Researchers at the U.S. Army Research Laboratory and the Johns Hopkins University Applied Physics Laboratory have designed a new software to guarantee that if a robot falls, it can get itself back to the original position, thereby making future military robots less dependent on their Soldier handlers.
Based on feedback from soldiers at an Army training course, ARL researcher Dr. Chad Kessens started working on the software to analyze whether any given robot could get itself "back on its feet" from any overturned orientation.
"One Soldier told me that he valued his robot so much, he got out of his vehicle to rescue the robot when he couldn't get it turned back over," Kessens said. "That is a story I never want to hear again."
Scientists from Navy PMS-408 (Expeditionary Missions) and its technical arm, the Indian Head Explosive Ordnance Disposal Technology Division, agree. They partnered with JHU/APL and the prime contractor, Northrop Grumman Remotec, to create the Advanced Explosive Ordnance Disposal Robotic System (AEODRS), a new group of EOD robotic systems containing a modular opens systems architecture. A lightweight backpackable platform, which is increment one of the program, is projected to move into production later this year. One crucial requirement of the program is that the robots should be able to achieve self-righting.
"These robots exist to keep Soldiers out of harm's way," said Reed Young, Robotics and Autonomy Program Manager at JHU/APL. "Self-righting is a critical capability that will only further that purpose."
To assess the AEODRS system's capacity to self-right, JHU/APL partnered with ARL to leverage the software Kessens designed. The team was able to spread its ability to robots having a greater number of joints (or degrees of freedom) because of JHU/APL researcher Galen Mullins' expertise in adaptive sampling methods.
"The analysis I've been working on looks at all possible geometries and orientations that the robot could find itself in," Kessens said. "The problem is that each additional joint adds a dimension to the search space--so it is important to look in the right places for stable states and transitions. Otherwise, the search could take too long."
Kessens said “Mullins' work is what allowed the analysis to work efficiently for analyzing higher degree of freedom systems. While Kessens' work determines what to look for and how, Mullins figures out where to look."
"This analysis was made possible by our newly developed range adversarial planning tool, or RAPT, a software framework for testing autonomous and robotic systems," Mullins said. "We originally developed the software for underwater vehicles, but when Chad explained his approach to the self-righting problem, I immediately saw how these technologies could work together."
He said the crucial aspect to this software is an adaptive sampling algorithm that looks for changes.
"For this work, we were looking for states where the robot could transition from a stable configuration to an unstable one, thus causing the robot to tip over," Mullins explained. "My techniques were able to effectively predict where those transitions might be so that we could search the space efficiently."
Eventually, the team was able to assess the AEODRS systems' eight degrees of freedom and proved it can right itself on level ground regardless of what initial state it finds itself in. The analysis also produces motion plans revealing how the robot can reorient itself. The team's findings have been described in "Evaluating Robot Self-Righting Capabilities using Adaptive Sampling," published in IEEE's Robotics and Automation Letters in August.
Beyond the assessment of any one particular robot, Kessens sees the analysis framework as crucial to the military's ability to compare robots from many vendors and choose the ideal one for purchasing.
"The Army and Navy want robots that can self-right, but we are still working to understand and evaluate what that means," Kessens said. "Self-right under what conditions? We have developed a metric analysis for evaluating a robot's ability to self-right on sloped planar ground, and we could even use it as a tool for improving robot design. Our next step is to determine what a robot is capable of on uneven terrain."