Visual Odometry is the process of estimating the movement of a (stereo) camera through its environment by matching point features between pairs of consecutive image frames. No prior knowledge of the scene nor the motion is necessary. In this work, we present a visual odometry approach using a specialized method of Sparse Bundle Adjustment. We show experimental results that proof our approach to...

Stereo odometry is the process of estimating the movement of a stereo camera through its environment by matching point features between pairs of consecutive image frames. No prior knowledge of the scene nor the motion is necessary. In this work, we present a stereo odometry approach using a specialized method of Sparse Bundle Adjustment. We show experimental results with simulated and real-worl...

| We describe a global motion planner for manipulating 3D objects by a dextrous multi-ngered robotic hand. We focus on the so-called re-connguration problem: nd a feasible quasi-static trajectory (motions and contact forces) that moves a hand-object system from an initial grasp to a nal desired connguration of the object. The planner is designed as a two-level process combining a graph search o...

This paper presents a method to capture human motion from silhouettes of a person in multi-view video streams. Applying a hierarchical kinematic body model motion parameters are estimated by optimizing the overlap between the projected model silhouettes and the input silhouettes. The energy function driving the optimization is computed very efficiently using off-the-shelf graphics hardware. Exp...

This paper shows how to effectively compute collisionfree and dynamically-feasible robot motion trajectories that satisfy task specifications given by Linear Temporal Logic (LTL). The proposed approach combines sampling-based motion planning over the continuous state space with discrete search over both the LTL task representation and a workspace decomposition. In distinction from related work,...

introduction: the use of multiple cameras for motion analysis and single joint motion is very difficult and needs high technology in laboratory conditions. detection of single joint motion in kinesthesia and analysis of its changes can be done by one camera at one direction. in this study, we present the validity and reliability of a new prototype simulator system used for motion analysis appli...

This paper presents a method to solve the regrasping problem in the context of object manipulation with a mechanical hand. This problem is met during an object manipulation when one finger reaches the boundary of its workspace or when a collision between parts occurs. Our method synthesizes a new feasible grasp when this problem appears by a sequence of grasps involving the fourth free finger. ...

Mine Countermeasures (MCM) present a challenging motion planning problem when taking into account ocean currents, complex bathymetry, and vehicle dynamics. In an effort to improve autonomous underwater vehicle (AUV) motion planning for MCM, this work presents a Physical Traveling Salesmen Problem (PTSP) approach as a way to quickly and robustly generate motions for the reacquisition and identif...

This paper introduces a high-quality, low-cost video converter, for the conversion of interlaced TV signals into progressive display formats of the same or higher frame repetition rate. This conversion is performed by motion compensated filtering which is preceeded by motion estimation. The applied motion estimation algorithm operates on blocks sized 4 x 4 pixels. For each of these blocks, a ca...

This article presents a robust and reliable human–robot collaboration (HRC) framework for bimanual manipulation. We propose an optimal motion adaptation method to retarget arbitrary human commands feasible robot pose references while maintaining payload stability. The comprises three modules: 1) a ...