Intelligent Unmanned Aerial Vehicle Research Articles

Algorithms for Route Planning and Navigation of Unmanned Aerial Vehicles

A brief overview of the results of recent research published in open sources in the field of route planning and navigation algorithms for unmanned aerial vehicles (UAV) is presented. Works devoted to global and local planning of trajectories taking into account known and detected obstacles in flight, as well as issues of navigation of groups of drones, are considered. Various approaches are analyzed, including graph algorithms (A*, Dijkstra, Rapidly-exploring Random Trees), methods of data mining in real time, potential fields. Special attention is paid to work on the use of neural networks and machine learning, SLAM and multi-agent technologies for planning UAV routes. The advantages and disadvantages of the main groups of algorithms are considered. A conclusion is drawn about the prospects for using hybrid methods, as well as machine learning technologies, to build intelligent UAV traffic control systems.

Systematic Research and Application of a 5G Medical Unmanned Aerial Vehicle to Deliver COVID-19 Nucleic Acid Samples.

The purpose of this study was to investigate the feasibility and effectiveness of COVID-19 throat swab samples delivered by medical drones in epidemic prevention and control. This study was carried out in both southern and northern hospital districts of the Affiliated Hospital of Jiangnan University from May to October 2022. The main participants were the Affiliated Hospital of Jiangnan University and Zhejiang Antwork Technology Co., Ltd. We first constructed an urban medical unmanned aerial vehicle (UAV) delivery system and developed a UAV-specific storage box for COVID-19 samples. The UAV system was used to transport COVID-19 throat swab samples from the northern hospital district to the southern hospital district, and the following indexes were obtained: (1) flight time of COVID-19 samples delivered by UAV, (2) real-time temperature of COVID-19 nucleic acid samples during transportation, and (3) the time of distribution of COVID-19 nucleic acid samples by road traffic as measured using the Baidu Maps application, compared with the flight time of UAV. The COVID-19 sample delivery system for urban medical UAV mainly consists of intelligent logistics UAV, low-temperature COVID-19 throat swab sample storage box, unmanned logistics hub, and cloud operation control platform. The flight distance between the northern and southern districts of the Affiliated Hospital of Jiangnan University was 10 km, and the ground distance was 24 km. From May 11 to October 28, 2022, a total of 1,190 UAV flights occurred. The average flight time was 13 minutes, which was 40 to 70 minutes faster than the average road travel time required for manual delivery of COVID-19 throat swab samples. At different time points in the day, UAV delivery efficiency increased by 67.5% to 82%. The use of 5G with the Internet of Things and UAV technology to deliver nucleic acid samples has the characteristics of fast speed, being unaffected by ground traffic conditions, and the ability to ensure the safety of nucleic acid samples in the transportation process, which is worthy of further study.

Trajectory Planning for UAV-Assisted Data Collection in IoT Network: A Double Deep Q Network Approach

Unmanned aerial vehicles (UAVs) are becoming increasingly valuable as a new type of mobile communication device and autonomous decision-making device in many application areas, including the Internet of Things (IoT). UAVs have advantages over other stationary devices in terms of high flexibility. However, a UAV, as a mobile device, still faces some challenges in optimizing its trajectory for data collection. Firstly, the high complexity of the movement action and state space of the UAV’s 3D trajectory is not negligible. Secondly, in unknown urban environments, a UAV must avoid obstacles accurately in order to ensure a safe flight. Furthermore, without a priori wireless channel characterization and ground device locations, a UAV must reliably and safely complete the data collection from the ground devices under the threat of unknown interference. All of these require the proposing of intelligent and automatic onboard trajectory optimization techniques. This paper transforms the trajectory optimization problem into a Markov decision process (MDP), and deep reinforcement learning (DRL) is applied to the data collection scenario. Specifically, the double deep Q-network (DDQN) algorithm is designed to address intelligent UAV trajectory planning that enables energy-efficient and safe data collection. Compared with the traditional algorithm, the DDQN algorithm is much better than the traditional Q-Learning algorithm, and the training time of the network is shorter than that of the deep Q-network (DQN) algorithm.

Multi-IRS-Assisted mmWave UAV-BS Network for Coverage Extension.

