Narrow Results

Tendon-driven continuum robot kinematic models are frequently computationally expensive, inaccurate due to unmodeled effects, or both. In particular, unmodeled effects produce uncertainties that arise during the robot’s operation that lead to variability in the resulting geometry. We propose a novel solution to these issues through the development of a Gaussian mixture kinematic model. We train a mixture density network to output a Gaussian mixture model representation of the robot geometry given the current tendon displacements. This model computes a probability distribution that is more representative of the true distribution of geometries at a given configuration than a model that outputs a single geometry, while also reducing the computation time. We demonstrate uses of this model through both a trajectory optimization method that explicitly reasons about the workspace uncertainty to minimize the probability of collision and an inverse kinematics method that maximizes the likelihood of occupying a desired geometry.

This paper proposes a self-supervised model which enables a humanoid robot to learn to reach to visual targets. Only 400 training samples are used to learn a forward kinematic model of the six degree-of-freedom (DOF) arm. The forward model is represented compactly with just 150 hidden neurons and enables high accuracy reaching in real time. We provide an optimization process for the learning parameters and a careful analysis of reaching errors. An extension of the model is presented to address additional DOFs in the neck. The consistency of the model with physiological and psychological observations is elaborated.

An exoskeleton is a wearable robot with joints and links corresponding to those of the human body. With applications in rehabilitation medicine, virtual reality simulation, and teleoperation, exoskeletons offer benefits for both disabled and healthy populations. Analytical and experimental approaches were used to develop, integrate, and study a powered exoskeleton for the upper limb and its application as an assistive device. The kinematic and dynamic dataset of the upper limb during daily living activities was one among several factors guiding the development of an anthropomorphic, seven degree-of-freedom, powered arm exoskeleton. Additional design inputs include anatomical and physiological considerations, workspace analyses, and upper limb joint ranges of motion. Proximal placement of motors and distal placement of cable-pulley reductions were incorporated into the design, leading to low inertia, high-stiffness links, and back-drivable transmissions with zero backlash. The design enables full glenohumeral, elbow, and wrist joint functionality. Establishing the human-machine interface at the neural level was facilitated by the development of a Hill-based muscle model (myoprocessor) that enables intuitive interaction between the operator and the wearable robot. Potential applications of the exoskeleton as a wearable robot include (i) an assistive (orthotic) device for human power amplifications, (ii) a therapeutic and diagnostics device for physiotherapy, (iii) a haptic device in virtual reality simulation, and (iv) a master device for teleoperation.

The paper presents a novel method for solving the kinematics problems in real time for fast-moving robot manipulators, animation characters, and hexapod robots. The method uses certain properties of the kinematics map and is based on spatial decomposition, classification with fuzzy logic, and neural network representation of data that are performed during an off-line process. As a result of the preprocessing, the online time for computing the kinematics is extremely small making it possible to perform real-time operations. Examples are provided to demonstrate the performance of the method.

A novel metamorphic anthropomorphic hand is for the first time introduced in this paper. This robotic hand has a reconfigurable palm that generates changeable topology and augments dexterity and versatility of the hand. Structure design of the robotic hand is presented and based on mechanism decomposition kinematics of the metamorphic anthropomorphic hand is characterized with closed-form solutions leading to the workspace investigation of the robotic hand. With characteristic matrix equation, twisting motion of the metamorphic robotic hand is investigated to reveal both dexterity and manipulability of the metamorphic hand. Through a prototype, grasping and prehension of the robotic hand are tested to illustrate characteristics of the new metamorphic anthropomorphic hand.

The relationship of velocity between the end of the manipulator and each joint is discussed in the basis coordinate system. The inverse velocity is analyzed using Jacobian matrix method for the manipulator. Considering its practical geometric parameters, restriction and physical characteristic, the virtual prototype of the robot is established in ADAMS, and then the co-simulation was completed by applying the ADAMS/Controls and MATLAB/Simulink. The virtual prototyping model of the robot provides a basis for research on off-line programming of the modular robot.

Legged robots rely on an accurate calibration of the system’s kinematics for reliable motion tracking of dynamic gaits and for precise foot placement when moving in rough terrain. In our automatic foot-eye calibration approach, a monocular camera is attached to the robot and observes the robot’s moving feet, which are equipped with Augmented Reality (AR) markers. The measurements are used to formulate a non-linear least squares problem over a fixed time window in order to estimate the 33 unknown parameters. This is effciently solved with the Levenberg-Marquardt algorithm and we get estimates for both the kinematic and the camera parameters. The approach is successfully evaluated on a real quadruped robot.

The rough terrain mobile robot "RT-Mover", which is a leg-wheel-type robot built of very simple mechanism, can move on continuous rough terrain.¹ However, in a real environment there is also discontinuous rough terrain, where it can not get about. The step-up gait for an upward step has been studied to walk on discontinuous rough terrain. In this paper, a flow of the step-up gait is introduced. After that, kinematics to climb up a step is discussed in detail, and is evaluated through simulation and experiment.