In lansford, Pennsylvania, a long legged “dog” robot manufactured by Penn spinoff ghost robotics navigates in mine 9. These robots are designed to detect cultural relics such as backpacks and virtual personnel to simulate real underground search and rescue missions.

Earlier this year, a group of students, postdoctors and faculty members of the University of Pennsylvania went to an experimental mine near Pittsburgh to participate in the first round of subterranean challenge hosted by the Defense Advanced Research Projects Agency (DAR PA). The team was led by Camillo J. Taylor. The researchers cooperated with the tertiary industry company in Pennsylvania to establish a robot team to navigate and explore the unknown underground environment.

DARPA’s challenge is to stimulate innovative solutions to complex problems. Subt’s goal is to develop robots that can be sent to places too dangerous for humans, such as subway tunnels behind four mines or mines where workers are trapped. These robots can then report what they see to a person who can stay in a safe place and deal with it quickly.


The Pennsylvania ghost robot company has developed a robot dog

Members of the Pennsylvania underground tunnel operation laboratory team (Pluto) have worked with UAVs in a challenging environment, but going underground means that another platform is needed to carry heavy equipment and navigate in a narrow space. By combining ghost robotics legged “dog” platform with exyn technology UAV, Pluto combines the advantages of legged system and previous professional fields.

In order to successfully cross the mine, robots need to be able to see the surrounding situation, so that they can avoid obstacles and share what they see with human operators. Each dog carries a light detection and sorting device that uses a laser to create a three-dimensional map, a stereo RGB camera to view artifacts, a thermal camera to detect thermal signals, and an onboard computer to process data.

Pluto’s robots also need the ability to decide where to go next, identify artifacts, and pass information to other dogs and humans outside the mine. The program developed by doctoral student Anthony Cowley is used to generate the position map of the robot according to the images collected by the sensor, while cultural relics such as backpacks and mobile phones are detected using the program developed by doctoral student shreas shivakumar.

Underground communication is particularly challenging because radio waves cannot pass through the thick cave walls. Led by master Fernando clardra, Pluto’s strategy is to create a “bucket bridge” system that allows robots to share data with each other. In this way, if a robot cannot return to the entrance, the data it collects can still be transmitted to the base station by other dogs.

Combining all these capabilities requires a high degree of autonomy to allow the robot to plan its exploration strategy without human direct input. Doctoral student Ian Miller led the work and helped ensure that all sensors, hardware and algorithms work together.

Earlier this year, Pluto spent some time in the No. 9 coal mine and Museum in lansford, Pennsylvania, and the experimental mine of the Colorado Institute of mining to observe the performance of their automation systems underground. After months of preparation, in the first round of the challenge in August, they played against ten other teams at a pilot mine near Pittsburgh.

Each team completed two mine courses and tried to find items twice in each course, including backpacks, mobile phones, fire extinguishers and virtual personnel, with a time limit of one hour. No team member was allowed to enter the mine, and only Miller was allowed to interact with the robot while collecting data.

Although their robots did not find as many artifacts as they hoped, the Pluto team was satisfied with the performance of the system in such a challenging and unknown environment. The components that work well include how dogs detect and explore tunnels, their ability to recognize objects, and several tests provided by dogs who share data through “bucket bridge”, showing how their system recovers even if individual robots trip.


The Pennsylvania ghost robot company has developed a robot dog

The team’s preparation venue for the subt challenge

Adarsh Kulkarni, a master’s student who also works for ghost robotics, said he was satisfied with the mechanical stability of these dogs and their performance after many falls. ” “This is by far the most difficult time for us to run robots, and it is also the worst environment they are in.”

“They were beaten every day and were still working the next morning,” shivakumar added jokingly. “This is really commendable.” although some of their designs have been overly suitable for the challenges of robot 9, including sensors designed for narrow and textured walls, while the walls of subt are wider and smoother, experience directly shows the team how difficult it is to design robots for unknown environments and is a rare opportunity to test robots in new environments. ” “It’s very different from the normal academic workflow,” Miller said. It’s a completely different problem from an algorithm to something working in a place you’ve never seen before. “

This “last 10%” of robotics makes automation systems robust and reliable. This is a challenge, which is usually solved by combining the most advanced technology and practical point of view. Sometimes these systems themselves are not novel, but the novelty lies in their implementation in an untested environment. The novelty lies in how to solve all these problems and make robots work reliably in a harsh environment. “

The team is still discussing their next rounds of subt plans. The next round will be carried out in the urban environment in February, which means more man-made structures and shapes, such as sharp corners, smooth walls and stairs, no matter what will happen in the future, Creating robots and sending them into a challenging real environment is very important for the progress of the University of Pennsylvania and the whole field of robotics, especially for the future, the automation system may undertake a series of challenging tasks from driving cars to searching for survivors.

Researchers at the general robotics, automation, sensing and perception laboratory in Pennsylvania are fully capable of meeting these challenges, thanks in part to a culture that encourages collaboration and communication. ” “This is what we instill into everyone who walks into our facilities,” Taylor said. If you don’t worry about having a project that is only suitable for your professional field, if you are willing to have a broader understanding of your ideas, it will let you do bigger things. “

Responsible editor; zl


Leave a Reply

Your email address will not be published. Required fields are marked *