Haoze Zhuo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haoze Zhuo has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Zhong Yang
Nanjing University of Aeronautics and Astronautics
10 shared publications - Luwei Liao
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
8 shared publications - Chi Zhang
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
4 shared publications - Nuo Xu
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
4 shared publications - Jiying Wu
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
3 shared publications - Naifeng He
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
3 shared publications
Latest Publications
- Open Access
Risk-Aware Adaptive Safety Margins for Model Predictive Control with Orientation–Motion Coupled Barrier Functions in Dynamic Environments
Safe navigation in dynamic environments remains challenging because classical distance-based constraints ignore the coupling between a robot’s translational motion and attitude dynamics, and fixed safety margins are either over-conservative or risky under varying uncertainty and approach speed. This paper presents a Risk-Aware Model Predictive Control (RA-MPC) framework that addresses both limitations through two integrated components. First, we introduce Orientation–Motion Coupled Control Barrier Functions (O-MCBFs) that enforce unified safety constraints linking collision avoidance with attitude stability limits, preventing dangerous pose configurations during dynamic obstacle avoidance. Second, we develop Risk-Aware Adaptive Margins (RAAMs) that compute time-varying safety buffers based on relative velocity, robot braking capability, and prediction uncertainty, enabling context-dependent safety–efficiency trade-offs without manual parameter tuning. The proposed method integrates these components into a quadratic programming formulation within MPC, ensuring real-time computational tractability. Experimental results demonstrate higher success rates, smoother trajectories, and improved progress toward the goal, with no observed safety violations under the tested conditions. These findings indicate that coupling pose-space safety with risk-adaptive margins provides a principled and practical path to safe and efficient navigation in dynamic scenes.
Open AccessRisk-Aware Adaptive Safety Margins for Model Predictive Control with Orientation–Motion Coupled Barrier Functions in Dynamic Environments
Safe navigation in dynamic environments remains challenging because classical distance-based constraints ignore the coupling between a robot’s translational motion and attitude dynamics, and fixed safety margins are either over-conservative or risky under varying uncertainty and approach speed. This paper presents a Risk-Aware Model Predictive Control (RA-MPC) framework that addresses both limitations through two integrated components. First, we introduce Orientation–Motion Coupled Control Barrier Functions (O-MCBFs) that enforce unified safety constraints linking collision avoidance with attitude stability limits, preventing dangerous pose configurations during dynamic obstacle avoidance. Second, we develop Risk-Aware Adaptive Margins (RAAMs) that compute time-varying safety buffers based on relative velocity, robot braking capability, and prediction uncertainty, enabling context-dependent safety–efficiency trade-offs without manual parameter tuning. The proposed method integrates these components into a quadratic programming formulation within MPC, ensuring real-time computational tractability. Experimental results demonstrate higher success rates, smoother trajectories, and improved progress toward the goal, with no observed safety violations under the tested conditions. These findings indicate that coupling pose-space safety with risk-adaptive margins provides a principled and practical path to safe and efficient navigation in dynamic scenes.
- Open Access
Encouraging Guidance: Floating Target Tracking Technology for Airborne Robotic Arm Based on Reinforcement Learning
Aerial robots equipped with operational robotic arms are a powerful means of achieving aerial contact operations, and their core competitiveness lies in target tracking control at the end of the airborne robotic arm (ARA). In order to improve the learning efficiency and flexibility of the ARA control algorithm, this paper proposes the encouraging guidance of an actor–critic (Eg-ac) algorithm based on the actor–critic (AC) algorithm and applies it to the floating target tracking control of ARA. It can quickly lock in the exploration direction and achieve stable tracking without increasing the learning cost. Firstly, this paper establishes approximate functions, policy functions, and encouragement functions for the state value of ARA. Secondly, an adoption rate controller (ARC) module was designed based on the concept of heavy rewards and light punishments (HRLP). Then, the kinematic and dynamic models of ARA were established. Finally, simulation was conducted using stable baselines3 (SB3). The experimental results show that, under the same computational cost, the convergence speed of the Eg-ac is improved by 21.4% compared to deep deterministic policy gradient (DDPG). Compared with soft actor–critic (SAC) and DDPG, Eg-ac has improved learning efficiency by at least 20% and has a more agile and stable floating target tracking effect.
