A5012653359- Adaptive Control of Nonlinear Systems
- Robotic Path Planning Algorithms
- Control and Dynamics of Mobile Robots
- Power Line Inspection Robots
- Distributed Control Multi-Agent Systems
- Adaptive Dynamic Programming Control
- Reinforcement Learning in Robotics
- Robotics and Sensor-Based Localization
- Advanced Control Systems Optimization
- UAV Applications and Optimization
- Multimodal Machine Learning Applications
- Islanding Detection in Power Systems
- AI-based Problem Solving and Planning
- Topic Modeling
- Vibration and Dynamic Analysis
Nanjing University of Aeronautics and Astronautics
2020-2025
Ministry of Industry and Information Technology
2020
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 airborne arm (ARA). In order to improve learning efficiency flexibility ARA algorithm, this paper proposes encouraging guidance an actor–critic (Eg-ac) algorithm based on (AC) applies it floating ARA. It can quickly lock exploration direction achieve stable without increasing cost. Firstly, establishes...
The application of drones carrying different devices for aerial hovering operations is becoming increasingly widespread, but currently there very little research relying on reinforcement learning methods control, and it has not been implemented physical machines. Drone’s behavior space regarding hover control continuous large-scale, making difficult basic algorithms value-based (RL) to have good results. In response this issue, article applies a watcher-actor-critic (WAC) algorithm the...
When a mobile robot inspects tasks with complex requirements indoors, the traditional backstepping method cannot guarantee accuracy of trajectory, leading to problems such as instrument not being inside image and focus failure when grabs high zoom. In order solve this problem, paper proposes an adaptive based on double Q-learning for tracking controlling trajectory robots. We design incremental model-free algorithm Double-Q learning, which can quickly learn rectify controller gain online....
To address the control challenges of an aerial manipulator arm (AMA) mounted on a drone under conditions model inaccuracy and strong disturbances, this paper proposes hierarchical architecture. In upper-level control, Bézier curves are first used to generate smooth continuous desired trajectory points, theory singular lines along with Radial Basis Function Neural Network (RBFNN) is introduced construct highly accurate multi-configuration inverse kinematic solver. This solver not only...
Autonomous decision-making is a hallmark of intelligent mobile robots and an essential element autonomous navigation. The challenge to enable complete navigation tasks in environments with mapless or low-precision maps, relying solely on sensors. To address this, we have proposed innovative algorithm called PEEMEF-DARC. This consists three parts: Double Actors Regularized Critics (DARC), priority-based excellence experience data collection mechanism, multi-source fusion strategy mechanism....
The unmanned aerial vehicle (UAV) trajectory tracking control algorithm based on deep reinforcement learning is generally inefficient for training in an unknown environment, and the convergence unstable. Aiming at this situation, a Markov decision process (MDP) model UAV established, state-compensated deterministic policy gradient (CDDPG) proposed. An additional neural network (C-Net) whose input compensation state output action added to of (DDPG) assist exploration training. It combined...
This paper proposes a novel aerial manipulator with front cutting effector (AMFCE) to address the physical interaction (APhI) problem. First, system uncertainty and external disturbance during movement contact operation are estimated by modeling entire robot position. Next, based on established model, nonlinear observer (NDO) is used estimate compensate unknown of model parameters in real time. Then, nonsingular terminal synovial membrane control method suppress part that difficult estimate....
Tree branches near the electric power transmission lines are of great threat to electricity supply. Nowadays, tasks clearing threatening tree still mostly operated by hand and simple tools. Traditional structures multirotor aerial robot have problem fixed structure limited performance, which affects stability efficiency pruning operation. In this article, in order obtain better environmental adaptability, an active deformable trees-pruning is presented. The deformation implemented through...