J. Frederico Carvalho
Technische Universität Darmstadt, KTH Royal Institute of Technology
Papers
7
Total Citations
134
H-Index
4
About
J. Frederico Carvalho is a robotics researcher whose work sits at the intersection of motion planning, machine learning, and topological data analysis. His most impactful contribution is "Motion Planning Diffusion" (2023, 96 citations), which pioneers the use of diffusion models to learn trajectory priors from past successful plans, dramatically accelerating robot motion planning optimization. This work represents a significant step toward robots that can generalize from experience rather than plan from scratch. Carvalho has also made notable contributions to human-robot interaction, developing methods for long-term human motion trajectory prediction using path homology clusters (2019, 12 citations)—a topological approach that enables robots to reason about human movement more effectively. His research extends to deformable object manipulation, where he constructs compact topological representations to capture the state of highly deformable objects (2020), and to bi-manual robotic control, integrating probabilistic movement primitives with cooperative control frameworks (2022). Through his innovative combination of topological methods and generative models, Carvalho is advancing the frontier of robots that can learn, adapt, and plan in complex, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Long-term Prediction of Motion Trajectories Using Path Homology Clusters12 citations · 2019
- 4
- 5
- 6
- 7