scholarly journals Human experience–inspired path planning for robots

2018 ◽  
Vol 15 (1) ◽  
pp. 172988141875704 ◽  
Author(s):  
Wenyong Gong ◽  
Xiaohua Xie ◽  
Yong-Jin Liu
Keyword(s):  
Path Planning ◽  
Energy Function ◽  
Optimal Path ◽  
Human Experience ◽  
Service Robots ◽  
A Algorithm ◽  
Slowing Down ◽  
Path Distance ◽  
Planning Algorithm ◽  
Path Planning Algorithm

In this article, we present a human experience–inspired path planning algorithm for service robots. In addition to considering the path distance and smoothness, we emphasize the safety of robot navigation. Specifically, we build a speed field in accordance with several human driving experiences, like slowing down or detouring at a narrow aisle, and keeping a safe distance to the obstacles. Based on this speed field, the path curvatures, path distance, and steering speed are all integrated to form an energy function, which can be efficiently solved by the A* algorithm to seek the optimal path by resorting to an admissible heuristic function estimated from the energy function. Moreover, a simple yet effective fast path smoothing algorithm is proposed so as to ease the robots steering. Several examples are presented, demonstrating the effectiveness of our human experience–inspired path planning method.

Development of a Non-hazardous Path Planning Algorithm for Mars Rover in Real Terrain Enviroment

2018 ◽  
Vol 19 (11) ◽  
pp. 734-744 ◽  
Author(s):  
G. Wang ◽  
A. V. Fomichev
Keyword(s):  
Path Planning ◽  
Optimal Path ◽  
Mobile Object ◽  
Risk Indicator ◽  
A Algorithm ◽  
Mars Rover ◽  
Planning Algorithm ◽  
Comprehensive Comparison ◽  
Path Planning Algorithm ◽  
Wheeled Vehicles

In order to fulfill the corresponding task successfully, a crucial issue should be addressed is the path planning for the exploration of the Mars surface owing to the environmental features of the tough terrain. Traditional path planning algorithms, such as the A* algorithm and the improved A* algorithm — the algorithm D* and the Field D*, which have been successfully implemented on the planetary rover during the expeditions of the Moon and Mars, have the problem of finding the shortest optimal path. One of the more effective algorithms derived from the modified A* refers to the Basic Theta* or the Lazy Theta* algorithms, which are faster any-angle path planning. Additionally, the algorithms can find shorter routes. In this paper, derived from a comprehensive comparison of the existing algorithms (A*, Basic Theta* and Lazy Theta*), a novel modification of the Lazy AT methodology is proposed to reduce the calculation time and obtain a shorter path. Based on the analysis of the surface feature of the Mars topography, the corresponding safety indicator is discussed. The principal hazards of the wheeled vehicles during the exploration on the surface of the Mars are the slopes and the obstacles. According to the requirements for avoiding obstacles as well as the exploration stability of the Mars rover in the period of the exploration, the following topographic coefficients have been chosen to develop the hazard indicator, i.e., the inclination angle of the terrain, the surface roughness and the height difference of the terrain. In addition, to obtain a safe trajectory in algorithm Lazy AT on the Mars surface, the terrain hazard indicator (risk indicator) for the modification of the Risk Lazy AT algorithm is also proposed in this paper. The comparing analysis modeling results of the Risk Lazy AT and Lazy Theta* has shown that our proposed algorithm Risk Lazy AT can guarantee the safety movement of a mobile object during the exploration on the surface of the planet. In light of the real-world surface features of the Mars terrain, the digital map of the planet’s surface has been developed and the spatial routing of the rover has been tested with our novel proposed algorithm, so-called Risk Lazy AT.

scholarly journals A 2D Optimal Path Planning Algorithm for Autonomous Underwater Vehicle Driving in Unknown Underwater Canyons

