Welcome to my website!
Leonel Rozo
Lead 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!
[May 2, 2024] So happy we made it in ICML'24! If you are curious about how motion taxonomies can be leveraged to build taxonomy-aware embeddings in hyperbolic manifolds, then check out our new paper on "Bringing Motion Taxonomies to Continuous Domains via GPLVM on Hyperbolic manifolds".
[January, 2024] Good news from ICRA'24! My partner in crime and I will be talking about "The Single Tangent Space Fallacy", a paper about technically-sound practices when applying Riemannian geometry in robot learning problems. See you in Japan!
[January, 2024] Super happy about Hadi's paper accepted as a spotlight in ICLR'24! We propose "Neural Contractive Dynamical Systems", a new method to learn low-dimensional dyn. systems in a VAE latent space with contraction-stability guarantees, and it works in the SE(3) Lie group!
[January, 2024] ICRA'24 will host the second edition of our tutorial on Riemannian manifolds applied in robot learning, optimization a control! We are so excited to meet you in Japan and talk about what is and how to exploit Riemannian methods in robotics problems.
[September, 2023] NeurIPS, we are back! Our paper on "Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies" got accepted at NeurIPS'23. This paper proposes an RL method that accounts for the Riemannian geometry of the Wasserstein space of Gaussian Mixtures, making it very sample efficient.
[August, 2023] Yay! Our paper "The e-Bike Motor Assembly: Towards Advanced Robotic Manipulation for Flexible Manufacturing" just got accepted in RCMI. This paper introduces a systems architecture for teaching robots to perform industrial tasks as challenging as assembling parts of an e-Bike motor.
[June, 2023] Congrats to Hadi Beik-Mohammadi, who just got his paper on "Reactive motion generation on learned Riemannian manifolds" accepted in IJRR. The idea is to formulate reactive motion planning as Riemannian metric learning and shaping that build on learning from demonstrations, VAEs, and IK.
[February, 2023] We released all the talks of our tutorial on Riemannian manifolds applied in robot learning, optimization a control at IROS2022. Check our YouTube playlist!
[January, 2024] Good news from ICRA'24! My partner in crime and I will be talking about "The Single Tangent Space Fallacy", a paper about technically-sound practices when applying Riemannian geometry in robot learning problems. See you in Japan!
[January, 2024] Super happy about Hadi's paper accepted as a spotlight in ICLR'24! We propose "Neural Contractive Dynamical Systems", a new method to learn low-dimensional dyn. systems in a VAE latent space with contraction-stability guarantees, and it works in the SE(3) Lie group!
[January, 2024] ICRA'24 will host the second edition of our tutorial on Riemannian manifolds applied in robot learning, optimization a control! We are so excited to meet you in Japan and talk about what is and how to exploit Riemannian methods in robotics problems.
[September, 2023] NeurIPS, we are back! Our paper on "Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies" got accepted at NeurIPS'23. This paper proposes an RL method that accounts for the Riemannian geometry of the Wasserstein space of Gaussian Mixtures, making it very sample efficient.
[August, 2023] Yay! Our paper "The e-Bike Motor Assembly: Towards Advanced Robotic Manipulation for Flexible Manufacturing" just got accepted in RCMI. This paper introduces a systems architecture for teaching robots to perform industrial tasks as challenging as assembling parts of an e-Bike motor.
[June, 2023] Congrats to Hadi Beik-Mohammadi, who just got his paper on "Reactive motion generation on learned Riemannian manifolds" accepted in IJRR. The idea is to formulate reactive motion planning as Riemannian metric learning and shaping that build on learning from demonstrations, VAEs, and IK.
[February, 2023] We released all the talks of our tutorial on Riemannian manifolds applied in robot learning, optimization a control at IROS2022. Check our YouTube playlist!
