Whole-Arm Sensing

Enabling robots to perceive contact across their entire arm for human-like interaction and coordination.

Whole-Arm Sensing 1
Whole-Arm Sensing 2

Human-like manipulation requires more than controlling a robot’s end-effector. People naturally use their entire arms to perceive and interact with the environment: we recognize where contact occurs, understand how forces are distributed, and coordinate the whole arm accordingly.

Giving Robots Whole-Arm Contact Awareness

My research focuses on giving robot manipulators this same sense of whole-arm awareness. Using only proprioceptive measurements, the robot estimates where along its entire arm it is in contact with the environment and identifies the forces acting at each location. This allows the whole robot arm, rather than only the gripper, to become an active sensing surface without relying on external cameras or artificial tactile skin.

By understanding its physical relationship with the surrounding environment, a robot can move beyond isolated end-effector motion toward coordinated use of all its links. Whole-arm sensing provides the contact-rich state information required for safe interaction, adaptive motion, and ultimately human-like whole-arm coordination in complex environments.

  1. Mixture of Flow Matching and Particle Filter for Proprioception-based Online Contact Estimation
    • Seo Wook Han, Min Jun Kim
    • IEEE Transactions on Robotics (T-RO), 2026 (accepted, will be presented at Humanoids 2026)
  2. CDM: Contact Diffusion Model for Multi-Contact Point Localization
    • Seo Wook Han, Min Jun Kim
    • IEEE International Conference on Robotics and Automation (ICRA), 2025
  3. Learning Multi-Contact Localization via Diffusion Models with Proprioceptive Sensing
    • Seo Wook Han, Min Jun Kim
    • RSS Workshop on Navigating Contact Dynamics in Robotics, 2025
  4. Contact Estimation Diffusion Model for Collaborative Robots
    • Seo Wook Han, Min Jun Kim
    • IEEE International Conference on Control, Automation, and Systems (ICCAS), 2024
  5. Proprioceptive Sensor-Based Simultaneous Multi-Contact Point Localization and Force Identification for Robotic Arms
    • Seo Wook Han, Min Jun Kim
    • IEEE International Conference on Robotics and Automation (ICRA), 2023
  6. Multi-Contact Point Localization and Force Identification for Collaborative Robot Arm using Proprioceptive Sensor
    • Seo Wook Han, Min Jun Kim
    • Korea Robotics Society Annual Conference (KRoC), 2023