Researchers are developing software that will help military robots be more independent.
The new software aims to ensure that a robot can always get itself back up after a fall, no matter what its orientation.
The ability for robots to get back on their own feet means soldiers wouldn’t have to risk their own lives to come to the aid of autonomous systems.
Scroll down for video
Army researchers are developing new software that aims to ensure that a robot can always get itself back up after a fall, no matter what its orientation. A test platform for the new system is shown
The latest effort from the US Army Research Lab and Johns Hopkins University Applied Physics Lab builds on feedback from soldiers at an Army training course.
‘One soldier told me that he value his robot so much, he got out of his vehicle to rescue the robot when he couldn’t get it turned back over,’ said ARL researcher Dr. Chad Kessens.
‘That is a story I never wanted to hear again.’
The team, working with contractor Northrop Grumman Remotec, is developing a new system with the critical requirement: self-righting capability.
The Advanced Explosive Ordnance Disposal Robotic System (AEORDRS) family of robots will have modular architecture and a lightweight ‘backpackable’ platform.
They’re expected to begin production later this year.
‘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.’
The system is designed to analyze whether a robot can correct its position from any overturned orientation.
‘The analysis I’ve been working on looks at all possible geometries and orientations that the robot could find itself in,’ Kessens said.
The ability for robots to get back on their own feet means soldiers wouldn’t have to risk their own lives to come to the aid of autonomous systems
‘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.’
The software relies on an adaptive sampling algorithm that looks for transitions.
The framework for the software was originally designed for underwater vehicles.
‘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,’ said HU/APL researcher Galen Mullins.
US ARMY TESTS ‘WINGMAN’? ROBO-TRUCKS THAT CAN SHOOT
The US Army is testing its self-driving Humvee truck to see if it can accurately identify and shoot targets
The Humvee is part of a ‘Wingman’ system, that also includes a manned command and control vehicle
‘Wingman’ is mounted with a .50-caliber machine gun and an autonomous remote engagement system
The Army conducted a live fire exercise using the Wingman Humvee last year
The live fire exercise involved a real-life scenario where there was a ‘complex breach in a minefield’
It’s the first time that the Army has conducted an exercise with an autonomous ground vehicle that’s capable of shooting
‘My techniques were able to effectively predict where those transitions might be so that we could search the space efficiency.’
The researchers say the AEODRS systems can let a robot right itself on level ground no matter what position it’s in.
‘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.’