Active Exploration Using Gaussian Random Fields and Gaussian Process Implicit Surfaces
Paper in proceedings, 2016

In this work we study the problem of exploring surfaces and building compact 3D representations of the environment surrounding a robot through active perception. We propose an online probabilistic framework that merges visual and tactile measurements using Gaussian Random Field and Gaussian Process Implicit Surfaces. The system investigates incomplete point clouds in order to find a small set of regions of interest which are then physically explored with a robotic arm equipped with tactile sensors. We show experimental results obtained using a PrimeSense camera, a Kinova Jaco2 robotic arm and Optoforce sensors on different scenarios. We then demostrate how to use the online framework for object detection and terrain classification.

Surface reconstruction


Three-dimensional displays

Robot sensing systems

Gaussian processes

Surface treatment


Sergio Caccamo

Royal Institute of Technology (KTH)

Yasemin Bekiroglu

Chalmers, Signals and Systems, Systems and control, Automatic Control

Carl Henrik Ek

University of Cambridge

Danica Kragic

Royal Institute of Technology (KTH)

EEE/RSJ International Conference on Intelligent Robots and Systems

2153-0866 (eISSN)

EEE/RSJ International Conference on Intelligent Robots and Systems
Daejeon, ,

Subject Categories

Other Computer and Information Science


Computer Vision and Robotics (Autonomous Systems)

More information


9/2/2020 1