Chris Vigorito

Papers

Total Citations

H-Index

About

Chris Vigorito is a researcher advancing the frontier of robot learning, with a focus on enabling machines to acquire complex skills from high-dimensional sensory data. His work centers on imitation learning, self-supervised learning, and goal-conditioned manipulation—areas critical for developing robots that can operate autonomously in unstructured environments. Vigorito’s major contributions include pioneering methods for learning from visual demonstrations that handle multiple intentions, a significant step beyond traditional single-task learning paradigms. His 2018 paper on this topic, which has garnered 6 citations, addresses the challenge of extracting diverse behaviors from raw image inputs using deep neural networks. In his 2020 work on self-supervised goal-conditioned pick and place (4 citations), Vigorito tackled the problem of learning from autonomously collected robot data without human labels, developing pixel-wise object representations that enable efficient manipulation. These contributions demonstrate his ability to address fundamental bottlenecks in robot learning, from handling perceptual complexity to leveraging unlabeled interaction data. Vigorito’s research is shaping how robots can learn more flexibly and autonomously, with implications for real-world applications in manufacturing, logistics, and service robotics.