In the era of Industry 5.0, advanced technologies like artificial intelligence (AI), robotics, big data, and the Internet of Things (IoT) offer promising avenues for economic growth and solutions to societal challenges. Digital twin technology is important for real-time three-dimensional space reproduction in this transition, and unmanned aerial vehicles (UAVs) can support it. While recent studies have explored the potential applications of UAVs in nonterrestrial networks (NTNs), bandwidth limitations have restricted their utility. This paper addresses these constraints by integrating millimeter wave (mmWave) technology into UAV networks for high-definition video transmission. Specifically, we focus on coordinating intelligent reflective surfaces (IRSs) and UAV networks to extend coverage while maintaining virtual line-of-sight (LoS) conditions essential for mmWave communication. We present a novel approach for integrating IRS into Beyond 5G/6G networks to enhance high-speed communication coverage. Our proposed IRS selection method ensures optimal communication paths between UAVs and user equipment (UE). We perform numerical analysis in a realistically modeled 3D urban environment to validate our approach. Our results demonstrate significant improvements in the received SNR for multiple UEs upon the introduction of IRSs, and they confirm the feasibility of coverage extension in mmWave UAV networks.

An Angular Acceleration Based Looming Detector for Moving UAVs.

Visual perception equips unmanned aerial vehicles (UAVs) with increasingly comprehensive and instant environmental perception, rendering it a crucial technology in intelligent UAV obstacle avoidance. However, the rapid movements of UAVs cause significant changes in the field of view, affecting the algorithms' ability to extract the visual features of collisions accurately. As a result, algorithms suffer from a high rate of false alarms and a delay in warning time. During the study of visual field angle curves of different orders, it was found that the peak times of the curves of higher-order information on the angular size of looming objects are linearly related to the time to collision (TTC) and occur before collisions. This discovery implies that encoding higher-order information on the angular size could resolve the issue of response lag. Furthermore, the fact that the image of a looming object adjusts to meet several looming visual cues compared to the background interference implies that integrating various field-of-view characteristics will likely enhance the model's resistance to motion interference. Therefore, this paper presents a concise A-LGMD model for detecting looming objects. The model is based on image angular acceleration and addresses problems related to imprecise feature extraction and insufficient time series modeling to enhance the model's ability to rapidly and precisely detect looming objects during the rapid self-motion of UAVs. The model draws inspiration from the lobula giant movement detector (LGMD), which shows high sensitivity to acceleration information. In the proposed model, higher-order information on the angular size is abstracted by the network and fused with multiple visual field angle characteristics to promote the selective response to looming objects. Experiments carried out on synthetic and real-world datasets reveal that the model can efficiently detect the angular acceleration of an image, filter out insignificant background motion, and provide early warnings. These findings indicate that the model could have significant potential in embedded collision detection systems of micro or small UAVs.

Federated Deep Reinforcement Learning-Based Intelligent Dynamic Services in UAV-Assisted MEC

Unmanned Aerial Vehicles (UAVs)-assisted Multi-access Edge Computing (MEC) has emerged as a promising solution in B5G/6G networks. The high flexibility and seamless connectivity of UAVs make them well-suited for providing enhanced communications coverage and efficient computing support. Particularly in situations where ground facilities may be compromised or communication is unreliable. In this paper, we study joint dynamic service switching and resource allocation for multiple UAVs in MEC network. We consider the heterogeneity of tasks and UAVs and model the dynamic service process of UAVs as a sequential decision problem based on the Markovian decision process. To enable dynamic and intelligent UAV service, we first propose a centralized dynamic service algorithm DDBC based on deep reinforcement learning. However, given the training difficulties of the centralized algorithm, we propose a more promising distributed learning algorithm FLBF, which combines federated learning. We conduct extensive simulations to evaluate the effectiveness and advantages of the proposed algorithms. Our results show that both DDBC and FLBF can improve the model convergence speed by 50%, and reduce the system cost by 12.30% to 35.72% compared to comparative algorithms. Furthermore, simulations indicate that FLBF is well-suited for training models in UAV-assisted MEC networks.

