Carnegie Mellon University-NREC designed CHIMP (CMU Highly Intelligent Mobile Platform) is shown during the 2013 DARPA Robotics Challenge Trials task of opening a series of doors. CHIMP finished third in the trials. (DARPA image)

Robotics Challenge Finals Set for June 2015

Teams will compete in Pomona, Calif. for DARPA's $2 million prize. The winner will be the team that best demonstrates robotic technology for disaster response.

DARPA announced last week that the finals of its Robotics Challenge competition will be held June 5-6, 2015, at Fairplex in Pomona, Calif. Eleven finalist teams have qualified to compete for the $2 million prize that will go to the team that best demonstrates robotic technology for disaster response. An additional team must qualify in February 2015 in order to participate, according to information posted on the event's website.

The March 2011 Fukushima Daiichi nuclear plant crisis inspired DARPA to create the challenge, which is intended to accelerate the development of robots that could aid in response efforts after natural and man-made disasters. The robot prototypes are tested on their ability to act semi-autonomously, and the earlier trials involved eight tasks – including driving and exiting a utility vehicle walking across rough terrain, removing debris from a doorway, carrying and connecting a fire hose, and climbing an industrial ladder.

"Six months ago at the DRC Trials, we began physically testing human-supervised robots against disaster-relevant tasks. Their impressive performance gave us the confidence to raise the bar," said Dr. Gill Pratt, the challenge's program manager. "A year from now at the DRC Finals, we will push the technology even further." According to DARPA's announcement, the tasks at the finals will be similar to those in the trials, but these new elements will challenge the team's systems:

  • Robots will not be connected to power cords, fall arrestors, or wired communications tethers.
  • Humans will not be allowed to physically intervene if a robot falls or get stuck. Robots that fall will have to do so without breaking and then get up without assistance.
  • Speed will be more heavily weighted in the scoring, and all tasks must be completed in a total time of approximately one hour (versus four hours in the trials).
  • Communications will be even more degraded and intermittent this time.

"For the first time, teams will be empowered to exploit cloud and crowd-augmented robotics, two highly promising research areas that allow on-site operators to leverage remote data, computing, and human resources," Pratt said. "These research areas are in their infancy, but after the DRC Finals we hope to see significant innovation."

Product Showcase

  • Magid® D-ROC® GPD412 21G Ultra-Thin Polyurethane Palm Coated Work Gloves

    Magid’s 21G line is more than just a 21-gauge glove, it’s a revolutionary knitting technology paired with an advanced selection of innovative fibers to create the ultimate in lightweight cut protection. The latest offering in our 21G line provides ANSI A4 cut resistance with unparalleled dexterity and extreme comfort that no other 21-gauge glove on the market can offer! Read More

  • Safety Shower Test Cart

    The Safety Shower Test Cart speeds up and simplifies emergency shower tests, ensures you stay in compliance with OSHA regulations, and significantly reduces testing costs. With 7 unique features, the cart makes testing easy, effective, and efficient. You can test water clarity, flow, temperature, and spread—all at the same time! Most safety shower testing kits create a mess, take too much time to use, and don't fully help you stay in compliance with OSHA & ANSI standards. Transform the way you test emergency showers with Green Gobbler Safety. Read More

  • Matrix's OmniPro Vision AI Collision Avoidance System

    OmniPro Vision AI is a state-of-the-art collision avoidance system that features NIOSH award-winning Visual Artificial Intelligence (AI) technology. This highly accurate, powerful system identifies and alerts on pedestrians, vehicles and specified objects, ensuring safer facilities, mining operations and industrial sites. With its web-based cloud application, OmniPro Vision AI also logs and analyzes a wide range of data related to zone breach notifications. Operating without needing personal wearable devices or tags, OmniPro has visual and audible zone breach alerts for both operators and pedestrians. Read More

Featured

Artificial Intelligence