Hoseong Seo

About

Hoseong Seo is a leading researcher in aerial manipulation, with a focus on enabling multirotor vehicles equipped with robotic arms to perform complex, real-world tasks. His work spans vision-guided control, cooperative manipulation, and safe motion planning. Seo’s seminal 2016 paper on vision-guided aerial manipulation using image-based visual servoing (173 citations) established foundational methods for precise, dynamic control of aerial manipulators. He further advanced the field by demonstrating autonomous interaction with unknown objects, such as opening an unknown drawer (92 citations), and by pioneering cooperative aerial manipulation with multiple multirotors (78 citations). Beyond manipulation, Seo has made significant contributions to robot safety and learning, developing real-time robust trajectory planning using Hamilton-Jacobi reachability analysis and fast funnel computation with multivariate Bernstein polynomials. His recent work on hierarchical action chunking transformers for learning multimodal manipulation skills from demonstrations reflects a growing interest in data-driven approaches. With over 400 total citations, Seo’s research is highly influential in robotics, particularly for applications in inspection, maintenance, and logistics where aerial robots must physically interact with their environment.

Research Focus

Key Achievements

Top Papers

1. 1
   Vision-Guided Aerial Manipulation Using a Multirotor With a Robotic Arm

   173 citations · 2016
2. 2
   Operating an unknown drawer using an aerial manipulator

   92 citations · 2015
3. 3
   Cooperative Aerial Manipulation Using Multirotors With Multi-DOF Robotic Arms

   78 citations · 2018
4. 4
   Learning and Generalizing Cooperative Manipulation Skills Using Parametric Dynamic Movement Primitives

   21 citations · 2022
5. 5
   Real-Time Robust Receding Horizon Planning Using Hamilton–Jacobi Reachability Analysis

   19 citations · 2022
6. 6
   Locally optimal trajectory planning for aerial manipulation in constrained environments

   17 citations · 2017
7. 7
   Position-based monocular visual servoing of an unknown target using online self-supervised learning

   15 citations · 2019
8. 8
   Fast Funnel Computation Using Multivariate Bernstein Polynomial

   10 citations · 2021
9. 9
   Vision-based Target Tracking for a Skid-steer Vehicle using Guided Policy Search with Field-of-view Constraint

   8 citations · 2018
10. 10
    Hierarchical Action Chunking Transformer: Learning Temporal Multimodality from Demonstrations with Fast Imitation Behavior

    3 citations · 2024

Key Collaborators

Contact & Links