Robust path planning for flexible needle insertion using Markov decision processes

2018 ◽  
Vol 13 (9) ◽  
pp. 1439-1451 ◽  
Author(s):  
Xiaoyu Tan ◽  
Pengqian Yu ◽  
Kah-Bin Lim ◽  
Chee-Kong Chui
Keyword(s):  
Path Planning ◽  
Markov Decision Processes ◽  
Needle Insertion ◽  
Decision Processes ◽  
Markov Decision

scholarly journals Robot Motion Planning in an Unknown Environment with Danger Space

Electronics ◽  
2019 ◽  
Vol 8 (2) ◽  
pp. 201 ◽  
Author(s):  
Hadi Jahanshahi ◽  
Mohsen Jafarzadeh ◽  
Naeimeh Najafizadeh Sari ◽  
Viet-Thanh Pham ◽  
Van Van Huynh ◽  
...  
Keyword(s):  
Path Planning ◽  
Motion Planning ◽  
Markov Decision Processes ◽  
Free Space ◽  
Optimal Path ◽  
Humanoid Robots ◽  
Decision Processes ◽  
Inference System ◽  
Unknown Environment ◽  
Markov Decision

This paper discusses the real-time optimal path planning of autonomous humanoid robots in unknown environments regarding the absence and presence of the danger space. The danger is defined as an environment which is not an obstacle nor free space and robot are permitted to cross when no free space options are available. In other words, the danger can be defined as the potentially risky areas of the map. For example, mud pits in a wooded area and greasy floor in a factory can be considered as a danger. The synthetic potential field, linguistic method, and Markov decision processes are methods which have been reviewed for path planning in a free-danger unknown environment. The modified Markov decision processes based on the Takagi–Sugeno fuzzy inference system is implemented to reach the target in the presence and absence of the danger space. In the proposed method, the reward function has been calculated without the exact estimation of the distance and shape of the obstacles. Unlike other existing path planning algorithms, the proposed methods can work with noisy data. Additionally, the entire motion planning procedure is fully autonomous. This feature makes the robot able to work in a real situation. The discussed methods ensure the collision avoidance and convergence to the target in an optimal and safe path. An Aldebaran humanoid robot, NAO H25, has been selected to verify the presented methods. The proposed methods require only vision data which can be obtained by only one camera. The experimental results demonstrate the efficiency of the proposed methods.

scholarly journals Humanoid robot path planning with fuzzy Markov decision processes

2016 ◽  
Vol 14 (5) ◽  
pp. 300-310 ◽  
Author(s):  
Mahdi Fakoor ◽  
Amirreza Kosari ◽  
Mohsen Jafarzadeh
Keyword(s):  
Path Planning ◽  
Markov Decision Processes ◽  
Humanoid Robot ◽  
Decision Processes ◽  
Robot Path Planning ◽  
Markov Decision ◽  
Robot Path

Extreme-point solutions in Markov decision processes

1983 ◽  
Vol 20 (04) ◽  
pp. 835-842
Author(s):  
David Assaf
Keyword(s):  
Convex Function ◽  
Extreme Point ◽  
Markov Decision Processes ◽  
Convex Functions ◽  
Sufficient Conditions ◽  
Decision Processes ◽  
Markov Decision ◽  
Full Solution

The paper presents sufficient conditions for certain functions to be convex. Functions of this type often appear in Markov decision processes, where their maximum is the solution of the problem. Since a convex function takes its maximum at an extreme point, the conditions may greatly simplify a problem. In some cases a full solution may be obtained after the reduction is made. Some illustrative examples are discussed.

Sign in / Sign up

Export Citation Format

Share Document