About

Lauren Miller’s research lies at the intersection of robotics, machine learning, and real-world sensing, with a focus on developing autonomous systems that learn from limited data and operate in unstructured environments. Her most impactful work, “Tumor localization using automated palpation with Gaussian Process Adaptive Sampling” (73 citations), introduces a probabilistic approach to robot-assisted surgery, enabling precise estimation of embedded tumor geometry to minimize tissue damage and improve cancer removal outcomes. In robotics learning, Miller’s SWIRL algorithm (66 citations) pioneers a hybrid method that combines unsupervised learning from a few expert demonstrations with sequential inverse reinforcement learning, allowing robots to efficiently acquire complex tasks with delayed rewards—a breakthrough for domains like surgical assistance and autonomous agriculture. Her contributions extend to precision agriculture with the DATE device (18 citations), a co-robotic handheld tool that automates drip irrigation emitter tuning, addressing global water scarcity. Miller’s work has been recognized in leading robotics venues, including the “Algorithmic Foundations of Robotics” proceedings (28 citations). Her research exemplifies how principled algorithmic design can translate into tangible solutions for healthcare, sustainability, and autonomous systems.

Research Focus

Key Achievements

5
H-Index
5
Papers
194
Total Citations
39
Avg Citations/Paper
🏆 Most Cited Paper
Tumor localization using automated palpation with Gaussian Process Adaptive Sampling
73 citations · 2016
📈 Most Prolific Year: 2016 (2 Papers)
🤝 Key Collaborators: 18
🏛 Institutions: University of California, Berkeley, Center for Information Technology Research in the Interest of Society

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago