Image-Based Humanoid Robot Pose Recognition System

This study utilized the Robot Operating System (ROS) to simulate various poses of humanoid robot. The distributed ROS architectures efficiently communicate with each other point to make sure the correct sequential procedures and execute full information exchange through the peer to peer topology. Humanoid robot software designed in Linux-based ROS environment to integrate the software and hardware system plant through ROS. The advanced Gazebo presents the cyber-physical behavior of humanoid robot in the reality experiments.

While recent advances in approaches for control of humanoid robot systems show highly promising results, consideration of fully integrated humanoid systems for solving complex tasks such as disaster response has only gained focus recently. In this work, a software framework for humanoid disaster response robots is introduced. It provides newcomers as well as experienced researchers in humanoid robotics a comprehensive system comprising open source packages for locomotion, manipulation, perception, world modeling, behavior control, and operator interaction. The system uses the Robot Operating System (ROS) as a middleware, which has emerged as a de-facto standard in robotics research in recent years. The described architecture and components allow for flexible interaction between operator(s) and robot from teleoperation to remotely supervised autonomous operation while considering bandwidth constraints. The components are self-­contained and can be used either in combination with others or standalone. They have been developed and evaluated during participation in the DARPA Robotics Challenge and their use for different tasks and parts of this competition are described.

The spread adoption of humanoid social robots in different application fields is growing the interest of hackers who could violate the privacy of people, or—even worse—threaten humans’ life from physical and emotional/social point of views. Different vectors of attack exist, which are more easily exploitable if physical access to the target robot is available. This is very likely for humanoids that typically reside in untrusted environments where physically access to the robot is allowed and expected, thus permitting anyone to exploit the Linux kernel vulnerability (e.g., through the insertion of a USB pen drive) with the objective of tampering sensitive data. The Robot Operating System (ROS) is at the core of humanoids. Thus, it is crucial for their security. The most-recent solutions introduced in ROS2, SROS, and H-ROS are not sufficient for facing powerful adversaries. In this paper, we first identify the uncovered ROS weaknesses, which are particularly worrying in the case of humanoids. Then, we present our patched ROS solution called Trusted-ROS (TROS) leveraging hardware-assisted trusted computing to shield data managed by ROS, which otherwise would reside in robot’s memory unencrypted. The design of TROS is reported, together with a prototype implementation using a simulated version of the NAO humanoid secured through an Intel SGX hardware. Finally, we evaluated the proposed solution from both security and performance perspectives in order to demonstrate the practicability of our approach.

A robust road markings detection algorithm is a fundamental component of intelligent vehicles' autonomous navigation in urban environment. This paper presents an algorithm for detecting road markings including zebra crossings, stop lines and lane markings to provide road information for intelligent vehicles. First, to eliminate the impact of the perspective effect, an Inverse Perspective Mapping (IPM) transformation is applied to the images grabbed by the camera; the region of interest (ROI) was extracted from IPM image by a low level processing. Then, different algorithms are adopted to extract zebra crossings, stop lines and lane markings. The experiments on a large number of street scenes in different conditions demonstrate the effectiveness of the proposed algorithm.

This paper addresses the imitation procedure of the human arms by a NAO humanoid robot. The exact position of the user arms are obtained based on the position of him/her shoulders, elbows and wrists, which are obtained by using the Microsoft Kinect as a 3-dimensional optical motion capture sensor. Communication between the kinect and computer server is done by using Robot Operating System (ROS) framework. Due to the differences between human and humanoid robot dimensions, captured motion should be mapped on the robot's dimensions. Mapped data is used for kinematic operation. In this paper, the inverse kinematic problem is solved by proposing an approach based on a novel simplified geometric method. In this approach, the distal form of the Denavit-Hartenberg convention of both arms is studied and a simple and fast geometric inverse kinematic solution is proposed. Finally, the proposed method is verified experimentally in Webots simulator and on a real NAO-H25 humanoid robot. Experiments are resulting in a coherent imitation between human arm and NAO with respect to time response.

The author interprets humanoid robots as a new communication medium with social interaction. Social interaction is essential for humanoid robots, because such robots are getting more common in social and home environments, such as a pet robot in the living room, a service robot at the office, or a robot serving people at a party. Social skills of such robots require robust, complex perceptual abilities: for example, it identifies people in the room, pays attention to their voices and looks at them to identify visually, and associates voice and visual images. Intelligent behavior of social interaction should emerge from rich channels of input sensors: visual, auditory, tactile, and others. The capabilities of humanoid robots and new communication media motivate us to develop a new remote home appliance control system HRUN (humanoid robots and ubiquitous network system, detailed in Appendix). In addition, the HRUN as a "network robots" example system of convergence of ubiquitous networks and robots is interpreted. In this paper, we describe two topics. First, we describe the results of usability test about the HRUN to over 30 students. The result shows "students want to use the HRUN and expect humanoid robot as a new communication medium. " Second, we describe a limitation of conventional metrology of usability tests. For example, students misunderstand "humanoid robot simulates a human motion - stand straight", since they able to understand the robot's rough motion and think "it's not perfect, but they are getting there". Finally, the author describes the importance of a new metrology of usability tests for the new medium

Adaptive inverse perspective mapping transformation method for ballasted railway based on differential edge detection and improved perspective mapping model

