Applying probability navigation function in dynamic uncertain environments

详细信息    查看全文

• 作者：Shlomi Hacohen^a ; ^{hacohenshlomi@gmail.com}Author Vitae ; Shraga Shoval^b ; ^c ; ^{s.shoval@adfa.edu.au}Author Vitae ; Nir Shvalb^c ; ^{nirsh@ariel.ac.il}Author Vitae
• 关键词：Navigation-function ; Collision probability ; Obstacle avoidance
• 刊名：Robotics and Autonomous Systems
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：87
• 期：Complete
• 页码：237-246
• 全文大小：2314 K
• 卷排序：87

文摘

This paper introduces the notion of a Probability Navigation Function for motion planning. We start by estimating and predicting the Probability Density Function (PDF) of the obstacles’ locations. We then calculate the PNFs for a sequence of NfwdNfwd time steps. We then calculate the kkth incremental movement taking into consideration the k+1,…,k+Nfwdk+1,…,k+Nfwd predicted configurations. The algorithm is demonstrated on different scenarios and compared with the performance of a static PNF with that of a traditional NF.