Open AccessEncouraging Guidance: Floating Target Tracking Technology for Airborne Robotic Arm Based on Reinforcement Learning
Aerial robots equipped with operational robotic arms are a powerful means of achieving aerial contact operations, and their core competitiveness lies in target tracking control at the end of the airborne robotic arm (ARA). In order to improve the learning efficiency and flexibility of the ARA control algorithm, this paper proposes the encouraging guidance of an actor–critic (Eg-ac) algorithm based on the actor–critic (AC) algorithm and applies it to the floating target tracking control of ARA. It can quickly lock in the exploration direction and achieve stable tracking without increasing the learning cost. Firstly, this paper establishes approximate functions, policy functions, and encouragement functions for the state value of ARA. Secondly, an adoption rate controller (ARC) module was designed based on the concept of heavy rewards and light punishments (HRLP). Then, the kinematic and dynamic models of ARA were established. Finally, simulation was conducted using stable baselines3 (SB3). The experimental results show that, under the same computational cost, the convergence speed of the Eg-ac is improved by 21.4% compared to deep deterministic policy gradient (DDPG). Compared with soft actor–critic (SAC) and DDPG, Eg-ac has improved learning efficiency by at least 20% and has a more agile and stable floating target tracking effect.
- Open Access
- 6 December 2024
- Published by MDPI AG in Biomimetics
- Vol. 9 (12) , 745
A Biomimetic Pose Estimation and Target Perception Strategy for Transmission Line Maintenance UAVs
High-voltage overhead power lines serve as the carrier of power transmission and are crucial to the stable operation of the power system. Therefore, it is particularly important to detect and remove foreign objects attached to transmission lines, as soon as possible. In this context, the widespread promotion and application of smart robots in the power industry can help address the increasingly complex challenges faced by the industry and ensure the efficient, economical, and safe operation of the power grid system. This article proposes a bionic-based UAV pose estimation and target perception strategy, which aims to address the lack of pattern recognition and automatic tracking capabilities of traditional power line inspection UAVs, as well as the poor robustness of visual odometry. Compared with the existing UAV environmental perception solutions, the bionic target perception algorithm proposed in this article can efficiently extract point and line features from infrared images and realize the target detection and automatic tracking function of small multi-rotor drones in the power line scenario, with low power consumption.
- 6 December 2024
- Published by MDPI AG in Biomimetics
- Vol. 9 (12) , 745
Open AccessA Biomimetic Pose Estimation and Target Perception Strategy for Transmission Line Maintenance UAVs
High-voltage overhead power lines serve as the carrier of power transmission and are crucial to the stable operation of the power system. Therefore, it is particularly important to detect and remove foreign objects attached to transmission lines, as soon as possible. In this context, the widespread promotion and application of smart robots in the power industry can help address the increasingly complex challenges faced by the industry and ensure the efficient, economical, and safe operation of the power grid system. This article proposes a bionic-based UAV pose estimation and target perception strategy, which aims to address the lack of pattern recognition and automatic tracking capabilities of traditional power line inspection UAVs, as well as the poor robustness of visual odometry. Compared with the existing UAV environmental perception solutions, the bionic target perception algorithm proposed in this article can efficiently extract point and line features from infrared images and realize the target detection and automatic tracking function of small multi-rotor drones in the power line scenario, with low power consumption.
