The May’s PGRs Research Presentations was held on Wed. 11th September, 2pm, Meeting Room, MC3108 (3rd floor).
This session we had the following presentations:
| Title: “Simultaneous Localisation and Dense Mapping“. | Title: “Cue-based Aggregation with a Mobile Robot Swarm using a Novel Fuzzy-based Method” | |
|
By: Farhad Bazyari |
By: Farshad Arvin |
|
| Abstract:Simultaneous Localisation and Dense Mapping. Starting with introducing SLAM systems, then talking about dense mapping techniques and some of my work on this subject and autonomous exploration. Time permitting, I will very briefly mention ‘factor graphs’ as well. In addition to gaining massive popularity in SLAM community, factor graphs are extremely flexible structures that can be used in a wide field of research. So hopefully people whose research field are far from mine will also get something out of the talk. | Abstract: In this work, we proposed a novel fuzzy-based method for cue-based aggregation with a mobile robot swarm. Our method is based on the state-of-the-art BEECLUST method that is inspired from thermotactic behavior of honeybee swarms. We assumed to have a sound source as the cue and designed a fuzzy-based controller with four microphone inputs and the output as the predicted direction of the sound source. We used 2 standard triangular membership functions, 12 fuzzy rules (3 for each microphone input) and centroid defuzzification method. We also proposed different variants of BEECLUST method, namely Naive and Vector-averaging methods. We compared the performance of our fuzzy-based method with BEECLUST and these methods using both Player/Stage simulator and custom-built autonomous robots (AMiR). Experiments were performed in two different settings: static and dynamic arenas. In all the experiments, the fuzzy-based method performed better in terms of aggregation time. | |
The Q/A was followed by a brief catch-up meeting.