The localization and autonomous navigation of robots in unknown environment is still a developing area. What is the best technique developed so far? What are the advantages and disadvantages of unsupervised learning technique for navigation?
This problem can be effectively addressed by fuzzy inference
system. The environment information and the position of
obstacles can be detected all by robot's sensors ( both regular and irregular). Suitable fuzzy variables could then be formed. FIS has proved to be very efficient. One recent paper on this aspect is:
Ran Zhao et all, Autonomous Navigation of a Mobile Robot in Unknown
Environment Based on Fuzzy Inference, Proceedings of 2015 International Automatic Control Conference (CACS), Yilan, Taiwan, Nov. 18-20,2015 available with IEEE Xplore.
Let have a look at SLAM (simultaneous localization and mapping) which the best in my opinion.
I think you can refer SLAM (Simultaneous Localization and Mapping) and it's various variants which are Visual-SLAM,EKF-SLAM,FAST-SLAM 1.0,FAST SLAM 2.0,GRAPH-SLAM,ORB-SLAM,MONO-SLAM,GRAPH-SLAM e.t.c.
For the basics start with EKF-SLAM.
Also you can refer PTAM(Parallel Tracking and Mapping).
You can get tutorials for SLAM online (one of the best being of Joan Sola on EKF SLAM) plus for basics refer book"Autonomous Mobile Robots" by Roland Siegwart.
Dr. Jayaram, thank you for the suggestion. Unfortunately, the technique presented in that paper can not overcome the famous problem of local minima, so I would not classify it as a very robust technique. Do you know of a robust technique for unsupervised learning?
Mr. Hoang and Mr. Sharma. Indeed SLAM is the best way for localization and mapping. I have been using it with a laser sensor. However, I would want to know of a robust navigation technique. Thanks.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Control Theory
- Control Systems