Clearpath Husky robot

Robots are Learning without Human Help

The ARL is working with Carnegie Mellon University to find faster ways to train robots, without human attention.

Robots are learning faster, and without help from human trainers. Experiments being performed by the U.S. Army Research Laboratory (ARL) and the Robotics Institute at Carnegie Mellon University (CMU) are discovering techniques for teaching robots transversal behaviors with minimal human oversight. With the technique, for example, robots can navigate autonomously in challenging environments while performing actions expected of a human.

A small unmanned Clearpath Husky robot was used by ARL researchers to develop a new technique to quickly teach robots novel traversal behaviors with minimal human oversight. (Photo courtesy of the U.S. Army)

ARL researchers include Drs. Maggie Wigness and John Rogers. “If a robot acts as a teammate, tasks can be accomplished faster and more situational awareness can be obtained,” Wigness said. “Robot teammates can be used as an initial investigator for potentially dangerous scenarios, thereby keeping soldiers from harm. The learning process is fast and requires minimal human demonstration, making it an ideal learning technique for on-the-fly learning in the field when mission requirements change.”

Research has been performed with a relatively small unmanned Clearpath Husky robotic system (see figure) and will eventually be transferred to larger systems with enhanced visual field of view. The research is funded through the Army's Robotics Collaborative Technology Alliance (RCTA), which brings together government, industrial, and academic institutions for R&D purposes.

Hide comments

Comments

  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Publish