scholarly journals An Automated Assembly of 3D Point Clouds using Coupling Matching and Path Planning Algorithm by Reinforcement Learning

2020 ◽  
Author(s):  
Dianthika Puteri Andini ◽  
Muhammad Yusuf Fadhlan
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Point Clouds ◽  
Automated Assembly ◽  
3D Point Clouds ◽  
Planning Algorithm ◽  
Path Planning Algorithm

Hybrid obstacle avoidance system with vision and ultrasonic sensors for multi-rotor MAVs

2018 ◽  
Vol 45 (2) ◽  
pp. 227-236 ◽  
Author(s):  
Qiang Zhou ◽  
Danping Zou ◽  
Peilin Liu
Keyword(s):  
Path Planning ◽  
Obstacle Avoidance ◽  
Moving Objects ◽  
Point Clouds ◽  
Ultrasonic Sensor ◽  
Content Type ◽  
Stereo Camera ◽  
3D Point Clouds ◽  
Planning Algorithm ◽  
Path Planning Algorithm

Purpose This paper aims to develop an obstacle avoidance system for a multi-rotor micro aerial vehicle (MAV) that flies in indoor environments which usually contain transparent, texture-less or moving objects. Design/methodology/approach The system adopts a combination of a stereo camera and an ultrasonic sensor to detect obstacles and extracts three-dimensional (3D) point clouds. The obstacle map is built on a coarse global map and updated by local maps generated by the recent 3D point clouds. An efficient layered A* path planning algorithm is also proposed to address the path planning in 3D space for MAVs. Findings The authors conducted a lot of experiments in both static and dynamic scenes. The results show that the obstacle avoidance system works reliably even when transparent or texture-less obstacles are present. The layered A* path planning algorithm is much faster than the traditional 3D algorithm and makes the system response quickly when the obstacle map has been changed because of the moving objects. Research limitations/implications The limited field of view of both stereo camera and ultrasonic sensor makes the system need to change heading first before moving side to side or moving backward. But this problem could be addressed when multiple systems are mounted toward different directions on the MAV. Practical implications The developed approach could be valuable to applications in indoors. Originality/value This paper presents a robust obstacle avoidance system and a fast layered path planning algorithm that are easy to be implemented for practical systems.

Path Planning Algorithm for Two-dimensional Raster Maps based on Deep Reinforcement Learning

2021 ◽  
Author(s):  
Jie Li ◽  
Yuhan Zhang ◽  
Jiaqi Tang ◽  
Xianjie Liu ◽  
Abdulhamid Ibrahim
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Two Dimensional ◽  
Raster Maps ◽  
Planning Algorithm ◽  
Path Planning Algorithm

scholarly journals Unmanned Aerial Vehicle Path Planning Algorithm Based on Deep Reinforcement Learning in Large-Scale and Dynamic Environments

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 24884-24900
Author(s):  
Ronglei Xie ◽  
Zhijun Meng ◽  
Lifeng Wang ◽  
Haochen Li ◽  
Kaipeng Wang ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Unmanned Aerial Vehicle ◽  
Large Scale ◽  
Dynamic Environments ◽  
Planning Algorithm ◽  
Aerial Vehicle ◽  
Vehicle Path ◽  
Path Planning Algorithm

scholarly journals Collision Avoidance for a Car-like Mobile Robots using Deep Reinforcement Learning

2021 ◽  
Vol 11 (11) ◽  
pp. 22-30
Author(s):  
Kiwon Yeom ◽  
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Mobile Robots ◽  
Autonomous Vehicle ◽  
Dynamic Environment ◽  
Time Step ◽  
Learning Path ◽  
Angular Velocities ◽  
Planning Algorithm ◽  
Path Planning Algorithm

—The applications of mobile robots are more and more diverse and extensive. The motion planning of the mobile robots should be considered in aspect of effectiveness of the navigation, and collision-free motion is essential for mobile robots. In addition, dynamic path planning of unknown environment has always been a challenge for mobile robots. Aiming at navigation problems, this paper proposes a Deep Reinforcement Learning (DRL) based path planning algorithm which can navigate nonholonomic car-like mobile robots in an unknown dynamic environment. The output of the learned network are the robot’s translational and angular velocities for the next time step. The method combines path planning on a 2D grid with reinforcement learning and does not need any supervision. The experiments illustrate that our trained policy can be applied to solve complex navigation tasks. Furthermore, we compare the performance of our learned controller to the popular approaches. Keywords— Deep reinforcement learning, path planning, , artificial neural network, mobile robot, autonomous vehicle

scholarly journals An Intelligent Path Selection Algorithm Based on Deep Reinforcement Learning

2021 ◽  
Vol 2078 (1) ◽  
pp. 012023
Author(s):  
Mengchen Sun
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Path Selection ◽  
Learning Ability ◽  
Continuous Learning ◽  
Selection Algorithm ◽  
Planning Algorithm ◽  
Intelligent Devices ◽  
Simulation Results ◽  
Path Planning Algorithm

Abstract Path selection is the most important algorithm in intelligent devices such as robots. At present, the traditional path-planning algorithm has achieved some results, but it lacks the ability of environmental perception and continuous learning. In order to solve the above problems, this paper proposes an intelligent path selection algorithm based on deep reinforcement learning, which uses the learning ability of deep learning and the decision-making ability of reinforcement learning to realize the autonomous path planning of robots and other equipment. Simulation results show that the proposed algorithm has faster convergence, efficiency and accuracy.

Energy management strategy of intelligent plug-in split hybrid electric vehicle based on deep reinforcement learning with optimized path planning algorithm

2021 ◽  
pp. 095440702110368
Author(s):  
Shengguang Xiong ◽  
Yishi Zhang ◽  
Chaozhong Wu ◽  
Zhijun Chen ◽  
Jiankun Peng ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Electric Vehicle ◽  
Energy Management ◽  
Management Strategy ◽  
Hybrid Electric Vehicle ◽  
Energy Management Strategy ◽  
Planning Algorithm ◽  
Hybrid Electric ◽  
Path Planning Algorithm

Energy management is a fundamental task and challenge of plug-in split hybrid electric vehicle (PSHEV) research field because of the complicated powertrain and variable driving conditions. Motivated by the foresight of intelligent vehicle and the breakthroughs of deep reinforcement learning framework, an energy management strategy of intelligent plug-in split hybrid electric vehicle (IPSHEV) based on optimized Dijkstra’s path planning algorithm (ODA) and reinforcement learning Deep-Q-Network (DQN) is proposed to cope with the challenge. Firstly, a gray model is used to predict the traffic congestion of each road and the length of each road calculated in the traditional Dijkstra’s algorithm (DA) is modified for path planning. Secondly, on the basis of the predicted velocity of each road, the planned velocity is constrained by the vehicle dynamics to ensure the driving security. Finally, the planning information is inputted to DQN to control the working mode of IPSHEV, so as to achieve energy saving of the vehicle. The simulation results show the optimized path planning algorithm and proposed energy management strategy is feasible and effective.

Sign in / Sign up

Export Citation Format

Share Document