Mobile Autonomous Vehicles for Manufacturing

Mobile equipment is heavily used in manufacturing. There is a growing acceptance of either partially or fully autonomous equipment in the manufacturing area. A major problem, however, is that (especially small) manufacturing facilities frequently operate with people and mobile equipment moving through the same cluttered and constantly-changing environment. Safety is of paramount concern, and standards are essential to reduce the potential for injury.  The ability to control multiple autonomous vehicles from different manufacturers and to mount different sensors from different vendors is also a challenge. This project will develop standard test methods and performance measures using advanced sensor and control systems and operator alerts to help improve standards for semi-autonomous and autonomous industrial vehicles.

Develop the measurement science and standards to enable humans and autonomous mobile vehicles to work safely in close proximity on the factory floor.

Automated guided vehicles (AGV's) are typically used in confined areas away from human interaction. It is not possible for a single controller to handle AGVs from multiple vendors and the entire vehicle fleet at a facility is typically controlled by a host computer, with each vehicle or group of vehicles working in an independent zone. Recently, the ANSI B56.5 standard was improved with substantial input from NIST to allow non-contact sensing of specific test pieces for safe AGV's. The standard now mandates non-contact safety sensing in 3D. Still missing are dynamic 3D measurements to improve the test methods and allow safe AGV use near humans, on flexible assembly lines, and in unstructured environments. Also, OSHA accident statistics^[1] show that high accident rates for manned forklifts are mainly due to the existence of blind spots around the vehicles. There are over one million manned vehicles in factories, causing, on average, an accident every 3 days of which 80% include a pedestrian. Today's advanced 3D imaging technology and control has the potential to eliminate blind spots and to provide semi-autonomous vehicle control for safe slow-downs and stops. The ANSI B56.5, B56.1 and B56.11.6 committees have all expressed interest in measurements that improve these standards to address visibility hazards.

The new technical idea is to develop the measurement science that will allow advances in 3D sensor technology and in open source, low cost control environments to improve control capabilities for safe autonomous industrial vehicles. This idea will also serve the much larger industry of manned manufacturing vehicles that will have semi-autonomous functionality. The project will develop performance measures and new test methods for sensor-based vehicle control. It will support standards including ANSI B56.5 (part A - AGV's and part B - automated functions of manned vehicles), B56.1 (high lift vehicles), and B56.11.6 (visibility for vehicles) and the recent international ISO/DIS 13564-1 (visibility for vehicles) standard. This project will also investigate data formats for high-level control software and integration and interoperability of sensor technologies with vehicle controllers.

The project will build on prior NIST contributions to the ANSI B56.5 standard, especially in part A, with performance measurements of moving test pieces (e.g., standard test pieces and mannequins) and autonomous navigation in close proximity to mannequins. Ground truth of these components will be obtained and combined with vehicle navigation and test apparatus position data to develop performance measures for improved standard vehicle safety tests.

Recently, a request was made by the B56 committees that "NIST provide additional information on how technologies might apply to B56.1 (lift vehicles) and B56.11.6 (visibility)". This is a natural extension from the B56.5 standard part B - automated functions of manned vehicles, where operator visibility is addressed.

Current methods specified in visibility standards provide poor estimates of blind spots and thereby allow 20% of the region around the operator to be obscured. Preliminary B56.1 pallet measurements performed at NIST showed promise for using vision, 2D LADAR and 3D LIDAR sensor technology for visualizing even obstructed pallet openings. Also, measurements performed at NIST in FY11 that followed both the ISO/DIS 13564-1 and the B56.11.6 standards uncovered several measurement and analysis issues suggesting that the standard test method of using a halogen lamp array may not be effective for determining operator blind spots around vehicles.^[2] Instead, in FY12 an advanced approach to measuring the visibility will be performed using laser measurement technology. The project will collaborate with a university, such as Georgia Tech, which has made advancements in construction vehicle visibility measurements that can be leveraged for manufacturing vehicles. Preliminary results and follow-on plans will be presented in February 2012 at the B56.11.6 committee meetings with the goal of developing test methods for automated visibilibility measurements in FY13.

These advanced methods are expected to provide accurate obscured region details of the as-built vehicle and payload and will provide the basis for new standards language in B56.5 part B. In FY12, performance measurements will be completed using advanced 2D and 3D imagers and data of obscured vehicle regions will be combined with vehicle driver alerts and semi-autonomous, open-source control. Independent measurement of vehicle response compared to advanced sensor data will be evaluated for semi-autonomous control of slow and stop vehicle performance to develop standard test methods. For example, these measurements would provide the standard with language to mandate that if an operator does not react to a hazardous situation, the vehicle itself will control a safe slow or stop. Concepts will be tested using standard test pieces, mock manufacturing environments, and mannequins. Findings will be published and provided as recommendations to the ANSI B56.11.6 and B56.5 committees and to the ISO 13564-1 standards committee to improve the current standards.

Also in FY12, the project will develop performance tests to assess advanced sensing and operator alert technologies to support improving operator visibility for low and high lift vehicles. Technologies to be explored include 2D and 3D imaging, etc. combined with 3D modeling and vehicle control in typical manufacturing spaces.

In future years, ANSI B56.x and ISO 13564-1 standards efforts are expected to continue from the FY12 basis. Specifically, In support of B56.5 and B56.11.6, manned vehicle blind-spot measurements will be improved through the use of automated sensing and 3D modeling that improve test methods.A strawman design for an automated measurement system will be developed and published in a journal article. A proposal to the ANSI B56.5 standards committee will be developed for improved test methods for semi-autonomous control of manned vehicles using advanced 2D and/or 3D imaging sensors.

The project will address the B56.1 need for safe, 3D modeling and display of vehicle access volumes for high reach vehicles Results will be published in conference and/or journal articles and will be used to draft new standards language.

A standards committee will be proposed and formed on multi-vendor AGV and sensor plug-and-play control and alerts

• Improved B56.5 draft standard with non-contact sensing clarification and addition of a new test piece and test piece reflectivity properties, currently under ballot in the main committee.
• Forklift safety research and conference papers were presented:
• • Bostelman, Shackleford: 'Performance Measurements Towards Improved Manufacturing Vehicle Safety Feasibility' PerMIS09
  • Bostelman, Shackleford: 'Advanced Sensing Towards Improved Forklift Safety' PerMIS'10
• Improving Forklift Safety 2009 Workshop and paper:
• • White Paper: Towards Improved Forklift Safety, PerMIS '09
• Conference paper on vehicle diagnostics tools:
• • Bostelman, Shackleford, "Improved Performance of an Automated Guided Vehicle by using a Smart Diagnostics Tool," IEEE International Conference on Industrial Technology (ICIT '10)
• Exhibited at ProMat Material Handling Show, Chicago, 2011 displaying experiments of humans near robots and vehicles.

Standards and Codes: 

• Participate in ANSI/ITSDF B56.5 committee for AGV's and unmanned industrial vehicles with automated functions
• Participate in ANSI/ITSDF B56.1 and B56.11.6 committees for visibility and lift vehicles. 
  

[1] Roger Bostelman, "White paper: Towards Improved Forklift Safety," PerMIS '09 Special session workshop. 2009.

[2] Roger Bostelman, Li Peng Liang, Measurement and Evaluation of Visibility Experiments for Powered Industrial Vehicles, NISTIR 7837, December 2011.