This paper focuses on high-performance robotic contour tracking under the uncertainties that commonly exist in actual robotic applications. These uncertainties can be attributed to the robot itself (such as modeling errors or mechanical defects like backlash) or to environmental issues (such as calibration errors or misalignment of the workpiece). We propose a non-model-based dynamic compensation approach based on the coarse-to-fine philosophy, which enables contour tracking with both high speed and good accuracy. This is achieved by adopting a methodology in which a main robot performs fast but coarse motion, while an add-on module conducts accurate compensation for the overall uncertainties using a high-speed camera and high-speed compensation actuator. An algorithm called pre-compensated proportionalderivative sliding mode control (pre-compensated PD-SMC) is proposed to control the compensation actuator. The effectiveness of the proposed contour tracking approach and control algorithm are experimentally verified using two typical planar-contour shapes: a random smooth-curvature and rectangle.

This work employs an adaptive learning mechanism to perform tracking of an unknown object through RGBD cameras. We extend our previous framework to robustly track a wider range of arbitrarily shaped objects by adapting the model to the measured object size. The size is estimated as the object undergoes motion, which is done by fitting an inscribed cuboid to the measurements. The region spanned by this cuboid is used during tracking, to determine whether or not new measurements should be added to the object model. In our experiments we test our tracker with a set of objects of arbitrary shape and we show the benefit of the proposed model due to its ability to adapt to the object shape which leads to more robust tracking results.

Visual tracking of unknown objects is an essential task in robotic perception, of importance to a wide range of applications. In the general scenario, the robot has no full 3D model of the object beforehand, just the partial view of the object visible in the first video frame. A tracker with this information only will inevitably lose track of the object after occlusions or large out-of-plane rotations. The way to overcome this is to incrementally learn the appearances of new views of the object. However, this bootstrapping approach is sensitive to drifting due to occasional inclusion of the background into the model.

We propose a method for tracking the boundary of an object at frame rates beyond 1 kHz, based on a novel contour propagation mechanism operating in polar image space. The work draws inspiration from well established methodologies in object tracking and segmentation. The main contribution is how the polar representation is exploited for tracking, including enabling parallelization for sub millisecond performance. The presented results show the feasibility of the method in a wide range of settings.

We consider the problem of grasp and manipulation planning when the state of the world is only partially observable. Specifically, we address the task of picking up unknown objects from a table top. The proposed approach to object shape prediction aims at closing the knowledge gaps in the robot's understanding of the world. A completed state estimate of the environment can then be provided to a simulator in which stable grasps and collision-free movements are planned. The proposed approach is based on the observation that many objects commonly in use in a service robotic scenario possess symmetries. We search for the optimal parameters of these symmetries given visibility constraints. Once found, the point cloud is completed and a surface mesh reconstructed. Quantitative experiments show that the predictions are valid approximations of the real object shape. By demonstrating the approach on two very different robotic platforms its generality is emphasized.

We propose a method for interactive modeling of objects and object relations based on real-time segmentation of video sequences. In interaction with a human, the robot can perform multi-object segmentation through principled modeling of physical constraints. The key contribution is an efficient multi-labeling framework, that allows object modeling and disambiguation in natural scenes. Object modeling and labeling is done in a real-time segmentation system, to which hypotheses and constraints denoting relations between objects can be added incrementally. Through instructions such as key presses or spoken words, a scene can be segmented in regions corresponding to multiple physical objects. The approach solves some of the difficult problems related to disambiguation of objects merged due to their direct physical contact. Results show that even a limited set of simple interactions with a human operator can substantially improve segmentation results.

A long standing research goal is to create robots capable of interacting with humans in dynamic environments. To realise this a robot needs to understand and interpret the underlying meaning and intentions of a human action through a model of its sensory data. The visual domain provides a rich description of the environment and data is readily available in most system through inexpensive cameras. However, such data is very high-dimensional and extremely redundant making modeling challenging.

For the interpretation of a visual scene, it is important for a robotic system to pay attention to the objects in the scene and segment them from their background. We focus on the segmentation of previously unseen objects in unknown scenes. The attention model therefore needs to be bottom-up and context-free. In this paper, we propose the use of symmetry, one of the Gestalt principles for figure-ground segregation, to guide the robot's attention. We show that our symmetry-saliency model outperforms the contrast-saliency model, proposed in. The symmetry model performs better in finding the objects of interest and selects a fixation point closer to the center of the object. Moreover, the objects are better segmented from the background when the initial points are selected on the basis of symmetry.

For a person to feel comfortable when approaching a robot it is necessary for the robot to behave in an expected way. Peoplepsilas behavior around a robot not being aware of them were observed during a preliminary experiment. Based on those observations people were classified into four groups depending on their interest in the robot. People were tracked with a laser range finder based system, and their positions, directions and velocities were estimated. A second classification based on that information was made and the relation between the two classifications were mapped. Different actions were created for the robot to be able to react naturally to different human behaviors. In this paper we evaluate three different robot behaviors with respect to how natural they appear. One behavior that actively tries to engage people, one that passively indicates that people have been noticed and a third that makes random gestures. During an experiment test subjects were instructed to act according to the groups from the classification based on interest, and the robotpsilas performance with regard to naturalness was evaluated. Both first and third person evaluation made clear that the active and passive behavior were considered equally natural, while a robot randomly making gestures was considered much less natural.