Seth Isaacson

Papers

Total Citations

H-Index

About

Seth Isaacson is a researcher at the forefront of 3D computer vision and safe autonomous robotics, with key contributions spanning neural scene representation, human-robot collaboration, and motion planning. His work on **SAD-GS: Shape-aligned Depth-supervised Gaussian Splatting** (2024, 4 citations) introduces a novel depth-supervision strategy that significantly enhances the geometric accuracy of 3D reconstructions from Gaussian Splatting, a critical advancement for applications in dynamic scene reconstruction and real-time simulation. In the domain of human-robot interaction, Isaacson developed **MAD-TN** (2019, 4 citations), a pioneering tool that leverages temporal constraint networks to quantitatively measure fluency in human-robot collaboration—a metric essential for evaluating coordination and timing in shared tasks. More recently, his 2025 work on **Conformalized Reachable Sets for Obstacle Avoidance with Spheres** (3 citations) addresses the pressing need for safe, real-time motion planning in unstructured environments, offering a mathematically rigorous framework to prevent collisions and ensure human safety. With each publication demonstrating immediate impact and relevance, Isaacson’s research consistently bridges theoretical innovation with practical deployment, making him a rising voice in the integration of perception, planning, and human-aware autonomy.