Safe Robotic Manipulation to Extract Objects from Piles:
From 3D Perception to Object Selection
av
Rasoul Mojtahedzadeh
Akademisk avhandling
Avhandling för teknologi doktorsexamen i computer science, som kommer att försvaras offentligt
Friday den 23 September 2016 kl. 13.15, Hörsal T, Teknikhuset , Örebro universitet
Opponent: Prof. Dr. Patric Jensfelt Royal Institute of Technology (KTH)
Sweden
Örebro universitet
Institutionen för naturvetenskap och teknik 701 82 Örebro
Abstract
Rasoul Mojtahedzadeh (2016): Safe Robotic Manipulation to Extract
Objects from Piles: From 3D Perception to Object Selection. Örebro Studies in Technology 71.
Keywords: Object Selection; Object Pose Refinement; Gravitational Sup-port Relation; Inter-penetration Resolving; 3D Ranging Sensor Evaluation. Rasoul Mojtahedzadeh, School of Science and Technology
Örebro University, SE-701 82 Örebro, Sweden
Abstract
Rasoul Mojtahedzadeh (2016): Safe Robotic Manipulation to Extract
Objects from Piles: From 3D Perception to Object Selection. Örebro Studies in Technology 71.
Keywords: Object Selection; Object Pose Refinement; Gravitational Sup-port Relation; Inter-penetration Resolving; 3D Ranging Sensor Evaluation. Rasoul Mojtahedzadeh, School of Science and Technology
Örebro University, SE-701 82 Örebro, Sweden
Abstract
This thesis is concerned with the task of autonomous selection of objects to re-move (unload) them from a pile in robotic manipulation systems. Applications such as the automation of logistics processes and service robots require an abil-ity to autonomously manipulate objects in the environment. A collapse of a pile of objects due to an inappropriate choice of the object to be removed from the pile cannot be afforded for an autonomous robotic manipulation system. This dissertation presents an in-depth analysis of the problem and proposes methods and algorithms to empower robotic manipulation systems to select a safe object from a pile elaborately and autonomously.
The contributions presented in this thesis are three-fold. First, a set of al-gorithms is proposed for extracting a minimal set of high level symbolic rela-tions, namely, gravitational act and support relarela-tions, of physical interactions between objects composing a pile. The symbolic relations, extracted by a geo-metrical reasoning method and a static equilibrium analysis can be readily used by AI paradigms to analyze the stability of a pile and reason about the safest set of objects to be removed. Considering the problem of undetected objects and the uncertainty in the estimated poses as they exist in realistic perception systems, a probabilistic approach is proposed to extract the support relations and to make a probabilistic decision about the set of safest objects using no-tions from machine learning and decision theory. Second, an efficient search based algorithm is proposed in an internal representation to automatically re-solve the inter-penetrations between the shapes of objects due to errors in the poses estimated by an existing object detection module. Refining the poses by resolving the inter-penetrations results in a geometrically consistent model of the environment, and was found to reduce the overall pose error of the objects. This dissertation presents the concept of minimum translation search for object pose refinement and discusses a discrete search paradigm based on the concept of depth of penetration between two polyhedrons. Third, an application centric evaluation of ranging sensors for selecting a set of appropriate sensors for the task of object detection in the design process of a real-world robotics manip-ulation system is presented. The performance of the proposed algorithms are tested on data sets generated in simulation and from real-world scenarios.
Keywords: Object Selection; Object Pose Refinement; Gravitational Support
Relation; Inter-penetration Resolving; 3D Ranging Sensor Evaluation.
i
Abstract
This thesis is concerned with the task of autonomous selection of objects to re-move (unload) them from a pile in robotic manipulation systems. Applications such as the automation of logistics processes and service robots require an abil-ity to autonomously manipulate objects in the environment. A collapse of a pile of objects due to an inappropriate choice of the object to be removed from the pile cannot be afforded for an autonomous robotic manipulation system. This dissertation presents an in-depth analysis of the problem and proposes methods and algorithms to empower robotic manipulation systems to select a safe object from a pile elaborately and autonomously.
The contributions presented in this thesis are three-fold. First, a set of al-gorithms is proposed for extracting a minimal set of high level symbolic rela-tions, namely, gravitational act and support relarela-tions, of physical interactions between objects composing a pile. The symbolic relations, extracted by a geo-metrical reasoning method and a static equilibrium analysis can be readily used by AI paradigms to analyze the stability of a pile and reason about the safest set of objects to be removed. Considering the problem of undetected objects and the uncertainty in the estimated poses as they exist in realistic perception systems, a probabilistic approach is proposed to extract the support relations and to make a probabilistic decision about the set of safest objects using no-tions from machine learning and decision theory. Second, an efficient search based algorithm is proposed in an internal representation to automatically re-solve the inter-penetrations between the shapes of objects due to errors in the poses estimated by an existing object detection module. Refining the poses by resolving the inter-penetrations results in a geometrically consistent model of the environment, and was found to reduce the overall pose error of the objects. This dissertation presents the concept of minimum translation search for object pose refinement and discusses a discrete search paradigm based on the concept of depth of penetration between two polyhedrons. Third, an application centric evaluation of ranging sensors for selecting a set of appropriate sensors for the task of object detection in the design process of a real-world robotics manip-ulation system is presented. The performance of the proposed algorithms are tested on data sets generated in simulation and from real-world scenarios.
Keywords: Object Selection; Object Pose Refinement; Gravitational Support
Relation; Inter-penetration Resolving; 3D Ranging Sensor Evaluation.
