Robert Haschke
YOU?
Author Swipe
View article: Grasping Emotion: A Vision-Based Study of Hand Movement and Feeling
Grasping Emotion: A Vision-Based Study of Hand Movement and Feeling Open
Aims: To explore how emotional responses to various objects are reflected in hand kinematics during natural grasping.Methods: Using a smartphone camera combined with MediaPipe and OpenCV, we recorded hand movements from 20participants as t…
View article: HydroelasticTouch: Simulation of Tactile Sensors with Hydroelastic Contact Surfaces
HydroelasticTouch: Simulation of Tactile Sensors with Hydroelastic Contact Surfaces Open
Thanks to recent advancements in the development of inexpensive, high-resolution tactile sensors, touch sensing has become popular in contact-rich robotic manipulation tasks. With the surge of data-driven methods and their requirement for …
View article: Precision-Focused Reinforcement Learning Model for Robotic Object Pushing
Precision-Focused Reinforcement Learning Model for Robotic Object Pushing Open
Non-prehensile manipulation, such as pushing objects to a desired target position, is an important skill for robots to assist humans in everyday situations. However, the task is challenging due to the large variety of objects with differen…
View article: Adaptive Kinematic Modeling for Improved Hand Posture Estimates Using a Haptic Glove
Adaptive Kinematic Modeling for Improved Hand Posture Estimates Using a Haptic Glove Open
Most commercially available haptic gloves compromise the accuracy of hand-posture measurements in favor of a simpler design with fewer sensors. While inaccurate posture data is often sufficient for the task at hand in biomedical settings s…
View article: Zero-Shot Transfer of a Tactile-based Continuous Force Control Policy from Simulation to Robot
Zero-Shot Transfer of a Tactile-based Continuous Force Control Policy from Simulation to Robot Open
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks. An important line of research in this regard is grasp …
View article: Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge
Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge Open
In order to develop robots that can effectively serve as versatile and capable home assistants, it is crucial for them to reliably perceive and interact with a wide variety of objects across diverse environments. To this end, we proposed O…
View article: UniTeam: Open Vocabulary Mobile Manipulation Challenge
UniTeam: Open Vocabulary Mobile Manipulation Challenge Open
This report introduces our UniTeam agent - an improved baseline for the "HomeRobot: Open Vocabulary Mobile Manipulation" challenge. The challenge poses problems of navigation in unfamiliar environments, manipulation of novel objects, and r…
View article: Language-Conditioned Semantic Search-Based Policy for Robotic Manipulation Tasks
Language-Conditioned Semantic Search-Based Policy for Robotic Manipulation Tasks Open
Reinforcement learning and Imitation Learning approaches utilize policy learning strategies that are difficult to generalize well with just a few examples of a task. In this work, we propose a language-conditioned semantic search-based met…
View article: TIAGo RL: Simulated Reinforcement Learning Environments with Tactile Data for Mobile Robots
TIAGo RL: Simulated Reinforcement Learning Environments with Tactile Data for Mobile Robots Open
Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling behavior becomes incre…
View article: Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot
Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot Open
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks. An important line of research in this regard is that o…
View article: Bio-Inspired Grasping Controller for Sensorized 2-DoF Grippers
Bio-Inspired Grasping Controller for Sensorized 2-DoF Grippers Open
We present a holistic grasping controller, combining free-space position control and in-contact force-control for reliable grasping given uncertain object pose estimates. Employing tactile fingertip sensors, undesired object displacement d…
View article: Placing by Touching: An empirical study on the importance of tactile sensing for precise object placing
Placing by Touching: An empirical study on the importance of tactile sensing for precise object placing Open
This work deals with a practical everyday problem: stable object placement on flat surfaces starting from unknown initial poses. Common object-placing approaches require either complete scene specifications or extrinsic sensor measurements…
View article: Toward More Robust Hand Gesture Recognition on EIT Data
Toward More Robust Hand Gesture Recognition on EIT Data Open
Striving for more robust and natural control of multi-fingered hand prostheses, we are studying electrical impedance tomography (EIT) as a method to monitor residual muscle activations. Previous work has shown promising results for hand ge…