Here, an extended version of the symmetrical local threshold (SLT) algorithm is introduced for lane feature extraction and used in a novel lane-detection system. The introduced feature map extractor utilises parallel lane border features as well as the dark-light-dark (DLD) pattern of the lane marking used in SLT. Hence, compared to the SLT, the true positive to positive rate of the calculated feature maps is increased from 69% to 86% on the ROMA dataset. In addition, the proposed algorithm supplies orientation information for the estimated feature points, which can be useful for many optimisation algorithms. Consequently, based on the estimated lane feature orientations, a global lane orientation is calculated and used for both enhancing the feature map and estimating a one-dimensional (1D) lateral offset likelihood function. Then, the estimated 1D functions are filtered temporally and up to two linear lane candidates are detected. For increased flexibility, robust fitting is applied to the feature points in the region of interest (ROI). Finally, based on the detection of the previous frame, a mask is created and applied to the next frame. When tested on 2301 road images, mean error in lateral offset is calculated as 4.1 pixel on the IPM images.

Whole-body humanoid robot imitation with pose similarity evaluation

Efficient and robust sound source recognition and localization is one of the basic techniques for humanoid robots in terms of reaction to environments. Due to the fixed sensor arrays and limited computation resources in humanoid robots, there comes challenge for sound source recognition and localization. This article proposes a sound source recognition and localization framework to realize real-time and precise sound source recognition and localization system using humanoid robots’ sensor arrays. The type of the audio is recognized according to the cross-correlation function. And steered response power-phase transform function in discrete angle space is used to search the sound source direction. The sound source recognition and localization framework presents a new multi-robots collaboration system to get the precise three-dimensional sound source position and introduces a distance weighting revision way to optimize the localization performance. Additionally, the experiment results carried out on humanoid robot NAO demonstrate that the proposed approaches can recognize and localize the sound source efficiently and robustly.

This paper introduces a robust algorithm for real-time lane detection using the lane markers in urban streets or highway roads. It is based on applying Region of Interest (ROI) on the input image of the road from a calibrated camera in the front of the car, generating the top view of the image using Inverse Perspective Mapping (IPM), applying the core algorithm Line Segment Detection (LSD) which is followed by post-processing steps. Applying curve fitting to the line segments to get the right and left lines or curves. Finally, to get the output stream inverse IPM is applied. The proposed algorithm can detect the road lanes discriminating dashed and solid road lanes, straight and curved road lanes overcoming the shadow effect challenge with real-time performance 70 frames per second.

Radiation mapping is the process of measuring radiation intensity level at distributed sampling points in a predefined region of interest (ROI). This procedure is crucial in any radiological related emergency to locate contamination hotspot(s) or in routine inspections in any radiation facilities. When workers knowingly enter a high radiation zone to perform radiation mapping, they are exposed to the risk of radiation exposure. Mobile robot is a potential solution that could eliminate the health and safety risk and subsequently improve the measurement accuracy. This paper reports implementation of mobile robot for radiation mapping by using a commercial mobile robot platform, Turtlebot2 in conjunction with Robot Operating System (ROS). Mobile robot is capable to generate physical map of the targeted environment by using Simultaneous Localization and Mapping (SLAM). Simultaneously, Geiger Muller detector is utilized to perform radiation measurement. The radiation data is directly plotted on the physical map hence the radiation intensity distribution throughout the ROI could be assessed. Functionality of the radiation mapping robot is evaluated in real-world experiments and the results will be presented in the paper.

This paper discusses effect of grouping on vector classifiers that are based on self-organising map (SOM). The SOM is an unsupervised learning neural network, and is used to form clusters using its topology preserving nature. Thus it is used for various pattern recognition applications. In image recognition, recognition accuracy is degraded under difficult lighting conditions. This paper proposes a new image recognition system that employs a grouping method. The proposed system does the grouping of vectors according to their brightness, and multiple vector classifiers are assigned to every groups. Recognition parameters of each classifier are tuned for the vectors belonging to its group. The proposed method is applied to position identification from images obtained from an on-board camera on a mobile robot. Comparison between the recognition systems with and without the grouping shows that the grouping can improve recognition accuracy.

A new image recognition system based on multiple linear regression is proposed. Particularly, there are a number of innovations in image segmentation and recognition system. In image segmentation, an improved histogram segmentation method which can calculate threshold automatically and accurately is proposed. Meanwhile, the regional growth method and true color image processing are combined with this system to improve the accuracy and intelligence. While creating the recognition system, multiple linear regression and image feature extraction are utilized. After evaluating the results of different image training libraries, the system is proved to have effective image recognition ability, high precision, and reliability.

Due to the rapid growth of computer science, image processing technology has recently been widely applied to various fields such as videoconferencing, computer vision and face tracking. However, the development of tracking systems is at a standstill because most studies have used the still camera and pure background. In an effort for advancement, this study proposes a wireless real-time tracking system based on background subtraction, the Gauss motion model, and the Otsu algorithm, to identify a moving object and then pursue it. This system consists of (a) a tracking platform with ARM and robot and (b) an image recognition system that regulates the location of the robot to trace the object and identifies the location of the object from the real-time image, respectively. In practice, the results of this study show that the proposed system can effectively trace the specific moving object and mark the object in the center of the view.