AI News, Lockheed Martin's Team TROOPER Sets Expectations for DRC Finals

Lockheed Martin's Team TROOPER Sets Expectations for DRC Finals

With the DRC Finals kicking off this week, competing teams have been practicing hard to get their robots ready for competition.A few weeks ago, we visitedTeam TROOPER atLockheed Martin Advanced Technology Laboratories (or more accurately, a nameless and windowless building in an office park somewhere near Philadelphia) to see how they’ve been preparing for the DRC Finals, and what we came back with should give you a good sense of what to expect.

At a minimum, a human will be monitoring the progress of the robot as it executes autonomously generated plans, but there are lots of other options, too: In general, Lockheed’s goal is to use as many high-level autonomy behaviors as possible, since that’s the fastest and most efficient way to complete the DRC tasks, but if they need to, they can always take more direct control.

Here’s the current strategy (assuming the robot is on a flat surface): We can’t wait to see that in practice, and we hope it actually works, since Lockheed says they haven’t (yet) been able to execute that on the physical robot:“There’s a lot to do, and not a lot of time left,” Dr. Danko told us.

DARPA Robotics Challenge Team and Approach

For the DARPA Robotics Challenge, Team TROOPER is creating a software solution that controls a robot using Human Guided Autonomy, which allows a robot to primarily work on its own, contacting a human only when it needs assistance.

We’re using the DARPA-furnished Atlas robot as a hardware test bed for this Human Guided Autonomy software—in other words, we’re building the “brains” of the robot using advanced perception, processing and planning technologies.

The DARPA Robotics Challenge Was A Bust

What followed were the most suspenseful minutes in the entire competition, as the bot—already a fan-favorite, thanks to its striking, primate-inspired design, and attention from media outlets (ours included) in the run-up to the finals—struggled to get up.

And with each failed, and undignified bout of writhing, it seemed more likely that CMU would join that sad DRC tradition, of treating its robot like a mechanical invalid.

There's no denying that CHIMP's eventual third-place finish was due to world-class engineering, the deep bench of robotics talent that CMU has developed, and some unquantifiable amount of grit and gumption on the part of the team members.

Years of work and tens of millions of funding culminated in an event that no one appeared to care about, despite the fact that it featured walking, driving, tool-grabbing humanoid robots.

“Every car failed, and the closest was CMU, which got seven and a half miles in and then hit a boulder,” says Boris Sofman, CEO of Anki, a San Francisco-based artificial intelligence startup that makes autonomous toy cars.

“But just three years later, they had autonomous cars driving in an urban setting, with moving vehicles, following traffic laws,” says Sofman.

“And less than 10 years later we have truly autonomous cars that are already at a functionality that's better than humans, in a lot of the roads they're being tested in.” DARPA's response to the 2004 Grand Challenge was bold.

But that initial dud in the Mojave desert was the foundation for the robot car competitions that came later, and for the rapid, and stunning pace of innovation in driverless vehicles within the commercial sector.

If DARPA is serious about pushing the development of robots that could respond to disasters, or at least navigate and function within human environments without making dangerous fools of themselves, the first step is to recognize failure.

The result was a performance that was good enough to win the finals, but if you applied the robot's timid, halting, 45-minute slog to a real-life disaster, it's hard to imagine it accomplishing anything useful.

And shouldn't a machine that's designed to charge into an emergency be both capable of moving with some measure of speed, and capable of surviving the sort of stumble that any human responder would easily recover from?

And the DRC's most indelible and embarrassing visual, of robot after robot tipping over, ramrod straight, like a felled tree, could be supplanted by the more inspirational optics of machines getting back up.

DARPA Robotics Challenge

and two live hardware challenges, the DRC Trials in December 2013 and the DRC Finals in June 2015.[2] [3] Besides spurring development of semi-autonomous robots, the DRC also sought to make robotic software and systems development more accessible beyond the end of the program.

To that end, the DRC funded the adaptation of the GAZEBO robot simulator by the Open Source Robotics Foundation (OSRF) for DRC purposes and the construction of six Boston Dynamics ATLAS robots that were given to the teams that performed best in the VRC.[4] Dr. Gill Pratt, Program Manager DARPA Robotics Challenge described DARPA and its goals with the Robotics Challenge:[5] DARPA’s role is to spur innovation.

Tracks B and C will go through the Virtual Robotics Challenge (VRC), after which successful teams may receive funding for subsequent stages.[4] Applications for tracks A and B closed in May 2012.[6] The track C application window closed on 18 December 2012, though late applications were still being considered as of January 2013,[7] though participants may still download the DRC Simulator, an open source application created by the Open Source Robotics Foundation.[8] Track D was open for registration through October 2013.[9] The signup site for Tracks C and D (no funding) shows illustrations of robots with most largely conforming to humanoid layouts (bipedal with two arms).

DARPA will provide to some participants 'a robotic hardware platform with arms, legs, torso and head.[1] In August 2012, DARPA announced that it would pay about $10.9 million to Boston Dynamics to build seven platforms based on the PETMAN project by August 2014.[12][13][14] The contest will also include 'supervised autonomy' tasks in which non-expert operators will be allowed/required to complete tasks using the robotic vehicle.

The Challenge will focus on the ability to complete such supervised autonomy tasks 'despite low fidelity (low bandwidth, high latency, intermittent) communications.'[4] The DRC Trials occurred on December 20 and 21, 2013 in Florida.

Twenty-five of the top robotics organizations in the world gathered to compete for $3.5 million in prizes as they attempted a simulated disaster-response course.[20] The 25 teams competing for the Finals are:[21] In the Finals, three teams had a perfect score of 8.

An Architecture for Human-Guided Autonomy: Team TROOPER at the DARPA Robotics Challenge Finals†

Recent robotics efforts have automated simple, repetitive tasks to increase execution speed and lessen an operator's cognitive load, allowing them to focus on higher-level objectives.

Our design emphasizes human-on-the-loop control where an operator expresses a desired high-level goal for which the reasoning component assembles an appropriate chain of subtasks.

The operator is able to intervene at any stage of execution, to provide input and adjustment to any control layer, enabling operator involvement to increase as confidence in automation decreases.

A Compilation of Robots Falling Down at the DARPA Robotics Challenge

Lots of robots fell over at the DARPA Robotics Challenge Finals. Learn more: Edited by Erico Guizzo/IEE..

Will Valkyrie Robot Go to Mars with a DRC Team?

NASA has big plans for its Valkyrie humanoid robot. Learn more:

DARPA Robotics Challenge

Robots are coming of age. As part of the DARPA Robotics Challenge, Lockheed Martin is developing autonomous systems that work together with human operators. This collaborative approach applies...

DURUS: SRI's Ultra-Efficient Walking Humanoid Robot

SRI has developed a legged robot that's much more efficient than traditional walking humanoids. Learn more:

IHMC DRC Finals Preview

IHMC DRC Finals preview. Hope to see you in California.

Robotics Humanitarian Relief

Team MIT: Preparing for DRC Finals

DARPA Robot Falls

DARPA robotics challenge robot falls, played with music from Carmina Burana ~ O Fortuna Carl Orff ~ André Rieu.

Team WPI-CMU DRC 2015

Team WPI-CMU 2015 DRC Preview Video.

Drexel at the 2013 DARPA Robotics Challenge

The DARPA Robotics Challenge, held from December 20-21, 2013, was a first-of-its-kind event showcasing the current state of robotics for use in disaster response. Drexel led a multi-school...