3 papers
cs.RO2026
When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation
Maxime Alvarez, Ryo Watanabe, Paul Crook +4
As end-to-end robotic policies are progressively deployed in the real world to solve real tasks, they face a gap between the training and inference conditions. Scaling the amount a…
cs.RO2025
Leave No Observation Behind: Real-time Correction for VLA Action Chunks
Kohei Sendai, Maxime Alvarez, Tatsuya Matsushima +2
To improve efficiency and temporal coherence, Vision-Language-Action (VLA) models often predict action chunks; however, this action chunking harms reactivity under inference delay…
cs.RO2025
FTACT: Force Torque aware Action Chunking Transformer for Pick-and-Reorient Bottle Task
Ryo Watanabe, Maxime Alvarez, Pablo Ferreiro +2
Manipulator robots are increasingly being deployed in retail environments, yet contact rich edge cases still trigger costly human teleoperation. A prominent example is upright lyin…