Physical simulation is an indispensable component of robotics simulation platforms that serves as the basis for a plethora of research directions. Looking strictly at robotics, the common characteristic of the most popular physics engines, such as ODE, DART, MuJoCo, bullet, SimBody, PhysX or RaiSim, is that they focus on the solution of articulated rigid bodies with collisions and contacts problems, while paying less attention to other physical phenomena. This restriction limits the range of addressable simulation problems, rendering applications such as soft robotics, cloth simulation, simulation of viscoelastic materials, and fluid dynamics, especially surface swimming, infeasible. In this work, we present Gazebo Fluids, an open-source extension of the popular Gazebo robotics simulator that enables the interaction of articulated rigid body dynamics with particle-based fluid and deformable solid simulation. We implement fluid dynamics and highly viscous and elastic material simulation capabilities based on the Smoothed Particle Hydrodynamics method. We demonstrate the practical impact of this extension for previously infeasible application scenarios in a series of experiments, showcasing one of the first self-propelled robot swimming simulations with SPH in a robotics simulator.

We present a novel hierarchical MRFs optimization method for dense and deformable motion extraction in dynamic scenes. In particular, this hierarchical MRFs structure consists of two layers, the segmentation and the correspondence layer. Firstly, dynamic RGB-D foreground data is segmented through a pixel-level MRF in the segmentation layer. Subsequently, the extracted foreground data is transformed into a 3D point-level MRF in the correspondence layer. A new surface descriptor named deformable color and shape histogram is proposed. It is combined with photometric and geometric features to represent a deformable surface. Finally, the dynamic scene motion is retrieved from correspondences established in the image sequence. Discrete optimization schemes are used for the binary classification and multi-labeling problems. We provide an RGB-D dataset of dynamic scenes, which involves different motion patterns and surface properties of foreground objects. The effectiveness and efficiency of our proposed approach for high accurate foreground segmentation and motion extraction is validated in experiments.

We present a hierarchical grid-based, globally optimal tracking-by-detection approach to track an unknown number of targets in complex and dense scenarios, particularly addressing the challenges of complex interaction and mutual occlusion. Frame-by-frame detection is performed by hierarchical likelihood grids, matching shape templates through a fast oriented distance transform. To allow recovery from misdetections, common heuristics such as nonmaxima suppression within observations is eschewed. Within a discretized state-space, the data association problem is formulated as a grid-based network flow model, resulting in a convex problem casted into an integer linear programming form, giving a global optimal solution. In addition, we show how a behavior cue (body orientation) can be integrated into our association affinity model, providing valuable hints for resolving ambiguities between crossing trajectories. Unlike traditional motion-based approaches, we estimate body orientation by a hybrid methodology, which combines the merits of motion-based and 3D appearance-based orientation estimation, thus being capable of dealing also with still-standing or slowly moving targets. The performance of our method is demonstrated through experiments on a large variety of benchmark video sequences, including both indoor and outdoor scenarios.

In this paper, we present an object recognition and pose estimation framework consisting of a novel global object descriptor, so called Viewpoint oriented Color-Shape Histogram (VCSH), which combines object's color and shape information. During the phase of object modeling and feature extraction, the whole object's color point cloud model is built by registration from multi-view color point clouds. VCSH is trained using partial-view object color point clouds generated from different synthetic viewpoints. During the recognition phase, the object is identified and the closest viewpoint is extracted using the built feature database and object's features from real scene. The estimated closest viewpoint provides a good initialization for object pose estimation optimization using the iterative closest point strategy. Finally, objects in real scene are recognized and their accurate poses are retrieved. A set of experiments is realized where our proposed approach is proven to outperform other existing methods by guaranteeing highly accurate object recognition, fast and accurate pose estimation as well as exhibiting the capability of dealing with environmental illumination changes.

Multiple people tracking is an important component for different tasks such as video surveillance and human-robot interaction. In this paper, a global optimization approach is proposed for long-term tracking of an a priori unknown number of targets, particularly aim to improve the robustness in case of complex interaction and mutual occlusion. With a state-space discretization scheme, the multiple object tracking problem is formulated with a grid-based network flow model, resulting in a convex problem that can be casted into an Integer Linear Programming (ILP), then solved through relaxation. In order to allow recovery from misdetections, common heuristics such as non-maxima suppression is eschewed within observations. In addition, we show that how behavior cue can be integrated into the association affinity model, providing discriminative hints for resolving ambiguities between crossing trajectories. The validity of the proposed method is demonstrated through experiments on multiple challenging video sequences, using a calibrated multi-camera setup.