Abstract Region-based methods have become increasingly popular for model-based, monocular 3D tracking of texture-less objects in cluttered scenes. However, while they achieve state-of-the-art results, most methods are computationally expensive, requiring significant resources to run in real-time. In the following, we build on our previous work and develop SRT3D , a sparse region-based approach to 3D object tracking that bridges this gap in efficiency. Our method considers image information sparsely along so-called correspondence lines that model the probability of the object’s contour location. We thereby improve on the current state of the art and introduce smoothed step functions that consider a defined global and local uncertainty. For the resulting probabilistic formulation, a thorough analysis is provided. Finally, we use a pre-rendered sparse viewpoint model to create a joint posterior probability for the object pose. The function is maximized using second-order Newton optimization with Tikhonov regularization. During the pose estimation, we differentiate between global and local optimization, using a novel approximation for the first-order derivative employed in the Newton method. In multiple experiments, we demonstrate that the resulting algorithm improves the current state of the art both in terms of runtime and quality, performing particularly well for noisy and cluttered images encountered in the real world.

In tendon-driven robotic hands, tendons are usually routed along several pulleys. The resulting friction is often substantial, and must therefore be modelled and estimated, for instance for accurate control and contact detection. Common approaches for friction estimation consider special dedicated setups, where the parameters of a static or dynamic friction model at a single contact point are determined. In this paper, we rather combine such individual friction models into an overall friction model for the entire finger. Furthermore, we propose a method for estimating the parameters of this overall model in situ, i.e. from trajectories executed on the assembled hand, avoiding the need for dedicated setups. An important component of the proposed model is a varying bias for treating friction at low velocities, allowing a simpler static friction model to be used. We demonstrate that our approach enables contacts to be detected more accurately on the DLR David hand, without additional sensors.

The ability to manipulate objects is the primary purpose of any robotic hand. However, when executing a grasp, the object and fingers rarely move exactly as planned. These unobserved deviations in the pose of the object or the contact configuration can make it impossible to solve a given task. In this paper, we presents a new approach to estimate the state of the grasp using only position and torque measurements from the joints of the hand. Based on the popular extended Kalman filter framework, the algorithm estimates the pose of the manipulated object, as well as the contact forces and positions on the surface of the object. It is able to reliably detect new and the loss of contacts and to incorporate this information in the estimation filter. The validity of this new method is shown in different grasp and manipulation tasks using David, a humanoid platform of DLR.

Robotic hands are a key component of humanoids. Initially more fragile and larger than their human counterparts, the technology has evolved and the latest generation is close to the human hand in size and robustness. However, it is still disappointing to see how little robotic hands are able to do once the grasp is acquired due to the difficulty to obtain a reliable pose of the object within the palm. This paper presents a novel method based on a particle filter used to estimate online the object pose. It is shown that the method is robust, accurate and handles many realistic scenario without hand crafted rules. It combines an efficient collision checker with a few very simple ideas, that require only a basic knowledge of the geometry of the objects. It is shown, by experiments and simulations, that the algorithm is able to deal with inaccurate finger position measurements and can integrate tactile measurements. The method greatly enhances the performance of common manipulation operations, such as a pick and place tasks, and boosts the sensing capabilities of the robot.