- Stewart J. Moorehead, John Deere: R Gator: An Unmanned Utility Vehicle for Off-Road Operations
- Marcel Bergerman, Carnegie Mellon University: Autonomous Orchard Vehicles for Specialty Crops Production
The R Gator is an unmanned ground vehicle built on the John Deere 6x4 M Gator utility vehicle chassis. The vehicle is capable of operating in urban and off road terrains and has a large payload to carry supplies, injured people or a marsupial robot. The robotic drive by wire system was added on top of the existing mechanical linkages so if the electronics fail, the vehicle can still be driven manually.
Operating in rough, off-road terrain is a challenge for any robotic system. Simple systems that work indoors or on parking lots are not sufficient to detect holes, deal with hills or allow the vehicle to push through tall, soft, vegetation such as grasses. The R Gator uses a pair of 3D lasers combined with a radar to create detailed maps of its surroundings and reason about the traversability of the terrain. This perception system allows it to negotiate rough, off-road and vegetated terrain.
Another key aspect of the R Gator, or any autonomous vehicle, is how easy it is to operate. The R Gator makes use of a standard game controller to provide a simple, intuitive interface that allows full operations of the vehicle with minimal training.
This talk will detail the systems developed for the R Gator, focusing on the novel user interface and the obstacle detection system, which allows autonomous operations in tall grass. Designs for a new four-wheel, independent suspension chassis version are also presented and how this can be applied to other agricultural vehicles will also be discussed.
Stewart Moorehead is the Manager, Field Robotics at John Deere’s Moline Technology Innovation Center. In this role, he is responsible for leading the enterprise efforts in field robotics technology development and coordinating activities with the business units.
Stewart joined John Deere in 2004 to work on the autonomous stadium mower project. Since then, he has been involved in several robotics projects including the R-Gator, Autonomous Orchard Tractor and Autonomous Fairway Mower. His work has focused on obstacle detection and improving the robustness of robotics technology to function in unforgiving conditions found on farms and construction sites.
Stewart has a PhD in Robotics from Carnegie Mellon University and Bachelor and Masters degrees in Electrical Engineering from the University of Waterloo.
Specialty crops constitute a $45 billion/year industry. As opposed to crops such as wheat, cotton, corn and soybean, they are characterized by the need for intensive cultivation. Specialty crops growers currently face serious labor cost and availability problems, and few technological solutions exist to increase their efficiency given the past history of abundant supply of low-cost labor. This leads to an opportunity to use recent technological advances to not only increase efficiency and reduce labor costs in specialty crops production but also to support a domestic engineering solutions industry for specialty crops.
We envision a family of reconfigurable vehicles that can be rapidly tasked to automate or augment pruning, thinning, harvesting, mowing, spraying, etc. They would share a common sensing and computing infrastructure, allowing applications created for one to be easily transferable to others—much like software applications today are transferable from one computer to another.
In this talk we describe our work over the last three years designing and deploying a family of such vehicles, the Autonomous Prime Movers (APMs). The five vehicles completed so far have traveled autonomously over 330 km in research and commercial tree fruit orchards; preliminary results in time trials conducted by extension educators indicate efficiency gains of up to 58%.
Marcel Bergerman is a systems scientist at Carnegie Mellon’s Robotics Institute, in Pittsburgh, PA, where he develops autonomous vehicles for field applications. His current work focuses on agricultural robotics and automation systems.
He received his Ph.D. degree from CMU in December, 1996. From 2001 to 2005 Mr. Bergerman worked at Genius Institute of Technology in Manaus, Brazil, as the leader of institutional relationships and knowledge management, and later as innovation manager. From 1997 to 2000 he was the coordinator of the Robotics and Computer Vision Laboratory at the Information Technology Institute in Campinas, Brazil, where he worked on Internet-accessible laboratories, autonomous robotic airships, and robotic manipulators.
Mr. Bergerman has published over 100 papers in the areas of robotics and innovation management, and has recently co-authored a book on robust control of robotic manipulators.