- Open Access
Quaternion-Based Non-Singular Terminal Sliding Mode Control of Quadrotor with a Two-Degree-of-Freedom Deformable Arm for Narrow Environments
Conventional multi-rotors with limited deformation capability are unable to meet the traversal capability of complex and narrow environments. In order to solve the above problems, a novel type of deformable quadrotor with a two-degree-of-freedom arm, named QTDA, is proposed. Firstly, the overall structural design of the QTDA is introduced, and its movement strategy is analyzed. Secondly, the Newton–Euler equations based on a quaternion are utilized to model the omnidirectional dynamics and kinematics of the system. Next, to tackle the multi-actuator control problem, a pseudo-inverse control allocation method is developed, along with an analysis of control allocation singularities. Furthermore, non-singular terminal sliding mode position control law and non-singular terminal sliding mode attitude control law based on a quaternion are designed. Finally, simulations are conducted to verify the effectiveness of the proposed control methods. The results demonstrate the QTDA’s ability to traverse both narrow horizontal and vertical environments, thereby validating the effectiveness of the approach presented in this paper.
Open AccessQuaternion-Based Non-Singular Terminal Sliding Mode Control of Quadrotor with a Two-Degree-of-Freedom Deformable Arm for Narrow Environments
Conventional multi-rotors with limited deformation capability are unable to meet the traversal capability of complex and narrow environments. In order to solve the above problems, a novel type of deformable quadrotor with a two-degree-of-freedom arm, named QTDA, is proposed. Firstly, the overall structural design of the QTDA is introduced, and its movement strategy is analyzed. Secondly, the Newton–Euler equations based on a quaternion are utilized to model the omnidirectional dynamics and kinematics of the system. Next, to tackle the multi-actuator control problem, a pseudo-inverse control allocation method is developed, along with an analysis of control allocation singularities. Furthermore, non-singular terminal sliding mode position control law and non-singular terminal sliding mode attitude control law based on a quaternion are designed. Finally, simulations are conducted to verify the effectiveness of the proposed control methods. The results demonstrate the QTDA’s ability to traverse both narrow horizontal and vertical environments, thereby validating the effectiveness of the approach presented in this paper.
- Open Access
A Fuzzy Pure Pursuit for Autonomous UGVs Based on Model Predictive Control and Whole-Body Motion Control
In this paper, we propose an adaptive fuzzy pure pursuit trajectory tracking algorithm for autonomous unmanned ground vehicles (UGVs), addressing the challenges of accurate and stable navigation in complex environments. Traditional pure pursuit methods with fixed look-ahead distances struggle to maintain precision in dynamic and uneven terrains. Our approach uniquely integrates a fuzzy control algorithm that allows for real-time adjustments of the look-ahead distance based on environmental feedback, thereby enhancing tracking accuracy and smoothness. Additionally, we combine this with model predictive control (MPC) and whole-body motion control (WBC), where MPC forecasts future states and optimally adjusts control actions, while WBC ensures coordinated motion of the UGV, maintaining balance and stability, especially in rough terrains. This integration not only improves responsiveness to changing conditions but also enables dynamic balance adjustments during movement. The proposed algorithm was validated through simulations in Gazebo and real-world experiments on physical platforms. In real-world tests, our algorithm reduced the average trajectory tracking error by 45% and the standard deviation by nearly 50%, significantly improving stability and accuracy compared to traditional methods.
Open AccessA Fuzzy Pure Pursuit for Autonomous UGVs Based on Model Predictive Control and Whole-Body Motion Control
In this paper, we propose an adaptive fuzzy pure pursuit trajectory tracking algorithm for autonomous unmanned ground vehicles (UGVs), addressing the challenges of accurate and stable navigation in complex environments. Traditional pure pursuit methods with fixed look-ahead distances struggle to maintain precision in dynamic and uneven terrains. Our approach uniquely integrates a fuzzy control algorithm that allows for real-time adjustments of the look-ahead distance based on environmental feedback, thereby enhancing tracking accuracy and smoothness. Additionally, we combine this with model predictive control (MPC) and whole-body motion control (WBC), where MPC forecasts future states and optimally adjusts control actions, while WBC ensures coordinated motion of the UGV, maintaining balance and stability, especially in rough terrains. This integration not only improves responsiveness to changing conditions but also enables dynamic balance adjustments during movement. The proposed algorithm was validated through simulations in Gazebo and real-world experiments on physical platforms. In real-world tests, our algorithm reduced the average trajectory tracking error by 45% and the standard deviation by nearly 50%, significantly improving stability and accuracy compared to traditional methods.
