Robert Cupec

Experiments in vision-guided biped walking

Goal-oriented vision-guided biped locomotion requires a high degree of coordination between perception and walking. How to establish this coordination remains a fundamental and rarely studied problem in legged robotics. Some of our investigations into this field are outlined in this article by presenting recent results in vision-guided biped locomotion. The guidance and control approaches developed are experimentally validated on the biped robot BARt-UH. It is shown how perception techniques are employed in closed-loop for step sequence adaptation and locomotion control of a walking machine.

Experiments in Vision-Guided Robot Walking in a Structured Scenario

Locomotion of a biped robot in a scenario with obstacles requires a high degree of coordination between perception and walking. This article presents key ideas of a vision-based strategy for guidance of walking robots in structured scenarios. Computer vision techniques are employed for reactive adaptation of step sequences allowing a robot to step over or upon or walk around obstacles. A highly accurate visual feedback is achieved by a combination of line-based scene analysis and real-time feature tracking. The proposed vision-based approach was evaluated by experiments with a real humanoid robot. I. INTRODUCTION

Machine vision based control of the ball and beam

The use of vision systems in motion control applications puts hard real-time constrains on image processing. However, constantly increasing performances and decreasing prices of vision hardware make vision measuring systems concurrent to other measuring systems in these applications, where vision systems can be used to precisely measure number of variables such as length, angle, position, orientation, etc. The main advantage of a vision measuring system in these applications is its noncontact measurement principle, which is important in cases when it is difficult to implement contact measurements. Apart from real-time constraints, the biggest problem that limits the applications of a machine vision system is its robustness to the noise present in the image as well as to the scene disturbances caused by background and foreground objects and to the nonideal illumination conditions. A simple, computationally efficient and robust machine vision measuring system is described, which is suitable for real-time angle measurement. Its behavior is experimentally tested on a ball and beam benchmark process, where high quality measurement of the beam angle is achieved even in nonideal lighting condition and also when no white background is used. The implemented vision system is used for feedback control of the ball and beam.

Three points method for searching the best least absolute deviations plane

In this paper a new method for estimation of optimal parameters of a best least absolute deviations plane is proposed, which is based on the fact that there always exists a best least absolute deviations plane passing through at least three different data points. The proposed method leads to a solution in finitely many steps. Moreover, a modification of the aforementioned method is proposed that is especially adjusted to the case of a large number of data and the need to estimate parameters in real time. Both methods are illustrated by numerical examples on the basis of simulated data and by one practical example from the field of robotics.

Place recognition based on matching of planar surfaces and line segments

This paper considers the potential of using three-dimensional (3D) planar surfaces and line segments detected in depth images for place recognition. A place recognition method is presented that is based on matching sets of surface and line features extracted from depth images provided by a 3D camera to features of the same type contained in a previously created environment model. The considered environment model consists of a set of local models representing particular locations in the modeled environment. Each local model consists of planar surface segments and line segments representing the edges of objects in the environment. The presented method is designed for indoor and urban environments. A computationally efficient pose hypothesis generation approach is proposed that ranks the features according to their potential contribution to the pose information, thereby reducing the time needed for obtaining accurate pose estimation. Furthermore, a robust probabilistic method for selecting the best pose hypothesis is proposed that allows matching of partially overlapping point clouds with gross outliers. The proposed approach is experimentally tested on a benchmark dataset containing depth images acquired in the indoor environment with changes in lighting conditions and the presence of moving objects. A comparison of the proposed method to FAB-MAP and DLoopDetector is reported.

An approach to environment modelling for biped walking robots

In this work, a novel environment representation method which facilitates path planning for biped walking robots is presented. The robots environment is represented by a 2D map consisting of free regions, obstacle regions and feasible paths over the obstacle regions. In the free regions, standard path planning methods can be applied to plan paths around large obstacles. These paths are combined with paths over obstacle regions which include stepping over small obstacles as well as changing the walking level. Search for feasible paths rests upon the approximation of the robot by a set of hulls whose shapes allow efficient checking of the path feasibility. By considering only a restricted set of paths over obstacles, some generality is traded against better time performance.

Step sequence planning for a biped robot by means of a cylindrical shape model and a high-resolution 2.5D map

A novel step sequence planning (SSP) method for biped-walking robots is presented. The method adopts a free space representation custom-designed for efficient biped robot motion planning. The method rests upon the approximation of the robot shape by a set of 3D cylindrical solids. This feature allows efficient determination of feasible paths in a 2.5D map, comprising stepping over obstacles and stair climbing. A SSP algorithm based on A^*-search is proposed which uses the advantages of the aforementioned environment representation. The efficiency of the proposed approach is evaluated by a series of simulations performed for eight walking scenarios.

Crop row detection by global energy minimization

This paper presents a new efficient method for crop row detection which uses a dynamic programming technique to combine image evidence and prior knowledge about the geometric structure which is searched for in the image. The proposed approach consists of three steps, i.e., (i) vegetation detection, (ii) detection of regular patterns, and (iii) determining an optimal crop model. The method is capable of accurately detecting both straight and curved crop rows. The proposed approach is experimentally evaluated on a set of 281 real-world camera images of crops of maize, celery, potato, onion, sunflower and soybean. The proposed approach is compared to two Hough transform based methods and one method based on linear regression. The methods are compared using a novel approach for evaluation of crop row detection methods. The experiments performed demonstrate that the proposed method outperforms the other three considered methods in straight crop row detection and that it is capable of detecting curved crop rows accurately.

Practical Experience with Vision-guided Biped Walking

This paper presents key ideas of our approach to perception-based biped robot walking. Computer vision techniques are employed for reactive adaptation of the stepsequence taking into account the restrictions imposed by dynamics and mechanical construction of the walking machine. The vision-based approach and guidance system were evaluated by experiments with the biped robot BARt-UH.

Fast planar surface 3D SLAM using LIDAR

In this paper we propose a fast 3D pose based SLAM system that estimates a vehicle’s trajectory by registering sets of planar surface segments, extracted from 360∘360∘ field of view (FOV) point clouds provided by a 3D LIDAR. Full FOV and planar representation of the map gives the proposed SLAM system the capability to map large-scale environments while maintaining fast execution time. For efficient point cloud processing we apply image-based techniques to project it to three two-dimensional images. The SLAM backend is based on Exactly Sparse Delayed State Filter as a non-iterative way of updating the pose graph and exploiting sparsity of the SLAM information matrix. Finally, our SLAM system enables reconstruction of the global map by merging the local planar surface segments in a highly efficient way. The proposed point cloud segmentation and registration method was tested and compared with the several state-of-the-art methods on two publicly available datasets. Complete SLAM system was also tested in one indoor and one outdoor experiment. The indoor experiment was conducted using a research mobile robot Husky A200 to map our university building and the outdoor experiment was performed on the publicly available dataset provided by the Ford Motor Company, in which a car equipped with a 3D LIDAR was driven in the downtown Dearborn Michigan.