General Electric Research [GE] said this week it conducted a successful demonstration of its autonomous ground robot for the Army, marking the completion of a one-year program to help further the service’s development of autonomous off-road mobility technology.
The company said its “ATVer” robot was able to successfully navigate complex off-road conditions, informing the Army’s ability to understand potential technology that could allow combat vehicles to traverse rough terrain autonomously.
“One of the big challenges with autonomous systems is overcoming the risk factor, particularly when it involves equipment for complex military operations or critical infrastructure where safety and reliability are most important,” Shiraj Sen, a senior robotics scientist at GE Research, said in a statement. “With the successful demonstration of our ‘risk-aware’ autonomous ground vehicle in our project with the Army, we’ve made progress in removing some of those risks and hopefully, provided a clearer path to more autonomous systems applications further down the road … or off-road.”
Last May, the Army Research Lab awarded nearly $3 million to GE Research and seven universities to work on the Scalable, Adaptive and Resilient Autonomy (SARA) program, with a specific focus on development and acceleration of technologies for off-road maneuver.
“In future Army scenarios, autonomous systems will have to reliably plan in the presence of challenging features they encounter while maneuvering in complex terrain,” Eric Spero, GE Research’s program manager for SARA, said in a statement. “Incorporating risk and uncertainty into the autonomy decision-making process enables our testbed platforms to show us what it looks like to plan a direct path instead of taking the long way around.”
The Army has said future technology sprints in the SARA program “will explore scalable heterogeneous and collaborative behaviors and human-agent teaming.”
GE Research said its ATVer robot makes use of the company’s Humble AI technology, which allows the vehicle to assess complex scenarios “much like a human might do when it encounters an uncertain situation.”
“In our autonomous ground vehicle system, Humble AI was the key mechanism that enabled it to decipher known paths vs. uncertain paths when navigating unstructured, off-road terrains,” Sen said. “It processed the information gathered from the eyes of our vehicle – the vision and LIDAR technologies – and was able to move safely and avoid objects like trees or brush that might stop it in its tracks.”