"This site requires JavaScript to work correctly"
Header minimieren

Leon Sievers, M.Sc.

  • Reinforcement Learning für Autonome Roboter
  • Nichtlineare Regelung

Zentrum für angewandte Forschung

BITZ Oberschneiding - Bayerisches Innovations Transformations Zentrum

Wissenschaftlicher Mitarbeiter

Sortierung:
Beitrag in Sammelwerk/Tagungsband

  • Leon Sievers
  • J. Pitz
  • Berthold Bäuml

Learning Purely Tactile In-Hand Manipulation with a Torque-Controlled Hand

pg. 2745-2751.

  • (2022)

DOI: 10.1109/ICRA46639.2022.9812093

We show that a purely tactile dextrous in-hand manipulation task with continuous regrasping, requiring permanent force closure, can be learned from scratch and executed robustly on a torque-controlled humanoid robotic hand. The task is rotating a cube without dropping it, but in contrast to OpenAI's seminal cube manipulation task [1], the palm faces downwards and no cameras but only the hand's position and torque sensing are used. Although the task seems simple, it combines for the first time all the challenges in execution as well as learning that are important for using in-hand manipulation in real-world applications. We efficiently train in a precisely modeled and identified rigid body simulation with off-policy deep reinforcement learning, significantly sped up by a domain adapted curriculum, leading to a moderate 600 CPU hours of training time. The resulting policy is robustly transferred to the real humanoid DLR Hand-II, e.g., reaching more than 46 full 2π rotations of the cube in a single run and allowing for disturbances like different cube sizes, hand orientation, or pulling a finger.
  • TC Plattling MoMo
  • DIGITAL
Beitrag in Sammelwerk/Tagungsband

  • Lennart Röstel
  • Leon Sievers
  • Johannes Pitz
  • Berthold Bäuml

Learning a State Estimator for Tactile In-Hand Manipulation

  • (2022)

DOI: 10.1109/IROS47612.2022.9981730

We study the problem of estimating the pose of an object which is being manipulated by a multi-fingered robotic hand by only using proprioceptive feedback. To address this challenging problem, we propose a novel variant of differentiable particle filters, which combines two key extensions. First, our learned proposal distribution incorporates recent measurements in a way that mitigates weight degeneracy. Second, the particle update works on non-euclidean manifolds like Lie-groups, enabling learning-based pose estimation in 3D on SE(3). We show that the method can represent the rich and often multi-modal distributions over poses that arise in tactile state estimation. The models are trained in simulation, but by using domain randomization, we obtain state estimators that can be employed for pose estimation on a real robotic hand (equipped with joint torque sensors). Moreover, the estimator runs fast, allowing for online usage with update rates of more than 100 Hz on a single CPU core. We quantitatively evaluate our method and benchmark it against other approaches in simulation. We also show qualitative experiments on the real torque-controlled DLR-Hand II.
  • TC Plattling MoMo
  • DIGITAL