Intelligent UAV planning for task-offloading with limited buffer and multiple computing servers

Dynamically moving Unmanned Aerial Vehicles (UAVs) have emerged as an effective means to significantly enhance the flexibility and transmission performance of mobile edge computing (MEC). However, in practical scenarios, UAVs often face limitations in terms of data storage capacity and computational power. In this paper, a UAV-enabled MEC network with multiple users and multiple edge computing servers is proposed, where the UAV is equipped with limited-size buffers. An optimization problem is formulated to jointly optimize UAV flight trajectories, offload server pairings, task offload ratios, and UAV transmit power to minimize transmission delay, computation delay, and system energy consumption. To tackle the intractable non-convex optimization issue, an intelligent optimization algorithm based on Deep Dueling Double Q-Network (D3QN)-Twin Delayed Deep Deterministic Policy Gradient (TD3) is proposed, which is able to efficiently determine the optimal solution. Simulation results demonstrate that our proposed intelligent algorithm exhibits good convergence and achieves a favorable balance between delay and energy consumption.

Representation Enhancement-Based Proximal Policy Optimization for UAV Path Planning and Obstacle Avoidance

Path planning and obstacle avoidance are pivotal for intelligent unmanned aerial vehicle (UAV) systems in various domains, such as postdisaster rescue, target detection, and wildlife conservation. Currently, reinforcement learning (RL) has become increasingly popular in UAV decision-making. However, the RL approaches confront the challenges of partial observation and large state space when searching for random targets through continuous actions. This paper proposes a representation enhancement-based proximal policy optimization (RE-PPO) framework to address these issues. The representation enhancement (RE) module consists of observation memory improvement (OMI) and dynamic relative position-attitude reshaping (DRPAR). OMI reduces collision under partially observable conditions by separately extracting perception features and state features through an embedding network and feeding the extracted features to a gated recurrent unit (GRU) to enhance observation memory. DRPAR compresses the state space when modeling continuous actions by transforming movement trajectories of different episodes from an absolute coordinate system into different local coordinate systems to utilize similarity. In addition, three step-wise reward functions are formulated to avoid sparsity and facilitate model convergence. We evaluate the proposed method in three 3D scenarios to demonstrate its effectiveness. Compared to other methods, our method achieves a faster convergence during training and demonstrates a higher success rate and a lower rate of timeout and collision during inference. Our method can significantly enhance the autonomy and intelligence of UAV systems under partially observable conditions and provide a reasonable solution for UAV decision-making under uncertainties.

A Niche Adaptive Elite Evolutionary Algorithm for the Clustering Optimization of Intelligent Unmanned Agricultural Unmanned Aerial Vehicle Swarm Collaboration Networks

Nowadays, the intelligent unmanned agricultural unmanned aerial vehicle (UAV) swarm collaboration network (AUSCN) has fully demonstrated its advantages in agricultural monitoring and management. By using an AUSCN, multi-machine cooperation can be realized to expand the detection range, and more complex tasks can be completed without human participation, so as to improve work efficiency and reduce the consumption of manpower and material resources. In AUSCNs, clustering is a key method to lower energy consumption. However, there is a challenge to select cluster heads in AUSCNs because of the limitation of transmission distances and the complexity of network topological structures. In addition, this problem has been confirmed as NP-hard. In this paper, a new niche adaptive elite evolutionary algorithm (NAEEA) is proposed to solve this problem. NAEEAs can search within various complicated stochastic situations at high speeds with characterized high precision and fast convergence. This algorithm integrates the merits of elite selection and adaptive adjusting to achieve high performance. In NAEEAs, a new adaptive operator is designed to speed up the convergence rate, while a novel elite operator is proposed to avoid local optima and raise the exploration ability. Furthermore, a new niche operator is also proposed to increase the population diversity. The simulation results show that, compared with an evolutionary algorithm (EA), a simulated annealing algorithm (SA) and a leapfrog algorithm (SFLA), clustering energy consumption based on an NAEEA is significantly reduced, and the network energy consumption of the AUSCN is up to 21.43%, 25.00% and 25.76% lower than the other three algorithms, respectively.

Research on logistics of intelligent unmanned aerial vehicle integration system

As Unmanned Aerial Vehicle (UAV) is more and more frequently used in farming and logistics, civil and military alike, researches involving UAVs also starts to boom. In the civil field, UAV is generally flown in urban areas, so buildings are the main factors hindering the normal flight of UAV. Therefore, it is necessary to calculate an optimal flight path of UAV under constraints. The intelligent logistics UAV proposed in this paper can be used to replace special couriers to deliver small goods. It is a quadcopter integrated with a webcam, ultrasound Ground Proximity Warning System (GPWS), and is controllable through a mobile APP. Gradient descent algorithm, Linear Quadratic Regulator (LQR) and improved Proportion-Integral-Derivative (PID) controllers are applied in its flight control system, MATLAB and wavelet transform to handle fuzzy image. In addition, ant colony algorithm and adaptive strategies are used in the path planning process. As a result, it can detect surrounding obstacles in-flight, and the ground control station can receive feedback information and prepare for emergency operations.