- Open Access
A Hierarchical Control Method for Trajectory Tracking of Aerial Manipulators Arms
To address the control challenges of an aerial manipulator arm (AMA) mounted on a drone under conditions of model inaccuracy and strong disturbances, this paper proposes a hierarchical control architecture. In the upper-level control, Bézier curves are first used to generate smooth and continuous desired trajectory points, and the theory of singular trajectory lines along with a Radial Basis Function Neural Network (RBFNN) is introduced to construct a highly accurate multi-configuration inverse kinematic solver. This solver not only effectively avoids singular solutions but also enhances its precision online through data-driven methods, ensuring the accurate calculation of joint angles. The lower-level control focuses on optimizing the dynamic model of the manipulator. Using a Model Predictive Control (MPC) strategy, the dynamic behavior of the manipulator is predicted, and a rolling optimization process is executed to solve for the optimal control sequence. To enhance system robustness, an RBFNN is specifically introduced to compensate for external disturbances, ensuring that the manipulator maintains stable performance in dynamic environments and computes the optimal control commands. Physical prototype testing results show that this control strategy achieves a root mean square (RMS) error of 0.035, demonstrating the adaptability and disturbance rejection capabilities of the proposed method.
Open AccessA Hierarchical Control Method for Trajectory Tracking of Aerial Manipulators Arms
To address the control challenges of an aerial manipulator arm (AMA) mounted on a drone under conditions of model inaccuracy and strong disturbances, this paper proposes a hierarchical control architecture. In the upper-level control, Bézier curves are first used to generate smooth and continuous desired trajectory points, and the theory of singular trajectory lines along with a Radial Basis Function Neural Network (RBFNN) is introduced to construct a highly accurate multi-configuration inverse kinematic solver. This solver not only effectively avoids singular solutions but also enhances its precision online through data-driven methods, ensuring the accurate calculation of joint angles. The lower-level control focuses on optimizing the dynamic model of the manipulator. Using a Model Predictive Control (MPC) strategy, the dynamic behavior of the manipulator is predicted, and a rolling optimization process is executed to solve for the optimal control sequence. To enhance system robustness, an RBFNN is specifically introduced to compensate for external disturbances, ensuring that the manipulator maintains stable performance in dynamic environments and computes the optimal control commands. Physical prototype testing results show that this control strategy achieves a root mean square (RMS) error of 0.035, demonstrating the adaptability and disturbance rejection capabilities of the proposed method.
- Open Access
Control and Application of Tree Obstacle-Clearing Coaxial Octocopter with Flexible Suspension Saw
Aiming at the challenges of clearing tree obstacles along power transmission lines, the control and application of a novel Tree-Obstacle Clearing Coaxial Octocopter with Flexible Suspension Saw (TOCCO-FSS) have been investigated. Firstly, an overall scheme design and modeling of the TOCCO-FSS were conducted, and dynamic modeling of the TOCCO-FSS was performed using the Lagrange equation. Secondly, to address the interference encountered during the operation, a contact operation model was established to estimate the uncertainties and external disturbances during the contact operation process. Further, the Non-Singular Terminal Sliding-Mode Active Disturbance Rejection Control (NTSM-ADRC) method was researched based on the mathematical model of the TOCCO-FSS. Finally, the performance of the controller was verified through simulations and physical experiments. The results demonstrate that the design, control, and application of the entire TOCCO-FSS system are effective.
Open AccessControl and Application of Tree Obstacle-Clearing Coaxial Octocopter with Flexible Suspension Saw
Aiming at the challenges of clearing tree obstacles along power transmission lines, the control and application of a novel Tree-Obstacle Clearing Coaxial Octocopter with Flexible Suspension Saw (TOCCO-FSS) have been investigated. Firstly, an overall scheme design and modeling of the TOCCO-FSS were conducted, and dynamic modeling of the TOCCO-FSS was performed using the Lagrange equation. Secondly, to address the interference encountered during the operation, a contact operation model was established to estimate the uncertainties and external disturbances during the contact operation process. Further, the Non-Singular Terminal Sliding-Mode Active Disturbance Rejection Control (NTSM-ADRC) method was researched based on the mathematical model of the TOCCO-FSS. Finally, the performance of the controller was verified through simulations and physical experiments. The results demonstrate that the design, control, and application of the entire TOCCO-FSS system are effective.
