Vision based localization of humanoid robots by inverse pose-estimation using a small set of fixed landmark features

2011 ◽  
Author(s):  
Luis F Lupian ◽  
Alberto Romay ◽  
Andres Espinola
Keyword(s):  
Pose Estimation ◽  
Humanoid Robots ◽  
Small Set ◽  
Vision Based Localization

Development of a Full-Sized Bipedal Humanoid Robot Utilizing Spring Assisted Parallel Four-Bar Linkages With Synchronized Actuation

2011 ◽  
Author(s):  
Jeakweon Han ◽  
Dennis Hong
Keyword(s):  
Humanoid Robot ◽  
Low Cost ◽  
Humanoid Robots ◽  
Bipedal Walking ◽  
Measurement Unit ◽  
Research Education ◽  
New Class ◽  
Vision Based Localization ◽  
The Individual ◽  
The Cost

Besides the difficulties in control and gait generation, designing a full-sized (taller than 1.3m) bipedal humanoid robot that can walk with two legs is a very challenging task, mainly due to the large torque requirements at the joints combined with the need for the actuators’ size and weight to be small. Most of the handful of successful humanoid robots in this size class that exist today utilize harmonic drives for gear reduction to gain high torque in a compact package. However, this makes the cost of such a robot too high and thus puts it out of reach of most of those who want to use it for general research, education and outreach activities. Besides the cost, the heavy weight of the robot also causes difficulties in handling and raises concerns for safety. In this paper we present the design of a new class of full-sized bipedal humanoid robots that is lightweight and low cost. This is achieved by utilizing spring assisted parallel four-bar linkages with synchronized actuation in the lower body to reduce the torque requirements of the individual actuators which also enables the use of off the shelf components to further reduce the cost significantly. The resulting savings in weight not only makes the operation of the robot safer, but also allows it to forgo the expensive force/torque sensors at the ankles and achieve stable bipedal walking only using the feedback from the IMU (Inertial Measurement Unit.) CHARLI-L (Cognitive Humanoid Autonomous Robot with Learning Intelligence - Lightweight) is developed using this approach and successfully demonstrated untethered bipedal locomotion using ZMP (Zero Moment Point) based control, stable omnidirectional gaits, and carrying out tasks autonomously using vision based localization.

scholarly journals POSE ESTIMATION AND MAPPING USING CATADIOPTRIC CAMERAS WITH SPHERICAL MIRRORS

2016 ◽  
Vol XLI-B3 ◽  
pp. 43-47
Author(s):  
Grigory Ilizirov ◽  
Sagi Filin
Keyword(s):  
Pose Estimation ◽  
Field Of View ◽  
Light Reflection ◽  
Control Points ◽  
Mirror Surface ◽  
Small Set ◽  
Catadioptric Cameras ◽  
Object Parts ◽  
Control Configuration ◽  
Spherical Mirrors

Catadioptric cameras have the advantage of broadening the field of view and revealing otherwise occluded object parts. However, they differ geometrically from standard central perspective cameras because of light reflection from the mirror surface which alters the collinearity relation and introduces severe non-linear distortions of the imaged scene. Accommodating for these features, we present in this paper a novel modeling for pose estimation and reconstruction while imaging through spherical mirrors. We derive a closed-form equivalent to the collinearity principle via which we estimate the system’s parameters. Our model yields a resection-like solution which can be developed into a linear one. We show that accurate estimates can be derived with only a small set of control points. Analysis shows that control configuration in the orientation scheme is rather flexible and that high levels of accuracy can be reached in both pose estimation and mapping. Clearly, the ability to model objects which fall outside of the immediate camera field-of-view offers an appealing means to supplement 3-D reconstruction and modeling.

scholarly journals Outdoor SLAM Using Monocular Vision-Based Localization with LIDAR-Aided Mapping for service robot in Highway

CONVERTER ◽  
2021 ◽  
pp. 397-406
Author(s):  
Shuwen Pan, Yuanyuan Li, Pengying Du, Yan Liu
Keyword(s):  
Kalman Filter ◽  
Pose Estimation ◽  
Monocular Vision ◽  
Service Robot ◽  
Robot System ◽  
Occupancy Grid ◽  
Occupancy Grid Map ◽  
Vision Based Localization ◽  
Slam Algorithm ◽  
Environmental Map

This paper designed an intelligent service robot system in highway based on multi-sensor fusion. The mobile robot attempts to fuse the lidar information and monocular vision information to estimate the pose of itself and obtain an environmental map. It adapts a new SLAM method which combines lidar and vision information. Lidar is used to obtain the 2D occupancy grid map and the monocular vision SLAM algorithm uses the Extended Kalman Filter (EKF) to magnify the pose estimation. The 3-DOF pose provided by lidar is obtained through Cartographer algorithm and the monocular vision SLAM who offers the 6-DOF pose is realized with ORB-SLAM. The experimental results show that the system is effective in application as an intelligent service robot of highway.

