Study on intelligent collision avoidance and recovery path planning system for the waterjet-propelled unmanned surface vehicle

2019 ◽  
Vol 182 ◽  
pp. 489-498 ◽  
Author(s):  
Binghua Shi ◽  
Yixin Su ◽  
Chen Wang ◽  
Lili Wan ◽  
Yi Luo
Keyword(s):  
Path Planning ◽  
Collision Avoidance ◽  
Planning System ◽  
Unmanned Surface Vehicle

scholarly journals Local Path Planning for Unmanned Surface Vehicle Collision Avoidance Based on Modified Quantum Particle Swarm Optimization

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Guoqing Xia ◽  
Zhiwei Han ◽  
Bo Zhao ◽  
Xinwei Wang
Keyword(s):  
Path Planning ◽  
Collision Avoidance ◽  
Optimization Problem ◽  
Quantum Particle ◽  
Swarm Optimization ◽  
Unmanned Surface Vehicle ◽  
Kinematic Constraints ◽  
Quantum Particle Swarm Optimization ◽  
Local Path Planning ◽  
Local Path

An unmanned surface vehicle (USV) plans its global path before the mission starts. When dynamic obstacles appear during sailing, the planned global path must be adjusted locally to avoid collision. This study proposes a local path planning algorithm based on the velocity obstacle (VO) method and modified quantum particle swarm optimization (MQPSO) for USV collision avoidance. The collision avoidance model based on VO not only considers the velocity and course of the USV but also handles the variable velocity and course of an obstacle. According to the collision avoidance model, the USV needs to adjust its velocity and course simultaneously to avoid collision. Due to the kinematic constraints of the USV, the velocity window and course window of the USV are determined by the dynamic window approach (DWA). In summary, local path planning is transformed into a multiobjective optimization problem with multiple constraints in a continuous search space. The optimization problem is to obtain the USV’s optimal velocity variation and course variation to avoid collision and minimize its energy consumption under the rules of the International Regulations for Preventing Collisions at Sea (COLREGs) and the kinematic constraints of the USV. Since USV local path planning is completed in a short time, it is essential that the optimization algorithm can quickly obtain the optimal value. MQPSO is primarily proposed to meet that requirement. In MQPSO, the efficiency of quantum encoding in quantum computing and the optimization ability of representing the motion states of the particles with wave functions to cover the whole feasible solution space are combined. Simulation results show that the proposed algorithm can obtain the optimal values of the benchmark functions and effectively plan a collision-free path for a USV.

scholarly journals iADA*-RL: Anytime Graph-Based Path Planning with Deep Reinforcement Learning for an Autonomous UAV

2021 ◽  
Vol 11 (9) ◽  
pp. 3948
Author(s):  
Aye Aye Maw ◽  
Maxim Tyan ◽  
Tuan Anh Nguyen ◽  
Jae-Woo Lee
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Real Time ◽  
Collision Avoidance ◽  
Real World ◽  
Mission Planning ◽  
Planning System ◽  
Local Planning ◽  
Planning Algorithm ◽  
Path Planning Algorithm

Path planning algorithms are of paramount importance in guidance and collision systems to provide trustworthiness and safety for operations of autonomous unmanned aerial vehicles (UAV). Previous works showed different approaches mostly focusing on shortest path discovery without a sufficient consideration on local planning and collision avoidance. In this paper, we propose a hybrid path planning algorithm that uses an anytime graph-based path planning algorithm for global planning and deep reinforcement learning for local planning which applied for a real-time mission planning system of an autonomous UAV. In particular, we aim to achieve a highly autonomous UAV mission planning system that is adaptive to real-world environments consisting of both static and moving obstacles for collision avoidance capabilities. To achieve adaptive behavior for real-world problems, a simulator is required that can imitate real environments for learning. For this reason, the simulator must be sufficiently flexible to allow the UAV to learn about the environment and to adapt to real-world conditions. In our scheme, the UAV first learns about the environment via a simulator, and only then is it applied to the real-world. The proposed system is divided into two main parts: optimal flight path generation and collision avoidance. A hybrid path planning approach is developed by combining a graph-based path planning algorithm with a learning-based algorithm for local planning to allow the UAV to avoid a collision in real time. The global path planning problem is solved in the first stage using a novel anytime incremental search algorithm called improved Anytime Dynamic A* (iADA*). A reinforcement learning method is used to carry out local planning between waypoints, to avoid any obstacles within the environment. The developed hybrid path planning system was investigated and validated in an AirSim environment. A number of different simulations and experiments were performed using AirSim platform in order to demonstrate the effectiveness of the proposed system for an autonomous UAV. This study helps expand the existing research area in designing efficient and safe path planning algorithms for UAVs.

scholarly journals Dynamic Path Planning Of Unmanned Surface Vehicle Based On Genetic Algorithm With Sliding Curve Guidance System

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Rusdhianto Effendie Abdul Kadir ◽  
Mochammad Sahal ◽  
Nurlita Gamayanti ◽  
Fian Ilham Pratama
Keyword(s):  
Genetic Algorithm ◽  
Control System ◽  
Path Planning ◽  
Dynamic Environment ◽  
Guidance System ◽  
Planning System ◽  
Unmanned Surface Vehicle ◽  
Dynamic Path Planning ◽  
Genetic Algorithm Method ◽  
Unmanned Ship

Unmanned Surface Vehicle (USV) is an unmanned ship that is controlled through a remote control system (manual) or automatic control system (autopilot), move due to the thrust force from thruster machine and can turning due to the deflection angle of rudder. The USV path planning system becomes an important task so that the ship can make the global trajectory with the minimum travel distance according to the desired navigation while at the same able to avoid various obstacles from local dangerous situations that have the potential for collisions. To be able to do dynamic USV path planning, the Genetic Algorithm method with a sliding curve guidance system and PID MRAC controller is used. The use of this method gives smooth ship track performance with shortest distance in a 400x400 square meter map with static and dynamic obstacles. In a dynamic environment, the path replanning process that takes place in 0,98 seconds is able to find a new path that does not collide the obstacles. For the purposes of algorithm validation, the simulation is performed using MATLAB software with real ship parameters of 6 meters length USV.

scholarly journals COLREG-Compliant Optimal Path Planning for Real-Time Guidance and Control of Autonomous Ships

2021 ◽  
Vol 9 (4) ◽  
pp. 405
Author(s):  
Raphael Zaccone
Keyword(s):  
Path Planning ◽  
Real Time ◽  
Collision Avoidance ◽  
Autonomous Navigation ◽  
Optimal Path ◽  
Open Water ◽  
Optimal Path Planning ◽  
Guidance And Control ◽  
Real Time Applications ◽  
And Control

While collisions and groundings still represent the most important source of accidents involving ships, autonomous vessels are a central topic in current research. When dealing with autonomous ships, collision avoidance and compliance with COLREG regulations are major vital points. However, most state-of-the-art literature focuses on offline path optimisation while neglecting many crucial aspects of dealing with real-time applications on vessels. In the framework of the proposed motion-planning, navigation and control architecture, this paper mainly focused on optimal path planning for marine vessels in the perspective of real-time applications. An RRT*-based optimal path-planning algorithm was proposed, and collision avoidance, compliance with COLREG regulations, path feasibility and optimality were discussed in detail. The proposed approach was then implemented and integrated with a guidance and control system. Tests on a high-fidelity simulation platform were carried out to assess the potential benefits brought to autonomous navigation. The tests featured real-time simulation, restricted and open-water navigation and dynamic scenarios with both moving and fixed obstacles.

Sign in / Sign up

Export Citation Format

Share Document