- Open Access
A Supervised Reinforcement Learning Algorithm for Controlling Drone Hovering
The application of drones carrying different devices for aerial hovering operations is becoming increasingly widespread, but currently there is very little research relying on reinforcement learning methods for hovering control, and it has not been implemented on physical machines. Drone’s behavior space regarding hover control is continuous and large-scale, making it difficult for basic algorithms and value-based reinforcement learning (RL) algorithms to have good results. In response to this issue, this article applies a watcher-actor-critic (WAC) algorithm to the drone’s hover control, which can quickly lock the exploration direction and achieve high robustness of the drone’s hover control while improving learning efficiency and reducing learning costs. This article first utilizes the actor-critic algorithm based on behavioral value Q (QAC) and the deep deterministic policy gradient algorithm (DDPG) for drone hover control learning. Subsequently, an actor-critic algorithm with an added watcher is proposed, in which the watcher uses a PID controller with parameters provided by a neural network as the dynamic monitor, transforming the learning process into supervised learning. Finally, this article uses a classic reinforcement learning environment library, Gym, and a current mainstream reinforcement learning framework, PARL, for simulation, and deploys the algorithm to a practical environment. A multi-sensor fusion strategy-based autonomous localization method for unmanned aerial vehicles is used for practical exercises. The simulation and experimental results show that the training episodes of WAC are reduced by 20% compared to the DDPG and 55% compared to the QAC, and the proposed algorithm has a higher learning efficiency, faster convergence speed, and smoother hovering effect compared to the QAC and DDPG.
Open AccessA Supervised Reinforcement Learning Algorithm for Controlling Drone Hovering
The application of drones carrying different devices for aerial hovering operations is becoming increasingly widespread, but currently there is very little research relying on reinforcement learning methods for hovering control, and it has not been implemented on physical machines. Drone’s behavior space regarding hover control is continuous and large-scale, making it difficult for basic algorithms and value-based reinforcement learning (RL) algorithms to have good results. In response to this issue, this article applies a watcher-actor-critic (WAC) algorithm to the drone’s hover control, which can quickly lock the exploration direction and achieve high robustness of the drone’s hover control while improving learning efficiency and reducing learning costs. This article first utilizes the actor-critic algorithm based on behavioral value Q (QAC) and the deep deterministic policy gradient algorithm (DDPG) for drone hover control learning. Subsequently, an actor-critic algorithm with an added watcher is proposed, in which the watcher uses a PID controller with parameters provided by a neural network as the dynamic monitor, transforming the learning process into supervised learning. Finally, this article uses a classic reinforcement learning environment library, Gym, and a current mainstream reinforcement learning framework, PARL, for simulation, and deploys the algorithm to a practical environment. A multi-sensor fusion strategy-based autonomous localization method for unmanned aerial vehicles is used for practical exercises. The simulation and experimental results show that the training episodes of WAC are reduced by 20% compared to the DDPG and 55% compared to the QAC, and the proposed algorithm has a higher learning efficiency, faster convergence speed, and smoother hovering effect compared to the QAC and DDPG.
- Open Access
- 19 September 2023
- Published by MDPI AG in Biomimetics
- Vol. 8 (5) , 436
Perceiving like a Bat: Hierarchical 3D Geometric–Semantic Scene Understanding Inspired by a Biomimetic Mechanism
Geometric–semantic scene understanding is a spatial intelligence capability that is essential for robots to perceive and navigate the world. However, understanding a natural scene remains challenging for robots because of restricted sensors and time-varying situations. In contrast, humans and animals are able to form a complex neuromorphic concept of the scene they move in. This neuromorphic concept captures geometric and semantic aspects of the scenario and reconstructs the scene at multiple levels of abstraction. This article seeks to reduce the gap between robot and animal perception by proposing an ingenious scene-understanding approach that seamlessly captures geometric and semantic aspects in an unexplored environment. We proposed two types of biologically inspired environment perception methods, i.e., a set of elaborate biomimetic sensors and a brain-inspired parsing algorithm related to scene understanding, that enable robots to perceive their surroundings like bats. Our evaluations show that the proposed scene-understanding system achieves competitive performance in image semantic segmentation and volumetric–semantic scene reconstruction. Moreover, to verify the practicability of our proposed scene-understanding method, we also conducted real-world geometric–semantic scene reconstruction in an indoor environment with our self-developed drone.
