A5023176055- Robotic Path Planning Algorithms
- Underwater Vehicles and Communication Systems
- Robotics and Sensor-Based Localization
- Adaptive Control of Nonlinear Systems
- Distributed Control Multi-Agent Systems
- Control and Dynamics of Mobile Robots
- Robotic Mechanisms and Dynamics
- Vibration Control and Rheological Fluids
- Reinforcement Learning in Robotics
- Guidance and Control Systems
- Software Testing and Debugging Techniques
- Modular Robots and Swarm Intelligence
- Innovative Energy Harvesting Technologies
- Maritime Navigation and Safety
- Fault Detection and Control Systems
- Advanced Control Systems Optimization
- Robot Manipulation and Learning
Naval University of Engineering
2019-2023
In order to plan the robot path in 3D space efficiently, a modified Rapidly-exploring Random Trees based on heuristic probability bias-goal (PBG-RRT) is proposed. The algorithm combines probabilistic and factor, which can get convergence quickly avoid falling into local minimum. Firstly, PBG-RRT used path. After obtaining points, points are rarefied by Douglas-Peucker while maintaining original characteristics. Then, smooth trajectory suitable for manipulator end effector generated...
Manipulator motion planning for real-time obstacle avoidance in a dynamic environment is explored this article. To address problems, multiple-query and sampling-based replanning algorithm with the bias-goal factor, rapidly exploring random tree (DBG-RRT), proposed to achieve rapid response high success rate. Differently from other studies on path planning, relay-node method adopted basis of generate new collision-free trajectory. Subsequently, an un-interrupt strategy embraced judge whether...
The survivability of autonomous underwater vehicles (AUV) in complex missions and dangerous situations is great significance to ocean resource exploration, hydrological research, maritime rescue, undersea military. Existing researches on motion control for the AUV mainly focus its normal operating, but active self-rescue method emergency hardly found. As classical methods are not sufficient enough complicated AUV, this paper uses deep reinforcement learning (DRL) algorithm solve problem...
This article addresses the real-time obstacle avoidance problem in 2D/3D path following missions for autonomous underwater vehicles (AUVs). To efficiently solve this problem, a novel universal framework based on guidance layer is proposed under-actuated AUVs to follow arbitrary referenced path. Based this, line-of-sight law designed avoid multi-static or slow time-varying obstacles that appear desired route and are pretreated by oriented bounding box method. The strategy of single-obstacle...
This paper analyzes the trajectory tracking problem in decoupled planes for X-rudder AUVs under time-varying, unknown environmental interferences. The proposed scheme consists of kinematic control law based on compound line-of-sight guidance and dynamic a non-singular adaptive integral terminal sliding mode (NAITSMC) to avoid chattering problems, parameter perturbation, time-varying disturbances. Meanwhile, we introduce reduced-order extended state observer (RESO) compensate ocean currents...
The magnetic antenna can receive extremely weak underwater signals, and induce the field intensity which reach femto-tesla (fT) level, making it widely used in electromagnetic signal detection. However, even slightest vibration environment transmitted to will make cut geomagnetic movement; as a result, electromagnetic-induced noise would be generated, affect performance of antenna. best method suppress motion induced is isolate effectively from ambient vibration. In this paper, reduction...