2021 ◽  
Vol 9 (3) ◽  
pp. 252
Author(s):  
Yushan Sun ◽  
Xiaokun Luo ◽  
Xiangrui Ran ◽  
Guocheng Zhang
Keyword(s):  
Path Planning ◽  
Obstacle Avoidance ◽  
Autonomous Underwater Vehicles ◽  
Optimal Path ◽  
Small Scale ◽  
Target Point ◽  
Safe Driving ◽  
Policy Gradient ◽  
Planning Algorithm ◽  
Path Planning Algorithm

This research aims to solve the safe navigation problem of autonomous underwater vehicles (AUVs) in deep ocean, which is a complex and changeable environment with various mountains. When an AUV reaches the deep sea navigation, it encounters many underwater canyons, and the hard valley walls threaten its safety seriously. To solve the problem on the safe driving of AUV in underwater canyons and address the potential of AUV autonomous obstacle avoidance in uncertain environments, an improved AUV path planning algorithm based on the deep deterministic policy gradient (DDPG) algorithm is proposed in this work. This method refers to an end-to-end path planning algorithm that optimizes the strategy directly. It takes sensor information as input and driving speed and yaw angle as outputs. The path planning algorithm can reach the predetermined target point while avoiding large-scale static obstacles, such as valley walls in the simulated underwater canyon environment, as well as sudden small-scale dynamic obstacles, such as marine life and other vehicles. In addition, this research aims at the multi-objective structure of the obstacle avoidance of path planning, modularized reward function design, and combined artificial potential field method to set continuous rewards. This research also proposes a new algorithm called deep SumTree-deterministic policy gradient algorithm (SumTree-DDPG), which improves the random storage and extraction strategy of DDPG algorithm experience samples. According to the importance of the experience samples, the samples are classified and stored in combination with the SumTree structure, high-quality samples are extracted continuously, and SumTree-DDPG algorithm finally improves the speed of the convergence model. Finally, this research uses Python language to write an underwater canyon simulation environment and builds a deep reinforcement learning simulation platform on a high-performance computer to conduct simulation learning training for AUV. Data simulation verified that the proposed path planning method can guide the under-actuated underwater robot to navigate to the target without colliding with any obstacles. In comparison with the DDPG algorithm, the stability, training’s total reward, and robustness of the improved Sumtree-DDPG algorithm planner in this study are better.

Optimal Collision-Free Path Planning for an Autonomous Multi-Wheeled Combat Vehicle

2017 ◽  
Author(s):  
Amr Mohamed ◽  
Moustafa El-Gindy ◽  
Jing Ren ◽  
Haoxiang Lang
Keyword(s):  
Path Planning ◽  
Potential Field ◽  
Vehicle Dynamics ◽  
Autonomous Vehicle ◽  
Optimal Path ◽  
Vehicle Model ◽  
Optimal Path Planning ◽  
Combat Vehicle ◽  
Planning Algorithm ◽  
Path Planning Algorithm

This paper presents an optimal collision-free path planning algorithm of an autonomous multi-wheeled combat vehicle using optimal control theory and artificial potential field function (APF). The optimal path of the autonomous vehicle between a given starting and goal points is generated by an optimal path planning algorithm. The cost function of the path planning is solved together with vehicle dynamics equations to satisfy the vehicle dynamics constraints and the boundary conditions. For this purpose, a simplified four-axle bicycle model of the actual vehicle considering the vehicle body lateral and yaw dynamics while neglecting roll dynamics is used. The obstacle avoidance technique is mathematically modeled based on the proposed sigmoid function as the artificial potential field method. This potential function is assigned to each obstacle as a repulsive potential field. The inclusion of these potential fields results in a new APF which controls the steering angle of the autonomous vehicle to reach the goal point. A full nonlinear multi-wheeled combat vehicle model in TruckSim software is used for validation. This is done by importing the generated optimal path data from the introduced optimal path planning MATLAB algorithm and comparing lateral acceleration, yaw rate and curvature at different speeds (9 km/h, 28 km/h) for both simplified and TruckSim vehicle model. The simulation results show that the obtained optimal path for the autonomous multi-wheeled combat vehicle satisfies all vehicle dynamics constraints and successfully validated with TruckSim vehicle model.

