Taylor Apgar

Papers

Total Citations

183

H-Index

About

Taylor Apgar is a leading researcher in the field of bipedal robotics, specializing in the intersection of trajectory optimization and reinforcement learning for dynamic locomotion. Her most impactful contribution is the development of fast online trajectory optimization for multi-step motion planning, applied to the Cassie bipedal robot. This work, which has garnered 135 citations, leverages Cassie’s compliant, spring-mass leg design to simultaneously optimize center-of-mass motion and foothold placement, enabling agile and efficient walking. Apgar has also pioneered the use of reinforcement learning to train task-space actions for bipedal locomotion, moving beyond traditional joint-coordination controllers. Her 2021 paper on this topic (45 citations) demonstrates how RL can learn robust policies directly from task-space objectives, reducing reliance on pre-existing controllers. This dual approach—combining model-based optimization with data-driven learning—positions Apgar as a key figure in advancing real-world bipedal mobility. Her work not only pushes the boundaries of robot agility but also provides practical frameworks for deploying legged robots in unstructured environments, making her research essential for students and engineers aiming to build the next generation of dynamic walking machines.