Papers
26
Total Citations
1,018
H-Index
16
About
Andrew Spielberg is a robotics and computational design researcher whose work bridges physical simulation, robot design automation, and soft robotics fabrication. He is perhaps best known for **ChainQueen** (2019, 223 citations), a real-time differentiable physical simulator that enabled gradient-based optimization for soft robot planning and control — a foundational contribution that helped establish differentiable simulation as a cornerstone of modern robotics research. His **RoboGrammar** framework (2020, 140 citations) further demonstrated his range, introducing graph-grammar-based automated robot structure generation optimized for terrain traversal. Spielberg has made significant strides in soft robotics fabrication, developing machine-knitting workflows for pneumatic actuators with integrated sensing (2022, 102 citations) and multi-material 3D printing platforms for programmable liquid crystal elastomer structures (2024, 67 citations). His earlier work democratized robot design through systems like Interactive Robogami (2017) and addressed multi-robot assembly planning challenges. Across co-design, sim-to-real transfer, and sensor placement optimization for soft robots, Spielberg consistently works at the intersection of computation, learning, and physical fabrication — producing tools that lower barriers for both expert and novice robot designers.
Research Focus
Key Achievements
Top Papers
- 1ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics223 citations · 2019
- 2RoboGrammar140 citations · 2020
- 3
- 4
- 5
- 6Multi-robot grasp planning for sequential assembly operations61 citations · 2015
- 7
- 8Multi-scale assembly with robot teams44 citations · 2015
- 9
- 10Co-Learning of Task and Sensor Placement for Soft Robotics33 citations · 2021