000131013 001__ 131013
000131013 005__ 20181126150232.0
000131013 037__ $$aBOOK_CHAP
000131013 245__ $$aActive Vision for Goal-Oriented Humanoid Robot Walking
000131013 269__ $$a2009
000131013 260__ $$bSpringer-Verlag$$c2009
000131013 336__ $$aBook Chapters
000131013 490__ $$aLNCS$$v5436
000131013 520__ $$aComplex visual tasks may be tackled with remarkably simple neural architectures generated by a co-evolutionary process of active vision and feature selection. This hypothesis has recently been tested in several robotic applications such as shape discrimination, car driving, indoor/outdoor navigation of a wheeled robot. Here we describe an experiment where this hypothesis is further examined in goal-oriented humanoid bipedal walking task. Hoap-2 humanoid robot equipped with a primitive vision system on its head is evolved while freely interacting with its environment. Unlike wheeled robots, bipedal walking robots are exposed to largely perturbed visual input caused by their own walking dynamics. We show that evolved robots are capable of coping with the dynamics and of accomplishing the task by means of active, efficient camera control.
000131013 6531_ $$aEvolutionary Robotics
000131013 700__ $$0241094$$aSuzuki, Mototaka$$g157788
000131013 700__ $$aGritti, Tommaso
000131013 700__ $$0240742$$aFloreano, Dario$$g111729
000131013 720_1 $$aSendhoff, Bernard$$eed.
000131013 720_1 $$aKoerner, Edgar$$eed.
000131013 720_1 $$aSporns, Olaf$$eed.
000131013 720_1 $$aRitter, Helge$$eed.
000131013 720_1 $$aDoya, Kenji$$eed.
000131013 773__ $$q303-313$$tCreating Brain-Like Intelligence
000131013 8564_ $$s1471339$$uhttps://infoscience.epfl.ch/record/131013/files/Humanoid_CBLI2009.pdf$$zn/a
000131013 909C0 $$0252161$$pLIS$$xU10370
000131013 909CO $$ooai:infoscience.tind.io:131013$$pSTI$$pchapter$$qGLOBAL_SET
000131013 917Z8 $$x255330
000131013 937__ $$aLIS-CHAPTER-2009-001
000131013 973__ $$aEPFL$$sPUBLISHED
000131013 980__ $$aCHAPTER