Research on obstacle avoidance path planning of UAV in complex environments based on improved Bézier curve

Obstacle avoidance path planning is considered an essential requirement for unmanned aerial vehicle (UAV) to reach its designated mission area and perform its tasks. This study established a motion model and obstacle threat model for UAVs, and defined the cost coefficients for evading and crossing threat areas. To solve the problem of obstacle avoidance path planning with full coverage of threats, the cost coefficients were incorporated into the objective optimization function and solved by a combination of Sequential Quadratic Programming and Nonlinear Programming Solver. The problem of path planning under threat full coverage with no solution was resolved by improving the Bézier curve algorithm. By introducing the dynamic threat velocity obstacle model and calculating the relative and absolute collision cones, a path planning algorithm under multiple dynamic threats was proposed to solve the difficulties of dynamic obstacle prediction and avoidance. Simulation results revealed that the proposed Through-out method was more effective in handling full threat coverage and dynamic threats than traditional path planning methods namely, Detour or Cross Gaps. Our study offers valuable insights into autonomous path planning for UAVs that operate under complex threat conditions. This work is anticipated to contribute to the future development of more advanced and intelligent UAV systems.

An Intelligent UAV Path-Planning Method Based on the Theory of the Three-Dimensional Subdivision of Earth Space

With the rapid development of the big data era, Unmanned Aerial Vehicles (UAVs) are being increasingly adopted for various complex environments. This has imposed new requirements for UAV path planning. How to efficiently organize, manage, and express all kinds of data in complex scenes and intelligently carry out fast and efficient path planning for UAVs are new challenges brought about by UAV application requirements. However, traditional path-planning methods lack the ability to effectively integrate and organize multivariate data in dynamic and complicated airspace environments. To address these challenges, this paper leverages the theory of the three-dimensional subdivision of earth space and proposes a novel environment-modeling approach based on airspace grids. In this approach, we carried out the grid-based modeling and storage of the UAV flight airspace environment and built a stable and intelligent deep-reinforcement-learning grid model to solve the problem of the passage cost of UAV path planning in the real world. Finally, we designed multiple sets of experiments to verify the efficiency of the global subdivision coding system as an environmental organization framework for path planning compared to a longitude–latitude system and to demonstrate the superiority of the improved deep-reinforcement-learning model in specific scenarios.

Differentiated Attention Guided Network Over Hierarchical and Aggregated Features for Intelligent UAV Surveillance

Intelligent unmanned aerial vehicle (UAV) surveillance based on infrared imaging has wide applications in the antiUAV system for protecting urban security and aerial safety. However, weak target features and complex background distraction pose great challenges for the accurate detection of UAVs. To address this issue, we propose a novel differentiated attention guided network to adaptively strengthen the discriminative features between UAV targets and complex background. First, a novel spatial-aware channel attention (SCA) is introduced into deep layers via preserving critical spatial features and leveraging channel interdependencies to focus on the large-scale targets. The channel-modulated deformable spatial attention is introduced into shallow layers via refining channel context and dynamically perceiving the spatial features for focusing on the small-scale targets. A combination of the above two attention mechanisms is employed in intermediate layers of the network for concentrating on the medium-scale targets. Then, we embed a feature aggregator at the detection branches to guide the information exchange of high-level feature maps and low-level feature maps with a bottom-up context modulation, and integrate an SCA at the end to further boost the distinctive feature representation for task-awareness. The above design can adaptively enhance multiscale UAV target features and suppress complex background interferences, leading to better detection performance, especially for small targets. Extensive experiments on real infrared UAV datasets reveal that the proposed method outperforms the baseline object detectors by a large margin, validating its feasibility in real-world infrared UAV detection. The source code can be found at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/KALEIDOSCOPEIP/DAGNet</uri> .

