The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, a new approach for 3D skeleton-based human motion recognition is discussed. First, we opted to represent the movement as a set of body joints trajectories. Those trajectories are then converted into ropes histograms. The motion records are obtained using the Kinect motion sensor. The classification phase consists in comparing those histograms with ropes histograms of a set of reference...
Human action recognition is currently a hot topic research domain including a variety of applications such as human HMI, rehabilitation and surveillance. The majority of existing approaches are based on the skeleton. They utilize either the joint locations or the joint angles in order to present a human skeleton. This study introduce a novel framework, which allows compact representation, quick comparison...
The temporomandibular joint (TMJ) is a complex bilateral articulation, and its movements are a combination of hinge movement and gliding movement guided by its articular surfaces. A masticatory robot with higher kinematic pairs (HKPs) simulating TMJ behavior is introduced. Kinematic equations of the HKPs are derived based on three-dimensional kinematics of rigid bodies and differential geometry. Position,...
The captured motion data can be utilized to produce kinds of animation for different characters. We propose a method to represent simulated motion, especially exaggerative motion by filtering the joint trajectories. The motion style is changed by shrinking or squashing the corresponding 3D trajectories. The similar but exaggerative motion with articulated constraints is generated by the inverse kinematic...
Graffiti work using a humanoid with artistic technique can convey the value of artists' work to people. Previous work that focused on drawing an image on a canvas accurately has not contained artistic processes like performance, drawing skills and other artists' intents at the time of creation. To combine such artistic processes, the work in this paper utilizes whole-body motion of a humanoid to paint...
Dexterous continuum manipulators (DCMs) offer great potential for increasing instrument reach in minimally-invasive surgical procedures. We previously designed and fabricated a tendon driven DCM with a large instrument channel and evenly distributed compliant joints for minimally-invasive skull base surgery and the treatment of osteolysis during hip revision surgery. The evenly distributed compliant...
A multimodal dataset is presented, which has been collected for analyzing and measuring the quality of movement performed during sport activities. Martial arts (namely karate) are taken as test-beds for investigation. Karate encompasses predefined sequences of movements (“katas”) that can be carried out with different qualities, e.g., by performers at different skill levels (highly vs. poorly skilled)...
This research aims at Inverse Kinematic Modeling of a Prosthetic Upper Limb which consist of four degree of freedom (DOF). Focus of this research is to obtain desired joint angles for specified positions and orientations of arm model with respect to reference frame based on the orientation and configuration. Inverse Kinematics play an important role in automation of Robotic Manipulators. Analytical...
The gesture recognition using motion capture data and depth sensors has recently drawn more attention in vision recognition. Currently most systems only classify dataset with a couple of dozens different actions. Moreover, feature extraction from the data is often computational complex. In this paper, we propose a novel system to recognize the actions from skeleton data with simple, but effective,...
Autonomous manipulation is one the the most complex fields of humanoid robotics research, because it involves several domains such as: object recognition, object tracking, manipulator positioning, grasping, etc. In this paper a tactile controller based on fuzzy logic is proposed, capable of complex inhand manipulation tasks. This fuzzy logic approach assures finger motion smoothness by dealing with...
Dynamic programming based track before detect (DP-TBD) is a batch processing method. It exploits the space-time correlation among several consecutive frames of measurements and jointly processes all the measurements in these frames. Due to this batch processing manner, DP-TBD suffers heavy computational load since it involves processing a large volume of data. Moreover, in order to track long continuous...
This paper proposes a new implementation for the delta generalized labeled multi-Bernoulli (δ-GLMB) filter by combining prediction and update into a single step. In contrast to the original implementation which requires different truncation procedures for each component in the prediction and update, the joint strategy involves only one truncation per component in the filtering density, thus drastically...
The robotic servicing of satellites on-orbit will play an important role in extending their lifespan and mitigating space debris expansion. However, most maneuvers related to these goals present a set of unique challenges which are hard to assess in reality. On the other hand, a reliable prediction of the feasibility of servicing maneuvers is increasingly required. This paper presents a simulation-driven...
Welding joints for offshore oil rigs present a complicated geometry and require multiple passes. This paper introduces a complete collision-free offline path planning approach for such joints. Collision detection is performed using A* search on a three dimensional grid, where triangular mesh representations of the welding joint and its fixture form the objects. A workflow is proposed for the complete...
This paper proposes a probabilistic generative model of a sequence of vectors called the latent trajectory hidden Markov model (HMM). While a conventional HMM isonly capable of describing piecewise stationary sequences of data vectors, the proposed model is capable of describing continuously time-varying sequences of data vectors, governed by discrete hidden states. This feature is noteworthy in that...
We present a planning approach for complex motions of reconfigurable snake-like robots to overcome challenging obstacles like stairs or large steps. The current robot configuration as well as different optimization criteria like distance, time or energy, are taken into account. The planning time remains unaffected by the amount of robot modules by combining the planning method with a follow-the-leader...
In this paper, an approach for learning optimal striking points is proposed. Based on a ball-flight model and a rebound model, a set of reachable striking points within the robot's workspace can be obtained. However, while these striking points are geometrically reachable, their success probability differs substantially due to the robot's nonlinear dynamics, the distance to the ball, the need to reach...
In this paper, the development and the experimental testing phases of an innovative assistive device for hand disabilities are presented. This robotic device is based on an parallel kinematic chain applied to a single phalanx architecture and it is designed to be extremely portable to easily assist people with physical disabilities in their everyday lives. Focusing on patients with hand opening disabilities,...
This paper describes the investigation of linear and parametric iterative learning control (ILC) methods with an integrated computed torque control approach and the application in a mobile multi-body service robot. In addition to the controller structure, the development of the nonlinear dynamic model and the trajectory generation for the robot-configuration control are briefly explained.
Balance and gait rehabilitation are the lesser progressed fields in robot aided rehabilitation, mostly due to the complexity of the involved tasks. One of the main problems is the impossibility for most patients to autonomously practice balance and gait rehabilitation safely, especially in the early fundamental stage of recovery. A solution to this limitation of the therapies is to realize a robotic...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.