Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences - Archive ouverte HAL Access content directly
Conference Papers Year :

Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences

Abstract

We study perception in the scenario of an embodied agent equipped with first-person sensors and a continuous motor space with multiple degrees of freedom.We introduce a method for movable and immovable object detection that exploitsthe commutative properties of action sequences. Our method is based on playingan action sequence in two different orders from the same starting point, and testedon 3D realistic robotics setups.
Fichier principal
Vignette du fichier
12.pdf (1.27 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03123933 , version 1 (28-01-2021)

Identifiers

  • HAL Id : hal-03123933 , version 1

Cite

Hugo Caselles-Dupré, Michael Garcia Ortiz, David Filliat. Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences. NeurIPS 2020 Workshop on BabyMind, Dec 2020, Vancouver / Virtual, Canada. ⟨hal-03123933⟩
25 View
66 Download

Share

Gmail Facebook Twitter LinkedIn More