Catherine Weaver
Papers
1
Total Citations
3
H-Index
1
About
Catherine Weaver is a rising researcher at the intersection of artificial intelligence, robotics, and autonomous systems, with a primary focus on imitation learning and control for high-speed, dynamic environments. Her most notable contribution, the paper "BeTAIL: Behavior Transformer Adversarial Imitation Learning From Human Racing Gameplay" (2024), introduces a novel framework that enables autonomous vehicles to learn complex racing maneuvers directly from human demonstrations, bypassing the need for hand-designed physical models or reward functions. This work addresses a critical challenge in autonomous racing—planning minimum-time trajectories under uncertain dynamics while controlling vehicles at their handling limits—by leveraging behavior transformers and adversarial imitation learning. Although early in her career, with 3 citations on this paper, Weaver's approach represents a significant step toward more adaptable and human-like control systems. Her research has implications beyond racing, including autonomous navigation in unpredictable environments and robotic manipulation. By reducing reliance on domain-specific engineering, Weaver's work paves the way for more generalizable AI-driven control, marking her as a promising innovator in the field of learning-based robotics.
Research Focus
Key Achievements
Top Papers
- 1