- 19 September 2023
- Published by MDPI AG in Biomimetics
- Vol. 8 (5) , 436
Open AccessPerceiving like a Bat: Hierarchical 3D Geometric–Semantic Scene Understanding Inspired by a Biomimetic Mechanism
Geometric–semantic scene understanding is a spatial intelligence capability that is essential for robots to perceive and navigate the world. However, understanding a natural scene remains challenging for robots because of restricted sensors and time-varying situations. In contrast, humans and animals are able to form a complex neuromorphic concept of the scene they move in. This neuromorphic concept captures geometric and semantic aspects of the scenario and reconstructs the scene at multiple levels of abstraction. This article seeks to reduce the gap between robot and animal perception by proposing an ingenious scene-understanding approach that seamlessly captures geometric and semantic aspects in an unexplored environment. We proposed two types of biologically inspired environment perception methods, i.e., a set of elaborate biomimetic sensors and a brain-inspired parsing algorithm related to scene understanding, that enable robots to perceive their surroundings like bats. Our evaluations show that the proposed scene-understanding system achieves competitive performance in image semantic segmentation and volumetric–semantic scene reconstruction. Moreover, to verify the practicability of our proposed scene-understanding method, we also conducted real-world geometric–semantic scene reconstruction in an indoor environment with our self-developed drone.
- Open Access
A Lightweight and Drift-Free Fusion Strategy for Drone Autonomous and Safe Navigation
Self-localization and state estimation are crucial capabilities for agile drone autonomous navigation. This article presents a lightweight and drift-free vision-IMU-GNSS tightly coupled multisensor fusion (LDMF) strategy for drones’ autonomous and safe navigation. The drone is carried out with a front-facing camera to create visual geometric constraints and generate a 3D environmental map. Ulteriorly, a GNSS receiver with multiple constellations support is used to continuously provide pseudo-range, Doppler frequency shift and UTC time pulse signals to the drone navigation system. The proposed multisensor fusion strategy leverages the Kanade–Lucas algorithm to track multiple visual features in each input image. The local graph solution is bounded in a restricted sliding window, which can immensely predigest the computational complexity in factor graph optimization procedures. The drone navigation system can achieve camera-rate performance on a small companion computer. We thoroughly experimented with the LDMF system in both simulated and real-world environments, and the results demonstrate dramatic advantages over the state-of-the-art sensor fusion strategies.
Open AccessA Lightweight and Drift-Free Fusion Strategy for Drone Autonomous and Safe Navigation
Self-localization and state estimation are crucial capabilities for agile drone autonomous navigation. This article presents a lightweight and drift-free vision-IMU-GNSS tightly coupled multisensor fusion (LDMF) strategy for drones’ autonomous and safe navigation. The drone is carried out with a front-facing camera to create visual geometric constraints and generate a 3D environmental map. Ulteriorly, a GNSS receiver with multiple constellations support is used to continuously provide pseudo-range, Doppler frequency shift and UTC time pulse signals to the drone navigation system. The proposed multisensor fusion strategy leverages the Kanade–Lucas algorithm to track multiple visual features in each input image. The local graph solution is bounded in a restricted sliding window, which can immensely predigest the computational complexity in factor graph optimization procedures. The drone navigation system can achieve camera-rate performance on a small companion computer. We thoroughly experimented with the LDMF system in both simulated and real-world environments, and the results demonstrate dramatic advantages over the state-of-the-art sensor fusion strategies.