Caroline Strickland
Papers
1
Total Citations
7
H-Index
1
About
Caroline Strickland is a leading researcher in decentralized robotics and multi-agent reinforcement learning, whose work bridges the gap between theoretical control and practical swarm construction. Her most influential contribution, "A Reinforcement Learning Approach to Multi-Robot Planar Construction" (2019, 7 citations), introduces a novel framework where robot swarms learn to form complex planar shapes by pushing ambient objects into desired patterns. The key innovation lies in her use of a projected scalar field that robots can sample locally, enabling fully decentralized coordination without central control or inter-robot communication. This approach has opened new pathways for scalable construction in unstructured environments, with applications ranging from disaster response to extraterrestrial habitat assembly. Strickland’s work is notable for its elegant fusion of reinforcement learning with physical constraints, demonstrating how simple local rules can produce sophisticated global behaviors. Her research continues to influence the fields of swarm intelligence and robotic construction, making her a rising figure in autonomous systems engineering.
Research Focus
Key Achievements
Top Papers
- 1A Reinforcement Learning Approach to Multi-Robot Planar Construction7 citations · 2019