Diogo Carneiro

Papers

Total Citations

H-Index

About

Diogo Carneiro’s research lies at the dynamic intersection of human-robot interaction, anticipatory robotics, and motor control. His work fundamentally addresses how robots can infer human intention from observed actions, enabling more fluid and responsive collaboration. Carneiro’s major contribution is pioneering the use of early anticipation signals—detecting subtle cues in a human partner’s movement before an action is fully executed—to dramatically improve robotic performance in real-time interactive tasks. His 2018 study on early anticipations for human-robot ball catching (7 citations) demonstrated that robots equipped with this predictive capability could significantly enhance catching success by acting on pre-movement information. Building on this, his 2021 work on a Robot Anticipation Learning System (5 citations) tackled the notoriously difficult challenge of catching flying objects, overcoming the critical limitations of short ball flight times and motion uncertainty. By shifting the predictive window earlier in the interaction, Carneiro has opened new pathways for robots to engage in fast-paced, cooperative physical tasks. His research is highly relevant for advancing assistive robotics, collaborative manufacturing, and any domain requiring seamless human-machine teamwork.