You are here

Research and Testing of a Robotic Arm Embedded with Artificial Intelligence (AI) for use within Defense Logistics Agency (DLA) Distribution Center Warehouses


RT&L FOCUS AREA(S): Warfighter Requirements (GWR) TECHNOLOGY AREA(S): Information Systems The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 3.5 of the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. OBJECTIVE: Concept statement: DLA is exploring the use of robots to include robot arms to better understand what capability these machines provide to leverage human tasks in materiel handling. One approach DLA wants to explore is to incorporate Artificial Intelligence into individual robots to provide autonomy to resolve current issues in materiel handling. Develop a Robotic Arm that utilizes an Artificial Intelligence (AI) solution (with deep learning if applicable) to provide a state-of-the-art capability to identify items, and pick, pack, and arrange picked items within selected boxes and operate within the DLA Distribution Warehouse environment. Additionally, the AI-embedded Robotic Arm must provide the adaptive pushing displacement required for the tight packing of items within shipping boxes, and must communicate with various warehouse systems (e.g., Internet of Things (IoT)) as needed. The desired solution should minimize infrastructure modifications to enable the artificial intelligence embedded robotic arm to operate within the warehouse environment. The goal of this effort is for the vendor to develop a capability an AI-embedded robotic arm system operating in the warehouse, that addresses the requirements for integrating with warehouse communications systems onsite (if required), such as the Warehouse Execution System (WES) at the specific warehouse. As such, this capability provides for the seamless execution of the AI-embedded Robotic Arm and its subsequent interactions with any future Smart Warehouse systems that may be developed and employed. Provide a report with a detailed analysis that captures concepts on using robotics to include robotic arms which incorporate features of artificial intelligence. The study and analysis can include concepts and approaches that are innovative and may not be known from current market research, or individual development through industry or academia. Prospective vendors should organize the objectives by priority as shown below: • Explore using methods and schemes that allow for least cube space. • How the robot system adapts or can be integrated into existing Warehouse Management System (WMS). • How the robotic system seamlessly integrates into communications and equipment like current Internet of Things (IoT), 5G communications, and knowledge systems to manage warehouse operations. • Future communications systems and equipment beyond 5G, and IoT. The state-of-the-art AI-embedded Robotic Arm solution must integrate into the existing warehouse communications systems to communicate with the WES system to allow for the embedded AI Robotic Arm to receive automated tasking instructions to pick and pack boxes, crates, and bins and use AI to accurately identify boxes, cases, crates, and individual end-items using loaded configuration information and task instructions. The provided packing instructions will be pushed to the Robotic Arm by the WES. The robotic arm should be able to operate continually as needed, and report back to the WES on the programmed Robotic Arm’s task success or failure. At a minimum, the prospective vendors should: • Explore what systems in a robotic arm or other mechanism can offer the best way to identify materiel correctly that matches with materiel transaction requests (i.e., machine vision). • Recommend methods and schemes that impact or complement robotic functionality like accurate transactions using block chain. • Discuss methods where robots and robotic arms adapt to random materiel requests regardless of timeframe, location, or item request. • Discuss methods and schemes as to the flexibility of robot tasks that mimic human tasks like packing, moving parts and equipment, wrapping, and other tasks in warehouse operations. In support of routine warehouse robotic arm operations, this research seeks to identify and test a Robotic Arm utilizing AI technology used to intelligently pack boxes within the DLA distribution warehouse environment. Importantly, the selected vendor must address the DLA-identified cybersecurity requirements by testing and evaluating the government's security control. The vendor should leverage the current technologies found in both the Robotic Arm and the AI industries. This research project will operate in locations at designated DLA Distribution Centers in the United States. DESCRIPTION: Defense Logistics Agency (DLA) Distribution Modernization Program (DMP) topics of interest are research focused on a Continental United States-based robotic arm with an Artificial Intelligence (AI) solution in support of the routine warehouse end-item picking for box packing operations. The resulting solution must be integrated with existing WES communications suites and integrate with warehouse navigation systems, that: 1. Supports a joint effort between DLA Research and Development (R&D) and DLA J4 Distribution Headquarters to conduct research and test an AI-embedded warehouse Robotic Arm system that works during warehouse operations. 2. Significantly addresses an AI-embedded Robotic arm's capabilities within an operational distribution warehouse environment. 3. Features an AI-embedded Robotic Arm that can implement repetitive box packing tasks with high precision and accuracy for regular use in warehouse operations. 4. Can be integrated into warehouse communications systems such as a WES to receive tasking and report on performance status. 5. Demonstrates a state-of-the-art operational capability when operating within the distribution warehouse environment through the application of AI-embedded Robotic Arm technology and seamlessly integrates with robust communications network technologies in a distribution warehouse environment shared with warehouse workers. 6. Provides for a reliable and robust technology solution that allows DLA Distribution Warehouses to perform automated tasks without significantly lowering operating speeds per existing industry trends. 