Built Different: Tactile Perception to Overcome Cross-Embodiment Capability Differences in Collaborative Manipulation
This work addresses the problem of cross-embodiment capability differences in robotics for collaborative manipulation, offering an incremental improvement by adapting existing methods to new hardware constraints.
The paper tackled the challenge of enabling collaborative manipulation across robots with different hardware capabilities, particularly those lacking joint torque sensing, by using tactile sensors and behavior cloning to transfer policies from force-controlled robots. The result was a single policy that achieved positive transfer across four tactile-enabled embodiments, with a decomposed tactile shear-field representation and pre-trained encoder improving success rates over alternatives.
Tactile sensing is a widely-studied means of implicit communication between robot and human. In this paper, we investigate how tactile sensing can help bridge differences between robotic embodiments in the context of collaborative manipulation. For a robot, learning and executing force-rich collaboration require compliance to human interaction. While compliance is often achieved with admittance control, many commercial robots lack the joint torque monitoring needed for such control. To address this challenge, we present an approach that uses tactile sensors and behavior cloning to transfer policies from robots with these capabilities to those without. We train a single policy that demonstrates positive transfer across embodiments, including robots without torque sensing. We demonstrate this positive transfer on four different tactile-enabled embodiments using the same policy trained on force-controlled robot data. Across multiple proposed metrics, the best performance came from a decomposed tactile shear-field representation combined with a pre-trained encoder, which improved success rates over alternative representations.