Joint Trajectory Planning, Application Placement, and Energy Renewal for UAV-Assisted MEC: A Triple-Learner-Based Approach

In this paper, an energy efficient scheduling problem for multiple unmanned aerial vehicle (UAV) assisted mobile edge computing (MEC) is studied. In the considered model, UAVs act as mobile edge servers to provide computing services to end-users with task offloading requests. Unlike existing works, we allow UAVs to determine not only their trajectories but also the decisions of whether returning to the depot for replenishing energies and updating application placements (due to their limited batteries and storage capacities). With the aim of maximizing the long-term energy efficiency of all UAVs, i.e., the total amount of offloaded tasks computed by all UAVs over their total energy consumption, a joint optimization of UAVs’ trajectory planning, energy renewal and application placement is formulated. Taking into account the underlying cooperation and competition among intelligent UAVs, we reformulate such optimization problem as three coupled multi-agent stochastic games. Since the prior environment information is unavailable to UAVs, we propose a novel triple learner based reinforcement learning (TLRL) approach, integrating a trajectory learner, an energy learner and an application learner, for reaching equilibriums. Moreover, we analyze the convergence and the complexity of the proposed solution. Simulations are conducted to evaluate the performance of the proposed TLRL approach, and demonstrate its superiority over counterparts.

An apollonius circle based game theory and Q-learning for cooperative hunting in unmanned aerial vehicle cluster

Cooperative hunting has attracted great research interests with both pursuer and evader behavior strategies. Existing approaches typically utilize computing power to improve the accuracy of hunting. However, these methods ignore the real-time characteristic of unmanned aerial vehicle (UAV) cluster and timeliness of hunting process, directly using them into UAV cluster application would lose efficacy. To solve the problem of cooperative hunting of UAV cluster (pursuers) for one intelligent UAV (evader), we propose an apollonius circle based game theory and Q-learning for cooperative hunting (ACGQ-CH). Specifically, it constructs the behavior strategies and payment matrix of the pursuers and the evader by using game theory and apollonius circle. Then, a state-action matrix is built and a dynamically adjusting the greedy factor is designed based on Q-learning algorithm and reward mean, respectively. Finally, it derives Nash equilibrium solution by solving the state-action matrix, and guides the pursuers to achieve cooperative hunting. The simulation results demonstrate our approach reduces the number of learning steps by 50.8% compared to traditional Q-learning and reduces the hunting time by 16.83, 27.35 and 12.56% respectively compared to baseline methods.

QEHLR: A Q-Learning Empowered Highly Dynamic and Latency-Aware Routing Algorithm for Flying Ad-Hoc Networks

With the growing utilization of intelligent unmanned aerial vehicle (UAV) clusters in both military and civilian domains, the routing protocol of flying ad-hoc networks (FANETs) has promised a crucial role in facilitating cluster communication. However, the highly dynamic nature of the network topology, owing to the rapid movement and changing direction of aircraft nodes, as well as frequent accesses and exits from the network, has resulted in an increased interruption rate of FANETs links. While traditional protocols can satisfy basic network service quality (QoS) requirements in mobile ad-hoc networks (MANETs) with relatively fixed topology changes, they may fail to achieve optimal routes and consequently restrict information dissemination in FANETs with topology changes, which ultimately leads to elevated packet loss and delay. This paper undertakes an in-depth investigation of the challenges faced by current routing protocols in high dynamic topology scenarios, such as delay and packet loss. It proposes a Q-learning empowered highly dynamic, and latency-aware routing algorithm for flying ad-hoc networks (QEHLR). Traditional routing algorithms are unable to effectively route packets in highly dynamic FANETs; hence, this paper employs a Q-learning method to learn the link status in the network and effectively select routes through Q-values to avoid connection loss. Additionally, the remaining time of the link or path lifespan is incorporated into the routing protocol to construct the routing table. QEHLR can delete predicted failed links based on network status, thereby reducing packet loss caused by failed route selection. Simulations show that the enhanced algorithm significantly improves the packet transmission rate, which addresses the challenge of routing protocols’ inability to adapt to various mobility scenarios in FANETs with dynamic topology by introducing a calculation factor based on the QEHLR protocol. The experimental results indicate that the improved routing algorithm achieves superior network performance.

