A lego robot for experimental benchmarking of robust exploration algorithms
A. Serri
- Year
- 2004
- Citations
- 4
Abstract
A very simple autonomous robot based on the Lego programmable brick (RCX) is proposed to test the performances of robust exploration algorithms. The robot must explore an unknown area with arbitrary boundary detected by a unique light-sensor and has to find a little target by travelling within the search area. The control algorithm must keep the robot within the area and adjust the trajectory after each collision to the boundary. The mechatronic design may be optimized but attention is focused on the robustness of the control strategy. Experimental benchmarking is presented for fixed and random turning. Programming details are discussed to further test other different algorithms.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991