7. Demonstrates compatibility with a Government data cloud environment to store and retrieve warehouse-generated data without relying on a separate commercial data cloud environment to navigate successfully. 8. Conclusively demonstrates the use of new AI technology and concepts for application and integration with a Robotic Arm to improve the distribution and delivery of material and goods during representative distribution warehouse operations in an innovative way. 9. All robotic/AI software control remains within the DLA server and does not transfer/communicate out to a vendor server. 10. Robotic arm needs to safely maneuver around humans without the need of a safety cage. PHASE I: Perform a design study to determine how to use a robotic arm that utilizes artificial intelligence to optimize DLA Distribution Warehouse operations, sustainment, and logistics support. Deliver a final design of a Robotic Arm with AI capability, a simulation model of DLA Distribution assets, and a demonstration of an AI-infused Robotic Arm model capable of making intelligent trade-off decisions to meet specified PM requirements. A successful design optimizes support, minimizes DLA Distribution Warehouse system downtime, and maximizes system availability using logistics inputs (component failure rates, shipping times, repair times, maintenance man-hours, and warehouse staffing). The SBIR Phase I expectation is to provide and successfully demonstrate how their proposed AI-embedded Robotic Arm concept of operations (CONOPS) improves the packing and arrangement of boxes. This automation provides for the more efficient distribution of goods and materials within the DLA distribution enterprise and effectively lessens the time to provide needed supplies to the Warfighter. The selected vendor will conduct a feasibility study to: 1. Address the requirements described above in the Description Section for AI-embedded Robotic Arm operations. 2. Identify capability gap(s) and the requirement for DLA to use an AI-embedded Robotic Arm in the DLA Distribution Operations environment. 3. Develop the vendor's Concept of Operations (CONOPS) to utilize an AI-embedded Robotic Arm and clearly describe how the requirements develop. The vendor must create a CONOPS for an AI-embedded Robotic Arm to support both routine and wartime distribution warehouse operations. The concept of operations covers the utilization of artificial intelligence with Robotic Arms within DLA distribution warehouses during routine box packing procedures, precisely describing all operational requirements as part of this process. The vendor must provide a CONOPS that includes the following tasks: • Picking, placing, and relocating items where needed • Perform packing operations mimicking human actions to complete the same steps. • Wrapping tasks to protect materiel, food, perishables, or consumables. • Distinguish in how to perform operations that have hazardous materials, or containers with volatile, caustic, corrosive, or possible explosive content. • Other operations in a warehouse as may be described with end users. This project's deliverables include a final report, including a cost breakdown of the proposed courses of action (COAs). Phase I – 6 Months $100K Phase II – 24 Months $1.6M PHASE II: Based on the research and the concept of operations developed during Phase I, Phase II's research and development goals emphasize the development of the AI-embedded Robotic Arm system following the typical DLA Distribution Warehouse concept of operations for materiel handling. During Phase II, the vendor will: 1. Address the specific user requirements, functional requirements, and system requirements as defined and provided by DLA. 2. Develop a prototype AI-embedded Robotic Arm system for Developmental Test and Evaluation (DT&E) and Operational Test and Evaluation (OT&E). 3. Implement government cybersecurity controls in the prototype design, and secure all necessary cybersecurity certifications to operate the AI-embedded Robotic Arm equipment in the DLA warehouse environment with DOD cloud connections. The DLA AI-embedded Robotic Arm system will operate across the United States at various DLA Distribution Center sites mutually agreed upon between DLA R&D and DLA Distribution HQ. This project's deliverables include a final report, including a cost breakdown of courses of action (COAs). PHASE III DUAL USE APPLICATIONS: Phase III is any proposal that “Derives From”, “Extends” or Completes a transition from a Phase I or II project. Phase III proposals will be accepted after the completion of Phase I and or Phase II projects. There is no specific funding is associated with Phase III, except Phase III is not allowed to use SBIR/STTR coded funding. Any other type funding is allowed. Phase III proposal Submission. Phase III proposals are emailed directly to DLA The PMO team will set up evaluations and coordinate the funding and contracting actions depending on the outcome of the evaluations. A Phase III proposal should follow the same format as Phase II for the content, and format. There are, however, no limitations to the amount of funding requested, or the period of performance. All other guidelines apply. During Phase I and Phase II, the progress made should result in a vendor's qualification as an approved source for an AI-embedded Robotic Arm system and support participation in future procurements. COMMERCIALIZATION: The manufacturer will pursue the commercialization of the AI-embedded Robotic Arm technologies and designs developed to apply to the warehouse environment-- the processes developed in preliminary phases and potential commercial sales of manufactured mechanical parts or other items. The first path for commercial use is at DLA's twenty-six Distribution Centers and twenty Disposition Centers. When fielded, DLA estimates 20 - 26 units, but the number of units could be more. REFERENCES: 1. J. J. Enright and P. R. Wurman, "Optimization and Coordinated Autonomy in Mobile Fulfillment Systems," in AAAIWS'11-09, 2011. 2. F. Wang and K. Hauser, "Stable bin packing of non-convex 3d objects with a robot manipulator," in IEEE ICRA, 2019, pp. 8698–8704. 3. F. Wang and K. Hauser, "Robot packing with known items and nondeterministic arrival order," in R: SS, 2019. 4. A. Sahbani, S. El-Khoury, and P. Bidaud, "An Overview of 3D Object Grasp Synthesis Algorithms," RAS, vol. 60, no. 3, 2012
US Flag An Official Website of the United States Government