When Hierarchical Federated Learning Meets Stochastic Game: Toward an Intelligent UAV Charging in Urban Prosumers

Unmanned aerial vehicles (UAVs) nowadays are developing rapidly for various applications such as UAV taxis and delivery drones. However, the limited battery energy restricts the flight distance of the UAVs. Thus, urban prosumers equipped with drone recharge stations are introduced to provide charging services for the UAVs. In this article, firstly, a day-ahead energy scheduling problem for UAV charging-enabled urban prosumers is studied, where the objective is to maximize the overall energy satisfaction of the prosumers with ensuring the quality of service (QoS) of the charged UAVs. Specifically, to deal with the considered problem, we decompose it into two stages: 1) day-ahead energy requirement data prediction stage, and 2) energy scheduling stage per prosumer. Thus, secondly, a joint method based on hierarchical federated learning (HFL) on long short-term memory (LSTM) architecture (HFL-LSTM) and stochastic game-based multi-agent double deep Q-learning (MADDQN) with community agent-independent approach is proposed. In particular, the HFL-LSTM approach is leveraged to forecast each prosumer’s energy requirement data without centralized collecting local prosumers’ data such that to protect data privacy. Then, the stochastic game is adopted to analyze the formulated problem, aiming to find the Nash equilibrium strategy. Afterward, MADDQN with a community agent-independent method is utilized to achieve the best energy scheduling strategy per prosumer. Finally, the experimental results demonstrate the superiority of the proposed joint method that can achieve the lowest mean squared error with the value of 0.0152 and the highest energy satisfaction (36388) achieved by the Nash equilibrium policy compared with the benchmarks.

Communication and Control in Collaborative UAVs: Recent Advances and Future Trends

The recent progress in unmanned aerial vehicles (UAV) technology has significantly advanced UAV-based applications for military, civil, and commercial domains. Nevertheless, the challenges of establishing high-speed communication links, flexible control strategies, and developing efficient collaborative decision-making algorithms for a swarm of UAVs limit their autonomy, robustness, and reliability. Thus, a growing focus has been witnessed on collaborative communication to allow a swarm of UAVs to coordinate and communicate autonomously for the cooperative completion of tasks in a short time with improved efficiency and reliability. This work presents a comprehensive review of collaborative communication in a multi-UAV system. We thoroughly discuss the characteristics of intelligent UAVs and their communication and control requirements for autonomous collaboration and coordination. Moreover, we review various UAV collaboration tasks, summarize the applications of UAV swarm networks for dense urban environments and present the use case scenarios to highlight the current developments of UAV-based applications in various domains. Finally, we identify several exciting future research direction that needs attention for advancing the research in collaborative UAVs.

SiamPRA: An Effective Network for UAV Visual Tracking

The visual navigation system is an important module in intelligent unmanned aerial vehicle (UAV) systems as it helps to guide them autonomously by tracking visual targets. In recent years, tracking algorithms based on Siamese networks have demonstrated outstanding performance. However, their application to UAV systems has been challenging due to the limited resources available in such systems.This paper proposes a simple and efficient tracking network called the Siamese Pruned ResNet Attention (SiamPRA) network and applied to embedded platforms that can be deployed on UAVs. SiamPRA is base on the SiamFC network and incorporates ResNet-24 as its backbone. It also utilizes the spatial-channel attention mechanism, thereby achieving higher accuracy while reducing the number of computations. Further, sparse training and pruning are used to reduce the size of the model while maintaining high precision. Experimental results on the challenging benchmarks VOT2018, UAV123 and OTB100 show that SiamPRA has a higher accuracy and lower complexity than other tracking networks.

Unmanned aerial vehicle visual scene understanding based on multitask learning network

With the continuous development of intelligent unmanned aerial vehicles reconnaissance, single-object detection or semantic segmentation can no longer meet the diversified requirements, while simple model stacking will cause the model to be too complex, which will seriously affect the real-time running effect. We propose a visual scene understanding algorithm based on a multitask learning network with an encoder–decoder structure. First, the efficient classification network VoVNet is selected as the feature-sharing network to obtain multiscale coding features. Second, based on the one-stage anchor-free object detector, the feature screening supplementary module implements feature interaction with segmented characters to enhance the detection capability of potential targets. Then for semantic segmentation and depth estimation pixel-level classification tasks, a cascaded chained residual pooling module is used as a parameter-sharing decoder, through the parameter-sharing mechanism to reduce the repeated decoding process to ensure the running speed. Finally, to improve the generalization ability of the model, a general-purpose dataset was constructed and network training was carried out based on the idea of knowledge distillation. Experiments on the dataset show that the performance of the multitask learning network can reach the mainstream algorithm level in semantic segmentation and depth estimation branches, whereas the object detection branch is better in multitarget recall rate, and the average time of each subtask is 39 ms, which meets the requirements of real-time performance and proves the effectiveness of the multitask network.