising methods for DeliverSense: Efficient Delivery Drone Scheduling for Crowdsensing with Deep Reinforcement Learning. In this paper, we apply the method Deep Deterministic Policy Gradient (DDPG) to train a neural network whose objective is to direct a simulated quadcopter towards a target, reproducing a simplified drone Nov 20, 2023 · In this paper, we propose a Same-Day Delivery with a Dynamic Number of Drones (SD4) problem. Dec 1, 2024 · Recently, there has been a growing trend to use deep reinforcement learning (DRL) to solve NP-hard combinatorial optimization problems such as routing problem, where a policy learned by a deep neural network guides the sequential construction of solutions. Computational results showed the efficiency of the improved heuristic in computational time and solution quality. To address this challenge, we propose a machine learning model that leverages public transportation vehicles as carriers to extend the range of drones, integrating Hybrid Pointer Networks (HPNs) and Deep Reinforcement Learning (DRL) to solve the complex routing problem. . Feb 27, 2025 · Abstract This paper proposes a holistic framework for autonomous guidance, navigation, and task distribution among multi-drone systems operating in Global Navigation Satellite System (GNSS)-denied indoor settings. Unlike the traditional methods relying on complex controllers, our approach uses deep reinforcement learning with cascade rewards, enabling a single drone to navigate obstacles and intercept targets using only a forward-facing depth Then, an improvement based on deep reinforcement learning (DRL) was proposed through learning a policy of selecting requests to remove and choose operators for the optimization of combined routes. This work is supported by NSF Award No. In Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp/ISWC '22 Adjunct), September 11–15, 2022, Cambridge, United Kingdom. Navigating drones in cluttered spaces poses significant challenges due to the presence of obstacles and dynamic environmental conditions. Jan 20, 2024 · To solve the truck–drone delivery problem in the multi-agent context, this research employs multi-agent deep reinforcement learning algorithms like Multi-Agent Proximal Policy Optimization (MAPPO) and Multi-Agent Deep Deterministic Policy Gradient (MADDPG). In this setting, a truck driver loads a package into the drone and sends the drone to an autonomous route to an address. 2146968. This work shows a successful application of deep reinforcement learning for autonomous drone delivery. In this paper, we propose DeepFreight, a model-free deep-reinforcement-learning-based algorithm for multi-transfer freight delivery, which includes two closely-collaborative components: truck-dispatch and package research-article Open access DeliverSense: Efficient Delivery Drone Scheduling for Crowdsensing with Deep Reinforcement Learning Authors: Xuecheng Chen Xuecheng Chen, Haoyang Wang, Zuxin Li, Wenbo Ding, Fan Dang, Chenye Wu, and Xinlei Chen. It requires the development of efficient algorithms for planning, control and intelligent decision-making against unexpected observations. jgqdny3c8sfaqczu3aznbg5fycvcilpebc9x0npcxoxguxpuq09igy