Welcome to my website!
Leonel Rozo
Research scientist @ Bosch center for AI
|
I love machine learning and robotics!
When I started my studies in Colombia, I got excited about how the future in AI and robotics would look like. Passion, endurance and great mentors have led me to work on what I love: research the intersection of machine learning and robotics. I envision a world where smart robots augment our capabilities at physical, cognitive and social levels! Robots that can easily assist, help, and empower people in a large diversity of scenarios and tasks. To make this dream come true, I spend my days working on machine learning tools that allow robots to naturally and smartly interact with their environment and humans. Day by day, I hit the books and investigate machine learning methods, robot control, differential geometry and optimization. |
News and updates!
[September, 2021] CoRL news! We got two papers accepted! The first one extends the well-known Probabilistic Movement Primitives (ProMPs) to handle Riemannian manifold trajectories! The second paper proposes Riemannian Matérn Kernels for Bayesian Optimization problems on Riemannian domains. Check them out!
[July, 2021] Oh boy, can't believe it! Our paper on "Learning Riemannian Manifolds for Geodesic Motion Skills" got the best student paper award in R:SS 2021! Couldn't be more proud and honored to work with such an amazing team of researchers!
[June, 2021] IROS news! An's paper on "Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations" has been accepted! This is a fantastic result from An's internship project at BCAI led by Meng Guo!
[May, 2021] Fantastic news! Our paper on "Learning Riemannian Manifolds for Geodesic Motion Skills" was accepted in R:SS 2021! The paper introduces a Riemannian perspective for robot motion generation. Kudos to Hadi Beik-Mohammadi, Soren Hauberg, Georgios Arvanitidis and Geri Neumann. Check the paper out!
[April, 2021] Super happy to be co-organizing along with very nice folks a new workshop on Geometry and Topology in Robotics at R:SS 2021! We have an amazing speakers lineup, and we will be receiving submissions on applications of geometry in robot learning, optimization, control, among others.
[March, 2021] I will be program co-chair of the LXAI workshop at ICML 2021. This is a great event that gathers many latin-american AI researchers from all around the world. Please consider to submit your work!
[October, 2020] OMG! We got our first paper accepted in NeurIPS 2020! It is probably our most theoretical paper so far, but the ideas behind are cool! Check it out!
[October, 2020] Yahoo! Two of my students got their extended abstracts accepted in the IROS workshop on "Bringing Geometric Methods to Robot Learning, Optimization and Control" Cool preliminary results on exploiting Riemannian manifolds in robot skills learning and refinement! Check them out!
[July, 2020] This is so cool! We got our paper on "Geometry-aware manipulability learning, tracking and transfer" accepted for publication in IJRR! We worked so hard for this paper and I am really happy about the theoretical contributions and experiments of this paper. Check it out here!
[July, 2020] Great news! We got two papers accepted at IROS 2020. One of them is a cool collaboration with Noémie Jaquier about human manipulability transfer. The second paper is about learning and sequencing robot skills for industrial tasks! More details in publications.
[June, 2020] Happy to announce we will be organizing the workshop "Bringing Geometric Methods to Robot Learning, Optimization and Control" at IROS 2020. BCAI will sponsor an award for the best contribution presented during the workshop!
[May, 2020] We have a new PhD student onboard! Hadi just started his PhD at BCAI, where he will be working on geometric machine learning methods for robot motion skills.
[April, 2020] Due to COVID-19 we have extended the submission deadline for our special issue on "Emerging Paradigms for Robotic Manipulation: from the Lab to the Productive World".
[March, 2020] I am a program co-chair of the LXAI workshop at ICML. This is a great event that gathers many latin-american researchers from all around the world. Please consider to submit your work! This year we go virtual!
[March, 2020] I am serving as associate editor for the IEEE Robotics and Automation Letters (RA-L). Happy to give a hand to the peer-review and publish process.
[January, 2020] Call for papers of our special issue in the IEEE Robotics and Automation Magazine. This special issue will be about "Emerging Paradigms for Robotic Manipulation: from the Lab to the Productive World". Happy to co-edit this issue with really amazing colleagues.
[July, 2021] Oh boy, can't believe it! Our paper on "Learning Riemannian Manifolds for Geodesic Motion Skills" got the best student paper award in R:SS 2021! Couldn't be more proud and honored to work with such an amazing team of researchers!
[June, 2021] IROS news! An's paper on "Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations" has been accepted! This is a fantastic result from An's internship project at BCAI led by Meng Guo!
[May, 2021] Fantastic news! Our paper on "Learning Riemannian Manifolds for Geodesic Motion Skills" was accepted in R:SS 2021! The paper introduces a Riemannian perspective for robot motion generation. Kudos to Hadi Beik-Mohammadi, Soren Hauberg, Georgios Arvanitidis and Geri Neumann. Check the paper out!
[April, 2021] Super happy to be co-organizing along with very nice folks a new workshop on Geometry and Topology in Robotics at R:SS 2021! We have an amazing speakers lineup, and we will be receiving submissions on applications of geometry in robot learning, optimization, control, among others.
[March, 2021] I will be program co-chair of the LXAI workshop at ICML 2021. This is a great event that gathers many latin-american AI researchers from all around the world. Please consider to submit your work!
[October, 2020] OMG! We got our first paper accepted in NeurIPS 2020! It is probably our most theoretical paper so far, but the ideas behind are cool! Check it out!
[October, 2020] Yahoo! Two of my students got their extended abstracts accepted in the IROS workshop on "Bringing Geometric Methods to Robot Learning, Optimization and Control" Cool preliminary results on exploiting Riemannian manifolds in robot skills learning and refinement! Check them out!
[July, 2020] This is so cool! We got our paper on "Geometry-aware manipulability learning, tracking and transfer" accepted for publication in IJRR! We worked so hard for this paper and I am really happy about the theoretical contributions and experiments of this paper. Check it out here!
[July, 2020] Great news! We got two papers accepted at IROS 2020. One of them is a cool collaboration with Noémie Jaquier about human manipulability transfer. The second paper is about learning and sequencing robot skills for industrial tasks! More details in publications.
[June, 2020] Happy to announce we will be organizing the workshop "Bringing Geometric Methods to Robot Learning, Optimization and Control" at IROS 2020. BCAI will sponsor an award for the best contribution presented during the workshop!
[May, 2020] We have a new PhD student onboard! Hadi just started his PhD at BCAI, where he will be working on geometric machine learning methods for robot motion skills.
[April, 2020] Due to COVID-19 we have extended the submission deadline for our special issue on "Emerging Paradigms for Robotic Manipulation: from the Lab to the Productive World".
[March, 2020] I am a program co-chair of the LXAI workshop at ICML. This is a great event that gathers many latin-american researchers from all around the world. Please consider to submit your work! This year we go virtual!
[March, 2020] I am serving as associate editor for the IEEE Robotics and Automation Letters (RA-L). Happy to give a hand to the peer-review and publish process.
[January, 2020] Call for papers of our special issue in the IEEE Robotics and Automation Magazine. This special issue will be about "Emerging Paradigms for Robotic Manipulation: from the Lab to the Productive World". Happy to co-edit this issue with really amazing colleagues.