scholarly journals A Bi-Level Path Planning Algorithm for Multi-AGV Routing Problem

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1351
Author(s):  
Zhiheng Yuan ◽  
Zhengmao Yang ◽  
Lingling Lv ◽  
Yanjun Shi
Keyword(s):  
Path Planning ◽  
Random Trees ◽  
Dijkstra Algorithm ◽  
A Algorithm ◽  
Routing Problem ◽  
Agv Routing ◽  
Planning Algorithm ◽  
Local Grid ◽  
Local Path ◽  
Path Planning Algorithm

Avoiding the multi-automated guided vehicle (AGV) path conflicts is of importance for the efficiency of the AGV system, and we propose a bi-level path planning algorithm to optimize the routing of multi-AGVs. In the first level, we propose an improved A* algorithm to plan the AGV global path in the global topology map, which aims to make the path shortest and reduce the AGV path conflicts as much as possible. In the second level, we present the dynamic rapidly-exploring random trees (RRT) algorithm with kinematic constraints to obtain the passable local path with collisions in the local grid map. Compared to the Dijkstra algorithm and classic A* algorithm, the simulation results showed that the proposed bi-level path planning algorithm performed well in terms of the search efficiency, significantly reducing the incidence of multiple AGV path conflicts.

scholarly journals NPQ-RRT ∗ : An Improved RRT ∗ Approach to Hybrid Path Planning

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Zihan Yu ◽  
Linying Xiang
Keyword(s):  
Path Planning ◽  
Optimal Path ◽  
Research Direction ◽  
Random Trees ◽  
Target Point ◽  
Evaluation Function ◽  
Local Planning ◽  
Planning Algorithm ◽  
Window Approach ◽  
Path Planning Algorithm

In recent years, the path planning of robot has been a hot research direction, and multirobot formation has practical application prospect in our life. This article proposes a hybrid path planning algorithm applied to robot formation. The improved Rapidly Exploring Random Trees algorithm PQ-RRT ∗ with new distance evaluation function is used as a global planning algorithm to generate the initial global path. The determined parent nodes and child nodes are used as the starting points and target points of the local planning algorithm, respectively. The dynamic window approach is used as the local planning algorithm to avoid dynamic obstacles. At the same time, the algorithm restricts the movement of robots inside the formation to avoid internal collisions. The local optimal path is selected by the evaluation function containing the possibility of formation collision. Therefore, multiple mobile robots can quickly and safely reach the global target point in a complex environment with dynamic and static obstacles through the hybrid path planning algorithm. Numerical simulations are given to verify the effectiveness and superiority of the proposed hybrid path planning algorithm.

AN EFFICIENT GRAPH THEORY-BASED ALGORITHM FOR SHIP TRAJECTORY PLANNING

2021 ◽  
Vol 161 (A2) ◽  
Author(s):  
A Lazarowska
Keyword(s):  
Graph Theory ◽  
Path Planning ◽  
Motion Control ◽  
Dynamic Environment ◽  
Computational Time ◽  
Optimization Approach ◽  
Application Area ◽  
A Algorithm ◽  
Planning Algorithm ◽  
Path Planning Algorithm

The research presented in this paper is dedicated to the development of a path planning algorithm for a moving object in a dynamic environment. The marine environment constitutes the application area. A graph theory-based path planning method for ships is introduced and supported by the results of simulation tests and comparative analysis with a heuristic Ant Colony Optimization approach. The method defines the environment with the use of a visibility graph and uses the A* algorithm to find the shortest, collision-free path. The main contribution is the development of an effective graph theory-based algorithm for path planning in an environment with static and dynamic obstacles. The computational time does not exceed a few seconds. Obtained results allow to state that the method is suitable for use in an intelligent motion control system for ships.

Sign in / Sign up

Export Citation Format

Share Document