No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Development of Local Mapping Generating Technique Using Planar Regions Applied for an Active Orthosis
Abstract
The focus of this paper is characterize the limited operation of the resistive flex sensor for joint angle displacement estimation and the movement analysis. Resistive flex sensor is often used in wearable systems for estimating body motion and in this it was used to estimate the movement of lower limb joints in order to achieve human gait. The proposed characterization employs a 3D printed mechanical testbed with three different diameters, to bend the sensors, which measures the amount of bend and finds a correlation to the biomechanical joint movement. A proof-of-concept study involving a healthy subject was conducted to estimate the bend angle displacement of the knee joint angle for slow and fast movements. Accuracy and precision are evaluated for its application and combine with other devices, such as an IMU and an incremental encoder. The objective of this research is to evaluate a customized angular displacement sensor that will be used to measure in real-time joint angle displacements of an active lower limb orthosis developed at the UFRN Robotics Laboratory.
The majority of visual simultaneous localization and mapping (SLAM) approaches consider feature correspondences as an input to the joint process of estimating the camera pose and the scene structure. In this paper, we propose a new approach for simultaneously obtaining the correspondences, the camera pose, the scene structure, and the illumination changes, all directly using image intensities as observations. Exploitation of all possible image information leads to more accurate estimates and avoids the inherent difficulties of reliably associating features. We also show here that, in this case, structural constraints can be enforced within the procedure as well (instead of a posteriori ), namely the cheirality, the rigidity, and those related to the lighting variations. We formulate the visual SLAM problem as a nonlinear image alignment task. The proposed parameters to perform this task are optimally computed by an efficient second-order approximation method for fast processing and avoidance of irrelevant minima. Furthermore, a new solution to the visual SLAM initialization problem is described whereby no assumptions are made about either the scene or the camera motion. Experimental results are provided for a variety of scenes, including urban and outdoor ones, under general camera motion and different types of perturbations.
We propose a direct (feature-less) monocular SLAM algorithm which, in contrast to current state-of-the-art regarding direct meth- ods, allows to build large-scale, consistent maps of the environment. Along with highly accurate pose estimation based on direct image alignment, the 3D environment is reconstructed in real-time as pose-graph of keyframes with associated semi-dense depth maps. These are obtained by filtering over a large number of pixelwise small-baseline stereo comparisons. The explicitly scale-drift aware formulation allows the approach to operate on challenging sequences including large variations in scene scale. Major enablers are two key novelties: (1) a novel direct tracking method which operates on sim(3), thereby explicitly detecting scale-drift, and (2) an elegant probabilistic solution to include the effect of noisy depth values into tracking. The resulting direct monocular SLAM system runs in real-time on a CPU.
We present a structured lighting system for creating high-resolution stereo datasets of static indoor scenes with highly accurate ground-truth disparities. The system includes novel techniques for efficient 2D subpixel correspondence search and self-calibration of cameras and projectors with modeling of lens distortion. Combining disparity estimates from multiple projector positions we are able to achieve a disparity accuracy of 0.2 pixels on most observed surfaces, including in half-occluded regions. We contribute 33 new 6-megapixel datasets obtained with our system and demonstrate that they present new challenges for the next generation of stereo algorithms.
This paper presents the design and development of a lower limb powered orthosis called Ortholeg. This device was designed to provide lower limb movements (such as walk) to spinal cord injured people unable to move their legs. Ortholeg weights 20kg and can be worn by users within a heights range between 1,55m to 1,70m, and weights up to 65 kg. This robotic device has two actuators for each leg, one at the knee and the other at the hip. Each one of the actuators controls one degree of freedom on the sagittal plane. The device is able to perform movements such as straight walk, sit and stand up. To ensure balance and safety, the user uses a pair of crutches. Ortholeg orthosis has an embedded modular system, motor controllers, sensors and two Human Machine Interfaces (HMI) based on buttons and electroculography.
In this paper, we propose a dense visual SLAM method for RGB-D cameras that minimizes both the photometric and the depth error over all pixels. In contrast to sparse, feature-based methods, this allows us to better exploit the available information in the image data which leads to higher pose accuracy. Furthermore, we propose an entropy-based similarity measure for keyframe selection and loop closure detection. From all successful matches, we build up a graph that we optimize using the g2o framework. We evaluated our approach extensively on publicly available benchmark datasets, and found that it performs well in scenes with low texture as well as low structure. In direct comparison to several state-of-the-art methods, our approach yields a significantly lower trajectory error. We release our software as open-source.
We present the major advantages of a new 'object oriented' 3D SLAM paradigm, which takes full advantage in the loop of prior knowledge that many scenes consist of repeated, domain-specific objects and structures. As a hand-held depth camera browses a cluttered scene, real-time 3D object recognition and tracking provides 6DoF camera-object constraints which feed into an explicit graph of objects, continually refined by efficient pose-graph optimisation. This offers the descriptive and predictive power of SLAM systems which perform dense surface reconstruction, but with a huge representation compression. The object graph enables predictions for accurate ICP-based camera to model tracking at each live frame, and efficient active search for new objects in currently undescribed image regions. We demonstrate real-time incremental SLAM in large, cluttered environments, including loop closure, relocalisation and the detection of moved objects, and of course the generation of an object level scene description with the potential to enable interaction.
Currently the increasing number of robotic devices for application in the mobility of people who had suffered some type of spinal cord injury, it is necessary to develop new equipment more adaptable, safe and efficient. Robotic devices that aid in locomotion of paraplegic people can play their function, they must be able to reproduce the lost movements with most of fidelity and security. This paper presents a prototype of an active orthosis for lower limbs developed by the robotic and dedicated systems group of Department of Computing Engineering and Automation (DCA/UFRN) named Ortholeg. The proposed orthosis is an orthopedic device with the main objective of providing walking capacity to people with partial or total loss of limbs movements. The orthosis was projected to reproduce the movements of human gait. The movements of the joints of the orthosis are controlled by DC motors equipped with mechanical reductions, whose purpose is to reduce rotational speed and increase the torque, thus generating smooth movements. An embedded electronic system for sensory data acquisition and motor control was projected.
An object recognition system has been developed that uses a new
class of local image features. The features are invariant to image
scaling, translation, and rotation, and partially invariant to
illumination changes and affine or 3D projection. These features share
similar properties with neurons in inferior temporal cortex that are
used for object recognition in primate vision. Features are efficiently
detected through a staged filtering approach that identifies stable
points in scale space. Image keys are created that allow for local
geometric deformations by representing blurred image gradients in
multiple orientation planes and at multiple scales. The keys are used as
input to a nearest neighbor indexing method that identifies candidate
object matches. Final verification of each match is achieved by finding
a low residual least squares solution for the unknown model parameters.
Experimental results show that robust object recognition can be achieved
in cluttered partially occluded images with a computation time of under
2 seconds