POSE: Phase I: Collaborative Open-source Manipulation and Perception Assets for Robotics Ecosystem (COMPARE)

Award ID: 2229577

Manipulation is an essential function for robots. Nearly all visions of advanced robot systems involve a human-like ability to grasp and manipulate objects in industrial or home settings. While great progress is being made, this domain has long suffered from a lack of systematic development and benchmarking methodologies, causing inefficiencies and even stagnation. This project strives to remove the longstanding roadblocks to the development and assessment of robot manipulation hardware and software by establishing an open-source ecosystem (OSE). This scoping project represents the first systematic, community-driven study to determine the needs and wants of robot manipulation researchers regarding open-source asset (OSA) development, utilization, and dissemination. This project will provide the a comprehensive OSE effort in robot manipulation covering physical, digital, instructional, and functional OSAs, leading to the establishment of an effective and sustainable OSE. The project team and collaborators represent five diverse OSAs (the YCB Object and Model Set, NIST Assembly Task Boards, Household Cloth Object Set, Yale OpenHands, and the Robot Operating System (ROS)), along with several industry partners and consortia. Removing the roadblocks that cause stagnation in robot manipulation research may trigger rapid progress towards enabling the robotics technology for a large array of applications in assistive robotics, manufacturing, and logistics industries. Having easy access to open-source assets is expected to expand the number of trained roboticists and stimulate the robotics market. The OSE is also expected to lower the barriers to affordable robotics education by significantly reducing both financial and effort burden. Project website: https://robot-manipulation. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Deepankar Medhi