ShapeMap 3-D: Efficient shape mapping through dense touch and vision
This work addresses shape mapping for robot manipulation, but it is incremental as it builds on existing visuo-tactile methods with a focus on efficiency.
The paper tackles the problem of 3-D object shape mapping in unstructured environments by combining dense tactile and vision data, achieving efficient incremental reconstructions of household objects in simulated and real-world experiments.
Knowledge of 3-D object shape is of great importance to robot manipulation tasks, but may not be readily available in unstructured environments. While vision is often occluded during robot-object interaction, high-resolution tactile sensors can give a dense local perspective of the object. However, tactile sensors have limited sensing area and the shape representation must faithfully approximate non-contact areas. In addition, a key challenge is efficiently incorporating these dense tactile measurements into a 3-D mapping framework. In this work, we propose an incremental shape mapping method using a GelSight tactile sensor and a depth camera. Local shape is recovered from tactile images via a learned model trained in simulation. Through efficient inference on a spatial factor graph informed by a Gaussian process, we build an implicit surface representation of the object. We demonstrate visuo-tactile mapping in both simulated and real-world experiments, to incrementally build 3-D reconstructions of household objects.