6 papers
Mind the Phase: Effective Rank and Representation Health in Legged Locomotion
Felipe Tommaselli, Thiago H. Segreto, Juliano D. Negri +2
Reinforcement learning has become the leading paradigm in legged locomotion, enabling complex behaviors from backflips to parkour via massively parallel simulation. Under PPO's non…
VLN on the Fly: An Onboard Vision-Language Navigation Stack for Aerial Robots
Marco S. Tayar, Felipe Tommaselli, Gianluca Capezutto +7
Running vision-language navigation fully onboard an aerial robot is hard, since grounding, planning, and control must share limited compute and a single-stage error is difficult to…
MIRA: A Modular Open-Source Micro-UAV for Indoor Research
Lucas K. de Oliveira, Felipe Tommaselli, Felipe A. G. Tommaselli +6
Indoor robotics research increasingly relies on micro-UAV platforms whose airframes, electronics, and control software are open to modification. Off-the-shelf platforms often lack…
Towards Capability-Aware Traversability Navigation for Unstructured Environments
Gianluca Capezzuto, Felipe Tommaselli, Matheus P. Angarola +2
Estimating traversability in unstructured environments requires conditioning on robot embodiment, as the same terrain can be traversable for one platform and unsafe for another. Ex…
LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields
Felipe Tommaselli, Francisco Affonso, Arthur Pompeu +4
Unstructured navigational features, such as irregular planting or discontinuities, remain the primary failure mode for under-canopy agricultural robots. Existing geometric approach…
Learning to Walk With Less: A Dyna-Style Approach to Quadrupedal Locomotion
Francisco Affonso, Felipe Tommaselli, João H. Aléssio +4
Traditional on-policy reinforcement learning (RL) controllers for quadrupedal locomotion often suffer from low data efficiency, requiring millions of interactions with simulated en…