Canonical mapping as a general-purpose object descriptor for robotic manipulation
This addresses the need for adaptable perception in semi-structured environments for robotics, though it appears incremental as it builds on existing representation concepts.
The paper tackles the problem of narrow, task-specific object representations in robotic manipulation by proposing canonical mapping as a universal descriptor, demonstrating its robustness in multi-stage experiments with two robot arms.
Perception is an essential part of robotic manipulation in a semi-structured environment. Traditional approaches produce a narrow task-specific prediction (e.g., object's 6D pose), that cannot be adapted to other tasks and is ill-suited for deformable objects. In this paper, we propose using canonical mapping as a near-universal and flexible object descriptor. We demonstrate that common object representations can be derived from a single pre-trained canonical mapping model, which in turn can be generated with minimal manual effort using an automated data generation and training pipeline. We perform a multi-stage experiment using two robot arms that demonstrate the robustness of the perception approach and the ways it can inform the manipulation strategy, thus serving as a powerful foundation for general-purpose robotic manipulation.