I am a Postdoctoral Researcher at the University of São Paulo (USP), Center for Robotics, where I lead the manipulation and locomanipulation team in an industry-funded project on robotic inspection and maintenance of offshore platforms.
I develop perception and control methods for manipulation and locomanipulation, including grasp estimation from partial RGB-D observations, collision-aware motion planning, and shared control for teleoperated robots.
I also develop EMG, lightmyography, and vision-based interfaces for teleoperation, shared control, and the control of robotic hands and prostheses.
arXiv preprint · RA-L submission, 2026
Combines target grounding, volumetric obstacle mapping, and model-predictive control to assist teleoperated reaching and grasping.
2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Capability conditioning produces different traversability predictions for legged and wheeled robots from the same scene.
Conference on Robot Learning (CoRL) 2026
Uses gait-phase-conditioned policy Jacobian rank to study learned representations and improve the smoothness of sim-to-real locomotion.
2026 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)
Combines object segmentation, shape completion, and 6-DoF grasp estimation to manipulate objects from partial RGB-D observations.
Nature Scientific Reports, 2023
A wearable optical interface decodes gestures and grasp force from tissue deformation using raw lightmyography signals.
A modular, 3D-printed benchmark board for evaluating robot grippers, hands, and prostheses on industrial mechanisms, with reusable simulation assets.
