arXiv subjects

Filip Marić

Publications and source records attributed to Filip Marić.

23 records · Page 2Linked to original sources

arXiv2018

Self-Calibration of Mobile Manipulator Kinematic and Sensor Extrinsic Parameters Through Contact-Based Interaction

We present a novel approach for mobile manipulator self-calibration using contact information. Our method, based on point cloud registration, is applied to estimate the extrinsic transform between a fixed vision sensor mounted on a mobile base and an end effector. Beyond sensor calibration, we demonstrate that the method can be extended to include manipulator kinematic model parameters, which involves a non-rigid registration process. Our procedure uses on-board sensing exclusively and does not rely on any external measurement devices, fiducial markers, or calibration rigs. Further, it is fully automatic in the general case. We experimentally validate the proposed method on a custom mobile manipulator platform, and demonstrate centimetre-level post-calibration accuracy in positioning of the end effector using visual guidance only. We also discuss the stability properties of the registration algorithm, in order to determine the conditions under which calibration is possible.

cs.RO↗

arXiv2018

Manipulability Maximization Using Continuous-Time Gaussian Processes

A significant challenge in motion planning is to avoid being in or near \emph{singular configurations} (\textit{singularities}), that is, joint configurations that result in the loss of the ability to move in certain directions in task space. A robotic system's capacity for motion is reduced even in regions that are in close proximity to (i.e., neighbouring) a singularity. In this work we examine singularity avoidance in a motion planning context, finding trajectories which minimize proximity to singular regions, subject to constraints. We define a manipulability-based likelihood associated with singularity avoidance over a continuous trajectory representation, which we then maximize using a \textit{maximum a posteriori} (MAP) estimator. Viewing the MAP problem as inference on a factor graph, we use gradient information from interpolated states to maximize the trajectory's overall manipulability. Both qualitative and quantitative analyses of experimental data show increases in manipulability that result in smooth trajectories with visibly more dexterous arm configurations.

cs.RO↗

arXiv2015

Short Portfolio Training for CSP Solving

Many different approaches for solving Constraint Satisfaction Problems (CSPs) and related Constraint Optimization Problems (COPs) exist. However, there is no single solver (nor approach) that performs well on all classes of problems and many portfolio approaches for selecting a suitable solver based on simple syntactic features of the input CSP instance have been developed. In this paper we first present a simple portfolio method for CSP based on k-nearest neighbors method. Then, we propose a new way of using portfolio systems --- training them shortly in the exploitation time, specifically for the set of instances to be solved and using them on that set. Thorough evaluation has been performed and has shown that the approach yields good results. We evaluated several machine learning techniques for our portfolio. Due to its simplicity and efficiency, the selected k-nearest neighbors method is especially suited for our short training approach and it also yields the best results among the tested methods. We also confirm that our approach yields good results on SAT domain.

cs.AI↗

arXiv2012

Formalizing Frankl's Conjecture: FC-families

The Frankl's conjecture, formulated in 1979. and still open, states that in every family of sets closed for unions there is an element contained in at least half of the sets. FC-families are families for which it is proved that every union-closed family containing them satisfies the Frankl's condition (e.g., in every union-closed family that contains a one-element set {a}, the element a is contained in at least half of the sets, so families of the form {a} are the simplest FC-families). FC-families play an important role in attacking the Frankl's conjecture, since they enable significant search space pruning. We present a formalization of the computer assisted approach for proving that a family is an FC-family. Proof-by-computation paradigm is used and the proof assistant Isabelle/HOL is used both to check mathematical content, and to perform (verified) combinatorial searches on which the proofs rely. FC-families known in the literature are confirmed, and a new FC-family is discovered.

cs.DM↗

arXiv2012

Formalization and Implementation of Algebraic Methods in Geometry

We describe our ongoing project of formalization of algebraic methods for geometry theorem proving (Wu's method and the Groebner bases method), their implementation and integration in educational tools. The project includes formal verification of the algebraic methods within Isabelle/HOL proof assistant and development of a new, open-source Java implementation of the algebraic methods. The project should fill-in some gaps still existing in this area (e.g., the lack of formal links between algebraic methods and synthetic geometry and the lack of self-contained implementations of algebraic methods suitable for integration with dynamic geometry tools) and should enable new applications of theorem proving in education.

cs.SC↗