New Lab Examines Mobile Autonomous Systems

 In GDI, Defense, Cyber/ICT, Air, Information

Best lis­ten­ing expe­ri­ence is on Chrome, Firefox or Safari. Subscribe to Federal Drive’s daily audio inter­views on Apple Podcasts or PodcastOne.

The Mitre Corporation, which oper­ates fed­er­al­ly funded research and devel­op­ment cen­ters, has set up a lab to explore mobile autonomous sys­tems. It’s already equipped a Jeep Grand Cherokee to give feed­back on the chal­lenges of auton­o­my. To learn more about the process, Federal Drive with Tom Temin spoke with Zachary LaCelle, the lead engi­neer, and Chris Hill, the direc­tor of Transportation.

Tom Temin: Let’s talk about this project. First of all, who is the fed­er­al spon­sor for this? Chris?

        Insight by Thundercat Technology and Dell Technologies: Technology lead­ers address cloud migra­tion and opti­miza­tion in this free webi­nar.

Chris Hill: Well, we’re doing work across the fed­er­al gov­ern­ment, help­ing to solve com­plex prob­lems in defense, nation­al secu­ri­ty, aero­space and trans­porta­tion. And we’re seeing a number of our spon­sors who are asking tough ques­tions right now about the impacts of vehi­cle auton­o­my. And we’ve put the lab togeth­er to help answer those for mul­ti­ple spon­sors.

Tom Temin So it’s mul­ti­ple agen­cies then that are behind this?

Chris Hill: We’re cer­tain­ly look­ing to sup­port mul­ti­ple agen­cies in this work.

Tom Temin: And that includes the Defense Department?

Zachary LaCelle: The Defense Department, Homeland Security and mul­ti­ple other agen­cies as well.

Tom Temin: What are you specif­i­cal­ly look­ing at here? What is the research cen­tered on?

        Do you have our mobile app yet? Download it your device today and never miss a beat.

Zachary LaCelle: So we’re look­ing at a few things. We’re look­ing at the types of infor­ma­tion used by autonomous vehi­cles such as the sensor infor­ma­tion or the behav­ior infor­ma­tion of a vehi­cle. And iden­ti­fy­ing the data, which is con­sis­tent across sys­tems from dif­fer­ent ven­dors, from dif­fer­ent com­pa­nies. And what data is impor­tant for vehi­cle safety? That’s one of Mitre’s pri­ma­ry con­cerns is the safety of the sys­tems.

Tom Temin: Zachary, you bring up an impor­tant point. There are a lot of com­pa­nies chas­ing this whole autonomous thing that people who oper­ate like Uber and Lyft I guess, have research pro­grams, and you’ve got the Googles of the world. I guess the tra­di­tion­al auto­mo­bile man­u­fac­tur­ers are all chas­ing this. What is the strat­e­gy for not over­lap­ping everyone’s work, but some­how shar­ing infor­ma­tion that’s pro­duced in terms of best practices?Zachary LaCelle: So Mitre pro­vides some unique expe­ri­ences here. We’re not trying to com­pete with indus­try. Our job is not to make a better autonomous vehi­cle. Nor do we want to. Mitre brings some unique things to this effort that I think maybe indus­try isn’t look­ing at. Mitre has a wide bench of of domains. Mitre has cyber­se­cu­ri­ty researchers, sys­tems engi­neers, experts in policy, a very wide range of people, avi­a­tion safety, for instance. And we can bring all those types of researchers to bear on this really unique and chal­leng­ing aspect of auton­o­my.

Tom Temin: Chris, is there some fed­er­al vision that trans­porta­tion and motion of vehi­cles is going in some grand direc­tion that might affect both the civil­ian side and the mil­i­tary side?

Chris Hill: I think there’s cer­tain­ly fed­er­al visions about where this should be headed. The Department of Transportation, in par­tic­u­lar, has devel­oped guid­ance so called AV 4.0 guid­ance to help chart the direc­tion of a AV devel­op­ment. But I think there’s still a lot of work that needs to be done, and right now, per­haps not a over­all guid­ing safety frame­work for how you accom­plish that. And that’s an area where we think we can pro­vide sup­port.

Tom Temin: Maybe the fed­er­al gov­ern­ment is the locus of where the safety stan­dards will even­tu­al­ly reside?

Chris Hill: Yes, cer­tain­ly the fed­er­al gov­ern­ment, in many instances, safety is their pri­ma­ry mis­sion, cer­tain­ly for the trans­porta­tion agen­cies. So that’s clear­ly of impor­tance to them. But they want to be able to make sure we have safe autonomous vehi­cles on the road­way, but in a way that doesn’t over-reg­u­late. Nor does it dis­cour­age pri­vate indus­try from inno­vat­ing and devel­op­ing new tech­nolo­gies.

Tom Temin: Zachary, what exact­ly does the Jeep Grand Cherokee do for you and what What’s on there?

