ICRA 2018 - State Estimation with Tactile and Visual Sensing
arXiv paper: https://arxiv.org/pdf/1709.09694
Accurate and robust object state estimation enables successful object manipulation. Visual sensing is widely used to estimate object poses. However, in a cluttered scene or in a tight workspace, the robot's end-effector often occludes the object from the visual sensor. The robot then loses visual feedback and must fall back on open-loop execution.
In this paper, we integrate both tactile and visual input using a framework for solving the SLAM problem, iSAM (incremental smoothing and mapping), to provide a fast and flexible solution. Visual sensing provides global pose information but is noisy in general, whereas contact sensing is local but the measurement is more accurate relative to the end-effector. By combining them, we aim to exploit their advantages in order to overcome their limitations. We explore the technique in the context of a pusher-slider system. We adapt iSAM's measurement cost and motion cost to the pushing scenario, and use an instrumented setup to evaluate the estimation quality with different object shapes and on different surface materials.