RoboSimian Beats Out Surrogate for JPL's DRC Finals Spot

For the DRC Finals, JPL is betting on a robot that looks like a monkey over a robot that looks like a human

2 min read
RoboSimian Beats Out Surrogate for JPL's DRC Finals Spot

We were very impressed with the creative design and solid performance that JPL’s RoboSimian demonstrated last year at the DRC Trials. But although RoboSimian was able to swing from trees and topple human society much more effectively than previous models, it seems that JPL itself wasn’t entirely sold on the optimalness (is that a word?) of its own design: immediately after the trials ended, they started building a new (and slightly more traditional) robot called Surrogate. Now, after six months of testing, the results are in.

It’s good news for RoboSimian: it gets to keep the top spot and will go to the DRC Finals next yearIf Surrogate looks sort of like it’s made out of three of RoboSimian’s leg-arms all stuck together, that’s because it was made out of three of RoboSimian’s leg-arms all stuck together, plus a pair of Robotiq hands, a sensor head, and tracked base. 

img RoboSimian and Surrogate: Which would do better at the DRC Finals? Photo: NASA JPL

Surrogate isn’t very humanoid looking, but you may say it’s more humanoid than RoboSimian is, with its flexible spine, arms, and upright posture. It’s about 1.4 meters tall, weighs just over 90 kilograms, and is much better suited for manipulation tasks, especially ones that require reach. For some DRC tasks, this might make it better than RoboSimian, but the tracks mean that it can’t negotiate rubble, climb ladders, or drive a vehicle without some seriously creative gymnastic feats. Also, Surrogate’s sensors are concentrated in its head, whereas RoboSimian has sensors all over the place, like its sides and belly.

It comes down to the fact that Surrogate is a better manipulation platform and faster on benign surfaces, but RoboSimian is an all-around solution, and we expect that the all-around solution is going to be more competitive in this case, says JPL’s Brett Kennedy. “[But] we'll continue to use it as an example of how we can take RoboSimian limbs and reconfigure them into other platforms.

JPL has released some videos demonstrating Surrogate’s navigation and manipulation capabilities. The two vids below show the robot operating two kinds of valve:

[ JPL ]

The Conversation (0)
Image of a combine harvester within a wheat field, harvesting.

Russia is the world's largest wheat exporter, with 20 percent of the world's wheat trade. Combine harvesters that can drive themselves using technology from Russian company Cognitive Pilot are helping to make the harvesting process faster and more efficient.

Cognitive Pilot
Blue

The field of automated precision agriculture is based on one concept—autonomous driving technologies that guide vehicles through GPS navigation. Fifteen years ago, when high-accuracy GPS became available for civilian use, farmers thought things would be simple: Put a GPS receiver station at the edge of the field, configure a route for a tractor or a combine harvester, and off you go, dear robot!

Practice has shown, however, that this kind of carefree field cultivation is inefficient and dangerous. It works only in ideal fields, which are almost never encountered in real life. If there's a log or a rock in the field, or a couple of village paramours dozing in the rye under the sun, the tractor will run right over them. And not all countries have reliable satellite coverage—in agricultural markets like Kazakhstan, coverage can be unstable. This is why, if you want safe and efficient farming, you need to equip your vehicle with sensors and an artificial intelligence that can see and understand its surroundings instead of blindly following GPS navigation instructions.

Keep Reading ↓ Show less