scispace - formally typeset
F

Felix Widmaier

Researcher at Max Planck Society

Publications -  19
Citations -  304

Felix Widmaier is an academic researcher from Max Planck Society. The author has contributed to research in topics: Computer science & Robot. The author has an hindex of 5, co-authored 13 publications receiving 130 citations. Previous affiliations of Felix Widmaier include University of Tübingen.

Papers
More filters
Journal ArticleDOI

An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research

TL;DR: A novel controller which combines feedforward contact forces computed from a kino-dynamic optimizer with impedance control of the center of mass and base orientation is presented, which can regulate complex motions while being robust to environmental uncertainty.
Posted Content

TriFinger: An Open-Source Robot for Learning Dexterity.

TL;DR: The proposed open-source robotic platform is inexpensive, robust, and capable of complex interaction with external objects, and the software framework is largely robot-agnostic and can be used independently of the hardware proposed herein.
Proceedings ArticleDOI

Robot arm pose estimation by pixel-wise regression of joint angles

TL;DR: This work proposes an approach for robot arm pose estimation that uses depth images of the arm as input to directly estimate angular joint positions and shows that this approach improves previous work both in terms of computational complexity and accuracy.
Proceedings ArticleDOI

Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation

TL;DR: The TriFinger system as mentioned in this paper is an open-source robotic platform for dexterous manipulation and the focus of the 2020 Real Robot Challenge, and the benchmarked methods, which were successful in the challenge, can be generally described as structured policies, as they combine elements of classical robotics and modern policy optimization.
Proceedings Article

The Role of Pretrained Representations for the OOD Generalization of RL Agents

TL;DR: This work evaluates to what extent different properties of pretrained VAE-based representations affect the OOD generalization of downstream agents, and finds that many agents are surprisingly robust to realistic distribution shifts, including the challenging sim-to-real case.