arXiv subjects

Svetoslav Kolev

Publications and source records attributed to Svetoslav Kolev.

3 recordsLinked to original sources

arXiv2026

Beyond Gestures: Estimating Full Hand Pose and Contact Forces from Wrist-Worn Pressure Sensor Array

Capturing hand motion and interaction forces is critical for interactive computing, VR, and high-fidelity tactile demonstrations for robot learning. We introduce a wrist-worn pressure-sensing wristband that recovers continuous full-hand pose and distributed contact force on a single wearable. The system consists of flexible capacitive sensor arrays around the wrist, which require no electrical skin contact, and a recurrent network that maps the resulting pressure signal to hand state. Our key insight is that muscle contraction and tendon displacement produce pressure patterns, which correlate strongly with hand pose and interaction force. To validate this, we collect synchronized recordings of wrist pressure, optical motion-capture hand pose, and tactile-glove interaction force, covering isolated finger motion, fingertip-force stress tests, and natural hand-object manipulation. On isolated single-user motion the wristband attains $4.6^\circ$ mean finger-joint MAE, and across four users manipulating everyday objects it estimates per-finger contact force at $R^2=0.57$, which an external pose signal brings up to $0.75$. We see the wristband as one node in a constellation of everyday wearables -- e.g. paired with an egocentric camera -- adding the contact force that vision cannot observe and taking over when the hand is occluded.

cs.HC↗

arXiv2018

Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system

Reinforcement learning has emerged as a promising methodology for training robot controllers. However, most results have been limited to simulation due to the need for a large number of samples and the lack of automated-yet-safe data collection methods. Model-based reinforcement learning methods provide an avenue to circumvent these challenges, but the traditional concern has been the mismatch between the simulator and the real world. Here, we show that control policies learned in simulation can successfully transfer to a physical system, composed of three Phantom robots pushing an object to various desired target positions. We use a modified form of the natural policy gradient algorithm for learning, applied to a carefully identified simulation model. The resulting policies, trained entirely in simulation, work well on the physical system without additional training. In addition, we show that training with an ensemble of models makes the learned policies more robust to modeling errors, thus compensating for difficulties in system identification.

cs.RO↗

arXiv2010

Structural and Magnetic Properties of Nanosized Barium Hexaferrite Powders Obtained by Microemulsion Technique

Thin hexagonal barium hexaferrite particles synthesized using the microemulsion technique were studied. A water-in-oil reverse microemulsion system with cetyltrimethylammonium bromide (CTAB) as a cationic surfactant, n-butanol as a co-surfactant, n-hexanol as a continuous oil phase, and an aqueous phase were used. The microstructural and magnetic properties were investigated. The particles obtained were mono-domain with average particle size 280 nm. The magnetic properties of the powder were investigated at 4.2 K and at room temperature. The saturation magnetization was 48.86 emu/g and the coercivity, 2.4 x 105 A/m at room temperature. The anisotropy field Ha and magneto-crystalline anisotropy K1 were 1.4 x 106 A/m and 2.37 x 105 J/m3, respectively.

cond-mat.mtrl-sci↗