Artur Sagitov

ROS-Based SLAM for a Gazebo-Simulated Mobile Robot in Image-Based 3D Model of Indoor Environment

Nowadays robot simulators have robust physics engines, high-quality graphics, and convenient interfaces, affording researchers to substitute physical systems with their simulation models in order to pre-estimate the performance of theoretical findings before applying them to real robots. This paper describes Gazebo simulation approach to simultaneous localization and mapping SLAM based on Robot Operating System ROS using PR2 robot. The ROS-based SLAM approach applies Rao-Blackwellized particle filters and laser data to locate the PR2 robot in unknown environment and build a map. The real room 3D model was obtained from camera shots and reconstructed with Autodesk 123D Catch and MeshLab software. The results demonstrate the fidelity of the simulated 3D room to the obtained from the robot laser system ROS-calculated map and the feasibility of ROS-based SLAM with a Gazebo-simulated mobile robot to its usage in camera-based 3D environment. This approach will be further extended to ROS-based robotic simulations in Gazebo with a Russian anthropomorphic robot AR-601M.

Comparing fiducial marker systems in the presence of occlusion

A fiducial marker system is a system of unique 2D (planar) marker, which is placed in an environment and automatically will be detected with a camera with a help of a corresponding detection algorithm. Application areas of these markers include industrial systems, augmented reality, robots navigation, human-robot interaction and others. Marker system designed for such different applications must be robust to such factors as view angles, occlusions, changing distances, etc. This paper compares three existing systems of markers: ARTag, AprilTag, and CALTag. As a benchmark, we use their reliability and detection rate in presence of occlusions of various types and intensity. The paper presents experimental comparison of these markers. The marker detection was performed with a simple inexpensive Web camera.

ARTag, AprilTag and CALTag Fiducial Marker Systems: Comparison in a Presence of Partial Marker Occlusion and Rotation.

© 2017 by SCITEPRESS Science and Technology Publications, Lda. All Rights Reserved. Fiducial marker systems consist of patterns that are placed in environment and are automatically detected with a camera using appropriate for the marker detection algorithm. Marker systems are useful for many modern visual applications such as augmented reality, robot navigation and collaboration, industrial and space robotics, and human-robot interaction. A variety of applications demands certain quality assurance for marker properties. Among the most common criteria are resistance to partial occlusion and rotation, sensitivity to lightning conditions, marker size, false positive and false negative rates. This paper compares three types of markers for their resistance to partial occlusion in various types of occlusion and resistance to normal, lateral, and longitudinal rotations. Intensive experimental comparison of tags is presented with analysis. Detection of markers was performed with a common Web camera. Based on our experimental results, we have selected a marker system, which should be preferred for real world applications when only simple inexpensive hardware is available and appearance of rotation and occlusion disturbances are expected in the environment. Our long term goal is to calibrate humanoid robot manipulators in real-world environment applying a pre-calibrated camera of the robot, while the presented in this paper results help selecting a most suitable marker system for further calibration procedures.

Towards Robot Fall Detection and Management for Russian Humanoid AR-601

While interacting in a human environment, a fall is the main threat to safety and successful operation of humanoid robots, and thus it is critical to explore ways to detect and manage an unavoidable fall of humanoid robots. Even assuming perfect bipedal walking strategies and algorithms, there exist several unexpected factors, which can threaten existing balance of a humanoid robot. These include such issues as power failure, robot component failures, communication disruptions and failures, sudden forces applied to the robot externally as well as internally generated exceed torques etc. As progress in a humanoid robotics continues, robots attain more autonomy and enter realistic human environments, they will inevitably encounter such factors more frequently. Undesirable fall might cause serious physical damage to a human user, to a robot and to surrounding environment. In this paper, we present a brief review of strategies that include algorithms for fall prediction, avoidance, and damage control of small-size and human-size humanoids, which will be further implemented for Russian humanoid robot AR-601.

Comparing Fiducial Markers Performance for a Task of a Humanoid Robot Self-calibration of Manipulators: A Pilot Experimental Study

This paper presents our pilot study of experiments automation with a real robot in order to compare performance of different fiducial marker systems, which could be used in automated camera calibration process. We used Russian humanoid robot AR-601M and automated it’s manipulators for performing joint rotations. This paper is an extension of our previous work on ARTag, AprilTag and CALTag marker comparison in laboratory settings with large-sized markers that had showed significant superiority of CALTag system over the competitors. This time the markers were scaled down and placed on AR-601M humanoid’s palms. We automated experiments of marker rotations, analyzed the results and compared them with the previously obtained results of manual experiments with large-sized markers. The new automated pilot experiments, which were performed both in pure laboratory conditions and pseudo field environments, demonstrated significant differences with previously obtained manual experimental results: AprilTag marker system demonstrated the best performance with a success rate of 97,3% in the pseudo field environment, while ARTag was the most successful in the laboratory conditions.

Arbitrary Trajectory Foot Planner for Bipedal Walking.

This paper presents a foot planner algorithm for bipedal walking along an arbitrary curve. It takes a parametrically defined desired path as an input and calculates feet positions and orientations at each step. Number of steps that are required to complete the path depends on a maximum step length and maximum foot rotation angle at each step. Provided with results of the foot planner, our walking engine successfully performs robot locomotion. Verification tests were executed with AR601M humanoid robot.