View article: Using Tactile Sensing to Improve the Sample Efficiency and Performance of Deep Deterministic Policy Gradients for Simulated In-Hand Manipulation Tasks
Using Tactile Sensing to Improve the Sample Efficiency and Performance of Deep Deterministic Policy Gradients for Simulated In-Hand Manipulation Tasks Open
Deep Reinforcement Learning techniques demonstrate advances in the domain of robotics. One of the limiting factors is a large number of interaction samples usually required for training in simulated and real-world environments. In this wor…
View article: Improving Manipulation Performance of Mobile Robots Using Tactile Sensors
Improving Manipulation Performance of Mobile Robots Using Tactile Sensors Open
The fundamental skill of grasping and manipulation still poses a great challenge to most service robots. One contributing factor to their poor performance is their inability to sense touch with their end-effectors. The ability to receive f…
View article: Robust Grasping with Mobile Robots Using Tactile Sensors
Robust Grasping with Mobile Robots Using Tactile Sensors Open
Grasping and object manipulation are vital skills for every service robot. In real-world applications however, their manipulation performance is often underwhelming. This is in part due to the lack of feedback from the environment during d…
View article: TIAGo RL: Simulated Reinforcement Learning Environments with Tactile Data for Mobile Robots
TIAGo RL: Simulated Reinforcement Learning Environments with Tactile Data for Mobile Robots Open
Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling behavior becomes incre…
View article: Leveraging Touch Sensors to Improve Mobile Manipulation
Leveraging Touch Sensors to Improve Mobile Manipulation Open
Despite many advances in service robotics, successful and secure object manipulation on mobile platforms is still a challenge. In order to come closer to human grasping performance, it is natural to provide robots with the same capability …
View article: Hand Gesture Recognition with Electrical Impedance Tomography (Dataset)
Hand Gesture Recognition with Electrical Impedance Tomography (Dataset) Open
This dataset consists of measurements using Electrical Impedance Tomography (EIT). An EIT system with 16 electrodes configured to a feed in signal of 50 kHz frequency and a 1 mA alternating current was used for the data acquisition. 12 Ges…
View article: SOM-based experience representation for Dextrous Grasping
SOM-based experience representation for Dextrous Grasping Open
We present an approach to dextrous robot grasping which combines a purely tactile-driven algorithm with an implicit representation of grasp experience to yield an algorithm which can handle arbitrary, partially unknown grasp situations. Du…
View article: Conditional WGAN for grasp generation.
Conditional WGAN for grasp generation. Open
Patzelt F, Haschke R, Ritter H. Conditional WGAN for grasp generation. In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). 2019.
View article: Tactile Sensing for Manipulation
Tactile Sensing for Manipulation Open
International audience
View article: Fast grasp tool design: From force to form closure
Fast grasp tool design: From force to form closure Open
We present a novel technique which integratesautomatic, part centered design of customized fingertips with agrasp planning stage for arbitrary parts of an assembly process.Starting with a set of CAD models of parts in an assemblysequence, …
View article: SARAFun, Smart Assembly Robot with Advanced FUNctionalities, H2020
SARAFun, Smart Assembly Robot with Advanced FUNctionalities, H2020 Open
While Industrial robots are very successful in many areas of industrial manufacturing, assembly automation still suffers from complex time consuming programming and the need of dedicated hardware. ABB has developed YuMi, a collaborative in…
View article: Multidigit force control during unconstrained grasping in response to object perturbations
Multidigit force control during unconstrained grasping in response to object perturbations Open
Because of the complex anatomy of the human hand, in the absence of external constraints, a large number of postures and force combinations can be used to attain a stable grasp. Motor synergies provide a viable strategy to solve this probl…
View article: A Multi-Modal Sensing Glove for Human Manual-Interaction Studies
A Multi-Modal Sensing Glove for Human Manual-Interaction Studies Open
We present an integrated sensing glove that combines two of the most visionary wearable sensing technologies to provide both hand posture sensing and tactile pressure sensing in a unique, lightweight, and stretchable device. Namely, hand p…