Robot gripper uses touch to find and grasp objects without vision
GLoTouch: Global-to-Local Haptic Perception Using a Parallel Gripper for Object Search, Recognition, and Grasping Without External Vision
Robotics
Summary
Robots usually use cameras to see objects they need to pick up, but that doesn’t work well in the dark or in messy containers. The authors created a system called GLoTouch that helps a robot gripper find, recognize, and grasp objects using only touch. It first uses a long probe to explore the space inside a container and get a rough idea of where things are, then it uses touch sensors on the gripper itself to carefully identify and grab the target object. This approach works without needing special training for each object.
What this means in practice
- •For industrial automation teams: Equip robots to search and grasp parts in dark or cluttered factory containers without using cameras.
- •For warehouse robotics operators: Enable warehouse robots to locate and pick items inside bins when visual cues are unavailable or unreliable.
Authors
Zonglin Li, Wanruo Zhang, Yiming Wang, Kun Song, Xinyi Zhou, Daolin Ma
Abstract
Perceiving objects in the environment is a fundamental capability of autonomous robots. In dark or low-light environments, external cameras often fail to reliably perceive object positions and geometry; when visual sensing is unavailable, completing target search, recognition, and grasping through touch alone becomes a key robot manipulation capability. This task must simultaneously address container-scale spatial exploration and object-scale fine-grained geometric perception, which is particularly challenging for low-degree-of-freedom parallel grippers. However, a unified framework remains lacking for connecting container-scale spatial exploration with object-scale fine-grained geometric perception and grasping. To address this challenge, we present \textbf{GLoTouch}, a global-to-local haptic perception and manipulation framework built on a parallel gripper. In the global stage, the gripper holds a passive long-reach probe, combining force measurements with known tool geometry to localize contacts and actively estimate candidate-object positions, coarse contours, and heights. In the local stage, the robot sets down the probe and uses the bilateral visuotactile sensors on the same gripper to directly acquire local haptic observations, which are matched against a given target 3-D model without object-specific training. We evaluate the framework in both simulation and real-robot experiments. Source code will be open-sourced.