000097491 001__ 97491
000097491 005__ 20180127202418.0
000097491 037__ $$aCONF
000097491 245__ $$aMotion Detection and Path Planning in Dynamic Environments
000097491 260__ $$c2003
000097491 269__ $$a2003
000097491 336__ $$aConference Papers
000097491 520__ $$aMotion detection from mobile platforms is a challenging task. It requires precise position information, which is difficult in cluttered dynamic environments. We combine motion detection and position estimation using Expectation Maximization.  To reduce the computational time of this iterative approach, we segment the scan into feature elements which are then compared against an a-priori map. The motion detection is tested on real world data from a mass exhibition, showing correct classification.  As one application of this information, we present a path planning approach with a unified probabilistic formalism for dynamic and static elements incorporating different levels of knowledge. The resulting probabilistic navigation function derives from co-occurrence probabilities and is currently computed using grids. 
000097491 6531_ $$ahuman-robot interaction
000097491 6531_ $$amotion planning
000097491 6531_ $$aexpectation maximization
000097491 6531_ $$aHuman-Robot Interaction
000097491 700__ $$0240971$$aJensen, B.$$g113529
000097491 700__ $$0240970$$aPhilippsen, R.$$g103090
000097491 700__ $$0240969$$aSiegwart, R.$$g112562
000097491 7112_ $$aNone
000097491 909C0 $$0252186$$pLSA
000097491 909CO $$ooai:infoscience.tind.io:97491$$pconf
000097491 937__ $$aLSA-CONF-2003-003
000097491 970__ $$a489/LSA
000097491 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000097491 980__ $$aCONF