Zachary LaCelle: So we have a wide vari­ety of capa­bil­i­ties on the Jeep. Our goal with this plat­form was to pro­vide a system that had a rep­re­sen­ta­tive sample of all the types of tech­nol­o­gy you might find on autonomous and auto­mat­ed vehi­cles. So we have a wide range of sen­sors, a wide range of com­put­ing power, and the abil­i­ty to con­trol the vehi­cle itself. And the goal of this test-bed is to pro­vide parody with what indus­try is doing, but also to pro­vide a place where we can com­pare dif­fer­ent and dis­parate tech­nolo­gies and soft­ware sys­tems, algo­rithms and pro­vide feed­back and rec­om­men­da­tions to our spon­sors.

Tom Temin: Where do you run it?

Zachary LaCelle: Most of our oper­a­tions are done local to Mitre. A lot of the tests that we do don’t require autonomous dri­ving, so we can drive around and take data wher­ev­er we’d like. On for auton­o­my tests we’re iden­ti­fy­ing tracks that we’re able to oper­ate at.

Tom Temin: Chris, what is the ulti­mate deliv­er­able to the gov­ern­ment that you will antic­i­pate from this project?

Chris Hill: Well, I don’t think there’s any single deliv­er­able. We antic­i­pate that will take on a number of research topics for fed­er­al spon­sors, and each of those will define par­tic­u­lar out­puts that they want. For us, I think we’re really look­ing to create some­thing that becomes a a resource capa­bil­i­ty that any­body can take advan­tage of.

Tom Temin: Now, in the real world, there are a couple of domains right now for auton­o­my. One you’ve got, the FAA and NASA deal­ing with how to oper­ate both unmanned and manned air­craft in the nation’s air­space. And then on the ground, you’ve got all these orga­ni­za­tions look­ing at trucks and cars. And then I guess maybe there’s a third­do­main, which is mil­i­tary, which tends to not oper­ate on stan­dard roads and bridges like every­body else. So is there any area of data or algo­rithms or learn­ings that are pos­si­bly cross domain in this whole area of auton­o­my?

Zachary LaCelle: So I think that’s one of the won­der­ful things about being an auton­o­my researcher is is the algo­rithms the capa­bil­i­ties, the sens­ing really cross­es domains, and this is a great oppor­tu­ni­ty we have to share knowl­edge and capa­bil­i­ties between defense and between trans­porta­tion, air, ground. The defense indus­try has been work­ing on autonomous vehi­cles for a very long time. People don’t real­ize this, but it’s been going on for decades. And now we have the com­mer­cial side that’s devel­op­ing really novel, inter­est­ing solu­tions to these prob­lems. And I think there’s a
lot that can trans­late between domains.

Tom Temin: At some point you have to make a divi­sion between autonomous and simply remote­ly oper­at­ed. Because that even goes back fur­ther in some sense

Zachary LaCelle: Absolutely. The entire spec­trum of auton­o­my really is a spec­trum. There’s pieces of it that apply between domains of dif­fer­ent capa­bil­i­ty levels. So like you men­tioned, tele-oper­a­tion, all the way up to fully self dri­ving.

Tom Temin: What is the scope of the oper­a­tion that you have going at Mitre? Is there an end-point? Is there some dead­lines? What does the project look like from a pro­gram stand­point?

Zachary LaCelle: The lab is focused on being a resource for Mitre and for our spon­sors. So there’s no set dead­line for the lab itself. We really see this capa­bil­i­ty as con­tin­u­ing and updat­ing as tech­nol­o­gy and algo­rithms improve. We’re look­ing at doing some research on safety stan­dards and cer­ti­fi­ca­tion process­es, and we hope to have results for that soon. But we really see the lab as a con­tin­u­ing
resource.

Tom Temin: Do you have fed­er­al spon­sors at this point or are you hoping to attract them once the capa­bil­i­ty is set up?

Chris Hill: We cer­tain­ly do have some fed­er­al work that’s being under­tak­en right now, and we’re having lots of con­ver­sa­tions with other fed­er­al agen­cies about oppor­tu­ni­ties to use this resource.

Tom Temin: Who are the early in agen­cies? Can you say?

Zachary LaCelle: We can say that there’s people from the defense com­mu­ni­ty that are inter­est­ed in what we’re doing. We have some small projects look­ing at spe­cif­ic chal­lenges that they face.

Tom Temin: Maybe DOT will come in at some point, I guess you’re hoping?

Chris Hill: We would cer­tain­ly like to engage DOT in some of these con­ver­sa­tions,

Tom Temin: What else do we need to know about this project?

Chris Hill: Well, I think this is a time when auto­mat­ed vehi­cle tech­nol­o­gy is begin­ning to touch the lives of many people. Yet some of the highly pub­li­cized set­backs are dam­ag­ing con­sumer trust. There’s test­ing going on by a number of dif­fer­ent devel­op­ers in many states right now. But I really don’t think there’s a clear under­stand­ing of what the bar for a safe solu­tion is right now. We’re really hoping that the work we’re doing in the lab can help define that safety require­ment.

Mitre’s Chris Hill (left) and Zachary LaCelle (right).

Copyright © 2020 Federal News Network. All rights reserved. This web­site is not intend­ed for users locat­ed within the European Economic Area.

Source: Federal News Network

Recommended Posts
0

Start typing and press Enter to search