Optimal path planning refers to find the collision free, shortest, and smooth route between start and goal positions. This task is essential in many robotic applications such as autonomous car, surveillance operations, agricultural robots, planetary and space exploration missions. Rapidly-exploring Random Tree Star (RRT*) is a renowned sampling based planning approach. It has gained immense popularity due to its support for high dimensional complex problems. A significant body of research has addressed the problem of optimal path planning for mobile robots using RRT* based approaches. However, no updated survey on RRT* based approaches is available. Considering the rapid pace of development in this field, this paper presents a comprehensive review of RRT* based path planning approaches. Current issues relevant to noticeable advancements in the field are investigated and whole discussion is concluded with challenges and future research directions.

/pdf/optimal-path-planning-using-rrt-based-approaches-a-survey-2uhc2blryh.pdf

Optimal Path Planning using RRT* based Approaches: A Survey and Future Directions

In recent years, multi-classifier learning is of significant interest in industrial and economic fields. Moreover, neural network is a popular approach in multi-classifier learning. However, the accuracies of neural networks are often limited by their loss functions. For this reason, we design a novel cross entropy loss function, named MPCE, which based on the maximum probability in predictive results. In this paper, we first analyze the difference of gradients between MPCE and the cross entropy loss function. Then, we propose the gradient update algorithm based on MPCE. In the experimental part of this paper, we utilize four groups of experiments to verify the performance of the proposed algorithm on six public datasets. The first group of experimental results show that the proposed algorithm converge faster than the algorithms based on other loss functions. Moreover, the results of the second group show that the proposed algorithm obtains the highest training and test accuracy on the six datasets, and the proposed algorithm perform better than others when class number changing on the sensor dataset. Furthermore, we use the model of convolutional neural network to implement the compared methods on the mnist dataset in the fourth group of experiments. The results show that the proposed algorithm has the highest accuracy among all executed methods.

MPCE: A Maximum Probability Based Cross Entropy Loss Function for Neural Network Classification

A survey of welding robot intelligent path optimization

Motion planning is a fundamental problem in autonomous robotics that requires finding a path to a specified goal that avoids obstacles and takes into account a robot's limitations and constraints. It is often desirable for this path to also optimize a cost function, such as path length. 
Formal path-quality guarantees for continuously valued search spaces are an active area of research interest. Recent results have proven that some sampling-based planning methods probabilistically converge toward the optimal solution as computational effort approaches infinity. This survey summarizes the assumptions behind these popular asymptotically optimal techniques and provides an introduction to the significant ongoing research on this topic.

Asymptotically Optimal Sampling-Based Motion Planning Methods

This paper presents a cost-effective motion-planning method for robots operating in complex and realistic environments. While sampling-based path-planning algorithms, such as a rapidly exploring random tree (RRT) and its variants, have been highly effective for general path-planning problems, it is still difficult to find the minimum cost path in a complex space efficiently since RRT-based algorithms extend a search tree locally, requiring a large number of samples before finding a good solution. This paper presents an efficient nonmyopic path-planning algorithm by combining RRT* and a stochastic optimization method, called cross entropy. The proposed method constructs two RRT trees: The first tree is a standard RRT* tree, which is used to determine the nearest node in the tree to be extended to a randomly chosen point, and the second tree contains the first tree with additional long extensions. By maintaining two separate trees, we can grow the search tree nonmyopically to improve the efficiency of the algorithm while ensuring the asymptotic optimality of RRT*. From an extensive set of simulations and experiments using mobile and humanoid robots, we demonstrate that the proposed method consistently finds low-cost paths faster than the existing algorithms.

Fast Sampling-Based Cost-Aware Path Planning With Nonmyopic Extensions Using Cross Entropy

This paper presents a method for planning a motion for a humanoid robot performing manipulation tasks in a high dimensional space such that the energy consumption of the robot is minimized. While sampling-based path planning algorithms, such as rapidly-exploring random tree (RRT) and its variants, have been highly effective for complex path planning problems, it is still difficult to find the minimum cost path in a high dimensional space since RRT-based algorithms extend a search tree locally, requiring a large number of samples to find a good solution. This paper presents an efficient nonmyopic motion planning algorithm for finding a minimum cost path by combining RRT∗ and cross entropy (CE). The proposed method constructs two RRT trees: the first tree is a standard RRT tree which is used to determine the nearest node in the tree to a randomly chosen point and the second tree contains the first tree with additional long extensions. By maintaining two separate trees, we can grow the search tree non-myopically to improve efficiency while ensuring the asymptotic optimality of RRT∗. We first identify and demonstrate the limitation of RRT∗ when it is applied to energy-efficient path planning in a high dimensional space. Results from experiments show that the proposed method consistently achieves the lowest energy consumption against other algorithms.

Energy-efficient high-dimensional motion planning for humanoids using stochastic optimization

This paper presents a humanoid robot playing a game called Alkagi. Alkagi is a game in which one shoots a Go stone to hit an opponent's stone with the goal of making the opponent's stone fall out of the Go board. When the position of a Go stone is obtained using a vision system, the robot places its hand at the desired position and orientation in order to shoot the stone to a desired direction. The proposed method is demonstrated using an Aldebaran NAO humanoid robot.

Playing Alkagi with a Humanoid Robot

This paper considers a human motion evaluation system (HMES) using two smartphones and a server. An HMES user wears retro-reflective markers on her 13 joints and follows a motion demonstrated by an expert. Two smartphones detect markers and transmit detected 2D marker positions to the server which reconstructs 3D motion of the user. The server performs a spatio-temporal alignment between the motion of the user and the motion demonstrated by an expert to evaluate the quality of the user's motion. The proposed system is applicable for physical therapy and sports education as an inexpensive alternative. We demonstrate that the 3D motion of the HMES user can be reconstructed reliably in real-time and successfully aligned with the reference motion of an expert, providing real-time feedback to the user.

http://cpslab.snu.ac.kr/publications/papers/2014_CPSNA_SmartPTA.pdf

Joonsig Gong

Papers

Fast Sampling-Based Cost-Aware Path Planning With Nonmyopic Extensions Using Cross Entropy

Energy-efficient high-dimensional motion planning for humanoids using stochastic optimization

Playing Alkagi with a Humanoid Robot

SmartPTA: A Smartphone-Based Human Motion Evaluation System