| NSF Org: |
TI Translational Impacts |
| Recipient: |
|
| Initial Amendment Date: | August 22, 2016 |
| Latest Amendment Date: | December 10, 2018 |
| Award Number: | 1632460 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Muralidharan Nair
TI Translational Impacts TIP Directorate for Technology, Innovation, and Partnerships |
| Start Date: | September 1, 2016 |
| End Date: | March 31, 2019 (Estimated) |
| Total Intended Award Amount: | $750,000.00 |
| Total Awarded Amount to Date: | $750,000.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
21 Wendell St Apt 20 Cambridge MA US 02138-1850 (617)501-0085 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
28 Dane Street Somerville MA US 02143-3237 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | STTR Phase II |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.084 |
ABSTRACT
The broader impact/commercial potential of this project affects one of the fastest-growing sectors of the US economy. E-commerce sales in 2015 accounted for 7.4% of total U.S. retail and are expected to rapidly rise. The potential for the commercial impact of general each-picking systems is high, as current manual labor methods are pain points for distribution centers; human picking is unpleasant, expensive and inefficient due to high absenteeism, high turnover and human error. The success of the proposed technology will also contribute to American competitiveness in the robotics industry. Of the top 20 distribution system integrators, only three are currently based in the U.S. Robotics is going to be the key driver of progress in this area, where each-picking, our core product capability, is a key component of future automated distribution systems. Beyond warehousing logistics, applications that our technology can benefit include: broad applications of industrial automation and manufacturing; military applications (e.g., IED disposal, where robots can perform tasks that are dangerous for humans to perform); and assistive healthcare (e.g., where robots must be compliant enough to be safe around humans while interacting successfully with unknown environments).
This Small Business Innovation Research Phase II project will focus on the development of a state-of-the-art each-picking robotic system and its deployment, initially targeted at the order fulfillment industry. To date, robotic systems have enabled significant progress on transporting inventory on shelves or in totes. However, there has not yet been a deployed system that can perform the task of picking individual items from inventory bins and placing them in boxes for shipment. During Phase I of this project, RightHand Robotics developed a picking system far in advance of the research literature on robotic grasping, picking tens of thousands of items previously unseen objects, with error rates of less than 0.1%. During Phase II, the project will focus on advancing the state of the art in data-driven refinement of grasp planning using machine learning techniques, and will develop methods for box-packing that exploit the company?s advanced compliant grippers. These improvements will result in an average pick-and-place time of 6 seconds or less and an undetected placement failure rate of fewer one in ten thousand.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
The growth of e-commerce is one of the major success stories of the last two decades, and has driven American wage growth and employment to levels not seen for half a century. In order to keep this growth going, retailers must find a way to sustainably expand their businesses. The primary challenge is in the backend logistics of e-commerce. Slick websites give the impression that fulfillment is clean and efficient; however, the explosive growth in demand for distribution and fulfillment has created a category of highly repetitive tasks such as barcode scanning and order sorting. It is difficult to find people to work in these jobs, and even more difficult to retain people in these jobs due to boredom and stress. Just as telecommunications companies had to automate the work of switchboard operators, retailers are now looking for technological solutions that will keep their workforce engaged.
Our company, RightHand Robotics, was started in 2014 as a spinout of the Harvard Biorobotics Laboratory to commercialize decades of work in underactuated robot hands, that is, hands that have more degrees of freedom than actuators. This SBIR grant, “Versatile robot hands for warehouse automation,” funded the initial development of our flagship product, RightPick. RightPick is a robotic piece-picking system that uses machine vision, machine learning and an underactuated robot hand to grasp and manipulate everyday objects it has never before seen. The primary advantage of our novel approach is that the hand has been engineered for the purpose of radically simplifying the machine vision and motion planning problems associated with grasping an object. The hand itself adapts passively to the shape of any grasped object, thereby reducing the need for accurate estimates of object shape or orientation. A library of stereotyped motion primitives is sufficient for grasping all but the most complicated class of items, and the features that must be extracted via machine vision are simple, such as the center of mass and principal axes of the object.
The first question addressed in the project was the design of an improved hand capable of surviving the millions of cycles required in the warehouse environment. The earlier prototypes developed at Harvard survived several hundred thousand cycles, but a major redesign was required to improve durability, thermal robustness, and control precision. Additionally, the grant funded development of better algorithms for segmentation of cluttered and tightly packed objects, and methods for the placement of items that take into account the passively adaptive behavior of the underactuated hands. The NSF’s commercialization process was immensely useful in finding early pilot customers and refining our product concept.
RightPick is now in operation with customers in the US, Europe and Asia, and RightHand Robotics has raised over $34 million in private venture funding to continue growing.
Last Modified: 10/30/2019
Modified by: Lael U Odhner
Please report errors in award information by writing to: awardsearch@nsf.gov.
