Adam Sigal
Papers
2
Total Citations
11
H-Index
2
About
Adam Sigal is a roboticist whose research sits at the intersection of tactile sensing, imitation learning, and socially-aware navigation. His work addresses two fundamental challenges in robotics: enabling robots to perform delicate, contact-rich manipulation tasks, and ensuring they can navigate human environments with social grace. In his highly-cited 2024 paper, "Multimodal and Force-Matched Imitation Learning With a See-Through Visuotactile Sensor" (9 citations), Sigal pioneered a novel approach that leverages a transparent visuotactile sensor to capture both visual and force feedback. This multimodal data allows robots to learn complex tasks involving relative motion—like slipping and sliding—through imitation, a significant step toward dexterous manipulation. Earlier, in his 2023 work "Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation" (2 citations), he tackled the problem of training robots to navigate crowded human spaces by developing reinforcement learning regimes that improve policy generalization across diverse social contexts. Sigal’s contributions are particularly notable for their practical focus on real-world deployment, bridging the gap between controlled lab settings and the unpredictable, contact-rich dynamics of human environments. His work is shaping the next generation of robots that can both handle objects with care and move among us with awareness.
Research Focus
Key Achievements
Top Papers
- 1
- 2