A VISION-BASED LOCATION POSITIONING SYSTEM VIA AUGMENTED REALITY: AN APPLICATION IN HUMANOID ROBOT NAVIGATION

2013 ◽  
Vol 10 (03) ◽  
pp. 1350019 ◽  
Author(s):  
OMID MOHARERI ◽  
AHMAD B. RAD
Keyword(s):  
Augmented Reality ◽  
Humanoid Robot ◽  
Smart Phone ◽  
Image Sequence ◽  
Humanoid Robots ◽  
Location Information ◽  
Indoor Environments ◽  
Navigation Systems ◽  
Hardware Complexity ◽  
Vision Based Localization

In this paper, we present a vision-based localization system using mobile augmented reality (MAR) and mobile audio augmented reality (MAAR) techniques, applicable to both humans and humanoid robots navigation in indoor environments. In the first stage, we propose a system that recognizes the location of a user from the image sequence of an indoor environment using its onboard camera. The location information is added to the user's view in the form of 3D objects and audio sounds with location information and navigation instruction content via augmented reality (AR). The location is recognized by using the prior knowledge about the layout of the environment and the location of the AR markers. The image sequence can be obtained using a smart phone's camera and the marker detection, 3D object placement and audio augmentation will be performed by the phone's operating processor and graphical/audio modules. Using this system will majorly reduce the hardware complexity of such navigation systems, as it replaces a system consisting of a mobile PC, wireless camera, head-mounted displays (HMD) and a remote PC with a smart phone with camera. In the second stage, the same algorithm is employed as a novel vision-based autonomous humanoid robot localization and navigation approach. The proposed technique is implemented on a humanoid robot NAO and improves the robot's navigation and localization performance previously done using an extended Kalman filter (EKF) by presenting location-based information to the robot through different AR markers placed in the robot environment.

scholarly journals POSE ESTIMATION AND MAPPING USING CATADIOPTRIC CAMERAS WITH SPHERICAL MIRRORS

2016 ◽  
Vol XLI-B3 ◽  
pp. 43-47
Author(s):  
Grigory Ilizirov ◽  
Sagi Filin
Keyword(s):  
Pose Estimation ◽  
Field Of View ◽  
Light Reflection ◽  
Control Points ◽  
Mirror Surface ◽  
Small Set ◽  
Catadioptric Cameras ◽  
Object Parts ◽  
Control Configuration ◽  
Spherical Mirrors

Catadioptric cameras have the advantage of broadening the field of view and revealing otherwise occluded object parts. However, they differ geometrically from standard central perspective cameras because of light reflection from the mirror surface which alters the collinearity relation and introduces severe non-linear distortions of the imaged scene. Accommodating for these features, we present in this paper a novel modeling for pose estimation and reconstruction while imaging through spherical mirrors. We derive a closed-form equivalent to the collinearity principle via which we estimate the system’s parameters. Our model yields a resection-like solution which can be developed into a linear one. We show that accurate estimates can be derived with only a small set of control points. Analysis shows that control configuration in the orientation scheme is rather flexible and that high levels of accuracy can be reached in both pose estimation and mapping. Clearly, the ability to model objects which fall outside of the immediate camera field-of-view offers an appealing means to supplement 3-D reconstruction and modeling.

Arrangement Of Monomeric Units In Fibrin

1979 ◽  
Author(s):  
Jan Hermans
Keyword(s):  
Fiber Axis ◽  
High Symmetry ◽  
Linear Polymers ◽  
Fiber Volume ◽  
High Fiber ◽  
Rotation Axes ◽  
Small Set ◽  
Helical Turn ◽  
The One ◽  
Kinetics Of

Measurements of light scattering have given much information about formation and properties of fibrin. These studies have determined mass-length ratio of linear polymers (protofibrils) and of fibers, kinetics of polymerization and of lateral association and volume-mass ratio of thick fibers. This ratio is 5 to 1. On the one hand, this high value suggests that the fiber contains channels that allow the diffusion of enzymes such as Factor XHIa and plasmin; on the other hand, the high value appears paradoxical for a stiff fiber made up of elongated units (fibrin monomers) arranged in parallel. Such a high fiber volume is a property of only a small set out of many high-symmetry models of fibrin, which may be constructed from overlapping three-domain monomers which are arranged into strands, are aligned nearly parallel to the fiber axis and make adequate longitudinal and lateral contacts. These models contain helical protofibrils related to each other by rotation axes parallel to the fiber axis. The protofibrils may contain 2, 3 or 4 monomers per helical turn and there are four possible symmetries. A large specific volume is achieved if the ends of each monomer are slightly displaced from the protofibril axis, either by a shift or by a tilt of the monomer. The fiber containing tilted monomers is more highly interconnected; the two ends of a tilted monomer form lateral contacts with different adjacent protofibrils, whereas the two ends of a non-tilted monomer contact the same adjacent protofibril(s).

Sign in / Sign up

Export Citation Format

Share Document