Enabling Robot-assisted Motion Capture with Human Scale Tracking Optimization
summary
System mounts an array of sensing coils and a driving coil to track LC resonant markers and actively rotates the sensor array with a robot using a PID controller plus a dampening layer, optimizing Theta and Phi via a steepest-ascent hill-climbing Gamma objective (product of marker axle projections). Results: stabilizes data across a 26× larger volume, prevents hundreds of sub‑optimal states per recording and yields about ~40% tracking error reduction compared to a static setup.
AI-written summary · about
related talks
31mData as an instrument for more efficient collaboration with robots
05mHuman-in-the-loop Pose Estimation via Shared Autonomy
24m3D Backscatter Localization for Fine-Grained Robotics
09mTask-Consistent Signaling Motions for Improved Understanding in Human-Robot Interaction and ...
26mFrom Panoramic Vision to Lightweight 3D Worlds for Semantic Visual Tracking
48mROS on your robot: the tale of an inside, an outside robot and 2 arms
47mAchieving Software Quality Excellence Thru Software-Hardware Co-Design & Co-Verification
55mUsing a Lidar for Robot Navigation in a Room