International Journal of Humanoid Robotics

In order to achieve real autonomy, robots have to be able to navigate in completely unknown environments. Due to the complexity of computer vision algorithms, almost every approach for robotic navigation is either based on previous knowledge of the environment, such as markers or as resulting from learning methods, or makes strong simplifying assumptions about it (height-map representations, static scenarios). While showing impressive success in certain applications, these approaches limit the potential of legged robots to achieve the amazing flexibility of humans in more complex environments. In this work, we present a strategy for full 3D vision processing that is able to handle changing, dynamic environments. These are modeled using 3D geometries that are processed in real-time by the motion planner of our biped robot Lola for avoiding moving obstacles and walking over platforms. In order to allow for a more intuitive development of such systems in the future, we present tools for visualization including two mixed reality applications using both an external camera and Microsoft’s HoloLens. We validate our system in simulations and experiments with our full-size humanoid robot Lola and publish our framework open source for the benefit of the community.

Enveloping cognitive or physical rehabilitation into a game highly increases the patients’ commitment with their treatment. Specially with children, keeping them motivated is a very time-consuming work, so therapists are demanding tools to help them with this task. NAOTherapist is a generic robotic architecture that uses Automated Planning techniques to autonomously drive noncontact upper-limb rehabilitation sessions for children with a humanoid NAO robot. Our aim is to develop more robotic games for this platform to enrich its variability and possibilities of interaction. The goal of this work is to present our first attempt to develop a different, more complex game that reuses the previous architecture. We contribute with the design description of a novel robotic Simon game that employs upper-limb poses instead of colors and could qualify as a cognitive and physical training. Statistics of evaluation tests with 14 adults and 56 children are displayed and the outcomes are analyzed in terms of human–robot interaction (HRI) quality. The results demonstrate the application-domain generalization capabilities of the NAOTherapist architecture and give an insight to further analyze the therapeutic benefits of the new developed Simon game.

The adaptation of a biped’s foot motion to the ground conditions and maintaining stability of the robot is an undeniable necessity that is the focus of this research. In this research, dynamics equations will be obtained for single support phase (SSP), double support phase (DSP), and impact. The results of impact dynamics have been used to correlate the gait parameters with the contact event following impact. In this study, in addition to explaining impact equations for a nine-link biped robot with toe and heel in first and second impact phases, a clear response for the external impulses is obtained in a compact form for the first time. In this paper, the trajectory of the foot and toe is done by determining the constraints of motion parameters with and without impact effect. Then, a method based on smooth hip motion with the largest stability margin using only two parameters, is implemented through iterative calculations, to ensure stability of the robot in accordance with the criterion of zero-moment point (ZMP). Finally, the response of a model-based controller, called feed-forward algorithm (FA), and a non-model-based controller, called the transposes Jacobian algorithm (TJ), will be used to control the robot.

Motion-blurred object tracking method integrating Histogram of Oriented Gradients and Hue Saturation (HOGHS) with Zernike moments features and based on ECO_HC tracker was proposed in this study to deal with object blur caused by the motion of the camera or the object itself. HOGHS was constructed by integrating fHOG with color features, and the properties of Zernike moments were introduced. The object was represented by combining HOGHS and Zernike moments. Furthermore, a novel quality evaluation method of response map considering both positioning accuracy and robustness was proposed and based on the method an adaptive fusion strategy utilizing the complementary properties of HOGHS and Zernike moments was implemented. Experiments were performed on the motion blur sequences from OTB-100 datasheet. Our method was compared with four other state-of-the-art methods. The precision as well as success rate were 0.849 and 0.827, respectively. Speed was 38.4 FPS. It is superior to VOT-2016’s excellent tracker ECO_HC, with relative gains of 2.3% for Pre-20 and 2.4% for AUC. The results show that the proposed method can effectively achieve the objective of motion-blurred object tracking.

A new hybrid joystick has been developed to share the six degrees of freedom (DOF) by three DOF inputs and three DOF feedback signals. For remotely controlling a mobile robot, steering and acceleration commands can be generated by a 3-DOF joystick using $x$, $y$, and $z$ directional motions, respectively. Usually, a remote operator cannot clearly watch dynamically changing terrain conditions; therefore, it is necessary to feedback the slope and tilt conditions of the road to the operator through the joystick. These values can be obtained based on the inertial navigation system (INS) and feedback to the joystick as kind of reflection forces. Further, a yaw angle has been used to feedback the actual direction of the robot through a steering control. The mechanism and control systems of the hybrid joystick are newly designed, and the effectiveness of this hybrid joystick has been verified through actual remote operation of a mobile robot driving on slanted and tilted terrain.