Niklas Fiedler

University of Hamburg | UHH · Department of Informatics

Adaptive grippers enable easy and robust grasping of diverse objects by adapting to their shapes and enclosing them. However, determining the exact state of the hand remains challenging. This is not always straightforward but is often necessary to assess grip success, quality, or the pose of the object. In this work, we present two deep learning ap...

We describe a fully integrated blackjack dealing robot system utilizing multimodal input to interact with human players. It can deal cards to players and visually detect which cards have been played. Furthermore, it detects gestures commonly used in blackjack, such as knocking and swiping performed by human players to indicate whether they would li...

In this work, we present a comprehensive multi-modal pipeline for grasping pieces of fabric from flat surfaces. The pipeline is capable of grasping the fabric with a success rate of 99% without the need for information on material or shape. Maintaining the pressure onto the fabric and surface while closing the gripper causes a fold in the material,...

Mixed reality (MR) technology has shown enormous potential for real-time human-robot teleoperation. To provide the user with sensor feedback, typically extensive instrumentation is required, such as wearable devices. In this paper, we introduce an MR human-robot teleoperation system based on the Microsoft HoloLens 2 (HL2). The user can directly con...

We showcase a pipeline to train, evaluate, and deploy deep learning architectures for monocular depth estimation in the RoboCup Soccer Humanoid domain. In contrast to previous approaches, we apply the methods on embedded systems in highly dynamic but heavily constrained environments. The results indicate that our monocular depth estimation pipeline...

While for vision and audio the same mass-produced units can be embedded in many different systems from smartphones to robots, tactile sensors have to be built in application-specific shapes and sizes. To use a commercially available tactile sensor, it can be necessary to develop the entire system around an existing sensor model. We present a set of...

We present a dataset specifically designed to be used as a benchmark to compare vision systems in the RoboCup Humanoid Soccer domain. The dataset is composed of a collection of images taken in various real-world locations as well as a collection of simulated images. It enables comparing vision approaches with a meaningful and expressive metric. The...

The key role of tactile sensing for human grasping and manipulation is widely acknowledged, but most industrial robot grippers and even multi-fingered hands are still designed and used without any tactile sensors. While the basic design principles for resistive or capacitive sensors are well known, several factors keep tactile sensing from large-sc...

In this work, a classifier for clothes was developed which solely relies on depth information. The task was approached using a neural network based on the PointNet architecture. The classification of clothes serves as a use case to investigate the usability of PointNet as a classifier of non-rigid objects. To train and evaluate the network, a new d...

We present a dataset specifically designed to be used as a benchmark to compare vision systems in the RoboCup Humanoid Soccer domain. The dataset is composed of a collection of images taken in various real-world locations as well as a collection of simulated images. It enables comparing vision approaches with a meaningful and expressive metric. The...

Robots are usually equipped with many different sensors that need to be integrated. While most research is focused on the integration of vision with other senses, we successfully integrate tactile and auditory sensor data from a complex robotic system. Herein, we train and evaluate a neural network for the classification of the content of eight opt...

Robots are usually equipped with many different sensors that need to be integrated. While most research is focused on the integration of vision with other senses, we successfully integrate tactile and auditory sensor data from a complex robotic system. Herein, we train and evaluate a neural network for the classification of the content of eight opt...

This extended abstract describes the current research of the Hamburg Bit-Bots Humanoid KidSize RoboCup team, lessons learned from last years competition and improvements planned for 2020. In the RoboCup 2019 competition, we had recently installed new cameras on the robots with a new 3D printed head. These heads sometimes broke when the robot fell....

We are proposing an Open Source ROS vision pipeline for the RoboCup Soccer context. It is written in Python and offers sufficient precision while running with an adequate frame rate on the hardware of kid-sized humanoid robots to allow a fluent course of the game. Fully Convolutional Neural Networks (FCNNs) are used to detect balls while convention...

The need for labeled training data for object recognition in RoboCup increased due to the spread of deep learning approaches. Creating large sets of training images from different environments and annotating the recorded objects is difficult for a single RoboCup team.

We are proposing an Open Source ROS vision pipeline for the RoboCup Soccer context. It is written in Python and offers sufficient precision while running with an adequate frame rate on the hardware of kid-sized humanoid robots to allow a fluent course of the game. Fully Convolutional Neural Networks (FCNNs) are used to detect balls while convention...

In this thesis, a novel world model for setups of multiple mobile robots is presented. A measurement filtering and fusion system is developed for the RoboCup Humanoid Soccer environment. An architecture consisting of two filtering layers is designed. In each layer, one particle filter each is used to process a detection class. Thus, the system is a...

This paper presents an approach for using an image-based heat map as measurement input of a particle filter. Pixels of the heat map are transformed into Cartesian space relative to the robot and regarded as single measurements. The approach uses a novel observation model to weight the particles accordingly to the heat map pixels. While this paper f...

This team description paper presents the developments made by the joint team Hamburg Bit-Bots & WF-Wolves. We present new software approaches we programmed and evaluated, like the Dynamic Stack Decider (DSD), our advances in image processing and our improvements to the walking engine. Additionally the newly developed foot pressure sensors as well a...

The need for labeled training data for object recognition in RoboCup increased due to the spread of deep learning approaches. Creating large sets of training images from different environments and annotating the recorded objects is difficult for a single RoboCup team. This paper presents our tool ImageTagger which facilitates creating and sharing s...