Strategies for Multi-Modal Scene Exploration

Bohg, JeannetteKTH,Centrum för Autonoma System, CAS,Datorseende och robotik, CVAP (author)

QC 20110407
We propose a method for multi-modal scene exploration where initial object hypothesis formed by active visual segmentation are confirmed and augmented through haptic exploration with a robotic arm. We update the current belief about the state of the map with the detection results and predict yet unknown parts of the map with a Gaussian Process. We show that through the integration of different sensor modalities, we achieve a more complete scene model. We also show that the prediction of the scene structure leads to a valid scene representation even if the map is not fully traversed. Furthermore, we propose different exploration strategies and evaluate them both in simulation and on our robotic platform.

Johnson-Roberson, MatthewKTH,Centrum för Autonoma System, CAS,Datorseende och robotik, CVAP(Swepub:kth)u1f7vhtf (author)
Björkman, MårtenKTH,Centrum för Autonoma System, CAS,Datorseende och robotik, CVAP(Swepub:kth)u1cs4x4i (author)
Kragic, DanicaKTH,Centrum för Autonoma System, CAS,Datorseende och robotik, CVAP(Swepub:kth)u1ydsyln (author)
KTHCentrum för Autonoma System, CAS (creator_code:org_t)

In:IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010), s. 4509-45159781424466757

By the author/editor: Bohg, Jeannette; Johnson-Roberson ...; Björkman, Mårten; Kragic, Danica

About the subject

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.