Michael C. Welle

Robotics and Representation Learning

I'm a Postdoctoral Researcher working with Danica Kragic, at the Robotics, Perception and Learning Lab (RPL), EECS, at KTH in Stockholm, Sweden. Where I also did my PhD under Danica Kragics supervission as well as co-supervision of Anastasiia Varava, and Hang Yin.

I'm working on learning representations for rigid and deformable objects manipulation. My work includes partial caging as well as working with highly deformable objects (clothing).

My CV can be found here (not neccesary up to date).

Recent Work

Representing clothing items for robotics tasks
Marco Moletta, Michael C. Welle, Alexander Kravchenko, Anastasia Varava and Danica Kragic

Abstract We study the problem of clothing item representation and build upon our recent work to perform a comparative study of the most commonly used representations of clothing items. We focus on visual and graph representations, both extracted from images. Visual representations follow the current trend of learning general representations rather than tailoring specific features relevant for the task. Our hypothesis is that graph representations may be more suitable for robotics tasks employing task and motion planning, while keeping the general properties and accuracy of visual representations. We rely on a subset of DeepFashion2 dataset and study performance of developed representations in an unsupervised, contrastive learning framework using a downstream classification task. We demonstrate the performance of graph representations in folding and flattening of different clothing items in a real robotic setup with a Baxter robot.

Dedicated website for Representing clothing items

Elastic Context: Encoding Elasticity in Data-driven Models of Textiles for Robotic Manipulation
Alberta Longhini, Marco Moletta, Alfredo Reichlin, Michael C. Welle, Alexander Kravchenko, Yufei Wang, David Held, Zackory Erickson, and Danica Kragic

Abstract Learning dynamic properties of elastic deformable objects such as textiles is relevant for applications such as assistive dressing, textile recycling, and automation of household tasks. Ongoing research in robotic manipulation has begun to explore interactions with textiles, where the textile properties are held constant or known a priori. We present an Elastic Context (EC) for data-driven models of textiles to leverage elastic-related information during robotic manipulation tasks. The definition of EC relies on force/displacement curves commonly used in textile engineering, which we reformulated for robotic applications. We evaluate EC using Graph Neural-Networks (GNN) to learn generalized elastic behaviours of textiles. In relation to the employed models, we discuss limitations of current robotic simulators in terms of learning data-driven elastic models for manipulation tasks.

Publications

Journal Papers:


Enabling Visual Action Planning for Object Manipulation through Latent Space Roadmap

Martina Lippi*, Petra Poklukar*, Michael C. Welle*, Anastasia Varava, Hang Yin, Alessandro Marino, and Danica Kragic
Accepted in Transactions on Robotics (TRO), 2022

Partial Caging: A Clearance-Based Definition, Datasets and Deep Learning

Michael Welle, Anastasiia Varava, Jeffrey Mahler, Ken Goldberg, Danica Kragic, and Florian T. Pokorny
Published in Autonomous Robots, Special Issue Topological Methods in Robotics 2021

Benchmarking Bimanual Cloth Manipulation

Irene Garcia-Camacho*, Martina Lippi*, Michael C. Welle, Hang Yin, Rika Antonova, Anastasiia Varava, Júlia Borràs, Carme Torras, Alessandro Marino, Guillem Alenyà, Danica Kragic
Puplished in IEEE Robotics and Automation Letters 5.2 (2020)

From Visual Understanding to Complex Object Manipulation

Judith Butepage, Silvia Cruciani, Mia Kokic, Michael Welle, and Danica Kragic
Published in Annual Review of Control, Robotics, and Autonomous Systems (2019)


Conference Papers:


Augment-Connect-Explore: a Paradigm for Visual Action Planning with Data Scarcity

Martina Lippi*, Michael C. Welle*, Petra Poklukar, Alessandro Marino and Danica Kragic
Accepted in International Conference on Intelligent Robots and Systems (IROS2022)

Embedding Koopman Optimal Control in Robot Policy Learning

Hang Yin, Michael C. Welle and Danica Kragic
Accepted in International Conference on Intelligent Robots and Systems (IROS2022)

Comparing Reconstruction- and Contrastive-based Models for Visual Task Planning

Constantinos Chamzas*, Martina Lippi*, Michael C. Welle*, Anastasia Varava, Lydia E. Kavraki, and Danica Kragic
Accepted in International Conference on Intelligent Robots and Systems (IROS2022)

Textile Taxonomy and Classification Using Pulling and Twisting

Alberta Longhini, Michael C. Welle, Ioanna Mitsioni and Danica Kragic
Accepted in International Conference on Intelligent Robots and Systems (IROS2021)

Learning Task Constraints in Visual-Action Planning from Demonstrations

Francesco Esposito, Christian Pek, Michael C. Welle and Danica Kragic
Puplished in IEEE Int. Conf. on Robot and Human Interactive Communication (ROMAN2021)

Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulation

Martina Lippi*, Petra Poklukar*, Michael C. Welle*, Anastasiia Varava, Hang Yin, Alessandro Marino, and Danica Kragic
Puplished in International Conference on Intelligent Robots and Systems (IROS2020)

Fashion Landmark Detection and Category Classification for Robotics

Thomas Ziegler, Judith Butepage, Michael C. Welle, Anastasiia Varava, Tonci Novkovic and Danica Kragic
Published in IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC2020)

Partial Caging: A Clearance-Based Definition and Deep Learning

Anastasiia Varava*, Michael Welle*, Jeffrey Mahler, Ken Goldberg, Danica Kragic, and Florian T. Pokorny
Published in International Conference on Intelligent Robots and Systems (IROS 2019)

On the use of Unmanned Aerial Vehicles for Autonomous Object Modeling

Michael Welle, Ludvig Ericson, Rares Ambrus, Patric Jensfelt
Published in European Conference on Mobile Robots (ECMR2017)



Workshops and Projects

Organisation:

Representing and Manipulating Deformable Objects Workshop @ ICRA2021

Martina Lippi*, Michael C. Welle*, Anastasiia Varava*, Hang Yin, Rika Antonova, Florian T. Pokorny, Danica Kragic, Yiannis Karayiannidis, Ville Kyrki, Alessandro Marino, Julia Borras, Guillem Alenya, Carme Torras
Workshop held at ICRA2021

2nd Workshop on Representing and Manipulating Deformable Objects @ ICRA2022

Martina Lippi*, Daniel Seita*, Michael C. Welle*, Hang Yin, Danica Kragic, David Held, Yiannis Karayiannidis
Workshop held at ICRA2022



Contributions:

Batch Curation for Unsupervised Contrastive Representation Learning

Michael C. Welle*, Petra Poklukar*, and Danica Kragic
Workshop on Self-Supervised Learning for Reasoning and Perception, Workshop at International Conference on Machine Learning 2021

State Representations in Robotics: Identifying Relevant Factors of Variation using Weak Supervision

Constantinos Chamzas*, Martina Lippi*, Michael C. Welle*, Anastasiia Varava, Lydia Kavraki, and Alessandro Marino, and Danica Kragic
NeurIPS 2020 Workshop on Robot Learning

Latent Space Roadmap for Visual Action Planning

Martina Lippi*, Petra Poklukar*, Michael C. Welle*, Anastasiia Varava, Hang Yin, Alessandro Marino, and Danica Kragic
RSS 2020 Workshop - Visual Learning and Reasoning for Robotic Manipulation

Analyzing Representations through Interventions

Petra Poklukar*, Michael C. Welle*, Anastasiia Varava and Danica Kragic
32nd annual workshop of the Swedish Artificial Intelligence Society (SAIS)

Projects:

Baxter plays Tic-Tac-Toe while shopping with Simtrack

Summer Internship at HKUST, HongKong, Supervisors: Michael Wang, Hang Kaiyu

Talks

Talking Robotics #40

27.04.2022 Talk information

Ph.D. defense

(As the official defense recording had technical difficulties it is a test recording of my thesis presentation)

Thesis title: Learning structured Representations for ridgid and deformable Object Manipulation

Teaching

PhD student Supervision

Co-supervising Alberta Longhini

Co-supervising Marco Moletta

Co-supervising Peiyang "Yonk" Shi

Master Thesis Supervision

Tommy Walling; Structural Comparison of Data Representations Obtained from Deep Learning Models

David Norrman; Impact of Semantic Segmentation on OOD Detection Performance for VAEs and Normalizing Flow Models

Samuel Norling; Probabilistic Forecasting through Reformer Conditioned Normalizing Flows

Simon Westberg; Investigating the Learning Behavior of Generative Adversarial Networks

Joakim Dahl; Analysis of the effect of Latent Dimensions on Disentagement in Variational Autoencoders

Alberta Longhini; Fabric Material Classification by Combining Force and Vision;

Nik Vaessen; Training Multi-Task Deep Neural Networks with Disjoint Datasets

Georgios Deligiorgis; Context-Aware Graph Convolutional Network with Multi-Clusters Mini-Batch for Link Prediction

Ching-An Wu; Investigation of Different Observation and Action Spaces for Reinforcement Learning on Reaching Tasks

Courses

Fall 2021: TA in Introduction to Robotics (Msc)

Fall 2020: TA in Introduction to Robotics (Msc)

Fall 2020: Teacher in Project Course in Data Science (Msc)

Fall 2019: TA in Introduction to Robotics (Msc)

Fall 2019: Teacher in Project Course in Data Science (Msc)

Fall 2018: TA in Introduction to Robotics (Msc)

Fall 2018: TA in Artificial Intelligence (Msc)

Fall 2018: Teacher in Project Course in Data Science (Msc)

Fall 2017: TA in Artificial Intelligence (Msc)

Fall 2016: TA in Artificial Intelligence (Msc)

Open Master Theses

There are currently no open Theses.