DARPA and OSRF Developing Next-Gen Prosthetic Limbs in Simulation and Reality

DARPA wants amputees to have prosthetics that act, and feel, just like real arms

2 min read
DARPA and OSRF Developing Next-Gen Prosthetic Limbs in Simulation and Reality
Image: DARPA

One of the most direct, tangible ways that robotics can help humanity is by restoring independence to people who don’t have it. This is especially true for robotic prosthetics, as they transition from systems with a mind of their own to systems that are leveraging your mind instead.

Earlier this week, DARPA announced contract awards for HAPTIX (“Hand Proprioception and Touch Interfaces”), a program that “seeks to create a prosthetic hand system that moves and provides sensation like a natural hand.”

It sounds cool, but what really drove the importance of this home for us were two videos that DARPA posted today: one showing amputees eating and drinking with DEKA arms—created by Dean Kamen’s DEKA R&D firm for DARPA—and another showing a U.S. Army volunteer using one to climb up a rock wall.

How cool is that? Here’s the other video:

These are early versions of the “Luke” arms from DEKA. You can read more about them here

What HAPTIX is trying to do is make the operation of arms like this as transparent to the user as possible. At this point, the arms themselves are mechanically pretty good. What’s missing is the interface. Specifically, a two-way interface, where the user can leverage their brain and nervous system to control the arm intuitively, while receiving force and touch feedback from sensors on the arm along those same channels. The robot arm should behave like a biological arm, be controlled like a biological arm, and feel like a biological arm.

HAPTIX seeks to create a sensory experience so rich and vibrant that users would want to wear their prostheses full time. The program plans to adapt one of the prosthetic limb systems developed recently under DARPA’s Revolutionizing Prosthetics program to incorporate interfaces that provide intuitive control and sensory feedback to users. These interfaces would build on advanced neural-interface technologies being developed through DARPA’s Reliable Neural-Interface Technology (RE-NET) program.

Where appropriate, HAPTIX teams intend to leverage commercially available technologies such as intramuscular electrodes and lead technologies developed initially for cardiac pacemakers and now used in several modern implantable medical devices. The program also plans to test advanced microelectrode array and nerve cuff electrode technologies that have been developed over the past two decades with support from the National Institutes of Health, the Department of Veterans Affairs and DARPA.

As you might expect (since it’s true with robotics in general), this hardware tends to be expensive to play around with. DARPA has tasked the Open Source Robotics Foundation with developing a Gazebo-based simulation environment for prosthetics so that researchers can test out software and interfaces:

HAPTIX is currently in Phase 1, which is “evaluating several distinct technical approaches.” Phase 2 will take the most successful of those approaches and mush them together into a complete, functional HAPTIX prosthetic system, which DARPA hopes to have ready for take-home trials within four years.

Via [ DARPA ] and [ OSRF ]

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman
LightGreen

“I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

This article is part of our special report on AI, “The Great AI Reckoning.”

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓ Show less