Search Results for author:
Found 8 papers, 3 papers with code
Learning Keypoints for Robotic Cloth Manipulation using Synthetic Data
To advance the use of synthetic data for cloth manipulation and to enable tasks such as robotic folding, we present a synthetic data pipeline to train keypoint detectors for almost flattened cloth items.
Revisiting Proprioceptive Sensing for Articulated Object Manipulation
We perform a qualitative evaluation of this system, where we find that slip between the gripper and handle limits the performance.
CenDerNet: Center and Curvature Representations for Render-and-Compare 6D Pose Estimation
We introduce CenDerNet, a framework for 6D pose estimation from multi-view images based on center and curvature representations.
Dataset of Industrial Metal Objects
The close correspondence between synthetic and real-world data, and controlled variations, will facilitate sim-to-real research.
KeyCLD: Learning Constrained Lagrangian Dynamics in Keypoint Coordinates from Images
We demonstrate learning of Lagrangian dynamics from images on the dm_control pendulum, cartpole and acrobot environments.
Learning Keypoints from Synthetic Data for Robotic Cloth Folding
We evaluate the performance of this detector for folding towels on a unimanual robot setup and find that the grasp and fold success rates are 77% and 53%, respectively.
Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped
Using the FORCE learning paradigm, we train a reservoir of spiking neuron populations to act as a central pattern generator.
A Differentiable Physics Engine for Deep Learning in Robotics
Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent.
